e499d69e3e
The OpenAI-compatible API server only enforced a hardcoded cap of 10 concurrent runs on /v1/runs, leaving /v1/chat/completions and /v1/responses unbounded — a request flood could exhaust CPU, memory, and upstream LLM quota (#7483). - Add gateway.api_server.max_concurrent_runs (config.yaml, default 10, 0 disables). No env var. - Shared concurrency gate across all three agent-serving endpoints, counting both the chat/responses in-flight counter and the /v1/runs stream set. Returns OpenAI-style 429 + Retry-After when at the cap. - Remove the dead hardcoded _MAX_CONCURRENT_RUNS class attribute. Closes #7483. |
||
|---|---|---|
| .. | ||
| qqbot | ||
| ADDING_A_PLATFORM.md | ||
| __init__.py | ||
| _http_client_limits.py | ||
| api_server.py | ||
| base.py | ||
| bluebubbles.py | ||
| helpers.py | ||
| msgraph_webhook.py | ||
| signal.py | ||
| signal_format.py | ||
| signal_rate_limit.py | ||
| webhook.py | ||
| weixin.py | ||
| whatsapp_cloud.py | ||
| whatsapp_common.py | ||
| yuanbao.py | ||
| yuanbao_media.py | ||
| yuanbao_proto.py | ||
| yuanbao_sticker.py | ||