toki 5cd7aea826 fix(openai): provider native thinking을 보존한다 ... OpenAI-compatible passthrough에서 caller가 보낸 provider-native thinking field가 catalog 기본 thinking budget으로 덮이지 않아야 한다. provider가 거부한 extension field도 Edge가 선판단하지 않고 provider status/body로 relay되는지 테스트 근거를 남긴다.		2026-07-14 07:21:37 +09:00
..
chat_handler.go	fix(openai): provider native thinking을 보존한다	2026-07-14 07:21:37 +09:00
identity_metering_test.go	feat: update edge config, usage docs, tests, and roadmap	2026-07-11 04:47:11 +09:00
input_estimator.go
input_estimator_test.go
log_safety_test.go
ollama_passthrough.go
principal.go	feat: usage metrics - identity metering, usage token logging, and runtime proto	2026-07-10 17:54:23 +09:00
responses_handler.go	feat(edge): OpenAI compatible provider pass-through & test coverage	2026-07-14 06:39:53 +09:00
routes.go	feat: usage metrics - identity metering, usage token logging, and runtime proto	2026-07-10 17:54:23 +09:00
run_result.go	feat: usage metrics - identity metering, usage token logging, and runtime proto	2026-07-10 17:54:23 +09:00
server.go	feat(edge): model group mixed provider dispatch implementation + archive completed tasks	2026-07-12 15:42:16 +09:00
server_test.go	fix(openai): provider native thinking을 보존한다	2026-07-14 07:21:37 +09:00
stream.go	refactor(openai): call metadata 기반 response_mode 라우터 선택을 제거한다	2026-07-13 21:05:04 +09:00
strict_output.go
tool_validation.go
types.go	feat: routing-policy-model-orchestration - responses passthrough & model group mixed provider dispatch	2026-07-11 12:42:16 +09:00
usage_metrics.go	feat: usage metrics - identity metering, usage token logging, and runtime proto	2026-07-10 17:54:23 +09:00
usage_metrics_test.go	refactor(openai): call metadata 기반 response_mode 라우터 선택을 제거한다	2026-07-13 21:05:04 +09:00