Merge branch 'codex/simp-ui-identity-residue' into codex/simp-hide-concrete-agent-loop

# Conflicts: # docs/event-producer-consumer.md # examples/coding-agent/tests/code-mode.e2e.ts # examples/coding-agent/tests/harness.ts # examples/coding-agent/tests/resume.e2e.ts # examples/cordis-agent/tests/harness.ts # packages/bash/tool-bash/tests/integration.spec.ts # packages/compact/compact-basic/tests/compact-loop-repro.spec.ts # packages/cordis/tool-cordis/tests/integration.spec.ts # packages/core/agent-loop/tests/contract-regressions.spec.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/todo/tool-todo/tests/integration.spec.ts
2026-07-18 12:33:49 +08:00
parent a5ac5b0ad2 35473c2701
commit 6f01d4d099
657 changed files with 36714 additions and 7631 deletions
@@ -1,13 +1,13 @@
-import { describe, expect, it } from 'vitest'
+import { afterEach, describe, expect, it, vi } from 'vitest'
 import { Context } from 'cordis'
-import LlmService from '@deepseek-ai/dsh-llm'
-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 from '@deepseek-ai/dsh-tools'
-import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
-
+import { existsSync, mkdtempSync, readFileSync, rmSync } from 'node:fs'
+import { tmpdir } from 'node:os'
+import { join } from 'node:path'
+import { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session'
+import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
+import type { Agent } from '@deepseek-ai/dsh-agent'
 import AgentLoop from '@deepseek-ai/dsh-agent-loop'
+import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit'
 import TaskService from '@deepseek-ai/dsh-tasks'
 import * as ToolTasks from '@deepseek-ai/dsh-tool-tasks'
 import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
@@ -20,22 +20,25 @@ import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent
 * (tool/call + tool/result session events, the generic `ctx.tasks` runtime,
 * agent.inject completion notices).
 */
-async function harness(adapter: MockAdapter) {
+async function harness(adapter: MockAdapter, sessionRoot?: string, dshHome?: string) {
  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)
+  if (sessionRoot !== undefined) await ctx.plugin(SessionPersistenceJsonl, { root: sessionRoot })
  await ctx.plugin(AgentLoop, { agents: [] })
  await ctx.plugin(TaskService)
  await ctx.plugin(ToolTasks)
  await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 })
-  await ctx.plugin(ToolBash)
+  await ctx.plugin(ToolBash, dshHome === undefined ? {} : { dshHome })
  ctx.llm.registerAdapter(['mock'], adapter)
  return ctx
 }

+const dirs: string[] = []
+afterEach(() => {
+  vi.unstubAllEnvs()
+  for (const dir of dirs.splice(0)) rmSync(dir, { recursive: true, force: true })
+})
+
 function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
  return new Promise((resolve) => {
    const dispose = ctx.on('agent/status', (subject, status) => {
@@ -83,13 +86,45 @@ async function pollUntil(predicate: () => boolean, timeoutMs = 5_000): Promise<v
 }

 describe('bash tool through the agent loop', () => {
+  it('first-turn bash receives session identity before the lazy JSONL file materializes', async () => {
+    const root = mkdtempSync(join(tmpdir(), 'dsh-bash-session-env-'))
+    dirs.push(root)
+    const dshHome = join(root, 'dsh-home')
+    vi.stubEnv('DSH_STALE_PARENT', 'stale')
+    const adapter = new MockAdapter([
+      toolCallResponse('call-1', 'bash', {
+        command: 'printf \'%s\\n%s\\n%s\\n%s\\n%s\\n\' "$DSH_HOME" "$DSH_SHELL" "$DSH_SESSION_ID" "$DSH_SESSION_JSONL" "${DSH_STALE_PARENT-unset}"; if [ -e "$DSH_SESSION_JSONL" ]; then printf \'present\\n\'; else printf \'absent\\n\'; fi',
+        description: 'inspect session environment',
+      }),
+      textResponse('Session environment inspected.'),
+    ])
+    const ctx = await harness(adapter, root, dshHome)
+    const handle = await ctx.agents.create({
+      sessionId: SessionId('session-env-id'),
+      agentOptions: { provider: 'mock', model: 'mock' },
+    })
+    const agent = handle.agent
+    const location = ctx.sessionPersistence.locate(agent.session.header)
+    expect(location?.kind).toBe('jsonl')
+
+    agent.send([{ type: 'text', text: 'inspect the current session' }])
+    await waitForIdle(ctx, agent)
+
+    const result = findEvent(events(agent), 'tool/result')
+    expect(resultText(result)).toBe(`${dshHome}\n1\nsession-env-id\n${location?.path}\nunset\nabsent\n`)
+    expect(existsSync(location!.path)).toBe(true)
+    const header = JSON.parse(readFileSync(location!.path, 'utf8').split('\n')[0]!) as { type: string; id: string }
+    expect(header).toMatchObject({ type: 'session', id: 'session-env-id' })
+    await handle.dispose()
+  })
+
  it('foreground: model calls bash, sees the result, replies', async () => {
    const adapter = new MockAdapter([
      toolCallResponse('call-1', 'bash', { command: 'echo integration-ok', description: 'test command' }, 'Running it.'),
      textResponse('The command printed integration-ok.'),
    ])
    const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(SessionId('it-fg'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('it-fg'), { provider: 'mock', model: 'mock' })

    agent.send([{ type: 'text', text: 'run echo integration-ok' }])
    await waitForIdle(ctx, agent)
@@ -121,7 +156,7 @@ describe('bash tool through the agent loop', () => {
      textResponse('It failed with code 9.'),
    ])
    const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(SessionId('it-exit'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('it-exit'), { provider: 'mock', model: 'mock' })

    agent.send([{ type: 'text', text: 'run exit 9' }])
    await waitForIdle(ctx, agent)
@@ -141,7 +176,7 @@ describe('bash tool through the agent loop', () => {
      textResponse('Background task finished.'),
    ])
    const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(SessionId('it-bg'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('it-bg'), { provider: 'mock', model: 'mock' })

    agent.send([{ type: 'text', text: 'run echo bg-ok in the background' }])
    await waitForIdle(ctx, agent)