> ## 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.

# v2.1.49

> Helm v2.1.49 changelog - 2026-11-12

**Bifrost Helm**

v2.1.49

## Changelog

* Added `serviceMonitor` to create a Prometheus Operator ServiceMonitor that scrapes Bifrost's `/metrics`. Off by default.
* Added `serviceMonitor.basicAuth` and `serviceMonitor.authorization` for scraping when auth is enabled. `basicAuth` reuses your existing auth Secret.
* The chart now refuses `serviceMonitor.enabled: true` when telemetry metrics are turned off.
* The main Service now carries the `app.kubernetes.io/component: server` label, so the ServiceMonitor scrapes only that Service.
* Added `bifrost.mcp.clientConfigs[].serverTypeOnSlug` to turn code mode on or off for a client on its own `/mcp/<slug>` endpoint.
* Added `bifrost.client.mcpClientMetadataUrl` to host Bifrost's MCP Client ID Metadata Document elsewhere, for MCP servers that cannot reach Bifrost.
* Added `bifrost.modelRouters` to configure model routers, which classify requests as simple, medium or complex and send each tier to a chosen model. They run after routing rules. With config.json as the source of truth, `[]` removes stored routers.
* `bifrost.governance.complexityAnalyzerConfig.classifier` now accepts `llm`, which requires the `llm` block.
* Added Prometheus metrics for the embedded Redis: `vectorStore.redis.metrics.enabled` runs a `redis_exporter` sidecar on port 9121.
* Added `vectorStore.redis.metrics.serviceMonitor` to create a Prometheus Operator ServiceMonitor for the Redis exporter, with optional basic auth.
* Added `vectorStore.redis.master.extraEnv` and `envFrom` to pass environment variables such as `REDIS_ARGS` to the embedded Redis. They work with Redis auth enabled.
* Fixed the embedded Redis not saving its data to the persistent volume when Redis auth is enabled, which lost data whenever the pod was replaced. **Behavior change:** the Redis pod restarts once on upgrade.
* Added `bifrost.client.usageEstimationTokenizers` to choose the tokenizers that estimate usage for cancelled or timed-out streams.
* Added `bifrost.datasheetOverrides` for pricing and model-parameter overrides that survive datasheet syncs. With config.json as the source of truth, `[]` removes stored overrides.
* Baseten keys now accept a per-alias `deployment_url`.
* The semantic cache now accepts `byteplus` and `baseten` as providers.
* Added `bifrost.client.mcpOpenapiMaxSpecMb` (`client.mcp_openapi_max_spec_mb`) to raise or lower the size limit on an openapi MCP client's spec. 0 keeps the 32 MiB default.
* Added `bifrost.client.bifrostUrl` (`client.bifrost_url`), the gateway's public base URL including `server.basePath`. `/v1/mcp` needs it; it accepts env and vault references.
* Added `bifrost.client.bifrostMcpAllowWrites` (`client.bifrost_mcp_allow_writes`) to stop `/v1/mcp` serving configuration changes as tools. On by default.
* Added `bifrost.framework.pricing.openapiUrl` (`framework.pricing.openapi_url`) to point `/v1/mcp` at a local OpenAPI spec on air-gapped installs.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.