Merge finalized Web transcript parent

packages/core/agent-loop/tests/mock-adapter.ts

@@ -67,6 +67,7 @@ export class MockAdapter extends LlmAdapter {
   constructor(
     private script: (StreamChunk[] | ((options: GenerateOptions) => StreamChunk[]) | 'hang')[],
     private readonly reasoning?: LlmModelReasoningInfo,
+    private readonly defaultMaxTokens?: number,
   ) {
     super()
   }
@@ -80,6 +81,7 @@ export class MockAdapter extends LlmAdapter {
       id: model,
       name: model,
       ...this.reasoning === undefined ? {} : { reasoning: this.reasoning },
+      ...this.defaultMaxTokens === undefined ? {} : { defaultMaxTokens: this.defaultMaxTokens },
     })
   }
 

packages/core/agent-loop/tests/request-cache.e2e.ts

@@ -71,7 +71,7 @@ function waitForIdle(context: Context, agent: Agent): Promise<void> {
 describe.skipIf(!process.env.DEEPSEEK_API_KEY)('log-derived request cache hits (real API)', () => {
   it('every request after the first hits the provider prefix cache', async () => {
     ctx = await loopHarness()
-    const agent = ctx.agentLoop.create(SessionId('cache-e2e'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
+    const agent = ctx.agentLoop.create(SessionId('cache-e2e'), { provider: 'deepseek-official', model: 'deepseek-v4-flash' })
 
     // Turn 1: forces a tool call → at least two steps (two model requests).
     agent.followup(createUserMessage({ content: [{ type: 'text', text: 'Look up the key "deploy-color" with the lookup tool and tell me the value.' }], source: { kind: 'user' } }))

packages/core/agent-loop/tests/request-reconstruction.spec.ts

@@ -18,6 +18,13 @@ import AgentLoop from '@deepseek-ai/dsh-agent-loop'
 import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'
 
 async function harness(adapter: MockAdapter, persona = 'stable base') {
+  return harnessRoutes([['mock', adapter]], persona)
+}
+
+async function harnessRoutes(
+  adapters: readonly (readonly [provider: string, adapter: MockAdapter])[],
+  persona = 'stable base',
+) {
   const ctx = new Context()
   await ctx.plugin(LlmService)
   await ctx.plugin(SessionStore)
@@ -25,7 +32,7 @@ async function harness(adapter: MockAdapter, persona = 'stable base') {
   await ctx.plugin(ToolRegistry)
   await ctx.plugin(AgentRegistry)
   await ctx.plugin(AgentLoop, { agents: [] })
-  ctx.llm.registerAdapter(['mock'], adapter)
+  for (const [provider, adapter] of adapters) ctx.llm.registerAdapter([provider], adapter)
   return ctx
 }
 
@@ -134,6 +141,10 @@ describe('request stability across the loop', () => {
       ReasoningEffortId('high'),
       ReasoningEffortId('max'),
     ])
+    expect(headers.map(event => event.data.header.adapterDefaults)).toEqual([
+      { reasoningEffort: true },
+      undefined,
+    ])
     expect(headers.map(event => event.data.reason)).toEqual(['initial', 'change'])
 
     for (const [model, effort] of [
@@ -158,6 +169,88 @@ describe('request stability across the loop', () => {
     }
   })
 
+  it('logs an adapter-owned maxTokens default before dispatch', async () => {
+    const adapter = new MockAdapter([textResponse('bounded')], undefined, 256_000)
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(SessionId('adapter-max-tokens'), {
+      provider: 'mock',
+      model: 'mock',
+    })
+
+    send(agent, 'use the adapter output limit')
+    await waitForIdle(ctx, agent)
+
+    expect(adapter.requests[0]?.maxTokens).toBe(256_000)
+    const header = agent.session.events.find(event => event.type === 'request/header')
+    expect(header?.type === 'request/header' && header.data.header.config.maxTokens).toBe(256_000)
+    expect(header?.type === 'request/header' && header.data.header.adapterDefaults)
+      .toEqual({ maxTokens: true })
+  })
+
+  it('rematerializes the selected adapter maxTokens default after a provider switch', async () => {
+    const deepseek = new MockAdapter([textResponse('deepseek')], undefined, 256_000)
+    const other = new MockAdapter([textResponse('other')], undefined, 8_192)
+    const ctx = await harnessRoutes([
+      ['deepseek', deepseek],
+      ['other', other],
+    ])
+    const agent = ctx.agentLoop.create(SessionId('adapter-max-tokens-switch'), {
+      provider: 'deepseek',
+      model: 'deepseek-model',
+    })
+    ctx.on('agent/request', async (_agent, turn, _step, _signal, next) => {
+      const config = await next()
+      return turn === 2
+        ? { ...config, provider: 'other', model: 'other-model' }
+        : config
+    })
+
+    send(agent, 'first')
+    await waitForIdle(ctx, agent)
+    send(agent, 'second')
+    await waitForIdle(ctx, agent)
+
+    expect(deepseek.requests[0]?.maxTokens).toBe(256_000)
+    expect(other.requests[0]?.maxTokens).toBe(8_192)
+    const headers = agent.session.events.filter(event => event.type === 'request/header')
+    expect(headers.map(event => event.data.header.config.maxTokens)).toEqual([256_000, 8_192])
+    expect(headers.map(event => event.data.header.adapterDefaults)).toEqual([
+      { maxTokens: true },
+      { maxTokens: true },
+    ])
+  })
+
+  it('preserves an explicit agent maxTokens cap across a provider switch', async () => {
+    const deepseek = new MockAdapter([textResponse('deepseek')], undefined, 256_000)
+    const other = new MockAdapter([textResponse('other')], undefined, 8_192)
+    const ctx = await harnessRoutes([
+      ['deepseek', deepseek],
+      ['other', other],
+    ])
+    const agent = ctx.agentLoop.create(SessionId('explicit-max-tokens-switch'), {
+      provider: 'deepseek',
+      model: 'deepseek-model',
+      maxTokens: 4_096,
+    })
+    ctx.on('agent/request', async (_agent, turn, _step, _signal, next) => {
+      const config = await next()
+      return turn === 2
+        ? { ...config, provider: 'other', model: 'other-model' }
+        : config
+    })
+
+    send(agent, 'first')
+    await waitForIdle(ctx, agent)
+    send(agent, 'second')
+    await waitForIdle(ctx, agent)
+
+    expect(deepseek.requests[0]?.maxTokens).toBe(4_096)
+    expect(other.requests[0]?.maxTokens).toBe(4_096)
+    const headers = agent.session.events.filter(event => event.type === 'request/header')
+    expect(headers.map(event => event.data.header.config.maxTokens)).toEqual([4_096, 4_096])
+    expect(headers.map(event => event.data.header.adapterDefaults)).toEqual([undefined, undefined])
+  })
+
   it('keeps exact-model resolution, request logging, and dispatch on one adapter registration', async () => {
     const ctx = new Context()
     await ctx.plugin(LlmService)