maximhq/bifrost ent-v1.4.2-base

Enterprise v1.4.2 base

on GitHub

What's Changed

• adds enteprise changelog by @akshaydeo in #3401
• fix: compat plugin drops cachePoint for unsupported bedrock model and non-bedrock models by @sammaji in #3154
• fix: converts role system to role user if only system message is present for non-openai models by @sammaji in #3200
• fix: enables all compat plugin settings by default by @sammaji in #3202
• fix: drops last assistant messages for anthropic models and converts unsupported reasoning effort values for mistral by @sammaji in #3203
• fix: drops messages with empty text or signature and adds conversion of thinking block for openai bedrock models by @sammaji in #3221
• Fix Gemini fallback propagation in GenAI integration by @Javtor in #3338
• enterprise docs updates by @akshaydeo in #3413
• updates to the contributions guideline by @akshaydeo in #3418
• fix: add *.quay.io:443 to release pipeline egress allowlist by @BearTS in #3402
• fix: include mcp.tool_manager_config in client config hash and sync tool manager settings on reload by @BearTS in #3432
• docs: update env var syntax from ${VAR} to env.VAR across enterprise and observability docs by @BearTS in #3419
• fix: set use raw request only for gemini provider by @TejasGhatte in #3437
• fix: fixes model passthrough prefix stripping in advisor tool for anthropic by @roroghost17 in #3420
• feat: supports toggling push-based and pull-based toggling separately and fixes hot-reload of plugin by @roroghost17 in #3433
• otel fixes by @akshaydeo in #3439
• v1.5.2 cut by @akshaydeo in #3442
• faiked test fixes by @akshaydeo in #3446
• fix: map supports_response_schema to response_format and text params, add Chat↔Responses format conversion by @TejasGhatte in #3454
• mod updates by @akshaydeo in #3461
• harness improvements by @akshaydeo in #3457
• makefile diff fixes by @akshaydeo in #3462

Full Changelog: ent-v1.4.1-base...ent-v1.4.2-base