Fix stale model references in AI tests after model regeneration

- Update GitHub Copilot tests to use available models (claude-haiku-4.5, gemini-2.5-pro)
- Update OpenRouter tests to use available models (google/gemini-2.5-flash, deepseek/deepseek-chat)
- Fix over-broad sed that incorrectly renamed OpenAI Responses gpt-4o test
- Remove nvidia.md from repo root
- Update packages/ai/CHANGELOG.md
This commit is contained in:
Mario Zechner
2026-06-02 11:37:32 +02:00
parent 7c531d0518
commit 7c08227019
9 changed files with 369 additions and 209 deletions

View File

@@ -6,6 +6,7 @@
- Fixed Amazon Bedrock requests to replace blank required user/tool-result text with a placeholder and skip blank replay text blocks ([#4975](https://github.com/earendil-works/pi/issues/4975)).
- Fixed OpenAI GPT-5.5 generated metadata to omit unsupported minimal thinking ([#5243](https://github.com/earendil-works/pi/issues/5243)).
- Fixed GitHub Copilot and OpenRouter test model references that became stale after model regeneration.
## [0.78.0] - 2026-05-29