LLM/CLIProxyAPIPlus
1
0
Fork 0
mirror of https://github.com/router-for-me/CLIProxyAPIPlus.git synced 2026-03-21 16:40:22 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,106 Commits 2 Branches 238 Tags
3f53eea1e0b7dda67210446699edaea4477f10c4
Commit Graph

180 Commits

Author SHA1 Message Date
Luis Pater
923a5d6efb Merge branch 'router-for-me:main' into main 2025-12-15 20:40:23 +08:00
Luis Pater
d9a65745df fix(translator): handle empty item type and string content in OpenAI response parser 2025-12-15 20:35:52 +08:00
Luis Pater
407020de0c Merge branch 'router-for-me:main' into main 2025-12-15 10:36:39 +08:00
hkfires
09c339953d fix(openai): forward reasoning.effort value 
Drop the hardcoded effort mapping in request conversion so
unknown values are preserved instead of being coerced to `auto
 2025-12-15 09:16:15 +08:00
hkfires
d20b71deb9 fix(thinking): normalize effort mapping 
Route OpenAI reasoning effort through ThinkingEffortToBudget for Claude
translators, preserve "minimal" when translating OpenAI Responses, and
treat blank/unknown efforts as no-ops for Gemini thinking configs.

Also map budget -1 to "auto" and expand cross-protocol thinking tests.
 2025-12-15 09:16:15 +08:00
hkfires
716aa71f6e fix(thinking): centralize reasoning_effort mapping 
Move OpenAI `reasoning_effort` -> Gemini `thinkingConfig` budget logic into
shared helpers used by Gemini, Gemini CLI, and antigravity translators.

Normalize Claude thinking handling by preferring positive budgets, applying
budget token normalization, and gating by model support.

Always convert Gemini `thinkingBudget` back to OpenAI `reasoning_effort` to
support allowCompat models, and update tests for normalization behavior.
 2025-12-15 09:16:14 +08:00
hkfires
e8976f9898 fix(thinking): map budgets to effort for level models 2025-12-15 09:16:14 +08:00
hkfires
5ef2d59e05 fix(thinking): gate reasoning effort by model support 
Only map OpenAI reasoning effort to Claude thinking for models that support
thinking and use budget tokens (not level-based thinking).

Also add "xhigh" effort mapping and adjust minimal/low budgets, with new
raw-payload conversion tests across protocols and models.
 2025-12-15 09:16:14 +08:00
sukakcoding
4a764afd76 refactor: extract parseFunctionResponse helper to reduce duplication 2025-12-15 01:05:36 +08:00
sukakcoding
ecf49d574b fix: handle malformed json in function response parsing 2025-12-15 00:59:46 +08:00
Ravens2121
c3ed3b40ea feat(kiro): Add token usage cross-validation and simplify thinking mode handling 2025-12-14 16:40:33 +08:00
Ravens2121
9c04c18c04 feat(kiro): enhance request translation and fix streaming issues 
English:
- Fix <thinking> tag parsing: only parse at response start, avoid misinterpreting discussion text
- Add token counting support using tiktoken for local estimation
- Support top_p parameter in inference config
- Handle max_tokens=-1 as maximum (32000 tokens)
- Add tool_choice and response_format parameter handling via system prompt hints
- Support multiple thinking mode detection formats (Claude API, OpenAI reasoning_effort, AMP/Cursor)
- Shorten MCP tool names exceeding 64 characters
- Fix duplicate [DONE] marker in OpenAI SSE streaming
- Enhance token usage statistics with multiple event format support
- Add code fence markers to constants

中文:
- 修复 <thinking> 标签解析：仅在响应开头解析，避免误解析讨论文本中的标签
- 使用 tiktoken 实现本地 token 计数功能
- 支持 top_p 推理配置参数
- 处理 max_tokens=-1 转换为最大值（32000 tokens）
- 通过系统提示词注入实现 tool_choice 和 response_format 参数支持
- 支持多种思考模式检测格式（Claude API、OpenAI reasoning_effort、AMP/Cursor）
- 截断超过64字符的 MCP 工具名称
- 修复 OpenAI SSE 流中重复的 [DONE] 标记
- 增强 token 使用量统计，支持多种事件格式
- 添加代码围栏标记常量
 2025-12-14 11:57:16 +08:00
Ravens2121
01cf221167 feat(kiro): 代码优化重构 + OpenAI翻译器实现 2025-12-14 06:58:50 +08:00
Luis Pater
7f4f6bc9ca Merge branch 'main' into plus 2025-12-12 18:41:39 +08:00
hkfires
d131435e25 fix(codex): raise default reasoning effort to medium 2025-12-12 18:18:48 +08:00
Ravens2121
84920cb670 feat(kiro): add multi-endpoint fallback & thinking mode support 2025-12-12 13:43:36 +08:00
Luis Pater
ef0edbfe69 refactor(claude): replace strings.Builder with simpler output string concatenation 2025-12-11 22:34:06 +08:00
Luis Pater
4ce7c61a17 Merge branch 'main' into plus 2025-12-11 21:33:49 +08:00
Luis Pater
a74ee3f319 Merge pull request #481 from sususu98/fix/increase-buffer-size 
fix: increase buffer size for stream scanners to 50MB across multiple executors
 2025-12-11 21:20:54 +08:00
Luis Pater
1da03bfe15 Merge pull request #479 from router-for-me/claude 
fix(claude): prevent final events when no content streamed
 2025-12-11 08:18:59 +08:00
Ravens2121
cd4e84a360 feat(kiro): enhance request format, stream handling, and usage tracking 
## English Description

### Request Format Fixes
- Fix conversationState field order (chatTriggerType must be first)
- Add conditional profileArn inclusion based on auth method
- builder-id auth (AWS SSO) doesn't require profileArn
- social auth (Google OAuth) requires profileArn

### Stream Processing Enhancements
- Add headersLen boundary validation to prevent slice out of bounds
- Handle incomplete tool use at EOF by flushing pending data
- Separate message_delta and message_stop events for proper streaming
- Add error logging for JSON unmarshal failures

### JSON Repair Improvements
- Add escapeNewlinesInStrings() to handle control characters in JSON strings
- Remove incorrect unquotedKeyPattern that broke valid JSON content
- Fix handling of streaming fragments with embedded newlines/tabs

### Debug Info Filtering (Optional)
- Add filterHeliosDebugInfo() to remove [HELIOS_CHK] blocks
- Pattern matches internal state tracking from Kiro/Amazon Q
- Currently disabled pending further testing

### Usage Tracking
- Add usage information extraction in message_delta response
- Include prompt_tokens, completion_tokens, total_tokens in OpenAI format

---

## 中文描述

### 请求格式修复
- 修复 conversationState 字段顺序（chatTriggerType 必须在第一位）
- 根据认证方式条件性包含 profileArn
- builder-id 认证（AWS SSO）不需要 profileArn
- social 认证（Google OAuth）需要 profileArn

### 流处理增强
- 添加 headersLen 边界验证，防止切片越界
- 在 EOF 时处理未完成的工具调用，刷新待处理数据
- 分离 message_delta 和 message_stop 事件以实现正确的流式传输
- 添加 JSON 反序列化失败的错误日志

### JSON 修复改进
- 添加 escapeNewlinesInStrings() 处理 JSON 字符串中的控制字符
- 移除错误的 unquotedKeyPattern，该模式会破坏有效的 JSON 内容
- 修复包含嵌入换行符/制表符的流式片段处理

### 调试信息过滤（可选）
- 添加 filterHeliosDebugInfo() 移除 [HELIOS_CHK] 块
- 模式匹配来自 Kiro/Amazon Q 的内部状态跟踪信息
- 目前已禁用，等待进一步测试

### 使用量跟踪
- 在 message_delta 响应中添加 usage 信息提取
- 以 OpenAI 格式包含 prompt_tokens、completion_tokens、total_tokens
 2025-12-11 05:37:22 +08:00
Luis Pater
b27a175fef Merge pull request #17 from Ravens2121/master 
由AI进行更改修复了Kiro供应商的Claude协议与OpenAI协议。（对比AIClient-2-API项目进行变更）
 2025-12-11 01:31:47 +08:00
Ravens
8d5f89ccfd fix(kiro): fix translator format mismatch for OpenAI protocol 
Amp-Thread-ID: https://ampcode.com/threads/T-019b092b-f2de-72a1-b428-72511c0de628
Co-authored-by: Amp <amp@ampcode.com>
 2025-12-11 01:15:00 +08:00
Ravens
084e2666cb fix(kiro): add SSE event: prefix for Claude client compatibility 
Amp-Thread-ID: https://ampcode.com/threads/T-019b08fc-ff96-766e-a942-63dd35ed28c6
Co-authored-by: Amp <amp@ampcode.com>
 2025-12-11 00:14:20 +08:00
Luis Pater
2eb2dbb266 Merge branch 'router-for-me:main' into main 2025-12-10 23:56:59 +08:00
Luis Pater
e717939edb Fixed: #478 
feat(antigravity): add support for inline image data in client responses
 2025-12-10 23:55:53 +08:00
sususu
76c563d161 fix(executor): increase buffer size for stream scanners to 50MB across multiple executors 2025-12-10 23:20:04 +08:00
hkfires
a89514951f fix(claude): prevent final events when no content streamed 2025-12-10 22:19:55 +08:00
Luis Pater
f999650322 Merge branch 'router-for-me:main' into main 2025-12-10 16:04:18 +08:00
Luis Pater
1249b07eb8 feat(responses): add unique identifiers for responses, function calls, and tool uses 2025-12-10 16:02:54 +08:00
Luis Pater
38319b0483 Merge branch 'router-for-me:main' into main 2025-12-10 15:29:19 +08:00
Luis Pater
6b37f33d31 feat(antigravity): add unique identifier for tool use blocks in response 2025-12-10 15:27:57 +08:00
Luis Pater
1fd1ccca17 Merge branch 'router-for-me:main' into main 2025-12-09 21:13:08 +08:00
hkfires
9b202b6c1c fix(executor): centralize default thinking config 2025-12-09 21:05:06 +08:00
hkfires
5b6d201408 refactor(translator): remove thinking budget normalization across all translators 2025-12-09 21:05:06 +08:00
Luis Pater
ab9e9442ec v6.5.56 (#12) 
* feat(api): add comprehensive ampcode management endpoints

Add new REST API endpoints under /v0/management/ampcode for managing
ampcode configuration including upstream URL, API key, localhost
restriction, model mappings, and force model mappings settings.

- Move force-model-mappings from config_basic to config_lists
- Add GET/PUT/PATCH/DELETE endpoints for all ampcode settings
- Support model mapping CRUD with upsert (PATCH) capability
- Add comprehensive test coverage for all ampcode endpoints

* refactor(api): simplify request body parsing in ampcode handlers

* feat(logging): add upstream API request/response capture to streaming logs

* style(logging): remove redundant separator line from response section

* feat(antigravity): enforce thinking budget limits for Claude models

* refactor(logging): remove unused variable in `ensureAttempt` and redundant function call

---------

Co-authored-by: hkfires <10558748+hkfires@users.noreply.github.com>
 2025-12-08 22:32:29 +08:00
hkfires
a283545b6b feat(antigravity): enforce thinking budget limits for Claude models 2025-12-08 20:36:17 +08:00
Luis Pater
0d4f32a881 Merge branch 'router-for-me:main' into main 2025-12-08 10:20:08 +08:00
Luis Pater
d26ed069fa Merge pull request #441 from huynguyen03dev/fix/claude-to-openai-whitespace-text 
fix: filter whitespace-only text in Claude to OpenAI translation
 2025-12-08 09:43:44 +08:00
Ravens2121
a0c6cffb0d fix(kiro):修复 base64 图片格式转换问题 (#10) 2025-12-07 21:55:13 +08:00
hkfires
a174d015f2 feat(openai): handle thinking.budget_tokens from Anthropic-style requests 2025-12-07 19:14:05 +08:00
huynguyen03.dev
549c0c2c5a fix: filter whitespace-only text content in Claude to OpenAI translation 
Remove redundant existence check since TrimSpace handles empty strings
 2025-12-07 16:08:12 +07:00
huynguyen03.dev
f092801b61 fix: filter whitespace-only text in Claude to OpenAI translation 
Skip text content blocks that are empty or contain only whitespace
when translating Claude messages to OpenAI format. This fixes GLM-4.6
and other strict OpenAI-compatible providers that reject empty text
with error 'text cannot be empty'.
 2025-12-07 15:39:58 +07:00
Luis Pater
15353a6b6a Merge branch 'router-for-me:main' into main 2025-12-07 13:37:43 +08:00
Luis Pater
76af454034 **feat(antigravity): enhance handling of "thinking" content and refine Claude model response processing** 2025-12-07 13:19:12 +08:00
Luis Pater
04f0070a80 Merge branch 'router-for-me:main' into main 2025-12-07 02:38:32 +08:00
Luis Pater
f383840cf9 fix(antigravity): update toolNode role from "tool" to "user" in chat completions 2025-12-07 02:37:46 +08:00
Luis Pater
239fc4a8c4 Merge branch 'router-for-me:main' into main 2025-12-07 01:58:03 +08:00
Luis Pater
fd29ab418a Fixed: #424 
**feat(antigravity): add support for maxOutputTokens and refine Claude model handling**
 2025-12-07 01:55:57 +08:00
Luis Pater
df91408919 Merge branch 'router-for-me:main' into main 2025-12-07 01:49:20 +08:00