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/skill-system
# Conflicts: # docs/event-producer-consumer.md # docs/module-graph.md # docs/rfc/README.md # packages/core/agent-core/package.json # packages/core/agent-core/src/index.ts # packages/core/agent-loop/README.md # packages/core/agent-loop/src/index.ts # packages/ui/acp-agent/src/index.ts # packages/ui/acp-agent/tests/acp-agent.spec.ts # packages/ui/stdio-agent/README.md # packages/ui/stdio-agent/src/index.ts # packages/ui/stdio-agent/tests/stdio-agent.spec.ts
This commit is contained in:
@@ -53,11 +53,8 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('coding task: fix a failing test
|
||||
const before = spawnSync('node', ['add.test.js'], { cwd: workdir })
|
||||
expect(before.status).not.toBe(0)
|
||||
|
||||
ctx = await codingHarness(workdir)
|
||||
const agent = ctx.agentLoop.create(AgentId('e2e-task'), {
|
||||
model: 'deepseek-v4-flash',
|
||||
systemPrompt: SYSTEM_PROMPT,
|
||||
})
|
||||
ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT })
|
||||
const agent = ctx.agentLoop.create(AgentId('e2e-task'), { model: 'deepseek-v4-flash' })
|
||||
|
||||
agent.send([{
|
||||
type: 'text',
|
||||
|
||||
@@ -53,6 +53,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compa
|
||||
// budget even though those blocks are stripped before the checkpoint is
|
||||
// stored.
|
||||
ctx = await codingHarness(workdir, {
|
||||
persona: SYSTEM_PROMPT,
|
||||
compact: {
|
||||
contextWindow: 2400,
|
||||
thresholdRatio: 0.5,
|
||||
@@ -63,10 +64,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compa
|
||||
},
|
||||
persistenceRoot: './.sessions',
|
||||
})
|
||||
const agent = ctx.agentLoop.create(AgentId('e2e-compaction'), {
|
||||
model: 'deepseek-v4-flash',
|
||||
systemPrompt: SYSTEM_PROMPT,
|
||||
})
|
||||
const agent = ctx.agentLoop.create(AgentId('e2e-compaction'), { model: 'deepseek-v4-flash' })
|
||||
|
||||
agent.send([{
|
||||
type: 'text',
|
||||
|
||||
@@ -20,11 +20,8 @@ afterEach(async () => {
|
||||
|
||||
describe.skipIf(!process.env.DEEPSEEK_API_KEY)('full loop: real model + real bash tool', () => {
|
||||
it('runs a bash command on request and reports its output', async () => {
|
||||
ctx = await codingHarness(process.cwd())
|
||||
const agent = ctx.agentLoop.create(AgentId('e2e-loop'), {
|
||||
model: 'deepseek-v4-flash',
|
||||
systemPrompt: SYSTEM_PROMPT,
|
||||
})
|
||||
ctx = await codingHarness(process.cwd(), { persona: SYSTEM_PROMPT })
|
||||
const agent = ctx.agentLoop.create(AgentId('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)
|
||||
|
||||
@@ -33,6 +33,11 @@ export const TODO_SYSTEM_PROMPT = 'You are a coding agent. For multi-step work,
|
||||
|
||||
/** Options for {@link codingHarness}. */
|
||||
export interface CodingHarnessOptions {
|
||||
/**
|
||||
* Deployment persona for the tree (the system-prompt plugin's `persona`
|
||||
* config — per-context, not per-agent). Omitted ⇒ no persona section.
|
||||
*/
|
||||
persona?: string
|
||||
/** Durable JSONL persistence root (the resume suite needs it; others stay file-free). */
|
||||
persistenceRoot?: string
|
||||
/**
|
||||
@@ -47,7 +52,7 @@ export async function codingHarness(workdir: string, options: CodingHarnessOptio
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(SystemPrompt, { persona: options.persona ?? '' })
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
await ctx.plugin(AgentLoop, { agents: [] })
|
||||
|
||||
@@ -38,11 +38,11 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses
|
||||
// Run 1: a fresh agent on a KNOWN session id learns a secret, then we
|
||||
// dispose the whole context (simulating process exit) so only the JSONL
|
||||
// log on disk survives.
|
||||
ctx = await codingHarness(process.cwd(), { persistenceRoot: root })
|
||||
ctx = await codingHarness(process.cwd(), { persona: SYSTEM_PROMPT, persistenceRoot: root })
|
||||
const first = ctx.agents.create({
|
||||
agentId: AgentId('resume-1'),
|
||||
sessionId: SESSION_ID,
|
||||
agentOptions: { model: 'deepseek-v4-flash', systemPrompt: SYSTEM_PROMPT },
|
||||
agentOptions: { model: 'deepseek-v4-flash' },
|
||||
}).agent as ReactLoopAgent
|
||||
first.send([{ type: 'text', text: `Remember this code for later: ${SECRET}. Just acknowledge it.` }])
|
||||
await waitForIdle(ctx, first)
|
||||
@@ -52,11 +52,11 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses
|
||||
// Run 2: a brand-new context over the SAME root resumes the persisted
|
||||
// session. The loaded event log seeds the live session, so the model sees
|
||||
// run 1's exchange as conversation history.
|
||||
ctx = await codingHarness(process.cwd(), { persistenceRoot: root })
|
||||
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', systemPrompt: SYSTEM_PROMPT },
|
||||
agentOptions: { model: 'deepseek-v4-flash' },
|
||||
})).agent as ReactLoopAgent
|
||||
expect(resumed.session.id).toBe(SESSION_ID)
|
||||
// The prior user turn is in the rehydrated log before the model is asked.
|
||||
|
||||
@@ -18,11 +18,8 @@ afterEach(async () => {
|
||||
|
||||
describe.skipIf(!process.env.DEEPSEEK_API_KEY)('todo_write: real model records a plan', () => {
|
||||
it('appends a todo/write event with the model-produced task list', async () => {
|
||||
ctx = await codingHarness(process.cwd())
|
||||
const agent = ctx.agentLoop.create(AgentId('e2e-todo'), {
|
||||
model: 'deepseek-v4-flash',
|
||||
systemPrompt: TODO_SYSTEM_PROMPT,
|
||||
})
|
||||
ctx = await codingHarness(process.cwd(), { persona: TODO_SYSTEM_PROMPT })
|
||||
const agent = ctx.agentLoop.create(AgentId('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 '
|
||||
|
||||
Reference in New Issue
Block a user