Merge branch 'master' into feature/cordis-temporary-tools

examples/headless-agent/composition.md

@@ -10,6 +10,8 @@ flowchart LR
   cfg["examples/headless-agent<br/>cordis.yml"]
   plugin_headless_llm_deepseek["llm-deepseek<br/>@deepseek-ai/dsh-llm-deepseek"]
   cfg --> plugin_headless_llm_deepseek
+  plugin_headless_subprocess["subprocess<br/>@deepseek-ai/dsh-subprocess-local"]
+  cfg --> plugin_headless_subprocess
   plugin_headless_bash["bash<br/>@deepseek-ai/dsh-bash-local"]
   cfg --> plugin_headless_bash
   plugin_headless_cli_agent["cli-agent<br/>@deepseek-ai/dsh-cli-demo"]
@@ -54,6 +56,7 @@ flowchart LR
 | Plugin id | Package / module |
 | --- | --- |
 | `llm-deepseek` | `@deepseek-ai/dsh-llm-deepseek` |
+| `subprocess` | `@deepseek-ai/dsh-subprocess-local` |
 | `bash` | `@deepseek-ai/dsh-bash-local` |
 | `cli-agent` | `@deepseek-ai/dsh-cli-demo` |
 | `token-meter` | `@deepseek-ai/dsh-token-meter` |

examples/headless-agent/cordis.yml

@@ -19,6 +19,10 @@
       - id: deepseek-v4-flash
         contextWindow: 128000
 
+# Managed child-process groups for the bash executor (spawn/kill/output plumbing).
+- id: subprocess
+  name: '@deepseek-ai/dsh-subprocess-local'
+
 - id: bash
   name: '@deepseek-ai/dsh-bash-local'
   config:

examples/headless-agent/semantic-checkpoint.cordis.snapshot.yml

@@ -17,6 +17,10 @@
     file: !!js process.env.DSH_SNAPSHOT_FILE
     overrideFile: !!js process.env.DSH_SNAPSHOT_OVERRIDE
 
+# Managed child-process groups for the bash executor (spawn/kill/output plumbing).
+- id: subprocess
+  name: '@deepseek-ai/dsh-subprocess-local'
+
 - id: bash
   name: '@deepseek-ai/dsh-bash-local'
   config:

examples/headless-agent/tests/code-mode.e2e.ts

@@ -13,6 +13,7 @@ import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
 
 import AgentLoop from '@deepseek-ai/dsh-agent-loop'
 import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
+import LocalSubprocessService from '@deepseek-ai/dsh-subprocess-local'
 import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
 import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
 import { WorkerCodeRuntime } from '@deepseek-ai/dsh-code-runtime-worker'
@@ -55,6 +56,7 @@ async function codeModeHarness(cwd: string): Promise<Context> {
   await harness.plugin(AgentRegistry)
   await harness.plugin(AgentLoop, { agents: [] })
   await harness.plugin(LlmDeepSeek)
+  await harness.plugin(LocalSubprocessService)
   await harness.plugin(LocalBashExecutor, { cwd, timeoutMs: 30_000 })
   await harness.plugin(ToolBash)
   await harness.plugin(WorkerCodeRuntime, {})
@@ -114,6 +116,7 @@ async function backgroundCodeModeHarness(cwd: string): Promise<Context> {
   const harness = await typedCodeModeHarness()
   await harness.plugin(LocalTaskService)
   await harness.plugin(ToolTasks, {})
+  await harness.plugin(LocalSubprocessService)
   await harness.plugin(LocalBashExecutor, { cwd, timeoutMs: 30_000 })
   await harness.plugin(ToolBash)
   return harness

examples/headless-agent/tests/fixtures/goal-domain/cordis.yml

@@ -2,6 +2,10 @@
 - id: cli-mock-llm
   name: '../cli-mock-llm.ts'
 
+# Managed child-process groups for the bash executor (spawn/kill/output plumbing).
+- id: subprocess
+  name: '@deepseek-ai/dsh-subprocess-local'
+
 - id: bash
   name: '@deepseek-ai/dsh-bash-local'
 

examples/headless-agent/tests/fixtures/telemetry-otel-driver.ts

@@ -0,0 +1,43 @@
+#!/usr/bin/env node
+/**
+ * Test driver: start a mock OTLP/HTTP collector, boot the telemetry Loader
+ * composition against it, run one turn whose prompt carries a fixture
+ * credential, then persist everything the collector captured to
+ * `./otlp-captures.json` for the e2e's inspect step.
+ */
+
+import { writeFile } from 'node:fs/promises'
+import { createServer } from 'node:http'
+import { once } from 'node:events'
+import { boot, resolveConfigPath } from '@deepseek-ai/dsh-app-boot'
+import { runOneShot } from '@deepseek-ai/dsh-cli-demo/src/cli.ts'
+
+const configPath = process.argv[2]
+if (configPath === undefined) throw new Error('telemetry-otel driver requires a config path')
+
+const captures: unknown[] = []
+const server = createServer((request, response) => {
+  const chunks: Buffer[] = []
+  request.on('data', chunk => chunks.push(chunk as Buffer))
+  request.on('end', () => {
+    captures.push(JSON.parse(Buffer.concat(chunks).toString()))
+    response.writeHead(200, { 'content-type': 'application/json' }).end('{}')
+  })
+})
+server.listen(0, '127.0.0.1')
+await once(server, 'listening')
+const address = server.address()
+if (address === null || typeof address === 'string') throw new Error('collector has no port')
+process.env.DSH_TELEMETRY_E2E_URL = `http://127.0.0.1:${address.port}/v1/logs`
+
+const ctx = await boot('telemetry-otel-e2e', resolveConfigPath(configPath, undefined))
+try {
+  // The fixture credential rides the model-visible user message; the exported
+  // copy must scrub it while the canonical log keeps the original bytes.
+  await runOneShot(ctx, { task: 'prove telemetry with key sk-e2efixture1234567890' })
+} finally {
+  await ctx.fiber.dispose()
+}
+await writeFile('./otlp-captures.json', JSON.stringify(captures))
+server.close()
+server.closeAllConnections()

examples/headless-agent/tests/fixtures/telemetry-otel.cordis.yml

@@ -0,0 +1,28 @@
+# Test-only composition: session-telemetry-otel through the real Loader/app
+# path, exporting to the mock OTLP collector the driver starts (url via env).
+# The redact-rule entry models a deployment mounting its own scrub rule on the
+# telemetry/record waterfall — the seam itself ships no rules.
+- id: cli-mock-llm
+  name: './cli-mock-llm.ts'
+
+- id: telemetry-redact-rule
+  name: './telemetry-redact-rule.ts'
+
+- id: bash
+  name: '@deepseek-ai/dsh-bash-local'
+
+- id: telemetry-otel
+  name: '@deepseek-ai/dsh-session-telemetry-otel'
+  config:
+    exporter:
+      url: !!js process.env.DSH_TELEMETRY_E2E_URL
+
+- id: cli-agent
+  name: '@deepseek-ai/dsh-cli-demo'
+  config:
+    provider: cli-mock
+    model: cli-mock
+    persona: 'Test the session-telemetry-otel plugin.'
+    persistenceRoot: './.sessions'
+    persistenceCompression: 'none'
+    workspaceContext: false

examples/headless-agent/tests/fixtures/telemetry-redact-rule.ts

@@ -0,0 +1,29 @@
+import type { Context } from 'cordis'
+
+/**
+ * Deployment-style redaction rule for the telemetry e2e: scrubs the fixture
+ * credential from body strings, exactly as a real deployment would mount its
+ * own rules on the `telemetry/record` waterfall.
+ */
+
+const SECRET = /sk-e2efixture[0-9]+/g
+const PLACEHOLDER = '[E2E-REDACTED]'
+
+function scrub(value: unknown): unknown {
+  if (typeof value === 'string') return value.replace(SECRET, PLACEHOLDER)
+  if (Array.isArray(value)) return value.map(scrub)
+  if (value !== null && typeof value === 'object') {
+    return Object.fromEntries(Object.entries(value).map(([key, entry]) => [key, scrub(entry)]))
+  }
+  return value
+}
+
+export const name = 'telemetry-redact-rule'
+
+/** Mount the fixture scrub rule onto the redact waterfall. */
+export function apply(ctx: Context): void {
+  ctx.on('telemetry/record', (_record, next) => {
+    const record = next()
+    return { ...record, body: scrub(record.body) }
+  })
+}

examples/headless-agent/tests/fixtures/time-context.cordis.yml

@@ -2,6 +2,10 @@
 - id: time-context-mock-llm
   name: './time-context-mock-llm.ts'
 
+# Managed child-process groups for the bash executor (spawn/kill/output plumbing).
+- id: subprocess
+  name: '@deepseek-ai/dsh-subprocess-local'
+
 - id: bash
   name: '@deepseek-ai/dsh-bash-local'
 

examples/headless-agent/tests/harness.ts

@@ -4,6 +4,7 @@ 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 { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
+import LocalSubprocessService from '@deepseek-ai/dsh-subprocess-local'
 import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
 import * as ToolTodo from '@deepseek-ai/dsh-tool-todo'
 import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
@@ -59,6 +60,7 @@ export async function codingHarness(workdir: string, options: CodingHarnessOptio
   await ctx.plugin(LlmDeepSeek, options.modelContextWindow === undefined ? {} : {
     models: [{ id: 'deepseek-v4-flash', contextWindow: options.modelContextWindow }],
   })
+  await ctx.plugin(LocalSubprocessService)
   await ctx.plugin(LocalBashExecutor, { cwd: workdir, timeoutMs: 30_000 })
   await ctx.plugin(ToolBash)
   await ctx.plugin(ToolTodo)