github maximhq/bifrost ent-v2.2.3-base
Enterprise v2.2.3 base

4 hours ago

What's Changed

  • cherrypicked key id selection to fallbacks by @akshaydeo in #7470
  • fix: move routing key pins with their routes when session affinity reorders the chain so a pinned key is never looked up under the wrong provider by @Pratham-Mishra04 in #7468
  • fix: carry route-level key pins through session affinity reorder and add e2e session-affinity matrix tests by @Pratham-Mishra04 in #7469
  • fix: drop session bindings the request followed into a failure and match route by provider and model together by @Pratham-Mishra04 in #7473
  • test: add session affinity matrix cases 12–13 (binding names provider+model, binding forgotten after key-selection failure) and new harness routing rules (anthropic-first, anthropic-first-other-model, vertex-badkey) by @Pratham-Mishra04 in #7474
  • fix: update UI path to correctly handle user labels toggle by @roroghost17 in #7490
  • fix(databricks): merge multi-part system prompts for Gemini-backed endpoints by @impoiler in #7461
  • fix: openai reasoning and params fixes by @TejasGhatte in #7239
  • fix: openai prompt cache breakpoint by @TejasGhatte in #7240
  • fix: responses type fixes by @TejasGhatte in #7241
  • feat: async tool execution in responsses by @TejasGhatte in #7242
  • fix: gpt-6 sol and luna support none effort by @TejasGhatte in #7492
  • tests: harness tests gpt-6 by @TejasGhatte in #7496
  • fix: openrouter cache breakpoint and harness fix by @TejasGhatte in #7521
  • 2.2.3 changelog by @akshaydeo in #7528
  • bedrock encrypted content decodding fix by @akshaydeo in #7529
  • kimi + codex fix. fixes mcp tool name length by @akshaydeo in #7530
  • tool_search support for gpt-6 models for non-openai providers by @akshaydeo in #7534

Full Changelog: ent-v2.2.2-base...ent-v2.2.3-base

Don't miss a new bifrost release

NewReleases is sending notifications on new releases.