v1.4.17

​

✨ Features

• Denylist Models — Provider keys support blacklisted_models field to exclude specific models from routing and filtered list-models; denylist takes precedence over the models allow list

​

🐞 Fixed

• MCP Gateway Headers — Fixed support for x-bf-mcp-include-clients and x-bf-mcp-include-tools headers to filter MCP tools/list response
• Bedrock Duplicate Events — Fixed duplicate content_block_stop events in Bedrock streaming responses
• Reasoning Content Marshaling — Fixed reasoning_content JSON tag in OpenAI response types
• OTEL Streaming Traces — Fixed response capture in OTEL tracing for streaming calls
• Broken Pipe Handling — Added broken pipe detection to connection pool error handler
• Cache Token Streaming — Fixed cache token capture for streaming calls across Anthropic and Bedrock providers
• Vertex Embedding URL — Fixed global region URL construction in Vertex embedding method
• Bedrock Reasoning Merge — Fixed reasoning content merge logic for Bedrock provider
• Bedrock HTTP/2 Toggle — Fixed enforce HTTP/2 toggle behavior for Bedrock provider
• Codex Store Parameter — Fixed store parameter handling for Codex conversations
• Gemini Duplicate Text — Skipped OutputTextDone events to prevent duplicate text in Gemini GenAI streaming (thanks @ava-grace-zoe!)
• Gemini Thought Signatures — Handled missing thought signatures in Gemini provider (thanks @mrcfps!)
• Replicate Model Slugs — Refined replicate model slug resolution in model catalog (thanks @brianphillips!)
• Logging Default — Kept logging enabled by default for new configurations
• Gin Migration Deadlocks — Moved all gin migrations to Go to avoid deadlocks
• WebSocket Concurrent Writes — Fixed concurrent write safety in WebSocket Responses API sessions
• Persist Store Config — Persisted store raw request/response config at provider level (thanks @chenbo515!)

• fix: fixed duplicate content_block_stop events in Bedrock streaming responses
• fix: fixed reasoning_content JSON tag in OpenAI response types
• fix: fixed response capture in OTEL tracing for streaming calls
• fix: added broken pipe detection to connection pool error handler
• fix: fixed cache token capture for streaming calls across Anthropic and Bedrock providers
• fix: fixed global region URL in Vertex embedding method
• feat: added blacklisted_models on provider keys to exclude models from routing and filtered list-models
• fix: fixed reasoning content merge logic for Bedrock provider
• fix: kept logging enabled by default
• fix: fixed store parameter handling for Codex conversations
• fix: fixed enforce HTTP/2 toggle for Bedrock provider
• fix: skipped OutputTextDone to prevent duplicate text in Gemini GenAI streaming (thanks @ava-grace-zoe!)
• fix: handled missing thought signatures in Gemini provider (thanks @mrcfps!)

• fix: fixed response capture in OTEL tracing for streaming calls
• fix: fixed cache token capture for streaming calls
• feat: added blacklisted_models migration and config store support
• fix: kept logging enabled by default
• fix: fixed store parameter config for Codex conversations
• fix: moved all gin migrations to Go to avoid deadlocks
• fix: refined replicate model slug resolution in model catalog (thanks @brianphillips!)

• feat: added blacklisted_models support for denylist filtering
• fix: refined replicate model slug resolution (thanks @brianphillips!)

• chore: upgraded core to v1.4.14 and framework to v1.2.33

• chore: upgraded core to v1.4.14 and framework to v1.2.33

• fix: fixed cache token capture for streaming calls

• chore: upgraded maxim-go dependency to latest version

• chore: upgraded core to v1.4.14 and framework to v1.2.33

• chore: upgraded core to v1.4.14 and framework to v1.2.33

• chore: upgraded core to v1.4.14 and framework to v1.2.33

• chore: upgraded core to v1.4.14 and framework to v1.2.33