feat: 重构供应商层次 (#286)

* refactor: 创建 @anthropic-ai/model-provider 包骨架与类型定义

- 新建 workspace 包 packages/@anthropic-ai/model-provider
- 定义 ModelProviderHooks 接口（依赖注入：分析、成本、日志等）
- 定义 ClientFactories 接口（Anthropic/OpenAI/Gemini/Grok 客户端工厂）
- 搬入核心类型：Message 体系、NonNullableUsage、EMPTY_USAGE、SystemPrompt、错误常量
- 主项目 src/types/message.ts 等改为 re-export，保持向后兼容

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor: 提升 OpenAI 转换器和模型映射到 model-provider 包

- 搬入 OpenAI 消息转换（convertMessages）、工具转换（convertTools）、流适配（streamAdapter）
- 搬入 OpenAI 和 Grok 模型映射（resolveOpenAIModel、resolveGrokModel）
- 主项目文件改为 thin re-export proxy

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor: 搬入 Gemini 兼容层到 model-provider 包

- 搬入 Gemini 类型定义、消息转换、工具转换、流适配、模型映射
- 主项目 gemini/ 目录下文件改为 thin re-export proxy

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor: 搬入 errorUtils 并迁移消费者导入到 model-provider

- 搬入 formatAPIError、extractConnectionErrorDetails 等 errorUtils
- 迁移 10 个消费者文件直接从 @anthropic-ai/model-provider 导入
- 更新 emptyUsage、sdkUtilityTypes、systemPromptType 为 re-export proxy

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat: compact 模型降级为 -1 模式（Opus→Sonnet, Sonnet→Haiku）

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* docs: 添加 agent-loop 绘图

* Revert "feat: compact 模型降级为 -1 模式（Opus→Sonnet, Sonnet→Haiku）"

This reverts commit e458d6391d.

* docs: 添加简化版 agent loop

* fix: 修复 n 快捷键导致关闭的问题

* fix: 修复 node 下 ws 没打包问题

* docs: 修复链接

* test: 添加测试支持

* fix: 修复类型问题(#267) (#271)

* fix: 修复 Bun 的 polyfill 问题

* fix: 类型修复完成

* feat: 统一所有包的类型文件

* fix: 修复构建问题

* test: 修复类型校验 (#279)

* fix: 修复 Bun 的 polyfill 问题

* fix: 类型修复完成

* feat: 统一所有包的类型文件

* fix: 修复构建问题

* fix(remote-control): harden self-hosted session flows (#278)

Co-authored-by: chengzifeng <chengzifeng@meituan.com>

* docs: update contributors

* build: 新增 vite 构建流程

* feat: 添加环境变量支持以覆盖 max_tokens 设置

* feat(langfuse): LLM generation 记录工具定义

将 Anthropic 格式的工具定义转换为 Langfuse 兼容的 OpenAI 格式，
并在 generation 的 input 中以 { messages, tools } 结构传入，
以便在 Langfuse UI 中查看完整的工具定义信息。

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat: 添加对 ACP 协议的支持 (#284)

* feat: 适配 zed acp 协议

* docs: 完善 acp 文档

* chore: 1.4.0

* conflict: 解决冲突

* feat: 添加测试覆盖率上报

* style: 改名加移动文件夹位置

* refactor: 移动测试用例及实现

* test: 修复测试用例完成

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Cheng Zi Feng <1154238323@qq.com>
Co-authored-by: chengzifeng <chengzifeng@meituan.com>
Co-authored-by: claude-code-best <272536312+claude-code-best@users.noreply.github.com>

src/services/api/openai/index.ts

@@ -10,17 +10,10 @@ import type { AgentId } from '../../../types/ids.js'
 import type { Tools } from '../../../Tool.js'
 import type { Stream } from 'openai/streaming.mjs'
 import type {
-  ChatCompletionChunk,
   ChatCompletionCreateParamsStreaming,
 } from 'openai/resources/chat/completions/completions.mjs'
 import { getOpenAIClient } from './client.js'
-import { anthropicMessagesToOpenAI } from './convertMessages.js'
-import {
-  anthropicToolsToOpenAI,
-  anthropicToolChoiceToOpenAI,
-} from './convertTools.js'
-import { adaptOpenAIStreamToAnthropic } from './streamAdapter.js'
-import { resolveOpenAIModel } from './modelMapping.js'
+import { anthropicMessagesToOpenAI, resolveOpenAIModel, adaptOpenAIStreamToAnthropic, anthropicToolsToOpenAI, anthropicToolChoiceToOpenAI } from '@ant/model-provider'
 import { normalizeMessagesForAPI } from '../../../utils/messages.js'
 import { toolToAPISchema } from '../../../utils/api.js'
 import {
@@ -30,7 +23,8 @@ import {
 import { logForDebugging } from '../../../utils/debug.js'
 import { addToTotalSessionCost } from '../../../cost-tracker.js'
 import { calculateUSDCost } from '../../../utils/modelCost.js'
-import { isEnvTruthy, isEnvDefinedFalsy } from '../../../utils/envUtils.js'
+import { isOpenAIThinkingEnabled, resolveOpenAIMaxTokens, buildOpenAIRequestBody } from './requestBody.js'
+export { isOpenAIThinkingEnabled, resolveOpenAIMaxTokens, buildOpenAIRequestBody }
 import { getModelMaxOutputTokens } from '../../../utils/context.js'
 import type { Options } from '../claude.js'
 import { randomUUID } from 'crypto'
@@ -48,104 +42,6 @@ import {
   TOOL_SEARCH_TOOL_NAME,
 } from '@claude-code-best/builtin-tools/tools/ToolSearchTool/prompt.js'
 
-/**
- * Detect whether DeepSeek-style thinking mode should be enabled.
- *
- * Enabled when:
- * 1. OPENAI_ENABLE_THINKING=1 is set (explicit enable), OR
- * 2. Model name contains "deepseek-reasoner" OR "DeepSeek-V3.2" (auto-detect, case-insensitive)
- *
- * Disabled when:
- * - OPENAI_ENABLE_THINKING=0/false/no/off is explicitly set (overrides model detection)
- *
- * @param model - The resolved OpenAI model name
- * @internal Exported for testing purposes only
- */
-export function isOpenAIThinkingEnabled(model: string): boolean {
-  // Explicit disable takes priority (overrides model auto-detect)
-  if (isEnvDefinedFalsy(process.env.OPENAI_ENABLE_THINKING)) return false
-  // Explicit enable
-  if (isEnvTruthy(process.env.OPENAI_ENABLE_THINKING)) return true
-  // Auto-detect from model name (deepseek-reasoner and DeepSeek-V3.2 support thinking mode)
-  const modelLower = model.toLowerCase()
-  return modelLower.includes('deepseek-reasoner') || modelLower.includes('deepseek-v3.2')
-}
-
-/**
- * Resolve max output tokens for the OpenAI-compatible path.
- *
- * Override priority:
- * 1. maxOutputTokensOverride (programmatic, from query pipeline)
- * 2. OPENAI_MAX_TOKENS env var (OpenAI-specific, useful for local models
- *    with small context windows, e.g. RTX 3060 12GB running 65536-token models)
- * 3. CLAUDE_CODE_MAX_OUTPUT_TOKENS env var (generic override)
- * 4. upperLimit default (64000)
- *
- * @internal Exported for testing purposes only
- */
-export function resolveOpenAIMaxTokens(
-  upperLimit: number,
-  maxOutputTokensOverride?: number,
-): number {
-  return maxOutputTokensOverride
-    ?? (process.env.OPENAI_MAX_TOKENS ? parseInt(process.env.OPENAI_MAX_TOKENS, 10) || undefined : undefined)
-    ?? (process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS ? parseInt(process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS, 10) || undefined : undefined)
-    ?? upperLimit
-}
-
-/**
- * Build the request body for OpenAI chat.completions.create().
- * Extracted for testability — the thinking mode params are injected here.
- *
- * DeepSeek thinking mode: inject thinking params via request body.
- * Two formats are added simultaneously to support different deployments:
- * - Official DeepSeek API: `thinking: { type: 'enabled' }`
- * - Self-hosted DeepSeek-V3.2: `enable_thinking: true` + `chat_template_kwargs: { thinking: true }`
- * OpenAI SDK passes unknown keys through to the HTTP body.
- * Each endpoint will use the format it recognizes and ignore the others.
- * @internal Exported for testing purposes only
- */
-export function buildOpenAIRequestBody(params: {
-  model: string
-  messages: any[]
-  tools: any[]
-  toolChoice: any
-  enableThinking: boolean
-  maxTokens: number
-  temperatureOverride?: number
-}): ChatCompletionCreateParamsStreaming & {
-  thinking?: { type: string }
-  enable_thinking?: boolean
-  chat_template_kwargs?: { thinking: boolean }
-} {
-  const { model, messages, tools, toolChoice, enableThinking, maxTokens, temperatureOverride } = params
-  return {
-    model,
-    messages,
-    max_tokens: maxTokens,
-    ...(tools.length > 0 && {
-      tools,
-      ...(toolChoice && { tool_choice: toolChoice }),
-    }),
-    stream: true,
-    stream_options: { include_usage: true },
-    // DeepSeek thinking mode: enable chain-of-thought output.
-    // When active, temperature/top_p/presence_penalty/frequency_penalty are ignored by DeepSeek.
-    ...(enableThinking && {
-      // Official DeepSeek API format
-      thinking: { type: 'enabled' },
-      // Self-hosted DeepSeek-V3.2 format
-      enable_thinking: true,
-      chat_template_kwargs: { thinking: true },
-    }),
-    // Only send temperature when thinking mode is off (DeepSeek ignores it anyway,
-    // but other providers may respect it)
-    ...(!enableThinking && temperatureOverride !== undefined && {
-      temperature: temperatureOverride,
-    }),
-  }
-}
-
 /**
  * Assemble the final AssistantMessage (and optional max_tokens error) from
  * accumulated stream state. Extracted to avoid duplication between the