refactor: only exclude google/gemini-2.5-pro-preview from caching

- More surgical approach - only exclude the specific problematic model
- Keep other Google models in caching (they work fine)
- Add comment explaining the exclusion with issue reference
- Update test to only exclude the specific model

This targets just the model causing 3+ minute lag while preserving
caching benefits for other Google models that work properly.

Author: hannesrudolph

packages/types/src/providers/openrouter.ts

@@ -39,6 +39,13 @@ export const OPEN_ROUTER_PROMPT_CACHING_MODELS = new Set([
 	"anthropic/claude-3.7-sonnet:thinking",
 	"anthropic/claude-sonnet-4",
 	"anthropic/claude-opus-4",
+	"google/gemini-2.5-flash-preview",
+	"google/gemini-2.5-flash-preview:thinking",
+	"google/gemini-2.5-flash-preview-05-20",
+	"google/gemini-2.5-flash-preview-05-20:thinking",
+	"google/gemini-2.0-flash-001",
+	"google/gemini-flash-1.5",
+	"google/gemini-flash-1.5-8b",
 ])
 
 // https://www.anthropic.com/news/3-5-models-and-computer-use

src/api/providers/fetchers/__tests__/openrouter.spec.ts

@@ -34,8 +34,9 @@ describe("OpenRouter API", () => {
 				expect(openRouterSupportedCaching).toContain(modelId)
 			}
 
-			// Verify we have all supported models except intentionally excluded Google models
-			const expectedCachingModels = openRouterSupportedCaching.filter((id) => !id.startsWith("google/")).sort()
+			// Verify we have all supported models except intentionally excluded ones
+			const excludedModels = new Set(["google/gemini-2.5-pro-preview"]) // Excluded due to lag issue (#4487)
+			const expectedCachingModels = openRouterSupportedCaching.filter((id) => !excludedModels.has(id)).sort()
 
 			expect(ourCachingModels.sort()).toEqual(expectedCachingModels)