Merge remote-tracking branch 'origin/master' into session-fork

examples/acp-agent/tests/acp.e2e.ts

@@ -92,6 +92,46 @@ function spawnAcpAgent(cwd: string, env: NodeJS.ProcessEnv = process.env): Spawn
 let spawned: Spawned | undefined
 let workdir: string | undefined
 
+function hasStdoutLine(out: string[]): boolean {
+  return out.join('').split('\n').some(line => line.trim().length > 0)
+}
+
+async function waitForStdoutLine(child: ChildProcessWithoutNullStreams, out: string[], stderr: string[], timeoutMs: number): Promise<void> {
+  await new Promise<void>((resolve, reject) => {
+    const cleanup = () => {
+      clearTimeout(timeout)
+      child.stdout.off('data', onData)
+      child.off('exit', onExit)
+      child.off('error', onError)
+    }
+    const pass = () => {
+      cleanup()
+      resolve()
+    }
+    const fail = (reason: string) => {
+      cleanup()
+      reject(new Error(`${reason}; stderr: ${stderr.join('')}`))
+    }
+    const onData = () => {
+      if (hasStdoutLine(out)) pass()
+    }
+    const onExit = (code: number | null, signal: NodeJS.Signals | null) => {
+      fail(`ACP child exited before emitting a stdout frame (code ${code ?? 'null'}, signal ${signal ?? 'null'})`)
+    }
+    const onError = (error: Error) => {
+      fail(`ACP child failed before emitting a stdout frame: ${error.message}`)
+    }
+    const timeout = setTimeout(() => {
+      fail(`ACP child did not emit a stdout frame within ${timeoutMs}ms`)
+    }, timeoutMs)
+
+    child.stdout.on('data', onData)
+    child.on('exit', onExit)
+    child.on('error', onError)
+    onData()
+  })
+}
+
 afterEach(async () => {
   if (spawned) {
     spawned.child.kill('SIGKILL')
@@ -114,16 +154,21 @@ describe('acp-agent over real stdio (no key required)', () => {
       stdio: ['pipe', 'pipe', 'pipe'],
     })
     const out: string[] = []
+    const stderr: string[] = []
     child.stdout.setEncoding('utf8')
+    child.stderr.setEncoding('utf8')
     child.stdout.on('data', (c: string) => out.push(c))
+    child.stderr.on('data', (c: string) => stderr.push(c))
 
     // Send a single initialize request as a newline-delimited JSON-RPC frame.
     const req = JSON.stringify({ jsonrpc: '2.0', id: 1, method: 'initialize', params: { protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} } })
     child.stdin.write(req + '\n')
 
-    // Give it a moment to boot + reply, then inspect stdout.
-    await new Promise(r => setTimeout(r, 4000))
-    child.kill('SIGKILL')
+    try {
+      await waitForStdoutLine(child, out, stderr, 15_000)
+    } finally {
+      child.kill('SIGKILL')
+    }
 
     const lines = out.join('').split('\n').filter(l => l.trim().length > 0)
     expect(lines.length).toBeGreaterThan(0)

examples/coding-agent/tests/compaction.e2e.ts

@@ -43,8 +43,8 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compa
     // A handful of files for the model to read, so multiple bash steps
     // accumulate surface nodes (tool calls + results) and grow the history past
     // the (deliberately tiny) window.
-    for (let i = 1; i <= 6; i++) {
-      await writeFile(join(workdir, `file${i}.txt`), `This is file number ${i}. `.repeat(40))
+    for (let i = 1; i <= 4; i++) {
+      await writeFile(join(workdir, `file${i}.txt`), `This is file number ${i}. `.repeat(50))
     }
 
     // Tiny window so a couple of steps crosses the threshold. The generation
@@ -55,21 +55,21 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compa
     ctx = await codingHarness(workdir, {
       persona: SYSTEM_PROMPT,
       compact: {
-        contextWindow: 2400,
+        contextWindow: 2000,
         thresholdRatio: 0.5,
-        retainTokens: 500,
+        retainTokens: 400,
         summarizationModel: '',
-        maxTokens: 2048,
+        maxTokens: 1024,
         compactionRetries: 1,
       },
-      persistenceRoot: './.sessions',
+      persistenceRoot: join(workdir, '.sessions'),
     })
     const agent = ctx.agentLoop.create(AgentId('e2e-compaction'), { model: 'deepseek-v4-flash' })
 
     agent.send([{
       type: 'text',
-      text: 'Read file1.txt, file2.txt, file3.txt, file4.txt, file5.txt, and file6.txt one at a '
-        + 'time using cat (a separate bash command for each). After reading all six, tell me how '
+      text: 'Read file1.txt, file2.txt, file3.txt, and file4.txt one at a '
+        + 'time using cat (a separate bash command for each). After reading all four, tell me how '
         + 'many files you read and the number mentioned in file1.txt.',
     }])
     await waitForIdle(ctx, agent)
@@ -98,9 +98,9 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compa
     expect(summaryData.shadowedSeqs.length).toBeGreaterThan(0)
 
     // The conversation survived compaction: the agent produced a final answer
-    // that reflects the work (it read six files).
+    // that reflects the work (it read four files).
     const answer = finalText(events).toLowerCase()
     expect(answer.length).toBeGreaterThan(0)
-    expect(answer).toMatch(/\b(6|six)\b/)
+    expect(answer).toMatch(/\b(4|four)\b/)
   }, 240_000)
 })

examples/coding-agent/tests/full-loop.e2e.ts

@@ -1,3 +1,6 @@
+import { mkdtemp, rm } from 'node:fs/promises'
+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'
@@ -9,6 +12,7 @@ import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.
  */
 
 let ctx: Context | undefined
+let workdir: string | undefined
 
 afterEach(async () => {
   // Always dispose the harness, even on failure/retry/timeout: agent-loop
@@ -16,11 +20,14 @@ afterEach(async () => {
   // process the model left behind.
   await ctx?.fiber.dispose()
   ctx = undefined
+  if (workdir !== undefined) await rm(workdir, { recursive: true, force: true })
+  workdir = undefined
 })
 
 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(), { persona: SYSTEM_PROMPT })
+    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' })
 
     agent.send([{ type: 'text', text: 'Run `echo e2e-ok` with the bash tool and tell me its exact output.' }])

examples/coding-agent/tests/todo-write.e2e.ts

@@ -1,3 +1,6 @@
+import { mkdtemp, rm } from 'node:fs/promises'
+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'
@@ -10,15 +13,19 @@ import { codingHarness, TODO_SYSTEM_PROMPT, waitForIdle } from './harness.ts'
  */
 
 let ctx: Context | undefined
+let workdir: string | undefined
 
 afterEach(async () => {
   await ctx?.fiber.dispose()
   ctx = undefined
+  if (workdir !== undefined) await rm(workdir, { recursive: true, force: true })
+  workdir = undefined
 })
 
 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(), { persona: TODO_SYSTEM_PROMPT })
+    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' })
 
     agent.send([{ type: 'text', text: