feat(dsbench): add SDK evaluation composition

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(),
 })