mmc/lingma-openai-gateway
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

test: freeze tool-call contract semantics

Browse Source 
Lock the current Anthropic streaming asymmetry so future refactors do not silently synthesize tool blocks. Align schema and docs with the actual support level to avoid over-promising forced-tool fallback.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
GitHub Actions
2026-04-22 10:56:21 +08:00
parent e3d3a63492
commit d081743924
6 changed files with 55 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
DESIGN.md
View File

@@ -49,7 +49,7 @@
- **多租户 / 水平扩缩**：单容器即可；真要大规模部署 → 套层反代 + N 个网关副本就够，不在进程内解决。
- **请求侧完整 function calling / tools 语义**：仍不是当前目标；现阶段仅支持 `tools`/`tool_choice` 在 `TOOL_FORWARD_ENABLED` 开关下灰度透传（默认关闭）。
- **响应侧工具事件桥接**：若 Lingma 上游产出 tool 事件，网关会向 OpenAI 输出 `tool_calls`，向 Anthropic 输出 `tool_use` / `tool_result`（stream + non-stream）。
- **强制工具回退闭环（non-stream）**：当上游未返回 tool 事件且请求为强制 `tool_choice` 时，网关会从文本里解析严格 JSON，合成 OpenAI `tool_calls` 与 Anthropic `tool_use` / `tool_result`。
- **强制工具回退闭环**：OpenAI 在 stream + non-stream 下都支持从文本里解析严格 JSON / `tool_code` 并合成 `tool_calls`；Anthropic 当前只在 non-stream 下合成 `tool_use` / `tool_result`，stream 仍保持原始文本流。
---