iop/apps/edge/internal/openai
toki ca5eb4685c fix(edge): provider-pool thinking과 queue 정책을 정리한다
vLLM-MLX provider-pool에서 strict output이 thinking을 끄지 않도록 하고, queue_timeout_ms=0을 IOP queue timeout 없음으로 해석해야 한다. long reasoning/long-context 요청은 IOP queue timeout이 아니라 caller cancellation과 backend timeout 정책으로 제어한다.
2026-07-06 10:16:43 +09:00
..
chat_handler.go fix(edge): provider-pool thinking과 queue 정책을 정리한다 2026-07-06 10:16:43 +09:00
input_estimator.go refactor: clean up long-context admission smoke test files and input estimator 2026-07-06 09:33:08 +09:00
input_estimator_test.go refactor: clean up long-context admission smoke test files and input estimator 2026-07-06 09:33:08 +09:00
ollama_passthrough.go
responses_handler.go fix(edge): provider-pool thinking과 queue 정책을 정리한다 2026-07-06 10:16:43 +09:00
routes.go update: edge/node config and openapi contract changes 2026-06-24 22:03:09 +09:00
run_result.go feat: edge openai handler updates and node provider first config surface 2026-07-01 10:44:48 +09:00
server.go feat: long context admission support - refactor edge server, add input estimator 2026-07-05 18:18:58 +09:00
server_test.go fix(edge): provider-pool thinking과 queue 정책을 정리한다 2026-07-06 10:16:43 +09:00
stream.go Update roadmap and openai server implementation 2026-07-05 05:19:02 +09:00
strict_output.go feat: openai-compatible tool call boundary hardening changes 2026-07-04 17:31:03 +09:00
tool_validation.go feat: openai-compatible tool call boundary hardening & knowledge tool optimization 2026-07-04 18:21:27 +09:00
types.go feat: openai-compatible tool call boundary hardening & knowledge tool optimization 2026-07-04 18:21:27 +09:00