Merge remote-tracking branch 'origin/master' into codex/simp-prune-tools-prompt-surface

packages/support/README.md

@@ -6,7 +6,8 @@ Packages that exist to serve development, testing, and the examples rather than
 |---|---|---|
 | `acp-snapshot/` | ACP snapshot suite kit: subprocess scenario harness + golden normalizers + the `defineAcpSnapshotSuite` factory | (library — imported by example `*.snapshot.ts` suites) |
 | `invariants/` | Runtime event-contract assertions for development diagnostics | (listens on `session/*`, `agent/*`) |
+| `loader-smoke/` | Shared real-Loader subprocess harness for keyless example smokes | (library — imported by example e2e suites) |
 | `llm-replay/` | Record/replay adapter: short-circuits `llm/stream` from a recorded session JSONL (keyless snapshot tests) | (listens on `llm/stream`) |
 | `subagent-mock/` | Scripted `SubagentProvider` for deterministic seam/tool tests | (registers on `ctx.subagents`) |
 
-`invariants` is development support but has no environment guard: it runs wherever registered, and the default `dsh-agent-core` bundle mounts it unconditionally. `llm-replay` backs the demos and the snapshot test tier under the per-file coverage gate. `acp-snapshot` carries the snapshot tier's harness/normalizer/suite machinery so every example's suite is a scenario table over one shared, gate-covered implementation. `subagent-mock` exercises the real `ctx.subagents` load path without a model or child agent. A package graduates OUT of `support/` into a product group only when it gains documented product consumers.
+`invariants` is development support but has no environment guard: it runs wherever registered, and the default `dsh-agent-core` bundle mounts it unconditionally. `llm-replay` backs the demos and the snapshot test tier under the per-file coverage gate. `acp-snapshot` carries the snapshot tier's harness/normalizer/suite machinery, while `loader-smoke` owns the parallel stdio/Loader process boundary used by keyless example e2e suites. `subagent-mock` exercises the real `ctx.subagents` load path without a model or child agent. A package graduates OUT of `support/` into a product group only when it gains documented product consumers.

packages/support/acp-snapshot/package.json

@@ -27,9 +27,9 @@
     "vitest": "^4.1.8"
   },
   "peerDependencies": {
-    "cordis": "^4.0.0-rc.6"
+    "cordis": "^4.0.0-rc.7"
   },
   "devDependencies": {
-    "cordis": "^4.0.0-rc.6"
+    "cordis": "^4.0.0-rc.7"
   }
 }

packages/support/invariants/package.json

@@ -26,7 +26,7 @@
     "@deepseek-ai/dsh-llm": "^0.0.1",
     "@deepseek-ai/dsh-scope": "^0.0.1",
     "@deepseek-ai/dsh-session": "^0.0.1",
-    "cordis": "^4.0.0-rc.6"
+    "cordis": "^4.0.0-rc.7"
   },
   "devDependencies": {
     "@deepseek-ai/dsh-agent": "workspace:^",
@@ -37,6 +37,6 @@
     "@deepseek-ai/dsh-system-prompt": "workspace:^",
     "@deepseek-ai/dsh-tools": "workspace:^",
     "@deepseek-ai/dsh-user-approval": "workspace:^",
-    "cordis": "^4.0.0-rc.6"
+    "cordis": "^4.0.0-rc.7"
   }
 }

packages/support/llm-replay/package.json

@@ -24,11 +24,11 @@
   "peerDependencies": {
     "@deepseek-ai/dsh-llm": "^0.0.1",
     "@deepseek-ai/dsh-session": "^0.0.1",
-    "cordis": "^4.0.0-rc.6"
+    "cordis": "^4.0.0-rc.7"
   },
   "devDependencies": {
     "@deepseek-ai/dsh-llm": "workspace:^",
     "@deepseek-ai/dsh-session": "workspace:^",
-    "cordis": "^4.0.0-rc.6"
+    "cordis": "^4.0.0-rc.7"
   }
 }

packages/support/loader-smoke/README.md

@@ -0,0 +1,17 @@
+# `@deepseek-ai/dsh-loader-smoke`
+
+Shared subprocess harness for keyless example smokes that boot the real stdio-agent bin and a real `cordis.yml` through the Cordis Loader. A test supplies absolute bin/config/tsconfig paths, optional environment overrides, and stdin lines; `runLoaderSmoke` owns the isolated cwd, DSH homes, tsx path resolution, 30-second process deadline, captured diagnostics, forced kill, EOF, and cleanup.
+
+Successful runs return stdout and stderr only after a zero exit. Non-zero exits and deadlines reject with both captured streams. `LOADER_SMOKE_TEST_TIMEOUT_MS` leaves Vitest enough room for the process-owned diagnostic timeout to fire first.
+
+This is support-tier test infrastructure, not product API. The consumers are the Loader-path smokes under `examples/{echo-agent,coding-agent,cordis-agent}`.
+
+## Model Experience
+
+None, as this test-only harness boots example processes and inspects their streams without changing an assembled model request.
+
+## Known Limitations and Deferred Work
+
+- **Only the unbuilt tsx/Loader path is exercised** — built-bin artifacts remain the responsibility of their separate e2e smokes.
+- **Captured stdout and stderr are unbounded** — a runaway child can consume memory until the deadline kills it.
+- **Timeout kills only the direct child** — a process tree spawned by a faulty fixture can outlive the smoke and needs external cleanup.

packages/support/loader-smoke/package.json

@@ -0,0 +1,33 @@
+{
+  "name": "@deepseek-ai/dsh-loader-smoke",
+  "description": "Shared subprocess harness for keyless real-Loader example smoke tests",
+  "version": "0.0.1",
+  "private": true,
+  "type": "module",
+  "main": "lib/index.js",
+  "types": "lib/types/index.d.ts",
+  "exports": {
+    ".": {
+      "types": "./lib/types/index.d.ts",
+      "default": "./lib/index.js"
+    },
+    "./src/*": "./src/*",
+    "./package.json": "./package.json"
+  },
+  "files": [
+    "lib/index.js",
+    "lib/types/**/*.d.ts",
+    "lib/types/**/*.d.ts.map",
+    "src"
+  ],
+  "license": "BSD-3-Clause",
+  "dependencies": {
+    "tsx": "^4.22.4"
+  },
+  "peerDependencies": {
+    "cordis": "^4.0.0-rc.6"
+  },
+  "devDependencies": {
+    "cordis": "^4.0.0-rc.6"
+  }
+}

packages/support/loader-smoke/src/index.ts

@@ -0,0 +1,117 @@
+/**
+ * Shared subprocess harness for keyless example smokes that boot a real
+ * `cordis.yml` through the stdio-agent bin and Cordis Loader.
+ *
+ * @module @deepseek-ai/dsh-loader-smoke
+ */
+
+import { spawn } from 'node:child_process'
+import { mkdtemp, rm } from 'node:fs/promises'
+import { tmpdir } from 'node:os'
+import { join } from 'node:path'
+import { fileURLToPath } from 'node:url'
+
+const DEFAULT_PROCESS_TIMEOUT_MS = 30_000
+const TSX_LOADER = fileURLToPath(import.meta.resolve('tsx'))
+
+/** Vitest deadline that leaves room for the subprocess-owned 30-second diagnostic timeout. */
+export const LOADER_SMOKE_TEST_TIMEOUT_MS = DEFAULT_PROCESS_TIMEOUT_MS + 15_000
+
+/** Inputs that vary between real-Loader example smokes. */
+export interface LoaderSmokeOptions {
+  /** Human-readable example name used in failure diagnostics. */
+  readonly label: string
+  /** Prefix for the isolated temporary process cwd. */
+  readonly tempDirPrefix: string
+  /** Absolute stdio-agent bin path. */
+  readonly binScript: string
+  /** Absolute real Loader config path. */
+  readonly configPath: string
+  /** Absolute repo tsconfig path used for unbuilt workspace-package resolution. */
+  readonly tsconfigPath: string
+  /** Environment overrides layered over the parent and isolated DSH homes. */
+  readonly env?: Readonly<NodeJS.ProcessEnv>
+  /** Lines written to stdin before EOF; omitted means immediate EOF. */
+  readonly stdinLines?: readonly string[]
+  /** Process deadline override for harness tests. */
+  readonly processTimeoutMs?: number
+}
+
+/** Captured output from a Loader smoke that exited successfully. */
+export interface LoaderSmokeResult {
+  /** Complete stdout after clean exit. */
+  readonly stdout: string
+  /** Complete stderr after clean exit. */
+  readonly stderr: string
+}
+
+/**
+ * Boot one real Loader tree from an isolated cwd, write the requested stdin
+ * script, close stdin, and await a clean exit. The helper owns process kill and
+ * temp-directory cleanup on every outcome.
+ * @param options - example paths, environment, stdin, and diagnostic identity.
+ * @returns captured stdout and stderr after a zero exit.
+ */
+export async function runLoaderSmoke(options: LoaderSmokeOptions): Promise<LoaderSmokeResult> {
+  const cwd = await mkdtemp(join(tmpdir(), options.tempDirPrefix))
+  const processTimeoutMs = options.processTimeoutMs ?? DEFAULT_PROCESS_TIMEOUT_MS
+  try {
+    return await new Promise((resolve, reject) => {
+      const child = spawn(
+        process.execPath,
+        ['--expose-internals', '--import', TSX_LOADER, options.binScript, options.configPath],
+        {
+          cwd,
+          env: {
+            ...process.env,
+            DSH_HOME: join(cwd, '.dsh'),
+            DSH_AGENTS_HOME: join(cwd, '.agents'),
+            ...options.env,
+            TSX_TSCONFIG_PATH: options.tsconfigPath,
+          },
+          stdio: ['pipe', 'pipe', 'pipe'],
+        },
+      )
+      let stdout = ''
+      let stderr = ''
+      let deferredFailure: Error | undefined
+      child.stdout.setEncoding('utf8')
+      child.stdout.on('data', (chunk: string) => { stdout += chunk })
+      child.stderr.setEncoding('utf8')
+      child.stderr.on('data', (chunk: string) => { stderr += chunk })
+
+      const timer = setTimeout(() => {
+        deferredFailure = new Error(`${options.label} did not exit within ${processTimeoutMs / 1_000}s. stdout:\n${stdout}\nstderr:\n${stderr}`)
+        child.kill('SIGKILL')
+      }, processTimeoutMs)
+
+      child.once('exit', (code) => {
+        clearTimeout(timer)
+        if (deferredFailure !== undefined) {
+          reject(deferredFailure)
+        } else if (code === 0) {
+          resolve({ stdout, stderr })
+        } else {
+          reject(new Error(`${options.label} exited ${String(code)}. stdout:\n${stdout}\nstderr:\n${stderr}`))
+        }
+      })
+
+      // process.execPath and a just-created pipe make these OS-error paths
+      // impractical to induce without replacing the boundary under test.
+      /* v8 ignore start */
+      child.once('error', (error) => {
+        clearTimeout(timer)
+        reject(new Error(`${options.label} failed to start: ${error.message}`))
+      })
+      child.stdin.once('error', (error) => {
+        deferredFailure ??= new Error(`${options.label} stdin failed: ${error.message}`)
+        child.kill('SIGKILL')
+      })
+      /* v8 ignore stop */
+
+      child.stdin.end((options.stdinLines ?? []).map(line => `${line}\n`).join(''))
+    })
+  } finally {
+    await rm(cwd, { recursive: true, force: true })
+  }
+}

packages/support/loader-smoke/tests/fixtures/fail.ts

@@ -0,0 +1,4 @@
+/** Non-zero subprocess fixture for the Loader-smoke harness. */
+
+console.error('fixture failed')
+process.exitCode = 7

packages/support/loader-smoke/tests/fixtures/hang.ts

@@ -0,0 +1,4 @@
+/** Deadline subprocess fixture for the Loader-smoke harness. */
+
+console.log('fixture hanging')
+setInterval(() => {}, 1_000)

packages/support/loader-smoke/tests/fixtures/success.ts

@@ -0,0 +1,16 @@
+/** Successful subprocess fixture for the Loader-smoke harness. */
+
+let input = ''
+process.stdin.setEncoding('utf8')
+process.stdin.on('data', (chunk: string) => { input += chunk })
+process.stdin.on('end', () => {
+  console.log(JSON.stringify({
+    configPath: process.argv[2],
+    cwd: process.cwd(),
+    dshHome: process.env.DSH_HOME,
+    agentsHome: process.env.DSH_AGENTS_HOME,
+    marker: process.env.LOADER_SMOKE_MARKER,
+    input,
+  }))
+  console.error('fixture stderr')
+})

packages/support/loader-smoke/tests/loader-smoke.spec.ts

@@ -0,0 +1,61 @@
+import { existsSync } from 'node:fs'
+import { fileURLToPath } from 'node:url'
+import { describe, expect, it } from 'vitest'
+import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke'
+
+const configPath = '/tmp/fixture.cordis.yml'
+const tsconfigPath = fileURLToPath(new URL('../../../../tsconfig.json', import.meta.url))
+const fixture = (name: string): string => fileURLToPath(new URL(`./fixtures/${name}.ts`, import.meta.url))
+const canonicalTempPath = (path: string): string => path.replace(/^\/private(?=\/var\/)/, '')
+
+describe('runLoaderSmoke', () => {
+  it('isolates the process, writes stdin, captures output, and removes the cwd', async () => {
+    const result = await runLoaderSmoke({
+      label: 'success fixture',
+      tempDirPrefix: 'loader-smoke-success-',
+      binScript: fixture('success'),
+      configPath,
+      tsconfigPath,
+      env: { LOADER_SMOKE_MARKER: 'present' },
+      stdinLines: ['one', 'two'],
+    })
+    const output = JSON.parse(result.stdout) as {
+      configPath: string
+      cwd: string
+      dshHome: string
+      agentsHome: string
+      marker: string
+      input: string
+    }
+    expect(output).toMatchObject({
+      configPath,
+      marker: 'present',
+      input: 'one\ntwo\n',
+    })
+    expect(canonicalTempPath(output.dshHome)).toBe(`${canonicalTempPath(output.cwd)}/.dsh`)
+    expect(canonicalTempPath(output.agentsHome)).toBe(`${canonicalTempPath(output.cwd)}/.agents`)
+    expect(result.stderr).toContain('fixture stderr')
+    expect(existsSync(output.cwd)).toBe(false)
+  }, LOADER_SMOKE_TEST_TIMEOUT_MS)
+
+  it('rejects a non-zero exit with captured diagnostics', async () => {
+    await expect(runLoaderSmoke({
+      label: 'failure fixture',
+      tempDirPrefix: 'loader-smoke-fail-',
+      binScript: fixture('fail'),
+      configPath,
+      tsconfigPath,
+    })).rejects.toThrow('failure fixture exited 7. stdout:\n\nstderr:\nfixture failed')
+  })
+
+  it('kills a process at its deadline and reports captured output', async () => {
+    await expect(runLoaderSmoke({
+      label: 'hanging fixture',
+      tempDirPrefix: 'loader-smoke-hang-',
+      binScript: fixture('hang'),
+      configPath,
+      tsconfigPath,
+      processTimeoutMs: 100,
+    })).rejects.toThrow('hanging fixture did not exit within 0.1s.')
+  })
+})

packages/support/loader-smoke/tsconfig.json

@@ -0,0 +1,11 @@
+{
+  "extends": "../../../tsconfig.base.json",
+  "compilerOptions": {
+    "rootDir": "src",
+    "outDir": "lib/types"
+  },
+  "include": [
+    "src"
+  ],
+  "references": []
+}

packages/support/subagent-mock/package.json

@@ -25,7 +25,7 @@
     "@deepseek-ai/dsh-agent": "^0.0.1",
     "@deepseek-ai/dsh-llm": "^0.0.1",
     "@deepseek-ai/dsh-subagent": "^0.0.1",
-    "cordis": "^4.0.0-rc.6"
+    "cordis": "^4.0.0-rc.7"
   },
   "dependencies": {
     "schemastery": "^3.18.0"
@@ -34,7 +34,7 @@
     "@deepseek-ai/dsh-agent": "workspace:^",
     "@deepseek-ai/dsh-llm": "workspace:^",
     "@deepseek-ai/dsh-subagent": "workspace:^",
-    "@cordisjs/plugin-loader": "^1.0.0-rc.4",
-    "cordis": "^4.0.0-rc.6"
+    "@cordisjs/plugin-loader": "^1.0.0-rc.5",
+    "cordis": "^4.0.0-rc.7"
   }
 }