Enhance chat handling and introduce Caveman feature

- Refactored handleChatCore to include Caveman functionality, allowing for terse-style system prompts to reduce output token usage.
- Updated APIPageClient to manage Caveman settings, including enabling/disabling and selecting compression levels.
- Adjusted AntigravityExecutor to consolidate function declarations for compatibility with Gemini.
- Removed unnecessary console logs during translator initialization across multiple routes.

open-sse/translator/index.js

@@ -5,7 +5,6 @@ import { cloakClaudeTools } from "../utils/claudeCloaking.js";
 import { filterToOpenAIFormat } from "./helpers/openaiHelper.js";
 import { normalizeThinkingConfig } from "../services/provider.js";
 import { AntigravityExecutor } from "../executors/antigravity.js";
-import { compressMessages, formatRtkLog } from "../rtk/index.js";
 
 // Registry for translators
 const requestRegistry = new Map();
@@ -71,17 +70,10 @@ function stripContentTypes(body, stripList = []) {
 }
 
 // Translate request: source -> openai -> target
-export function translateRequest(sourceFormat, targetFormat, model, body, stream = true, credentials = null, provider = null, reqLogger = null, stripList = [], connectionId = null, rtkEnabled = false, clientTool = null) {
+export function translateRequest(sourceFormat, targetFormat, model, body, stream = true, credentials = null, provider = null, reqLogger = null, stripList = [], connectionId = null, clientTool = null) {
   ensureInitialized();
   let result = body;
 
-  // RTK: compress tool_result content before any translation (shape-agnostic)
-  const rtkStats = compressMessages(result, rtkEnabled);
-  if (rtkStats) {
-    const line = formatRtkLog(rtkStats);
-    if (line) console.log(line);
-  }
-
   // Strip explicit content types (opt-in via strip[] in PROVIDER_MODELS entry)
   stripContentTypes(result, stripList);