> ## Documentation Index
> Fetch the complete documentation index at: https://docs.getbifrost.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# v1.5.0-prerelease2

> v1.5.0-prerelease2 changelog - 2026-04-08

<Tabs>
  <Tab title="NPX">
    ```bash theme={null}
    npx -y @maximhq/bifrost --transport-version v1.5.0-prerelease2
    ```
  </Tab>

  <Tab title="Docker">
    ```bash theme={null}
    docker pull maximhq/bifrost:v1.5.0-prerelease2
    docker run -p 8080:8080 maximhq/bifrost:v1.5.0-prerelease2
    ```
  </Tab>
</Tabs>

<Update label="Bifrost(HTTP)" description="1.5.0-prerelease2">
  ## ✨ Features

  * **Model Alias** - Map model names to provider-specific identifiers (deployment names, inference profile ARNs, fine-tuned model IDs, custom model names, etc.) via per-key alias config
  * **Realtime Support** - Add WebSocket, WebRTC, and client secret handlers with session state management and transport context helpers
  * **Fireworks AI Provider** - Add Fireworks AI as a first-class provider with native completions, responses, embeddings, and image generations (thanks [@ivanetchart](https://github.com/ivanetchart)!)
  * **Per-User OAuth Consent** - Add per-user OAuth consent flow with identity selection and MCP authentication
  * **Prompts Plugin** - New prompts plugin with direct key header resolver and selective message inclusion when committing prompt sessions
  * **Access Profiles** - Add access profiles for fine-grained permission control
  * **Bedrock Embeddings & Image Gen** - Add embeddings, image gen, edit and variation support to Bedrock
  * **EnvVar Improvements** - Add IsSet method to EnvVar and auto-redact env-backed values in JSON serialization
  * **Logging Tracking Fields** - Add support for tracking userId, teamId, customerId, and businessUnitId in logging
  * **Virtual Keys Export** - Add sorting and CSV export to virtual keys table
  * **Path Whitelisting** - Allow path whitelisting from security config
  * **Server Bootstrap Timer** - Add server bootstrap timer for startup diagnostics

  ## 🐞 Fixed

  * **Bedrock Tool Choice** - Fix bedrock tool choice conversion to auto
  * **Bedrock Streaming Retries** - Retry retryable AWS exceptions and stale/closed-connection errors in bedrock streaming
  * **Bedrock SigV4 Service** - Correct SigV4 service name for agent runtime rerank
  * **MCP Tool Logs** - Fix MCP tool logs not being captured correctly
  * **Routing Rule Targets** - Preserve routing rule targets for genai and bedrock paths
  * **Provider Budget Duplication** - Fix provider level multiline budget duplication issue
  * **Vertex Endpoint** - Fix vertex endpoint correction
  * **Gemini Thinking Budget** - Fix thinking budget validation for gemini models
  * **SQLite Migrations** - Fix SQLite migration connections, error handling, and disable foreign key checks during migration
  * **Tool Parameter Schemas** - Preserve explicit empty tool parameter schemas for openai passthrough
  * **List Models Output** - Include raw model ID in list-models output alongside aliases
  * **Config Schema** - Fix config schema for bedrock key config
  * **Data Race Fix** - Fix race in data reading from fasthttp request for integrations
  * **Model Listing** - Unify /api/models and /api/models/details listing behavior
</Update>

<Update label="Core" description="1.5.1">
  * feat: add Fireworks AI as a first-class provider (thanks [@ivanetchart](https://github.com/ivanetchart)!)
  * feat: add realtime provider interfaces, schemas, and engine hooks
  * feat: add session log storage and realtime request normalization
  * feat: add per-user OAuth consent flow with identity selection and MCP authentication
  * feat: add IsSet method to EnvVar and improve provider auth validation
  * feat: add support for tracking userId, teamId, customerId, and businessUnitId
  * feat: add prompts plugin with direct key header resolver
  * feat: add embeddings, image gen, edit and variation to bedrock
  * feat: allow path whitelisting from security config
  * fix: auto-redact env-backed values in EnvVar JSON serialization
  * fix: bedrock tool choice conversion to auto
  * fix: MCP tool logs not being captured correctly
  * fix: preserve explicit empty tool parameter schemas for openai passthrough
  * fix: correct SigV4 service name for bedrock agent runtime rerank
  * fix: include raw model ID in list-models output alongside aliases
  * fix: vertex endpoint correction
  * fix: bedrock streaming retry for retryable AWS exceptions and stale connections
  * fix: thinking budget validation for gemini models
  * fix: add empty arguments guard in bedrock utils
</Update>

<Update label="Framework" description="1.3.1">
  * feat: add per-user OAuth consent flow with identity selection and MCP authentication
  * feat: add access profiles for fine-grained permission control
  * feat: add user level OAuth for MCP gateway
  * feat: add IsSet method to EnvVar and improve provider auth validation
  * feat: add session log storage and realtime request normalization
  * feat: add support for tracking userId, teamId, customerId, and businessUnitId
  * feat: add prompts plugin with direct key header resolver
  * feat: add Fireworks AI provider support (thanks [@ivanetchart](https://github.com/ivanetchart)!)
  * feat: add sorting and CSV export to virtual keys table
  * feat: allow path whitelisting from security config
  * fix: auto-redact env-backed values in EnvVar JSON serialization
  * fix: MCP tool logs not being captured correctly
  * fix: SQLite migration connections and error handling
  * fix: disable SQLite foreign key checks during migration
  * fix: add retry mechanism to model catalog pricing sync lock
  * fix: increases buffer size for custom plugin installs from URLs
</Update>

<Update label="governance" description="1.5.1">
  * feat: add realtime WebSocket, WebRTC, and client secret handlers
  * feat: add access profiles for fine-grained permission control
  * feat: add support for tracking userId, teamId, customerId, and businessUnitId
  * fix: SQLite migration connections and error handling + vk not found message
  * fix: preserve routing rule targets for genai and bedrock paths
</Update>

<Update label="jsonparser" description="1.5.1">
  * chore: upgraded core to v1.5.1 and framework to v1.3.1
</Update>

<Update label="litellmcompat" description="0.1.1">
  * chore: upgraded core to v1.5.1 and framework to v1.3.1
</Update>

<Update label="logging" description="1.5.1">
  * feat: add realtime turn logging
  * feat: add support for tracking userId, teamId, customerId, and businessUnitId
  * feat: allow path whitelisting from security config
  * fix: MCP tool logs not being captured correctly
</Update>

<Update label="maxim" description="1.6.1">
  * feat: add per-user OAuth consent flow with identity selection and MCP authentication
  * feat: add support for image generation requests
  * feat: add realtime turn logging
  * feat: add support for tracking userId, teamId, customerId, and businessUnitId
</Update>

<Update label="mocker" description="1.5.1">
  * chore: upgraded core to v1.5.1 and framework to v1.3.1
</Update>

<Update label="otel" description="1.2.1">
  * chore: upgraded core to v1.5.1 and framework to v1.3.1
</Update>

<Update label="prompts" description="1.0.1">
  * feat: add prompts plugin with direct key header resolver
  * feat: add per-user OAuth consent flow with identity selection and MCP authentication
  * feat: add selective message inclusion when committing prompt sessions
</Update>

<Update label="semanticcache" description="1.5.1">
  * chore: upgraded core to v1.5.1 and framework to v1.3.1
</Update>

<Update label="telemetry" description="1.5.1">
  * chore: upgraded core to v1.5.1 and framework to v1.3.1
</Update>