- NPX
- Docker
- chore: version update core to 1.2.13 and framework to 1.1.15
- feat: added headers support for OTel configuration. Value prefixed with env will be fetched from environment variables (
env.ENV_VAR_NAME) - feat: emission of OTel resource spans is completely async - this brings down inference overhead to < 1µsecond
- fix: added latency calculation for vertex native requests
- feat: added cached tokens and reasoning tokens to the usage in ui
- fix: cost calculation for vertex requests
- feat: added global region support for vertex API
- fix: added filter for extra fields in chat completions request for Mistral provider
- fix: added wildcard validation for allowed origins in UI security settings
- fix: fixed code field in pending_safety_checks for Responses API
- bug: fixed embedding request not being handled in
GetExtraFields()method ofBifrostResponse - fix: added latency calculation for vertex native requests
- feat: added cached tokens and reasoning tokens to the usage metadata for chat completions
- feat: added global region support for vertex API
- fix: added filter for extra fields in chat completions request for Mistral provider
- fix: fixed ResponsesComputerToolCallPendingSafetyCheck code field
- chore: version update core to 1.2.13
- feat: added support for vertex provider/model format in pricing lookup
- chore: version update core to 1.2.13 and framework to 1.1.15
- chore: version update core to 1.2.13 and framework to 1.1.15
- chore: version update core to 1.2.13 and framework to 1.1.15
- chore: version update core to 1.2.13 and framework to 1.1.15
- chore: version update core to 1.2.13 and framework to 1.1.15
- feat: added support for responses request
- feat: added “skip-mocker” context key to skip mocker plugin per request
- chore: version update core to 1.2.13 and framework to 1.1.15
- feat: added headers support for OTel configuration. Value prefixed with env will be fetched from environment variables (
env.ENV_VAR_NAME) - feat: emission of OTel resource spans is completely async - this brings down inference overhead to < 1µsecond
- chore: version update core to 1.2.13 and framework to 1.1.15
- tests: added mocker plugin to all chat/responses tests
- chore: version update core to 1.2.13 and framework to 1.1.15

