core/v1.6.4

## Core Release v1.6.4

- feat: add Sarvam AI provider with chat, text-to-speech, and speech-to-text support (thanks [@Purvi09](https://github.com/Purvi09)!)
- feat: add ElevenLabs sound effects (text-to-sound) support (thanks [@SecretSun](https://github.com/SecretSun)!)
- feat: add `ProjectID` to Bedrock and Bedrock Mantle key configs with per-alias overrides for Bedrock, Bedrock Mantle, and Vertex
- feat: add `additional_tools` message type support
- feat: force single-region config in Vertex key config
- feat: phase-scoped redaction and revealing with transient redaction data field, plus `ClearPausedStreamBuffer` for pause-accumulate stream flows
- fix: map web search options to Google Search grounding in the Gemini API
- fix: parse `SecretVar` JSON with `ref`/`env_var` fields even when `value` is absent
- fix: cap max reasoning effort in OpenAI
- fix: honor service tier in OpenAI chat completion
- fix: support GA transcription-type sessions in POST /v1/realtime/client_secrets (thanks [@Shaik-Sirajuddin](https://github.com/Shaik-Sirajuddin)!)
- fix: support diarized_json transcription segments and ElevenLabs speaker passthrough (thanks [@Shaik-Sirajuddin](https://github.com/Shaik-Sirajuddin)!)
- fix: sanitize tool_use/tool_result ids to Anthropic's charset (thanks [@Shaik-Sirajuddin](https://github.com/Shaik-Sirajuddin)!)
- fix: never persist masked provider key previews (thanks [@eyeveil](https://github.com/eyeveil)!)
- fix: make tracing span lookup nil-safe to prevent panic on streaming errors (thanks [@eyeveil](https://github.com/eyeveil)!)
- fix: enable rerank for custom OpenAI-compatible providers (thanks [@eyeveil](https://github.com/eyeveil)!)
- fix: forward and rebuild Anthropic server-side tool_search on the Responses path (thanks [@ws4charlie](https://github.com/ws4charlie)!)
- fix: zero pooled ChannelMessage references on release to avoid pinning request bodies (thanks [@citrocat](https://github.com/citrocat)!)
- fix: round-trip Anthropic `redacted_thinking` blocks on the responses surface so multi-turn tool use with redacted reasoning can be replayed (thanks [@fus3r](https://github.com/fus3r)!)
- fix: reset `HasEmittedWebSearch` when recycling pooled Gemini responses stream state so grounded streaming requests keep emitting `web_search_call` items (thanks [@fus3r](https://github.com/fus3r)!)
- fix: omit role from OpenAI Responses non-message items (thanks [@nettee](https://github.com/nettee)!)
- fix: serialize OpenAI compaction request `input` correctly (thanks [@mcclurmc](https://github.com/mcclurmc)!)
- fix: preserve `reasoning_config` on Bedrock cross-provider translation (thanks [@Purvi09](https://github.com/Purvi09)!)
- fix: preserve Gemini file upload MIME types for GenAI file URI completions
- fix: Gemini video reference fields map to instances (thanks [@vojthor](https://github.com/vojthor)!)
- fix: accept object-valued tool-call arguments (e.g. tool_search_call) on the Responses API streaming path
- fix: recover from idle-timeout timer-goroutine panic that could crash the process
- fix: deterministic MCP tool ordering for prompt cache stability
- fix: pass through `gs://` image URLs on Vertex Gemini
- fix: signal Bedrock max_output_tokens truncation on Responses API (thanks [@jeremym-tanium](https://github.com/jeremym-tanium)!)
- fix: warn callers not to truncate the `#t=` temp-token fragment on MCP inline-auth links (thanks [@MarcusPeng](https://github.com/MarcusPeng)!)
- fix: add `ExtraContent` to ChatStreamResponseChoiceDelta (thanks [@nghodkicisco](https://github.com/nghodkicisco)!)
- fix: correct inference geo cost on Anthropic and cache rate for fast mode
- fix: send MIME type when specified
- fix: send status code on OTEL metrics
- fix: reduce telemetry metrics cardinality explosion risk
- fix: race conditions in tracer span locks
- fix: pass container block from Anthropic API
- fix: pass Azure auth headers in helpers
- chore: upgrade ClickHouse client library

### Installation

```bash
go get github.com/maximhq/bifrost/core@v1.6.4
```

---
_This release was automatically created from version file: `core/version`_