v1.4.23

​

✨ Features

• Claude Opus 4.7 Support — Added compatibility for Anthropic’s Claude Opus 4.7 model, including adaptive thinking, task-budgets beta header, display parameter handling, and “xhigh” effort mapping
• Anthropic Structured Outputs — Added response_format and structured output support for Anthropic models across chat completions and Responses API, including JSON-schema and JSON-object formats with order-preserving merge of additional model request fields (thanks @emirhanmutlu-natuvion!)
• MCP Tool Annotations — Preserve MCP tool annotations (title, readOnly, destructive, idempotent, openWorld) in bidirectional conversion between MCP tools and Bifrost chat tools so agents can reason about tool behavior
• Anthropic Server Tools — Expanded Anthropic chat schema and Responses converters to surface server-side tools (web search, code execution, computer use containers) end-to-end

​

🐞 Fixed

• Provider Queue Shutdown Panic — Eliminated send on closed channel panics in provider queue shutdown by leaving queue channels open and exiting workers via the done signal; stale producers transparently re-route to new queues during UpdateProvider, with rollback on failed updates
• OpenAI Tool Result Output — Flatten array-form tool_result output into a newline-joined string before marshaling for the Responses API so strict upstreams (Ollama Cloud, openai-go typed models) no longer reject it with HTTP 400; non-text blocks (images, files) are preserved (thanks @martingiguere!)
• vLLM Token Usage — Treat delta.content="" the same as nil in streaming so the synthesis chunk retains its finish_reason, restoring token usage attribution in logs and UI
• Config Schema Validator — Corrected JSON-path lookups for concurrency and SCIM blocks in the schema validation script, and reformatted transports/config.schema.json for readability
• CI Egress Hardening — Switched step-security/harden-runner from audit to block across all GitHub Actions workflows with explicit allowed-endpoints per job
• Gemini Tool Outputs — Handle content block tool outputs in Responses API path for function_call_output messages (thanks @tom-diacono!)
• Bedrock Streaming — Emit message_stop event for Anthropic invoke stream and case-insensitive anthropic-beta header merging (thanks @tefimov!)
• Bedrock Tool Images — Preserve image content blocks in tool results when converting Anthropic Messages to Bedrock Converse API (thanks @Edward-Upton!)
• Gemini Thinking Level — Preserved thinkingLevel parameters across round-trip conversions and corrected finish reason mapping
• Anthropic WebSearch — Removed the Claude Code user agent restriction so WebSearch tool arguments flow for all clients
• Responses Streaming Errors — Capture errors mid-stream in the Responses API so transport clients see failures instead of silent termination
• Anthropic Request Fallbacks — Dropped fallback fields from outgoing Anthropic requests to avoid schema validation errors
• Async Context Propagation — Preserve context values in async requests so downstream handlers retain request-scoped data
• Custom Providers — Allow custom providers without a list-models endpoint to accept any model rather than restricting on virtual key registration
• OTEL Plugin — Default insecure to true in config.json and include fallbacks in emitted OTEL metrics
• Payload Marshalling — Removed unnecessary marshalling of payload in the transport path
• Helm mcpClientConfig — Fixed templating for mcpClientConfig (thanks @crust3780!)
• Helm Chart — Refreshed the helm chart with validation fixes and removed the prerelease tag

• fix: OpenAI provider - flatten array-form tool_result output for Responses API (thanks @martingiguere!)
• fix: Gemini provider - handle content block tool outputs in Responses API path (thanks @tom-diacono!)
• fix: case-insensitive anthropic-beta merge in MergeBetaHeaders
• fix: Bedrock provider - emit message_stop event for Anthropic invoke stream (thanks @tefimov!)
• fix: Bedrock provider - preserve image content in tool results for Converse API (thanks @Edward-Upton!)
• fix: gemini preserves thinkingLevel parameters during round-trip and finish reason mapping
• fix: WebSearch tool argument handling for all clients by removing the Claude Code user agent restriction
• fix: capture responses streaming API errors
• fix: delete fallbacks from outgoing Anthropic requests
• feat: claude-opus-4-7 compatibility
• fix: token usage for vllm

• chore: upgraded core to v1.4.20
• fix: preserve context values in async requests
• fix: capture responses streaming API errors
• fix: otel plugin fixes
• fix: allow custom providers without a list models endpoint to register any model

• chore: upgraded core to v1.4.20 and framework to v1.2.39
• fix: allow custom providers without a list models endpoint to pass in any model rather than restrict it on vk

• chore: upgraded core to v1.4.20 and framework to v1.2.39

• chore: upgraded core to v1.4.20 and framework to v1.2.39

• chore: upgraded core to v1.4.20 and framework to v1.2.39
• fix: capture responses streaming API errors

• chore: upgraded core to v1.4.20 and framework to v1.2.39

• chore: upgraded core to v1.4.20 and framework to v1.2.39

• chore: upgraded core to v1.4.20 and framework to v1.2.39
• fix: sets default for insecure to true for config.json
• fix: includes fallbacks in otel metrics

• chore: upgraded core to v1.4.20 and framework to v1.2.39

• chore: upgraded core to v1.4.20 and framework to v1.2.39