mirror of
https://github.com/claude-code-best/claude-code.git
synced 2026-06-22 08:15:53 +00:00
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>
This commit is contained in:
claude-code-best
327
packages/@ant/model-provider/src/shared/openaiStreamAdapter.ts
Normal file
327
packages/@ant/model-provider/src/shared/openaiStreamAdapter.ts
Normal file
@@ -0,0 +1,327 @@
|
||||
import type { BetaRawMessageStreamEvent } from '@anthropic-ai/sdk/resources/beta/messages/messages.mjs'
|
||||
import type { ChatCompletionChunk } from 'openai/resources/chat/completions/completions.mjs'
|
||||
import { randomUUID } from 'crypto'
|
||||
|
||||
/**
|
||||
* Adapt an OpenAI streaming response into Anthropic BetaRawMessageStreamEvent.
|
||||
*
|
||||
* Mapping:
|
||||
* First chunk → message_start
|
||||
* delta.reasoning_content → content_block_start(thinking) + thinking_delta + content_block_stop
|
||||
* delta.content → content_block_start(text) + text_delta + content_block_stop
|
||||
* delta.tool_calls → content_block_start(tool_use) + input_json_delta + content_block_stop
|
||||
* finish_reason → message_delta(stop_reason) + message_stop
|
||||
*
|
||||
* Usage field mapping (OpenAI → Anthropic):
|
||||
* prompt_tokens → input_tokens
|
||||
* completion_tokens → output_tokens
|
||||
* prompt_tokens_details.cached_tokens → cache_read_input_tokens
|
||||
* (no OpenAI equivalent) → cache_creation_input_tokens (always 0)
|
||||
*
|
||||
* All four fields are emitted in the post-loop message_delta (not message_start)
|
||||
* so that trailing usage chunks (sent after finish_reason by some
|
||||
* OpenAI-compatible endpoints) are fully captured before the final counts are reported.
|
||||
*
|
||||
* Thinking support:
|
||||
* DeepSeek and compatible providers send `delta.reasoning_content` for chain-of-thought.
|
||||
* This is mapped to Anthropic's `thinking` content blocks:
|
||||
* content_block_start: { type: 'thinking', thinking: '', signature: '' }
|
||||
* content_block_delta: { type: 'thinking_delta', thinking: '...' }
|
||||
*
|
||||
* Prompt caching:
|
||||
* OpenAI reports cached tokens in usage.prompt_tokens_details.cached_tokens.
|
||||
* This is mapped to Anthropic's cache_read_input_tokens.
|
||||
*/
|
||||
export async function* adaptOpenAIStreamToAnthropic(
|
||||
stream: AsyncIterable<ChatCompletionChunk>,
|
||||
model: string,
|
||||
): AsyncGenerator<BetaRawMessageStreamEvent, void> {
|
||||
const messageId = `msg_${randomUUID().replace(/-/g, '').slice(0, 24)}`
|
||||
|
||||
let started = false
|
||||
let currentContentIndex = -1
|
||||
|
||||
// Track tool_use blocks: tool_calls index → { contentIndex, id, name, arguments }
|
||||
const toolBlocks = new Map<number, { contentIndex: number; id: string; name: string; arguments: string }>()
|
||||
|
||||
// Track thinking block state
|
||||
let thinkingBlockOpen = false
|
||||
|
||||
// Track text block state
|
||||
let textBlockOpen = false
|
||||
|
||||
// Track usage — all four Anthropic fields, populated from OpenAI usage fields:
|
||||
let inputTokens = 0
|
||||
let outputTokens = 0
|
||||
let cachedReadTokens = 0
|
||||
|
||||
// Track all open content block indices (for cleanup)
|
||||
const openBlockIndices = new Set<number>()
|
||||
|
||||
// Deferred finish state
|
||||
let pendingFinishReason: string | null = null
|
||||
let pendingHasToolCalls = false
|
||||
|
||||
for await (const chunk of stream) {
|
||||
const choice = chunk.choices?.[0]
|
||||
const delta = choice?.delta
|
||||
|
||||
// Extract usage from any chunk that carries it.
|
||||
if (chunk.usage) {
|
||||
inputTokens = chunk.usage.prompt_tokens ?? inputTokens
|
||||
outputTokens = chunk.usage.completion_tokens ?? outputTokens
|
||||
const details = (chunk.usage as any).prompt_tokens_details
|
||||
if (details?.cached_tokens != null) {
|
||||
cachedReadTokens = details.cached_tokens
|
||||
}
|
||||
}
|
||||
|
||||
// Emit message_start on first chunk
|
||||
if (!started) {
|
||||
started = true
|
||||
|
||||
yield {
|
||||
type: 'message_start',
|
||||
message: {
|
||||
id: messageId,
|
||||
type: 'message',
|
||||
role: 'assistant',
|
||||
content: [],
|
||||
model,
|
||||
stop_reason: null,
|
||||
stop_sequence: null,
|
||||
usage: {
|
||||
input_tokens: inputTokens,
|
||||
output_tokens: 0,
|
||||
cache_creation_input_tokens: 0,
|
||||
cache_read_input_tokens: cachedReadTokens,
|
||||
},
|
||||
},
|
||||
} as unknown as BetaRawMessageStreamEvent
|
||||
}
|
||||
|
||||
// Skip chunks that carry only usage data (no delta content)
|
||||
if (!delta) continue
|
||||
|
||||
// Handle reasoning_content → Anthropic thinking block
|
||||
const reasoningContent = (delta as any).reasoning_content
|
||||
if (reasoningContent != null && reasoningContent !== '') {
|
||||
if (!thinkingBlockOpen) {
|
||||
currentContentIndex++
|
||||
thinkingBlockOpen = true
|
||||
openBlockIndices.add(currentContentIndex)
|
||||
|
||||
yield {
|
||||
type: 'content_block_start',
|
||||
index: currentContentIndex,
|
||||
content_block: {
|
||||
type: 'thinking',
|
||||
thinking: '',
|
||||
signature: '',
|
||||
},
|
||||
} as BetaRawMessageStreamEvent
|
||||
}
|
||||
|
||||
yield {
|
||||
type: 'content_block_delta',
|
||||
index: currentContentIndex,
|
||||
delta: {
|
||||
type: 'thinking_delta',
|
||||
thinking: reasoningContent,
|
||||
},
|
||||
} as BetaRawMessageStreamEvent
|
||||
}
|
||||
|
||||
// Handle text content
|
||||
if (delta.content != null && delta.content !== '') {
|
||||
if (!textBlockOpen) {
|
||||
// Close thinking block if still open
|
||||
if (thinkingBlockOpen) {
|
||||
yield {
|
||||
type: 'content_block_stop',
|
||||
index: currentContentIndex,
|
||||
} as BetaRawMessageStreamEvent
|
||||
openBlockIndices.delete(currentContentIndex)
|
||||
thinkingBlockOpen = false
|
||||
}
|
||||
|
||||
currentContentIndex++
|
||||
textBlockOpen = true
|
||||
openBlockIndices.add(currentContentIndex)
|
||||
|
||||
yield {
|
||||
type: 'content_block_start',
|
||||
index: currentContentIndex,
|
||||
content_block: {
|
||||
type: 'text',
|
||||
text: '',
|
||||
},
|
||||
} as BetaRawMessageStreamEvent
|
||||
}
|
||||
|
||||
yield {
|
||||
type: 'content_block_delta',
|
||||
index: currentContentIndex,
|
||||
delta: {
|
||||
type: 'text_delta',
|
||||
text: delta.content,
|
||||
},
|
||||
} as BetaRawMessageStreamEvent
|
||||
}
|
||||
|
||||
// Handle tool calls
|
||||
if (delta.tool_calls) {
|
||||
for (const tc of delta.tool_calls) {
|
||||
const tcIndex = tc.index
|
||||
|
||||
if (!toolBlocks.has(tcIndex)) {
|
||||
// Close thinking block if open
|
||||
if (thinkingBlockOpen) {
|
||||
yield {
|
||||
type: 'content_block_stop',
|
||||
index: currentContentIndex,
|
||||
} as BetaRawMessageStreamEvent
|
||||
openBlockIndices.delete(currentContentIndex)
|
||||
thinkingBlockOpen = false
|
||||
}
|
||||
|
||||
// Close text block if open
|
||||
if (textBlockOpen) {
|
||||
yield {
|
||||
type: 'content_block_stop',
|
||||
index: currentContentIndex,
|
||||
} as BetaRawMessageStreamEvent
|
||||
openBlockIndices.delete(currentContentIndex)
|
||||
textBlockOpen = false
|
||||
}
|
||||
|
||||
// Start new tool_use block
|
||||
currentContentIndex++
|
||||
const toolId = tc.id || `toolu_${randomUUID().replace(/-/g, '').slice(0, 24)}`
|
||||
const toolName = tc.function?.name || ''
|
||||
|
||||
toolBlocks.set(tcIndex, {
|
||||
contentIndex: currentContentIndex,
|
||||
id: toolId,
|
||||
name: toolName,
|
||||
arguments: '',
|
||||
})
|
||||
openBlockIndices.add(currentContentIndex)
|
||||
|
||||
yield {
|
||||
type: 'content_block_start',
|
||||
index: currentContentIndex,
|
||||
content_block: {
|
||||
type: 'tool_use',
|
||||
id: toolId,
|
||||
name: toolName,
|
||||
input: {},
|
||||
},
|
||||
} as BetaRawMessageStreamEvent
|
||||
}
|
||||
|
||||
// Stream argument fragments
|
||||
const argFragment = tc.function?.arguments
|
||||
if (argFragment) {
|
||||
toolBlocks.get(tcIndex)!.arguments += argFragment
|
||||
yield {
|
||||
type: 'content_block_delta',
|
||||
index: toolBlocks.get(tcIndex)!.contentIndex,
|
||||
delta: {
|
||||
type: 'input_json_delta',
|
||||
partial_json: argFragment,
|
||||
},
|
||||
} as BetaRawMessageStreamEvent
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Handle finish
|
||||
if (choice?.finish_reason) {
|
||||
if (thinkingBlockOpen) {
|
||||
yield {
|
||||
type: 'content_block_stop',
|
||||
index: currentContentIndex,
|
||||
} as BetaRawMessageStreamEvent
|
||||
openBlockIndices.delete(currentContentIndex)
|
||||
thinkingBlockOpen = false
|
||||
}
|
||||
|
||||
if (textBlockOpen) {
|
||||
yield {
|
||||
type: 'content_block_stop',
|
||||
index: currentContentIndex,
|
||||
} as BetaRawMessageStreamEvent
|
||||
openBlockIndices.delete(currentContentIndex)
|
||||
textBlockOpen = false
|
||||
}
|
||||
|
||||
for (const [, block] of toolBlocks) {
|
||||
if (openBlockIndices.has(block.contentIndex)) {
|
||||
yield {
|
||||
type: 'content_block_stop',
|
||||
index: block.contentIndex,
|
||||
} as BetaRawMessageStreamEvent
|
||||
openBlockIndices.delete(block.contentIndex)
|
||||
}
|
||||
}
|
||||
|
||||
pendingFinishReason = choice.finish_reason
|
||||
pendingHasToolCalls = toolBlocks.size > 0
|
||||
}
|
||||
}
|
||||
|
||||
// Safety: close any remaining open blocks
|
||||
for (const idx of openBlockIndices) {
|
||||
yield {
|
||||
type: 'content_block_stop',
|
||||
index: idx,
|
||||
} as BetaRawMessageStreamEvent
|
||||
}
|
||||
|
||||
// Emit message_delta + message_stop
|
||||
if (pendingFinishReason !== null) {
|
||||
const stopReason =
|
||||
pendingFinishReason === 'length'
|
||||
? 'max_tokens'
|
||||
: pendingHasToolCalls
|
||||
? 'tool_use'
|
||||
: mapFinishReason(pendingFinishReason)
|
||||
|
||||
yield {
|
||||
type: 'message_delta',
|
||||
delta: {
|
||||
stop_reason: stopReason,
|
||||
stop_sequence: null,
|
||||
},
|
||||
usage: {
|
||||
input_tokens: inputTokens,
|
||||
output_tokens: outputTokens,
|
||||
cache_read_input_tokens: cachedReadTokens,
|
||||
cache_creation_input_tokens: 0,
|
||||
},
|
||||
} as BetaRawMessageStreamEvent
|
||||
|
||||
yield {
|
||||
type: 'message_stop',
|
||||
} as BetaRawMessageStreamEvent
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Map OpenAI finish_reason to Anthropic stop_reason.
|
||||
*/
|
||||
function mapFinishReason(reason: string): string {
|
||||
switch (reason) {
|
||||
case 'stop':
|
||||
return 'end_turn'
|
||||
case 'tool_calls':
|
||||
return 'tool_use'
|
||||
case 'length':
|
||||
return 'max_tokens'
|
||||
case 'content_filter':
|
||||
return 'end_turn'
|
||||
default:
|
||||
return 'end_turn'
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user