feat(dsbench): add SDK evaluation composition

docs/config-catalog.md

@@ -56,7 +56,7 @@ export interface Config {
   skills?: agentCore.SkillConfig
   /** Model-facing bash tool config forwarded through agent-core. */
   toolBash?: NonNullable<agentCore.Config['toolBash']>
-  /** Generic background-task control-tool config forwarded through agent-core. */
+  /** Generic background-task controls forwarded through agent-core; set false to omit their tool surface. */
   toolTasks?: NonNullable<agentCore.Config['toolTasks']>
 }
 ```
@@ -120,12 +120,14 @@ export interface Config {
   skills?: SkillConfig
   /** Model-facing bash tool config, including this producer's background opt-in. */
   toolBash?: toolBash.Config
-  /** Generic background-task control-tool wait bounds. */
-  toolTasks?: toolTasks.Config
+  /** Generic background-task controls; set false to keep the task service without model-facing task tools. */
+  toolTasks?: toolTasks.Config | false
 }
 
 /** Skill bundle config forwarded to the registry, local provider, and model-facing consumer. */
 export interface SkillConfig {
+  /** Mount the bundled local skill provider and model-facing skill tool (default true). */
+  enabled?: boolean
   /** Registry-level discovery cache settings. */
   registry?: SkillRegistryConfig
   /** Local filesystem skill provider settings. */
@@ -137,7 +139,7 @@ export interface SkillConfig {
 
 Depends on: [`AgentLoopConfig`](#deepseek-aidsh-agent-loop) · [`SkillLocal`](../packages/skill/skill-local/src/index.ts) · [`SkillRegistryConfig`](#deepseek-aidsh-skill) · [`SystemPromptConfig`](#deepseek-aidsh-system-prompt) · [`toolBash`](../packages/bash/tool-bash/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) · [`toolSkill`](../packages/skill/tool-skill/src/index.ts) · [`toolTasks`](../packages/tasks/tool-tasks/src/index.ts) · [`workspaceContext`](../packages/context/workspace-context/src/index.ts)
 
-Source: [`packages/examples/agent-spine-demo/src/index.ts:55`](../packages/examples/agent-spine-demo/src/index.ts)
+Source: [`packages/examples/agent-spine-demo/src/index.ts:57`](../packages/examples/agent-spine-demo/src/index.ts)
 
 ## `@deepseek-ai/dsh-bash-local`
 
@@ -343,8 +345,10 @@ Source: [`packages/hooks/hooks-codex/src/index.ts:41`](../packages/hooks/hooks-c
 Requires: `agents`
 
 ```ts config-catalog
-/** Runtime-only test seams; no field is configurable from `cordis.yml`. */
+/** JSON-RPC deployment config plus runtime-only test seams. */
 export interface JsonRpcConfig {
+  /** Report max-token turn/subagent termination as a successful SDK result. */
+  maxTokensAsSuccess?: boolean
   /** Transport input override; production uses `process.stdin`. */
   input?: Readable
   /** Transport output override; production uses `process.stdout`. */
@@ -724,7 +728,7 @@ export interface Config {
   skills?: agentCore.SkillConfig
   /** Model-facing bash tool config forwarded through agent-core. */
   toolBash?: NonNullable<agentCore.Config['toolBash']>
-  /** Generic background-task control-tool config forwarded through agent-core. */
+  /** Generic background-task controls forwarded through agent-core; set false to omit their tool surface. */
   toolTasks?: NonNullable<agentCore.Config['toolTasks']>
   /**
    * If set, the `main` agent RESUMES this persisted session id instead of

examples/README.md

@@ -21,6 +21,10 @@ Run with: `pnpm run demo:repl` (needs `DEEPSEEK_API_KEY` in the environment or a
 
 Run the Code Mode overlay with `pnpm run demo:code-mode`, or pass `acp` for the ACP example. See the [Code Mode example](coding-agent/README.md#code-mode) for its composition and a sample task.
 
+## dsbench-coding-agent
+
+The unattended SDK composition used by DSBench: 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 [dsbench-coding-agent/README.md](dsbench-coding-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/dsbench-coding-agent/README.md

@@ -0,0 +1,24 @@
+# dsbench-coding-agent
+
+The DSBench deployment 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 benchmark turns are unattended.
+
+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 benchmark 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` | Benchmark workspace for bash and filesystem tools |
+| `DSH_SESSION_ROOT` | JSONL trajectory directory |
+| `DSH_SYSTEM_PROMPT` | DSBench-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/dsbench-coding-agent/cordis.yml

@@ -0,0 +1,77 @@
+# DSBench 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
+    models:
+      - deepseek-v4-flash
+      - deepseek-v4-pro
+
+- 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 driven by DSBench.'
+    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/dsbench-coding-agent/package.json

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

examples/dsbench-coding-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 DSBench 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('dsbench-coding-agent keyless smoke', () => {
+  it('boots the real Cordis tree and serves initialize/shutdown over clean stdout', async () => {
+    const root = await mkdtemp(join(tmpdir(), 'dsh-dsbench-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, 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)
+})

packages/examples/acp-demo/src/index.ts

@@ -46,7 +46,7 @@ export interface Config {
   skills?: agentCore.SkillConfig
   /** Model-facing bash tool config forwarded through agent-core. */
   toolBash?: NonNullable<agentCore.Config['toolBash']>
-  /** Generic background-task control-tool config forwarded through agent-core. */
+  /** Generic background-task controls forwarded through agent-core; set false to omit their tool surface. */
   toolTasks?: NonNullable<agentCore.Config['toolTasks']>
 }
 
@@ -67,7 +67,7 @@ export const Config: z<Config> = z.object({
   workspaceContext: z.union([z.const(false), workspaceContext.Config]).required(),
   skills: agentCore.SkillConfigSchema,
   toolBash: agentCore.ToolBashConfigSchema,
-  toolTasks: agentCore.ToolTasksConfigSchema,
+  toolTasks: z.union([z.const(false), agentCore.ToolTasksConfigSchema]),
 })
 /* jscpd:ignore-end */
 

packages/examples/agent-spine-demo/README.md

@@ -46,7 +46,7 @@ import type { Config } from '@deepseek-ai/dsh-agent-spine-demo'
 // workspaceContext requires { maxBytes } or false; the other owner schemas supply defaults.
 ```
 
-The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates a `main`; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer; the required `workspaceContext` choice to `dsh-workspace-context` (`{ maxBytes }` enables loading and `false` disables it); and `toolBash`/`toolTasks` to the two model-facing tool plugins the bundle owns. `toolBash.enableRunInBackground` controls only the bash producer, while `toolTasks` controls generic `task_output` wait bounds; independently loaded producers keep their own config. Workspace instructions register before the skill catalog so their session-prefix message renders first. App packages use `pickSpineConfig()` to copy only these bundle-owned fields.
+The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates a `main`; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer; the required `workspaceContext` choice to `dsh-workspace-context` (`{ maxBytes }` enables loading and `false` disables it); and `toolBash`/`toolTasks` to the two model-facing tool plugins the bundle owns. Set `skills.enabled: false` to omit both the local provider and model-facing skill tool, and set `toolTasks: false` to retain the task service for foreground producers without exposing `task_output` / `task_list` / `task_kill`. `toolBash.enableRunInBackground` controls only the bash producer; independently loaded producers keep their own config. Workspace instructions register before the skill catalog so their session-prefix message renders first. App packages use `pickSpineConfig()` to copy only these bundle-owned fields.
 
 ## Why a code bundle, not a shared YAML include
 

packages/examples/agent-spine-demo/src/index.ts

@@ -30,6 +30,8 @@ export const name = 'agent-spine-demo'
 
 /** Skill bundle config forwarded to the registry, local provider, and model-facing consumer. */
 export interface SkillConfig {
+  /** Mount the bundled local skill provider and model-facing skill tool (default true). */
+  enabled?: boolean
   /** Registry-level discovery cache settings. */
   registry?: SkillRegistryConfig
   /** Local filesystem skill provider settings. */
@@ -67,12 +69,13 @@ export interface Config {
   skills?: SkillConfig
   /** Model-facing bash tool config, including this producer's background opt-in. */
   toolBash?: toolBash.Config
-  /** Generic background-task control-tool wait bounds. */
-  toolTasks?: toolTasks.Config
+  /** Generic background-task controls; set false to keep the task service without model-facing task tools. */
+  toolTasks?: toolTasks.Config | false
 }
 
 /** The skill config schema exported for app packages that forward `skills`. */
 export const SkillConfigSchema: z<SkillConfig> = z.object({
+  enabled: z.boolean().default(true),
   registry: SkillService.Config,
   local: SkillLocal.Config,
   tool: toolSkill.Config,
@@ -93,7 +96,7 @@ export const Config = z.intersect([
     skills: SkillConfigSchema,
     workspaceContext: z.union([z.const(false), workspaceContext.Config]).required(),
     toolBash: ToolBashConfigSchema,
-    toolTasks: ToolTasksConfigSchema,
+    toolTasks: z.union([z.const(false), ToolTasksConfigSchema]),
   }) as unknown as z<Pick<Config, 'tools' | 'skills' | 'workspaceContext' | 'toolBash' | 'toolTasks'>>,
 ]) as unknown as z<Config>
 
@@ -134,8 +137,11 @@ export function apply(ctx: Context, config: Config): void {
     ...config.toolOrder !== undefined ? { toolOrder: config.toolOrder } : {},
   })
   ctx.plugin(ToolRegistry, config.tools ?? {})
-  ctx.plugin(SkillService, config.skills?.registry ?? {})
-  ctx.plugin(SkillLocal, config.skills?.local ?? {})
+  const skillsEnabled = config.skills?.enabled ?? true
+  if (skillsEnabled) {
+    ctx.plugin(SkillService, config.skills?.registry ?? {})
+    ctx.plugin(SkillLocal, config.skills?.local ?? {})
+  }
   ctx.plugin(AgentRegistry)
   ctx.plugin(TaskService)
   ctx.plugin(invariants)
@@ -145,7 +151,7 @@ export function apply(ctx: Context, config: Config): void {
   }
   // Both plugins prepend session-prefix messages. Registration order is the
   // rendered order, so workspace instructions must precede the skill catalog.
-  ctx.plugin(toolSkill, config.skills?.tool ?? {})
-  ctx.plugin(toolTasks, config.toolTasks ?? {})
+  if (skillsEnabled) ctx.plugin(toolSkill, config.skills?.tool ?? {})
+  if (config.toolTasks !== false) ctx.plugin(toolTasks, config.toolTasks ?? {})
   ctx.plugin(AgentLoop, { agents: config.agents ?? [] })
 }

packages/examples/agent-spine-demo/tests/agent-core.spec.ts

@@ -301,6 +301,21 @@ describe('dsh-agent-spine-demo bundle', () => {
     await ctx.fiber.dispose()
   })
 
+  it('can omit skills and model-facing task controls for a foreground-only deployment', async () => {
+    const ctx = await mount({
+      workspaceContext: false,
+      skills: { enabled: false },
+      toolBash: { enableRunInBackground: false },
+      toolTasks: false,
+    }, true)
+
+    expect(ctx.tools.schemas().map(tool => tool.name)).toEqual(['bash'])
+    expect(ctx.get('skills')).toBeUndefined()
+    expect(ctx.get('tasks')).toBeDefined()
+
+    await ctx.fiber.dispose()
+  })
+
   it('picks shared spine config without leaking front-door fields', () => {
     const appConfig = {
       model: 'front-door-only',
@@ -308,9 +323,9 @@ describe('dsh-agent-spine-demo bundle', () => {
       toolOrder: ['zulu'],
       tools: { mode: 'native' as const },
       workspaceContext: false as const,
-      skills: {},
+      skills: { enabled: false },
       toolBash: { enableRunInBackground: false },
-      toolTasks: { waitTimeoutMs: 7, maxWaitTimeoutMs: 11 },
+      toolTasks: false as const,
     }
 
     expect(agentCore.pickSpineConfig(appConfig)).toEqual({
@@ -318,7 +333,7 @@ describe('dsh-agent-spine-demo bundle', () => {
       toolOrder: appConfig.toolOrder,
       tools: appConfig.tools,
       workspaceContext: false,
-      skills: {},
+      skills: appConfig.skills,
       toolBash: appConfig.toolBash,
       toolTasks: appConfig.toolTasks,
     })

packages/examples/stdio-demo/src/index.ts

@@ -51,7 +51,7 @@ export interface Config {
   skills?: agentCore.SkillConfig
   /** Model-facing bash tool config forwarded through agent-core. */
   toolBash?: NonNullable<agentCore.Config['toolBash']>
-  /** Generic background-task control-tool config forwarded through agent-core. */
+  /** Generic background-task controls forwarded through agent-core; set false to omit their tool surface. */
   toolTasks?: NonNullable<agentCore.Config['toolTasks']>
   /**
    * If set, the `main` agent RESUMES this persisted session id instead of
@@ -77,7 +77,7 @@ export const Config: z<Config> = z.object({
   welcome: z.string().default('ready.'),
   skills: agentCore.SkillConfigSchema,
   toolBash: agentCore.ToolBashConfigSchema,
-  toolTasks: agentCore.ToolTasksConfigSchema,
+  toolTasks: z.union([z.const(false), agentCore.ToolTasksConfigSchema]),
   resumeSessionId: z.string(),
   workspaceContext: z.union([z.const(false), workspaceContext.Config]).required(),
 })

packages/llm/llm-deepseek/src/adapter.ts

@@ -61,6 +61,9 @@ export class DeepSeekAdapter extends LlmAdapter {
         'content-type': 'application/json',
         'accept': 'text/event-stream',
         ...attributionHeaders(),
+        ...options.sessionId !== undefined
+          ? { 'x-deepseek-harness-session-id': String(options.sessionId) }
+          : {},
       },
       body: JSON.stringify(body),
       ...options.signal ? { signal: options.signal } : {},

packages/llm/llm-deepseek/tests/adapter.spec.ts

@@ -3,6 +3,7 @@ import type { IncomingMessage, Server, ServerResponse } from 'node:http'
 import { afterEach, describe, expect, it, vi } from 'vitest'
 import { Context } from 'cordis'
 import LlmService, { LlmError, userAgent } from '@deepseek-ai/dsh-llm'
+import { SessionId } from '@deepseek-ai/dsh-session'
 import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
 import { DeepSeekAdapter, httpErrorCode } from '@deepseek-ai/dsh-llm-deepseek'
 import { assemble } from './assemble.ts'
@@ -131,6 +132,19 @@ describe('DeepSeekAdapter against a mock server', () => {
     expect(kinds).toEqual(['block-start', 'text-delta', 'block-end', 'usage', 'finish'])
   })
 
+  it('forwards the harness session id for host-side trajectory routing', async () => {
+    const server = await mockServer([{ kind: 'sse', events: textEvents }])
+    const ctx = await harness(server.url)
+
+    await assemble(ctx, {
+      model: 'deepseek-v4-flash',
+      messages: [{ role: 'user', content: [{ type: 'text', text: 'hi' }] }],
+      sessionId: SessionId('child-session'),
+    })
+
+    expect(server.headers[0]?.['x-deepseek-harness-session-id']).toBe('child-session')
+  })
+
   it('forwards thinking config onto the wire', async () => {
     const server = await mockServer([{ kind: 'sse', events: textEvents }])
     const ctx = await harness(server.url, { thinking: 'disabled', reasoningEffort: 'high' })

packages/ui/jsonrpc/README.md

@@ -8,7 +8,7 @@ Stdio JSON-RPC plugin for out-of-process SDK clients such as Python `deepseek_ha
 
 ## Config
 
-No `cordis.yml` keys. `JsonRpcConfig.input`, `output`, and `exit` are test-only runtime seams; production uses process stdio and `process.exit`.
+`maxTokensAsSuccess` defaults to `false`. Set it to `true` for evaluation hosts that distinguish an accepted, token-limited agent result from an infrastructure failure. `JsonRpcConfig.input`, `output`, and `exit` are test-only runtime seams; production uses process stdio and `process.exit`.
 
 ## stdout is the protocol
 

packages/ui/jsonrpc/src/index.ts

@@ -22,8 +22,10 @@ export const name = 'jsonrpc'
 // Only the agent factory is required; initialize reads the optional LLM seam with ctx.get().
 export const inject = ['agents']
 
-/** Runtime-only test seams; no field is configurable from `cordis.yml`. */
+/** JSON-RPC deployment config plus runtime-only test seams. */
 export interface JsonRpcConfig {
+  /** Report max-token turn/subagent termination as a successful SDK result. */
+  maxTokensAsSuccess?: boolean
   /** Transport input override; production uses `process.stdin`. */
   input?: Readable
   /** Transport output override; production uses `process.stdout`. */
@@ -32,7 +34,9 @@ export interface JsonRpcConfig {
   exit?: (code: number) => void
 }
 
-export const Config: Schema<JsonRpcConfig> = Schema.object({})
+export const Config: Schema<JsonRpcConfig> = Schema.object({
+  maxTokensAsSuccess: Schema.boolean().default(false),
+})
 
 /**
  * Serve SDK requests over the configured streams. Effect disposal shuts down
@@ -51,7 +55,9 @@ export function apply(ctx: Context, config: JsonRpcConfig): void {
   const exit = config.exit ?? ((code: number): void => { process.exit(code) })
 
   const transport = new JsonRpcLineTransport(input, output)
-  const server = new HarnessSdkServer(ctx, transport)
+  const server = new HarnessSdkServer(ctx, transport, {
+    maxTokensAsSuccess: config.maxTokensAsSuccess ?? false,
+  })
 
   // Share one exit task and attempt flush and disposal independently before exiting.
   let exitTask: Promise<void> | undefined

packages/ui/jsonrpc/src/server.ts

@@ -59,6 +59,12 @@ interface SubagentRecord {
   parentSessionId: string | undefined
 }
 
+/** Deployment-specific status mapping for SDK turn and subagent outcomes. */
+export interface HarnessSdkServerOptions {
+  /** Report max-token termination as an accepted result instead of an infrastructure error. */
+  maxTokensAsSuccess?: boolean
+}
+
 /**
  * SDK server over one booted harness context and transport peer. Construction
  * subscribes to session, agent, and subagent lifecycle events until shutdown;
@@ -78,6 +84,7 @@ export class HarnessSdkServer {
   constructor(
     private readonly ctx: Context,
     private readonly transport: JsonRpcTransportPeer,
+    private readonly options: HarnessSdkServerOptions = {},
   ) {
     this.disposers.push(ctx.on('session/event', (session, event) => {
       if (event.type === 'turn/end') {
@@ -116,7 +123,7 @@ export class HarnessSdkServer {
         agentId: String(info.id),
         ...(parentSessionId === undefined ? {} : { parentSessionId }),
         childSessionId,
-        status: info.stopReason === 'completed' ? 'ok' : 'error',
+        status: this.successStatus(info.stopReason),
         stopReason: info.stopReason,
         ...(info.lastAssistantMessage === undefined ? {} : { lastAssistantMessage: info.lastAssistantMessage }),
       })
@@ -253,7 +260,12 @@ export class HarnessSdkServer {
 
   private finishedStatus(reason: TurnEndReason | undefined): 'ok' | 'error' {
     if (!reason) return 'error'
-    return reason.kind === 'completed' ? 'ok' : 'error'
+    return this.successStatus(reason.kind)
+  }
+
+  private successStatus(reason: string): 'ok' | 'error' {
+    if (reason === 'completed') return 'ok'
+    return reason === 'max-tokens' && this.options.maxTokensAsSuccess === true ? 'ok' : 'error'
   }
 
   private hasAdapterFor(model: string): boolean {

packages/ui/jsonrpc/tests/server.spec.ts

@@ -329,7 +329,7 @@ describe('HarnessSdkServer', () => {
         agentOptions: { model: 'deepseek' },
       })
       const transport = new FakeTransport()
-      const server = new HarnessSdkServer(ctx, transport)
+      const server = new HarnessSdkServer(ctx, transport, { maxTokensAsSuccess: true })
 
       await settleSubagent(ctx, parentHandle.agent, {
         provider: 'fork',
@@ -355,7 +355,7 @@ describe('HarnessSdkServer', () => {
           agentId: 'fallback-child-agent',
           parentSessionId: 'fallback-parent',
           childSessionId: 'fallback-child-session',
-          status: 'error',
+          status: 'ok',
           stopReason: 'max-tokens',
           lastAssistantMessage: [],
         },
@@ -443,6 +443,24 @@ describe('HarnessSdkServer', () => {
     }
   })
 
+  it('can report max-token turn termination as an accepted evaluation result', async () => {
+    const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-max-tokens-success-'))
+    const ctx = await makeHarness(storageDir)
+    try {
+      const server = new HarnessSdkServer(ctx, new FakeTransport(), { maxTokensAsSuccess: true }) as unknown as {
+        finishedStatus(reason: unknown): 'ok' | 'error'
+        shutdown(): Promise<Record<string, never>>
+      }
+
+      expect(server.finishedStatus({ kind: 'max-tokens' })).toBe('ok')
+      expect(server.finishedStatus({ kind: 'error' })).toBe('error')
+      await server.shutdown()
+    } finally {
+      await ctx.fiber.dispose()
+      await rm(storageDir, { recursive: true, force: true })
+    }
+  })
+
   it('reports no adapter when the LLM service is absent', async () => {
     const ctx = new Context()
     try {