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

Merge branch 'codex/simp-agent-entry-state' into codex/simp-unify-agent-session-id

Browse Source 
# Conflicts:
#	docs/architecture.md
#	docs/config-catalog.md
#	docs/cordis-catalog/events.md
#	docs/cordis-catalog/services.md
#	docs/core-data-structures/core.md
#	docs/event-producer-consumer.md
#	docs/module-graph.md
#	examples/coding-agent/tests/code-mode.e2e.ts
#	examples/coding-agent/tests/coding-task.e2e.ts
#	examples/coding-agent/tests/compaction.e2e.ts
#	examples/coding-agent/tests/full-loop.e2e.ts
#	examples/coding-agent/tests/todo-write.e2e.ts
#	examples/cordis-agent/tests/cordis-tools.e2e.ts
#	packages/bash/tool-bash/tests/integration.spec.ts
#	packages/bash/tool-bash/tests/tools.spec.ts
#	packages/compact/compact-basic/tests/compact-loop-repro.spec.ts
#	packages/context/time-context/tests/time-context.spec.ts
#	packages/cordis/tool-cordis/src/api-catalog.ts
#	packages/cordis/tool-cordis/tests/integration.spec.ts
#	packages/core/agent-loop/README.md
#	packages/core/agent-loop/src/agent.ts
#	packages/core/agent-loop/src/index.ts
#	packages/core/agent-loop/tests/agent.spec.ts
#	packages/core/agent-loop/tests/cancel.spec.ts
#	packages/core/agent-loop/tests/config-session-id.spec.ts
#	packages/core/agent-loop/tests/contract-regressions.spec.ts
#	packages/core/agent-loop/tests/coverage-edges.spec.ts
#	packages/core/agent-loop/tests/interception.spec.ts
#	packages/core/agent-loop/tests/loop.spec.ts
#	packages/core/agent-loop/tests/properties.spec.ts
#	packages/core/agent-loop/tests/request-cache.e2e.ts
#	packages/core/agent-loop/tests/request-reconstruction.spec.ts
#	packages/core/agent-loop/tests/resume.spec.ts
#	packages/core/agent-loop/tests/scope-lifecycle.spec.ts
#	packages/core/agent-loop/tests/tool-order.spec.ts
#	packages/core/agent-loop/tests/turn-stop.spec.ts
#	packages/core/agent/src/types.ts
#	packages/examples/agent-spine-demo/README.md
#	packages/examples/agent-spine-demo/tests/agent-core.spec.ts
#	packages/examples/stdio-demo/README.md
#	packages/examples/stdio-demo/src/index.ts
#	packages/examples/stdio-demo/tests/stdio-agent.spec.ts
#	packages/fs/tool-fs/tests/fs-tools.e2e.ts
#	packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts
#	packages/hooks/hooks-claude/tests/bridge.spec.ts
#	packages/hooks/hooks-claude/tests/coverage.spec.ts
#	packages/hooks/hooks-codex/tests/bridge.spec.ts
#	packages/hooks/hooks-codex/tests/coverage.spec.ts
#	packages/subagent/subagent-fork/tests/multi-subagent.spec.ts
#	packages/subagent/subagent-fork/tests/subagent-fork.spec.ts
#	packages/subagent/subagent-inprocess/tests/structured.spec.ts
#	packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts
#	packages/subagent/subagent-spawn/tests/spawn.e2e.ts
#	packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts
#	packages/todo/tool-todo/tests/integration.spec.ts
#	packages/ui/acp/tests/dispose.spec.ts
#	packages/ui/acp/tests/edges.spec.ts
#	packages/workflow/workflow-workerthread/tests/integration.spec.ts
This commit is contained in:
Tianyi Cui
2026-07-18 12:21:15 +08:00
parent c0c0f8b3a4 3fc6f91cea
commit 59dc310bb5
657 changed files with 36658 additions and 7514 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts
+27 -37
View File
@@ -1,12 +1,10 @@
import { describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import LlmService, { CallId } from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
import AgentRegistry from '@deepseek-ai/dsh-agent'
import { CallId } from '@deepseek-ai/dsh-llm'
import { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session'
import { defineTool } from '@deepseek-ai/dsh-tools'
import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit'
import * as RepeatToolGuard from '@deepseek-ai/dsh-repeat-tool-guard'
import type { Config } from '@deepseek-ai/dsh-repeat-tool-guard'
import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts'
@@ -22,11 +20,7 @@ import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent
/** Boot the core spine + the guard; the caller registers adapters and extra listeners. */
async function harness(config: Config = {}): Promise<Context> {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await mountAgentLoopTestDependencies(ctx)
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(RepeatToolGuard, config)
ctx.tools.register(defineTool({ name: 'probe', description: 'p', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
@@ -58,7 +52,7 @@ describe('threshold escalation', () => {
textResponse('done'),
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
@@ -79,7 +73,7 @@ describe('threshold escalation', () => {
textResponse('done'),
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
@@ -101,7 +95,7 @@ describe('chain semantics', () => {
textResponse('done'),
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
@@ -125,7 +119,7 @@ describe('chain semantics', () => {
textResponse('done'),
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
@@ -143,7 +137,7 @@ describe('chain semantics', () => {
textResponse('done'),
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
@@ -164,7 +158,7 @@ describe('chain semantics', () => {
textResponse('done'),
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
@@ -180,7 +174,7 @@ describe('chain semantics', () => {
textResponse('done'),
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
@@ -196,7 +190,7 @@ describe('chain semantics', () => {
textResponse('done'),
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
@@ -216,8 +210,8 @@ describe('chain semantics', () => {
toolCallResponse('b3', 'probe', { q: 1 }),
textResponse('done'),
]))
const agentA = ctx.agentLoop.create(SessionId('a'), { model: 'mock-a' })
const agentB = ctx.agentLoop.create(SessionId('b'), { model: 'mock-b' })
const agentA = ctx.agentLoop.create(SessionId('a'), { provider: 'mock-a', model: 'model-a' })
const agentB = ctx.agentLoop.create(SessionId('b'), { provider: 'mock-b', model: 'model-b' })
agentA.send([{ type: 'text', text: 'go' }])
agentB.send([{ type: 'text', text: 'go' }])
await Promise.all([waitForIdle(ctx, agentA), waitForIdle(ctx, agentB)])
@@ -236,7 +230,7 @@ describe('chain semantics', () => {
textResponse('turn two done'),
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
agent.send([{ type: 'text', text: 'again' }])
@@ -257,14 +251,14 @@ describe('chain semantics', () => {
// (the loop.spec pattern): a child plugin fiber owns `first`.
let first!: ReactLoopAgent
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
first = inner.agentLoop.create(SessionId('reused'), { model: 'mock' })
first = inner.agentLoop.create(SessionId('reused'), { provider: 'mock', model: 'mock' })
}, { inject: ['agentLoop'] }))
first.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, first)
await fiber.dispose()
await first.done
const second = ctx.agentLoop.create(SessionId('reused'), { model: 'mock' })
const second = ctx.agentLoop.create(SessionId('reused'), { provider: 'mock', model: 'mock' })
second.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, second)
@@ -280,7 +274,7 @@ describe('chain semantics', () => {
textResponse('done'),
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
@@ -296,7 +290,7 @@ describe('chain semantics', () => {
toolCallResponse('c1', 'probe', { q: 1 }), // if the direct call had counted, this would be #2
textResponse('done'),
]))
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
@@ -310,7 +304,7 @@ describe('fold onto the downstream decision', () => {
ctx.on('tools/post-execute', async () => ({
kind: 'block' as const,
feedback: [{ type: 'text' as const, text: 'nope' }],
additionalContext: { content: [{ type: 'text' as const, text: 'downstream-ctx' }], source: { kind: 'plugin' as const, plugin: 'test' } },
additionalContexts: [{ content: [{ type: 'text' as const, text: 'downstream-ctx' }], source: { kind: 'plugin' as const, plugin: 'test' } }],
}))
const adapter = new MockAdapter([
toolCallResponse('c1', 'probe', { q: 1 }),
@@ -318,19 +312,19 @@ describe('fold onto the downstream decision', () => {
textResponse('done'),
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
const found = reminders(agent)
expect(found).toHaveLength(2)
expect(found).toHaveLength(3)
// Call 1: below threshold — the downstream context passes through untouched.
expect(found[0]!.text).toBe('downstream-ctx')
expect(found[0]!.source).toEqual({ kind: 'plugin', plugin: 'test' })
// Call 2: reminder folded in front, single merged context, the guard's source.
// Call 2: reminder and downstream context retain separate provenance.
expect(found[1]!.text).toContain('repeating the exact same tool call')
expect(found[1]!.text).toContain('|downstream-ctx')
expect(found[1]!.source).toEqual(GUARD_SOURCE)
expect(found[2]).toEqual({ text: 'downstream-ctx', source: { kind: 'plugin', plugin: 'test' } })
// The block's feedback reached the tool result unchanged.
const results = [...agent.session.events].filter((e): e is SessionEvent<'tool/result'> => e.type === 'tool/result')
expect(results.every(r => r.data.isError)).toBe(true)
@@ -349,7 +343,7 @@ describe('fold onto the downstream decision', () => {
textResponse('done'),
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
@@ -364,11 +358,7 @@ describe('fold onto the downstream decision', () => {
describe('config validation fails loud', () => {
async function spine(): Promise<Context> {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await mountAgentLoopTestDependencies(ctx)
await ctx.plugin(AgentLoop, { agents: [] })
return ctx
}