Update gemini caching for open router and cline provider (RooCodeInc#3260)

* gemini caching

* changeset

Author: 0xToshii

.changeset/quiet-cups-tie.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": minor
+---
+
+updated gemini caching for OR and cline provider

src/api/transform/openrouter-stream.ts

@@ -21,7 +21,7 @@ export async function createOpenRouterStream(
 
 	// prompt caching: https://openrouter.ai/docs/prompt-caching
 	// this was initially specifically for claude models (some models may 'support prompt caching' automatically without this)
-	// gemini models only use the last breakpoint for caching, so the others will be ignored
+	// includes custom support for gemini which does not have iterative caching
 	switch (model.id) {
 		case "anthropic/claude-3.7-sonnet":
 		case "anthropic/claude-3.7-sonnet:beta":
@@ -40,10 +40,6 @@ export async function createOpenRouterStream(
 		case "anthropic/claude-3-haiku:beta":
 		case "anthropic/claude-3-opus":
 		case "anthropic/claude-3-opus:beta":
-		case "google/gemini-2.5-pro-preview-03-25":
-		case "google/gemini-2.0-flash-001":
-		case "google/gemini-flash-1.5":
-		case "google/gemini-pro-1.5":
 			openAiMessages[0] = {
 				role: "system",
 				content: [
@@ -75,6 +71,52 @@ export async function createOpenRouterStream(
 				}
 			})
 			break
+		case "google/gemini-2.5-pro-preview-03-25":
+		case "google/gemini-2.0-flash-001":
+		case "google/gemini-flash-1.5":
+		case "google/gemini-pro-1.5":
+			// gemini only uses the last breakpoint for caching, so the others will be ignored
+			openAiMessages[0] = {
+				role: "system",
+				content: [
+					{
+						type: "text",
+						text: systemPrompt,
+						// @ts-ignore-next-line
+						cache_control: { type: "ephemeral" },
+					},
+				],
+			}
+
+			const GEMINI_CACHE_USER_MESSAGE_INTERVAL = 4 // add new breakpoint every 4 turns
+			const userMessages = openAiMessages.filter((msg) => msg.role === "user")
+
+			const userMessageCount = userMessages.length
+			const targetUserMessageNumber =
+				Math.floor(userMessageCount / GEMINI_CACHE_USER_MESSAGE_INTERVAL) * GEMINI_CACHE_USER_MESSAGE_INTERVAL
+
+			if (targetUserMessageNumber > 0) {
+				// otherwise dont need to add a breakpoint
+				const msg = userMessages[targetUserMessageNumber - 1]
+
+				if (msg) {
+					if (typeof msg.content === "string") {
+						msg.content = [{ type: "text", text: msg.content }]
+					}
+					if (Array.isArray(msg.content)) {
+						// NOTE: this is fine since env details will always be added at the end. but if it weren't there, and the user added a image_url type message, it would pop a text part before it and then move it after to the end.
+						let lastTextPart = msg.content.filter((part) => part.type === "text").pop()
+
+						if (!lastTextPart) {
+							lastTextPart = { type: "text", text: "..." }
+							msg.content.push(lastTextPart)
+						}
+						// @ts-ignore-next-line
+						lastTextPart["cache_control"] = { type: "ephemeral" }
+					}
+				}
+			}
+			break
 		default:
 			break
 	}