Merge remote-tracking branch 'origin/master' into codex/enforce-tool-cancellation

examples/README.md

@@ -33,6 +33,10 @@ The full-screen terminal sibling of `repl-agent`: it reuses the same coding back
 
 Run with: `pnpm run demo:tui` (needs `DEEPSEEK_API_KEY`). See [tui-agent/README.md](tui-agent/README.md) for controls and composition.
 
+## jsonrpc-agent
+
+An unattended coding agent driven through the Python SDK: JSON-RPC stdio, foreground-only `bash`, `read` / `write` / `edit`, one foreground `subagent`, `todo_write`, JSONL persistence, and compaction. It excludes terminal UI, stdout logging, approvals, skills, and background task controls. See [jsonrpc-agent/README.md](jsonrpc-agent/README.md).
+
 ## cordis-agent
 
 The **self-referential** demo: the coding spine plus [`@deepseek-ai/dsh-tool-cordis`](../packages/cordis/tool-cordis), whose three tools (`cordis_inspect` / `cordis_mount` / `cordis_unmount`) let the agent inspect the live cordis runtime it runs inside, mount model-written plugins into it (an event listener, a brand-new tool for itself, or a service another mount injects), and dispose them again — all dynamic mounts grouped under one `cordis-dynamic` fiber subtree. The `ctx.fs`/`ctx.web` services ride along provider-only, as the capabilities those plugins build on.

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

@@ -5,10 +5,10 @@ import { defineAcpSnapshotSuite, type Scenario, type SnapshotSuiteOptions } from
 /**
  * The acp-agent example's snapshot suite: the scenario table for
  * `dsh-acp-snapshot`'s suite factory, which owns every compare/guard mechanic
- * (golden + re-persisted-log diffs, record/refresh write-back, the pinned-header
+ * (expected-output + re-persisted-log diffs, record/refresh write-back, the pinned-header
  * uniformity guard, the fixture guards). Fixtures live under `snapshots/<name>/`;
  * `pnpm run test:snapshot:record` re-records model transcripts against the real
- * API; `pnpm run test:snapshot:refresh` rewrites current replay goldens keyless.
+ * API; `pnpm run test:snapshot:refresh` rewrites current replay expected outputs keyless.
  * See the package README (packages/support/acp-snapshot) and the snapshot RFC,
  * docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md.
  */
@@ -137,7 +137,7 @@ const SCENARIOS: Scenario[] = [
   // The mid-turn seams fire during a real model turn, so each is recorded with its hook active
   // (the model's reaction to a deny/block/force-continue is part of the captured transcript).
   // SessionStart/SubagentStart are excluded because detached injection races log
-  // order; SubagentStop writes no transcript, so a golden could not prove it ran.
+  // order; SubagentStop writes no transcript, so an expected output could not prove it ran.
   // Unit tests cover those points; the hook-snapshot-matrix RFC owns the rationale.
   { name: 'hook-cc-promptsubmit-context', hasModelTurn: true, recorded: true },
   { name: 'hook-cc-pretool-deny', hasModelTurn: true, recorded: true },

examples/headless-agent/tests/headless.snapshot.ts

@@ -13,7 +13,7 @@ import { describe, expect, it } from 'vitest'
 const snapshotsDir = join(dirname(fileURLToPath(import.meta.url)), 'snapshots')
 const scenarioDir = join(snapshotsDir, 'advanced-toolchain')
 const sessionFixture = join(scenarioDir, 'session.jsonl')
-const streamGolden = join(scenarioDir, 'stream-json.golden.jsonl')
+const streamExpected = join(scenarioDir, 'stream-json.expected.jsonl')
 const configPath = fileURLToPath(new URL('../advanced.cordis.snapshot.yml', import.meta.url))
 const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src/bin.ts', import.meta.url))
 const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
@@ -134,7 +134,7 @@ describe('headless stream-json snapshots', () => {
 
     expect(result.stderr).toBe('')
     const normalized = normalizeHeadlessStream(result.stdout, runCwd)
-    if (refreshing) await writeFile(streamGolden, normalized)
-    expect(normalized).toBe(await readFile(streamGolden, 'utf8'))
+    if (refreshing) await writeFile(streamExpected, normalized)
+    expect(normalized).toBe(await readFile(streamExpected, 'utf8'))
   }, LOADER_SMOKE_TEST_TIMEOUT_MS)
 })

examples/jsonrpc-agent/README.md

@@ -0,0 +1,24 @@
+# jsonrpc-agent
+
+The unattended coding-agent composition for the Python SDK's bundled JSON-RPC runtime. It intentionally loads no terminal UI, console logger, approval surface, or user-interaction tool because stdout belongs to the SDK protocol and turns are driven by the SDK.
+
+The model-facing tools are:
+
+- `bash`, foreground only
+- `read`, `write`, and `edit`
+- `subagent`, using one foreground in-process spawn provider
+- `todo_write`
+
+The surrounding runtime also loads JSONL session persistence and automatic context compaction. `maxTokensAsSuccess` keeps a token-limited model turn as an accepted evaluation result while preserving its `max-tokens` reason.
+
+## Runtime environment
+
+| Variable | Purpose |
+|---|---|
+| `DEEPSEEK_API_KEY` | Credential passed to the OpenAI-compatible host endpoint |
+| `DEEPSEEK_BASE_URL` | Host endpoint used by `dsh-llm-deepseek` |
+| `DSH_CWD` | Agent workspace for bash and filesystem tools |
+| `DSH_SESSION_ROOT` | JSONL trajectory directory |
+| `DSH_SYSTEM_PROMPT` | Deployment-provided coding persona |
+
+Pass the config path through the Python SDK's `cordis` option or `DSH_CORDIS_CONFIG`. The bundled executable already carries every plugin named by this file; the target machine does not need Node.js.

examples/jsonrpc-agent/cordis.yml

@@ -0,0 +1,74 @@
+# Unattended coding-agent deployment for the bundled dsh-jsonrpc-agent runtime.
+# stdout is reserved for JSON-RPC; do not add a console logger or terminal UI.
+
+- id: jsonrpc
+  name: '@deepseek-ai/dsh-jsonrpc'
+  config:
+    maxTokensAsSuccess: true
+
+- id: llm-deepseek
+  name: '@deepseek-ai/dsh-llm-deepseek'
+  config:
+    apiKey: !!js process.env.DEEPSEEK_API_KEY
+    baseURL: !!js process.env.DEEPSEEK_BASE_URL
+
+- id: bash
+  name: '@deepseek-ai/dsh-bash-local'
+  config:
+    cwd: !!js process.env.DSH_CWD ?? process.cwd()
+    timeoutMs: 60000
+
+- id: agent-spine
+  name: '@deepseek-ai/dsh-agent-spine-demo'
+  config:
+    persona: !!js process.env.DSH_SYSTEM_PROMPT ?? 'You are a coding agent.'
+    workspaceContext: false
+    skills:
+      enabled: false
+    toolBash:
+      enableRunInBackground: false
+    toolTasks: false
+
+- id: sessions
+  name: '@deepseek-ai/dsh-session-persistence-jsonl'
+  config:
+    root: !!js process.env.DSH_SESSION_ROOT ?? './.sessions'
+
+- id: subagent
+  name: '@deepseek-ai/dsh-subagent'
+
+- id: subagent-spawn
+  name: '@deepseek-ai/dsh-subagent-spawn'
+  config:
+    providerName: spawn
+
+- id: tool-subagent
+  name: '@deepseek-ai/dsh-tool-subagent'
+  config:
+    provider: spawn
+    toolName: subagent
+    enableRunInBackground: false
+
+- id: tool-todo
+  name: '@deepseek-ai/dsh-tool-todo'
+
+- id: fs-local
+  name: '@deepseek-ai/dsh-fs-local'
+  config:
+    cwd: !!js process.env.DSH_CWD ?? process.cwd()
+
+- id: fs-policy
+  name: '@deepseek-ai/dsh-fs-policy'
+
+- id: tool-fs
+  name: '@deepseek-ai/dsh-tool-fs'
+
+- id: compact-basic
+  name: '@deepseek-ai/dsh-compact-basic'
+  config:
+    contextWindow: 128000
+    thresholdRatio: 0.8
+    retainTokens: 20480
+    summarizationModel: ''
+    maxTokens: 8192
+    compactionRetries: 1

examples/jsonrpc-agent/package.json

@@ -0,0 +1,7 @@
+{
+  "name": "jsonrpc-agent-example",
+  "private": true,
+  "version": "0.0.1",
+  "type": "module",
+  "description": "Unattended JSON-RPC coding-agent composition"
+}

examples/jsonrpc-agent/tests/keyless-smoke.e2e.ts

@@ -0,0 +1,146 @@
+import { spawn } from 'node:child_process'
+import { createServer } from 'node:http'
+import { mkdtemp, rm } from 'node:fs/promises'
+import { tmpdir } from 'node:os'
+import { join } from 'node:path'
+import { fileURLToPath } from 'node:url'
+import { describe, expect, it } from 'vitest'
+
+const binScript = fileURLToPath(new URL('../../../packages/examples/jsonrpc-demo/src/bin.ts', import.meta.url))
+const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url))
+const repoRoot = fileURLToPath(new URL('../../..', import.meta.url))
+
+function waitForLine(
+  lines: string[],
+  predicate: (value: Record<string, unknown>) => boolean,
+  stderr: () => string,
+): Promise<Record<string, unknown>> {
+  return new Promise((resolve, reject) => {
+    const deadline = Date.now() + 30_000
+    const poll = (): void => {
+      while (lines.length > 0) {
+        const line = lines.shift()!
+        if (!line.trim()) continue
+        try {
+          const value = JSON.parse(line) as Record<string, unknown>
+          if (predicate(value)) {
+            resolve(value)
+            return
+          }
+        } catch {
+          reject(new Error(`non-JSON stdout from JSON-RPC agent runtime: ${line}`))
+          return
+        }
+      }
+      if (Date.now() >= deadline) {
+        reject(new Error(`timed out waiting for JSON-RPC response; stderr=${stderr()}`))
+        return
+      }
+      setTimeout(poll, 10)
+    }
+    poll()
+  })
+}
+
+describe('jsonrpc-agent keyless smoke', () => {
+  it('boots the real Cordis tree and serves initialize/shutdown over clean stdout', async () => {
+    const root = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-agent-smoke-'))
+    const modelRequests: Record<string, unknown>[] = []
+    const modelServer = createServer((request, response) => {
+      let body = ''
+      request.setEncoding('utf8')
+      request.on('data', (chunk: string) => { body += chunk })
+      request.on('end', () => {
+        modelRequests.push(JSON.parse(body) as Record<string, unknown>)
+        response.writeHead(200, { 'content-type': 'text/event-stream' })
+        response.write('data: {"choices":[{"delta":{"role":"assistant","content":null}}]}\n\n')
+        response.write('data: {"choices":[{"delta":{"content":"done"}}]}\n\n')
+        response.write('data: {"choices":[{"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":3,"completion_tokens":1}}\n\n')
+        response.end('data: [DONE]\n\n')
+      })
+    })
+    await new Promise<void>(resolve => modelServer.listen(0, '127.0.0.1', resolve))
+    const address = modelServer.address()
+    if (address === null || typeof address === 'string') throw new Error('model server did not bind a TCP port')
+    const child = spawn(process.execPath, [
+      '--expose-internals',
+      '--import',
+      'tsx',
+      binScript,
+      configPath,
+    ], {
+      cwd: repoRoot,
+      env: {
+        ...process.env,
+        DEEPSEEK_API_KEY: 'keyless-smoke-no-call',
+        DEEPSEEK_BASE_URL: `http://127.0.0.1:${address.port}`,
+        DSH_CWD: root,
+        DSH_SESSION_ROOT: join(root, '.sessions'),
+      },
+      stdio: ['pipe', 'pipe', 'pipe'],
+    })
+    const lines: string[] = []
+    let stdoutBuffer = ''
+    let stderr = ''
+    child.stdout.setEncoding('utf8')
+    child.stdout.on('data', (chunk: string) => {
+      stdoutBuffer += chunk
+      const parts = stdoutBuffer.split('\n')
+      stdoutBuffer = parts.pop() ?? ''
+      lines.push(...parts)
+    })
+    child.stderr.setEncoding('utf8')
+    child.stderr.on('data', (chunk: string) => { stderr += chunk })
+
+    try {
+      child.stdin.write(`${JSON.stringify({
+        jsonrpc: '2.0',
+        id: 1,
+        method: 'initialize',
+        params: { cwd: root, provider: 'deepseek', model: 'deepseek-v4-pro' },
+      })}\n`)
+      const initialized = await waitForLine(lines, value => value.id === 1, () => stderr)
+      expect(initialized).toMatchObject({
+        jsonrpc: '2.0',
+        id: 1,
+        result: { serverInfo: { name: 'deepseek-harness-sdk-runtime' } },
+      })
+
+      child.stdin.write(`${JSON.stringify({
+        jsonrpc: '2.0',
+        id: 2,
+        method: 'session/prompt',
+        params: { sessionId: 'main', contentBlocks: [{ type: 'text', text: 'inspect tools' }] },
+      })}\n`)
+      const prompt = await waitForLine(lines, value => value.id === 2, () => stderr)
+      expect(prompt).toMatchObject({ jsonrpc: '2.0', id: 2, result: { accepted: true } })
+      const tools = modelRequests[0]?.tools as { function?: { name?: string } }[]
+      expect(tools.map(tool => tool.function?.name).sort()).toEqual([
+        'bash',
+        'edit',
+        'read',
+        'subagent',
+        'todo_write',
+        'write',
+      ])
+
+      child.stdin.write(`${JSON.stringify({ jsonrpc: '2.0', id: 3, method: 'shutdown' })}\n`)
+      const shutdown = await waitForLine(lines, value => value.id === 3, () => stderr)
+      expect(shutdown).toMatchObject({ jsonrpc: '2.0', id: 3, result: {} })
+      if (child.exitCode === null) {
+        await new Promise<void>((resolve, reject) => {
+          child.once('exit', (code) => {
+            if (code === 0) resolve()
+            else reject(new Error(`runtime exited ${code}; stderr=${stderr}`))
+          })
+        })
+      } else {
+        expect(child.exitCode, stderr).toBe(0)
+      }
+    } finally {
+      if (child.exitCode === null) child.kill('SIGKILL')
+      await new Promise<void>(resolve => modelServer.close(() => { resolve() }))
+      await rm(root, { recursive: true, force: true })
+    }
+  }, 40_000)
+})

examples/package.json

@@ -8,6 +8,7 @@
     "@cordisjs/plugin-hmr": "workspace:*",
     "@cordisjs/plugin-include": "workspace:*",
     "@deepseek-ai/dsh-acp-demo": "workspace:*",
+    "@deepseek-ai/dsh-agent-spine-demo": "workspace:*",
     "@deepseek-ai/dsh-bash-local": "workspace:*",
     "@deepseek-ai/dsh-bash-sandbox": "workspace:*",
     "@deepseek-ai/dsh-cli-demo": "workspace:*",
@@ -17,12 +18,14 @@
     "@deepseek-ai/dsh-fs-policy": "workspace:*",
     "@deepseek-ai/dsh-hooks-claude": "workspace:*",
     "@deepseek-ai/dsh-hooks-codex": "workspace:*",
+    "@deepseek-ai/dsh-jsonrpc": "workspace:*",
     "@deepseek-ai/dsh-llm": "workspace:*",
     "@deepseek-ai/dsh-llm-deepseek": "workspace:*",
     "@deepseek-ai/dsh-llm-replay": "workspace:*",
     "@deepseek-ai/dsh-permission": "workspace:*",
     "@deepseek-ai/dsh-repeat-tool-guard": "workspace:*",
     "@deepseek-ai/dsh-sandbox-local": "workspace:*",
+    "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:*",
     "@deepseek-ai/dsh-spill-local": "workspace:*",
     "@deepseek-ai/dsh-spill-policy": "workspace:*",
     "@deepseek-ai/dsh-stdio-demo": "workspace:*",

examples/tui-agent/README.md

@@ -20,4 +20,4 @@ Run `pnpm run demo:code-mode tui` for the sibling Code Mode overlay.
 
 ## Snapshot tests
 
-`tests/snapshots/<scenario>/session.jsonl` supplies recorded user prompts and model chunks; sibling child logs drive subagents and workflows. The keyless suite executes those scripts through the real loop and tool implementations, then compares readable terminal cell/style goldens. Use `pnpm run test:snapshot:refresh` for presentation-only changes and `pnpm run test:snapshot:record` with a DeepSeek key when a recorded model journey changes. The implemented [TUI snapshot RFC](../../docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md) owns the scenario matrix and the split between recorded journeys, transient package snapshots, and PTY coverage.
+`tests/snapshots/<scenario>/session.jsonl` supplies recorded user prompts and model chunks; sibling child logs drive subagents and workflows. The keyless suite executes those scripts through the real loop and tool implementations, then compares readable expected terminal cell/style output. Use `pnpm run test:snapshot:refresh` for presentation-only changes and `pnpm run test:snapshot:record` with a DeepSeek key when a recorded model journey changes. The implemented [TUI snapshot RFC](../../docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md) owns the scenario matrix and the split between recorded journeys, transient package snapshots, and PTY coverage.

examples/tui-agent/tests/tui.snapshot.ts

@@ -296,7 +296,7 @@ describe('TUI recorded-session terminal snapshots', () => {
     it(scenario.name, async () => {
       observedScenarios.add(scenario.name)
       const result = await runScenario(scenario)
-      const terminalFile = join(scenarioDir(scenario), 'terminal.golden.txt')
+      const terminalFile = join(scenarioDir(scenario), 'terminal.expected.txt')
       if (MODE === 'record' || MODE === 'refresh') {
         await mkdir(scenarioDir(scenario), { recursive: true })
         await writeFile(terminalFile, result.terminal)
@@ -317,7 +317,7 @@ afterAll(async () => {
   for (const scenario of SCENARIOS) {
     const expected = [
       'session.jsonl',
-      'terminal.golden.txt',
+      'terminal.expected.txt',
       ...scenario.seedWorkspace === true ? ['workspace'] : [],
       ...Array.from({ length: scenario.childSessions ?? 0 }, (_, index) => `session.${index + 1}.jsonl`),
     ].sort()