Merge remote-tracking branch 'origin/master' into worktree/web-multimodal-image-input

# Conflicts: # docs/architecture.i18n.yaml # docs/architecture.md # docs/architecture.zh.md # docs/config-catalog.md # docs/core-data-structures/core.i18n.yaml # docs/core-data-structures/llm-streaming.i18n.yaml # docs/module-graph.md # examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl # packages/README.i18n.yaml # packages/client/connection/src/client/fixture.ts # packages/client/connection/src/index.ts # packages/client/runtime/README.i18n.yaml # packages/client/runtime/README.md # packages/client/runtime/README.zh.md # packages/client/runtime/src/client/sessions/conversation.ts # packages/client/ui-conversation/README.i18n.yaml # packages/client/ui-conversation/src/client/apply.ts # packages/client/ui-conversation/src/client/chat/ChatView.tsx # packages/client/ui-conversation/src/client/chat/MessageItem.tsx # packages/client/ui-conversation/src/client/contract/slots.ts # packages/client/ui-trajectory/tests/views.spec.tsx # packages/compact/compact-basic/README.i18n.yaml # packages/cordis/tool-cordis/src/api-catalog.ts # packages/host/apiproxy/src/api-proxy.ts # packages/host/apiproxy/src/api/index.ts # packages/host/apiproxy/src/api/sessions.ts # packages/host/apiproxy/src/index.ts # packages/host/apiproxy/tests/fetch-carrier.spec.ts # packages/llm/llm-deepseek/src/adapter.ts # packages/llm/llm-deepseek/tests/adapter.spec.ts # packages/llm/llm-deepseek/tests/serialize.spec.ts # packages/llm/llm-pi-ai/README.i18n.yaml # packages/llm/llm-pi-ai/src/adapter.ts # packages/llm/llm-pi-ai/src/index.ts # packages/llm/llm-pi-ai/tests/adapter.spec.ts # packages/llm/llm/src/types.ts # packages/ui/tui/README.i18n.yaml # packages/ui/tui/src/index.ts # packages/ui/tui/tests/tui.spec.ts
2026-07-28 11:41:40 +08:00
parent a1835c3228 2a46685414
commit 004f598917
1499 changed files with 48621 additions and 21956 deletions
--- a/packages/llm/llm-pi-ai/tests/adapter.e2e.ts
+++ b/packages/llm/llm-pi-ai/tests/adapter.e2e.ts
@@ -1,6 +1,6 @@
 import { afterEach, describe, expect, it } from 'vitest'
 import { Context } from 'cordis'
-import LlmService, { CallId } from '@deepseek-ai/dsh-llm'
+import LlmService, { CallId, ReasoningEffortId } from '@deepseek-ai/dsh-llm'
 import type { Message, ToolSchema } from '@deepseek-ai/dsh-llm'
 import * as LlmPiAi from '@deepseek-ai/dsh-llm-pi-ai'
 import type { PiAiProviderProfile } from '@deepseek-ai/dsh-llm-pi-ai'
@@ -9,7 +9,7 @@ import { assemble, type AssembledResult } from './assemble.ts'

 /**
 * Real-API e2e for the pi-ai-backed adapter: V4 Flash + V4 Pro with provider
- * defaults and representative high/xhigh reasoning. Mirrors the native
+ * defaults and representative off/high/max reasoning. Mirrors the native
 * adapter's StreamChunk contract and exercises a replayed tool follow-up.
 * Key-gated.
 */
@@ -74,10 +74,24 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('llm-pi-ai e2e (real API)', () =>
    expect(textOf(result).toLowerCase()).toContain('pong')
  })

+  it('flash + reasoning off: plain text without reasoning blocks', async () => {
+    const ctx = await harness(FLASH)
+    const result = await assemble(ctx,{
+      model: FLASH,
+      reasoningEffort: ReasoningEffortId('off'),
+      messages: ask('Reply with exactly the word: pong'),
+      maxTokens: 50,
+    })
+    expect(result.finish.kind).toBe('stop')
+    expect(result.message.content.some(block => block.type === 'reasoning')).toBe(false)
+    expect(textOf(result).toLowerCase()).toContain('pong')
+  })
+
  it.each([FLASH, PRO])('%s + reasoning high: reasoning blocks present', async (model) => {
-    const ctx = await harness(model, { reasoning: 'high' })
+    const ctx = await harness(model)
    const result = await assemble(ctx,{
      model,
+      reasoningEffort: ReasoningEffortId('high'),
      messages: ask('Which is larger, 9.11 or 9.8? Answer with just the number.'),
      maxTokens: 2000,
    })
@@ -86,11 +100,12 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('llm-pi-ai e2e (real API)', () =>
    expect(textOf(result)).toContain('9.8')
  })

-  it('pro + reasoning xhigh (wire max): tool-call round trip', async () => {
-    const ctx = await harness(PRO, { reasoning: 'xhigh' })
+  it('pro + reasoning max: tool-call round trip', async () => {
+    const ctx = await harness(PRO)

    const first = await assemble(ctx,{
      model: PRO,
+      reasoningEffort: ReasoningEffortId('max'),
      messages: ask('What is the weather in Paris right now? Use the get_weather tool.'),
      tools: [weatherTool],
      maxTokens: 2000,
@@ -103,6 +118,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('llm-pi-ai e2e (real API)', () =>

    const second = await assemble(ctx,{
      model: PRO,
+      reasoningEffort: ReasoningEffortId('max'),
      messages: [
        ...ask('What is the weather in Paris right now? Use the get_weather tool.'),
        first.message,
--- a/packages/llm/llm-pi-ai/tests/adapter.spec.ts
+++ b/packages/llm/llm-pi-ai/tests/adapter.spec.ts
@@ -9,7 +9,7 @@ import type {
  SaveImageAttachment,
  StoredImageAttachment,
 } from '@deepseek-ai/dsh-attachment'
-import LlmService, { CONTEXT_WINDOW_EXCEEDED_CODE, LlmError, userAgent } from '@deepseek-ai/dsh-llm'
+import LlmService, { CONTEXT_WINDOW_EXCEEDED_CODE, LlmError, ReasoningEffortId, userAgent } from '@deepseek-ai/dsh-llm'
 import * as LlmPiAi from '@deepseek-ai/dsh-llm-pi-ai'
 import { PiAiAdapter } from '@deepseek-ai/dsh-llm-pi-ai'
 import { MAX_TIMER_DELAY_MS } from '@deepseek-ai/dsh-timeout'
@@ -139,7 +139,7 @@ describe('PiAiAdapter provider routing', () => {
  it('forwards common stream options and profile reasoning', async () => {
    const server = await mockServer([{ events: textEvents }])
    const ctx = await harness(server.url, {
-      reasoning: 'xhigh',
+      reasoning: 'max',
      cacheRetention: 'none',
      transport: 'sse',
      timeoutMs: 5000,
@@ -163,6 +163,33 @@ describe('PiAiAdapter provider routing', () => {
    })
  })

+  it('uses a dynamic request effort and rejects unsupported efforts before network I/O', async () => {
+    const server = await mockServer([{ events: textEvents }, { events: textEvents }])
+    const ctx = await harness(server.url, { reasoning: 'max' })
+
+    await assemble(ctx, {
+      model: 'deepseek-v4-flash',
+      reasoningEffort: ReasoningEffortId('high'),
+      messages: [],
+    })
+    expect(server.requests[0]).toMatchObject({ reasoning_effort: 'high' })
+
+    await assemble(ctx, {
+      model: 'deepseek-v4-flash',
+      reasoningEffort: ReasoningEffortId('off'),
+      messages: [],
+    })
+    expect(server.requests[1]).toMatchObject({ thinking: { type: 'disabled' } })
+    expect(server.requests[1]).not.toHaveProperty('reasoning_effort')
+
+    await expect(assemble(ctx, {
+      model: 'deepseek-v4-flash',
+      reasoningEffort: ReasoningEffortId('xhigh'),
+      messages: [],
+    })).rejects.toMatchObject({ code: 'UNSUPPORTED_REASONING_EFFORT' })
+    expect(server.requests).toHaveLength(2)
+  })
+
  it('preserves omitted profile options when constructing the adapter directly', async () => {
    const server = await mockServer([{ events: textEvents }])
    const ctx = new Context()
@@ -371,12 +398,31 @@ describe('provider profile lifecycle', () => {
    const ctx = new Context()
    await ctx.plugin(LlmService)
    const fiber = await ctx.plugin(LlmPiAi, {
-      providers: [{ provider: 'openai' }, { provider: 'anthropic' }],
+      providers: [
+        {
+          provider: 'openai',
+          retryPolicy: {
+            mode: 'always',
+            backoff: { initialDelayMs: 25, maxDelayMs: 100, jitterRatio: 0.2 },
+          },
+        },
+        { provider: 'anthropic' },
+      ],
    })
    expect(ctx.llm.listProviders()).toEqual([
      { id: 'openai', name: 'openai' },
      { id: 'anthropic', name: 'anthropic' },
    ])
+    expect(ctx.llm.providerRetryPolicy('openai')).toEqual({
+      mode: 'always',
+      initialDelayMs: 25,
+      maxDelayMs: 100,
+      jitterRatio: 0.2,
+    })
+    expect(ctx.llm.providerRetryPolicy('anthropic')).toMatchObject({
+      mode: 'normal',
+      maxRetries: 2,
+    })
    await fiber.dispose()
    expect(ctx.llm.listProviders()).toEqual([])
  })
@@ -391,9 +437,68 @@ describe('provider profile lifecycle', () => {
      inputModalities: ['text', 'image'], outputModalities: ['text'],
    })
    expect(models.every(model => model.provider === 'openai')).toBe(true)
-    const context = await ctx.llm.resolveModelContext('openai', 'gpt-4.1')
-    expect(context).toBeDefined()
-    expect(typeof context?.contextWindow).toBe('number')
+    const info = await ctx.llm.resolveModelInfo('openai', 'gpt-4.1')
+    expect(typeof info.context?.contextWindow).toBe('number')
+  })
+
+  it('exposes pi-ai model thinking levels verbatim without inventing a provider default', async () => {
+    const ctx = new Context()
+    await ctx.plugin(LlmService)
+    await ctx.plugin(LlmPiAi, {
+      providers: [{ provider: 'deepseek' }, { provider: 'openai' }],
+    })
+
+    await expect(ctx.llm.resolveModelInfo('deepseek', 'deepseek-v4-flash'))
+      .resolves.toMatchObject({
+        reasoning: {
+          efforts: [
+            { id: ReasoningEffortId('off'), name: 'Off' },
+            { id: ReasoningEffortId('high'), name: 'High' },
+            { id: ReasoningEffortId('max'), name: 'Max' },
+          ],
+        },
+      })
+    const extended = await ctx.llm.resolveModelInfo('openai', 'gpt-5.6-sol')
+    expect(extended.reasoning?.efforts.map(effort => effort.id)).toEqual([
+      ReasoningEffortId('off'),
+      ReasoningEffortId('low'),
+      ReasoningEffortId('medium'),
+      ReasoningEffortId('high'),
+      ReasoningEffortId('xhigh'),
+      ReasoningEffortId('max'),
+    ])
+    await expect(ctx.llm.resolveModelInfo('openai', 'gpt-4.1'))
+      .resolves.toMatchObject({
+        reasoning: {
+          efforts: [{ id: ReasoningEffortId('off'), name: 'Off' }],
+        },
+      })
+  })
+
+  it('uses a supported profile reasoning value as the model default and rejects an unsupported one', async () => {
+    const supported = new Context()
+    await supported.plugin(LlmService)
+    await supported.plugin(LlmPiAi, {
+      providers: [{ provider: 'deepseek', reasoning: 'max' }],
+    })
+    await expect(supported.llm.resolveModelInfo('deepseek', 'deepseek-v4-flash'))
+      .resolves.toMatchObject({ reasoning: { defaultEffort: ReasoningEffortId('max') } })
+
+    const unsupported = new Context()
+    await unsupported.plugin(LlmService)
+    await unsupported.plugin(LlmPiAi, {
+      providers: [{ provider: 'deepseek', reasoning: 'medium' }],
+    })
+    await expect(unsupported.llm.resolveModelInfo('deepseek', 'deepseek-v4-flash'))
+      .rejects.toMatchObject({ code: 'UNSUPPORTED_REASONING_EFFORT' })
+
+    const disabled = new Context()
+    await disabled.plugin(LlmService)
+    await disabled.plugin(LlmPiAi, {
+      providers: [{ provider: 'deepseek', reasoning: 'off' }],
+    })
+    await expect(disabled.llm.resolveModelInfo('deepseek', 'deepseek-v4-flash'))
+      .resolves.toMatchObject({ reasoning: { defaultEffort: ReasoningEffortId('off') } })
  })

  it('accepts absent credentials for pi-ai ambient authentication', async () => {
@@ -442,12 +547,29 @@ describe('provider profile lifecycle', () => {
    }
  })

+  it('rejects invalid nested retryPolicy at the provider-profile boundary', async () => {
+    expect(() => resolveProfiles([{
+      provider: 'openai',
+      retryPolicy: { mode: 'always', backoff: { jitterRatio: -1 } },
+    }])).toThrow(/retryPolicy\.backoff\.jitterRatio/)
+
+    const ctx = new Context()
+    await ctx.plugin(LlmService)
+    await expect(ctx.plugin(LlmPiAi, {
+      providers: [{
+        provider: 'openai',
+        retryPolicy: { mode: 'normal', maxRetries: -1 },
+      }],
+    })).rejects.toThrow(/retryPolicy/)
+    expect(ctx.llm.listProviders()).toEqual([])
+  })
+
  it('constructs the adapter directly and rejects routes it does not own', async () => {
    const adapter = new PiAiAdapter({ profiles: [{ provider: 'openai' }] })
    await expect(adapter.listModels('anthropic')).rejects.toMatchObject({ code: 'NO_ADAPTER' })
-    await expect(adapter.resolveModelContext('anthropic', 'claude-sonnet-4'))
+    await expect(adapter.resolveModel('anthropic', 'claude-sonnet-4'))
      .rejects.toMatchObject({ code: 'NO_ADAPTER' })
-    await expect(adapter.resolveModelContext('openai', 'not-a-catalog-model'))
+    await expect(adapter.resolveModel('openai', 'not-a-catalog-model'))
      .rejects.toMatchObject({ code: 'UNKNOWN_MODEL' })
    await expect((async () => {
      for await (const _chunk of adapter.stream({ provider: 'anthropic', model: 'claude-sonnet-4', messages: [] })) { /* drain */ }
--- a/packages/llm/llm-pi-ai/tests/convert.spec.ts
+++ b/packages/llm/llm-pi-ai/tests/convert.spec.ts
@@ -622,6 +622,15 @@ describe('mapStopReason / mapUsage', () => {
    'other side closed',
    'HTTP2 request did not get a response',
    'WebSocket closed unexpectedly',
+    // undici flattens a mid-stream socket drop to this bare word (its SocketError
+    // cause is discarded upstream before it reaches us).
+    'terminated',
+    'Premature close',
+    // pi-ai's per-provider throws when the wire closes before the terminal event.
+    'Anthropic stream ended before message_stop',
+    'OpenAI Responses stream ended before a terminal response event',
+    'openrouter stream ended without a terminal event',
+    'Stream ended without finish_reason',
  ])('maps pi-ai transport wording %j', (errorMessage) => {
    expect(mapStopReason(assistant({ stopReason: 'error', errorMessage })))
      .toMatchObject({ kind: 'error', failure: { code: 'TRANSPORT' } })