What's Changed
- fix(list_models): respect API key profile filtering in full model data mode by @djdembeck in #1480
- feat: success rate page for all channels by @banlanzs in #1483
- feat: array override ops (array_append, array_prepend, array_insert) by @paopaoandlingyia in #1481
- fix: deepseek reasoning content content aggregator by @looplj in #1485
- chore(deps): bump go.opentelemetry.io/otel from 1.39.0 to 1.41.0 in /integration_test/gemini by @dependabot[bot] in #1479
- feat(anthropic): perserve top level cache control, close #1484 by @looplj in #1486
- fix: should not mark as completed if upstream error, close #1444 by @looplj in #1488
- fix: force keep reasoning content for deepseek by @looplj in #1491
- feat: add NanoGPT API quota monitoring support by @djdembeck in #1490
- chore: sync model developers data by @github-actions[bot] in #1494
- fix: should pass through response/stream, close #1442 by @looplj in #1495
- feat: add stream condition to the model association by @looplj in #1498
- opt: enable vacuum by default, close #1492 by @looplj in #1500
- fix(xiaomi): map models provided mimo token plan as xiaomi models by @trim21 in #1501
- feat: api key prefix config, close #1475 by @looplj in #1502
- feat: deepseek anthropic adaptive thinking by @looplj in #1505
New Contributors
- @paopaoandlingyia made their first contribution in #1481
- @trim21 made their first contribution in #1501
Full Changelog: v0.9.37...v0.9.38