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

@@ -120,15 +120,15 @@ describe("Context overflow error handling", () => {
// =============================================================================
// GitHub Copilot (OAuth)
// Tests both OpenAI and Anthropic models via Copilot
// Tests both Google and Anthropic models via Copilot
// =============================================================================
describe("GitHub Copilot (OAuth)", () => {
// OpenAI model via Copilot
// Google model via Copilot
it.skipIf(!githubCopilotToken)(
"gpt-4o - should detect overflow via isContextOverflow",
"gemini-2.5-pro - should detect overflow via isContextOverflow",
async () => {
const model = getModel("github-copilot", "gpt-4o");
const model = getModel("github-copilot", "gemini-2.5-pro");
const result = await testContextOverflow(model, githubCopilotToken!);
logResult(result);