fix: removing contextLimit test and removing token management in translations

Author: HahaBill

src/api/providers/__tests__/gemini-handler.spec.ts

@@ -1,26 +1,8 @@
 import { describe, it, expect, vi } from "vitest"
 import { GeminiHandler } from "../gemini"
 import type { ApiHandlerOptions } from "../../../shared/api"
-import type { Anthropic } from "@anthropic-ai/sdk"
 
 describe("GeminiHandler backend support", () => {
-	it("slices messages when contextLimit is set", async () => {
-		const options = { apiProvider: "gemini", contextLimit: 1 } as ApiHandlerOptions
-		const handler = new GeminiHandler(options)
-		const stub = vi.fn().mockReturnValue((async function* () {})())
-		// @ts-ignore access private client
-		handler["client"].models.generateContentStream = stub
-		const messages = [
-			{ role: "user", content: [{ type: "text", text: "first" }] },
-			{ role: "assistant", content: [{ type: "text", text: "second" }] },
-		] as Anthropic.Messages.MessageParam[]
-		for await (const _ of handler.createMessage("instr", messages)) {
-		}
-		expect(stub).toHaveBeenCalledOnce()
-		const params = stub.mock.calls[0][0]
-		expect(params.contents).toHaveLength(1)
-	})
-
 	it("passes maxOutputTokens, topP, topK, and tools for URL context and grounding in config", async () => {
 		const options = {
 			apiProvider: "gemini",

webview-ui/src/i18n/locales/ca/settings.json

@@ -250,23 +250,7 @@
 		},
 		"geminiSections": {
 			"modelParameters": "Paràmetres del model",
-			"advancedFeatures": "Funcions avançades",
-			"geminiTokentManagement": "Gestió de tokens"
-		},
-		"geminiTokentManagement": {
-			"useCustomContextWindow": "Use custom context window limit",
-			"description": "Override the model's default context window.",
-			"modelDefault": "Model's default context window",
-			"condensingThreshold": {
-				"tokens": "tokens",
-				"title": "Context Condensing Threshold",
-				"description": "Set the percentage of context window usage that triggers automatic condensing. Note: If the calculated token limit (after reserving space for output and safety buffers) is lower than this percentage, the token limit will trigger condensing instead.",
-				"condensingtriggerAt": "Condensing will trigger at",
-				"tokenLimitTriggered": "due to token limit, not percentage",
-				"availableContext": "Available context window",
-				"tokenLimitTrigger": "Token limit trigger (after reserving output tokens and safety buffer)",
-				"actualTrigger": "Actual trigger (minimum of percentage and token limit)"
-			}
+			"advancedFeatures": "Funcions avançades"
 		},
 		"googleCloudSetup": {
 			"title": "Per utilitzar Google Cloud Vertex AI, necessiteu:",
@@ -366,21 +350,6 @@
 			"pathLabel": "Ruta del Codi Claude",
 			"description": "Ruta opcional al teu CLI de Claude Code. Per defecte, 'claude' si no s'estableix.",
 			"placeholder": "Per defecte: claude"
-		},
-		"geminiContextManagement": {
-			"useCustomContextWindow": "Use custom context window limit",
-			"description": "Override the model's default context window.",
-			"modelDefault": "Model's default context window",
-			"condensingThreshold": {
-				"tokens": "tokens",
-				"title": "Context Condensing Threshold",
-				"description": "Set the percentage of context window usage that triggers automatic condensing. Note: If the calculated token limit (after reserving space for output and safety buffers) is lower than this percentage, the token limit will trigger condensing instead.",
-				"condensingtriggerAt": "Condensing will trigger at",
-				"tokenLimitTriggered": "due to token limit, not percentage",
-				"availableContext": "Available context window",
-				"tokenLimitTrigger": "Token limit trigger (after reserving output tokens and safety buffer)",
-				"actualTrigger": "Actual trigger (minimum of percentage and token limit)"
-			}
 		}
 	},
 	"browser": {

webview-ui/src/i18n/locales/en/settings.json

@@ -224,8 +224,7 @@
 		"vscodeLmWarning": "Note: This is a very experimental integration and provider support will vary. If you get an error about a model not being supported, that's an issue on the provider's end.",
 		"geminiSections": {
 			"modelParameters": "Model Parameters",
-			"advancedFeatures": "Advanced Features",
-			"geminiTokentManagement": "Token Management"
+			"advancedFeatures": "Advanced Features"
 		},
 		"geminiParameters": {
 			"topK": {