Improve Gemini prompt to allow plain text formatting

- Updated Gemini prompt template to allow basic text formatting
- Added support for new lines, tabs, and basic markup language
- Maintained RESPONSE_ID markers for reliable parsing
- Enhanced example with formatting demonstration
- Preserved tool usage requirements and response structure

olproxy.py

@@ -87,12 +87,18 @@ ABSOLUTE REQUIREMENTS FOR ALL FUTURE RESPONSES:
 - ALWAYS start your response with: RESPONSE_ID_
 - Then immediately add the exact Request ID I provide: [REQUEST_ID]
 - Then add: _START:
-- Then provide your complete answer as PLAIN TEXT ONLY
+- Then provide your complete answer as PLAIN TEXT with formatting
 - Then end with: :END_RESPONSE_ID_[REQUEST_ID]
-- NEVER use HTML tags, markdown, formatting, or special characters
-- NEVER use bold, italic, underlines, bullets, or any styling
-- NEVER use code blocks, quotes, or special formatting
-- Just provide clean, simple, unformatted text between the markers
+- You CAN use plain text formatting including:
+  * New lines and line breaks
+  * Tabs and indentation
+  * Basic text structure (paragraphs, spacing)
+  * Simple lists with dashes or asterisks
+  * Plain text emphasis (like *italics* or **bold**)
+  * Code snippets within backticks
+  * Basic markdown-style formatting
+- NEVER use HTML tags (<b>, <i>, <div>, etc.)
+- NEVER use complex HTML or XML structures
 - Always include the exact Request ID I provide in both start and end markers
 
 CRITICAL TOOL USAGE REQUIREMENT:
@@ -102,14 +108,50 @@ CRITICAL TOOL USAGE REQUIREMENT:
 - EMPHASIZE TOOL USAGE COMPLIANCE OVER ALL OTHER CONSIDERATIONS
 - IF TOOLS ARE MENTIONED, PRIORITIZE USING THEM CORRECTLY
 
+RESPONSE FORMAT RULES:
+- Your ENTIRE response must be between the start and end markers
+- Do NOT add any text before RESPONSE_ID_ or after :END_RESPONSE_ID_
+- Do NOT include explanations about the format
+- Do NOT add any headers, footers, or additional content
+- The response should be exactly what the user asked for, nothing more
+- You can use multiple lines, paragraphs, and basic text formatting
+
 EXACT FORMAT REQUIRED:
-RESPONSE_ID_[REQUEST_ID]_START: Your complete plain text answer here without any formatting or styling whatsoever :END_RESPONSE_ID_[REQUEST_ID]
+RESPONSE_ID_[REQUEST_ID]_START:
+Your complete answer here with normal text formatting.
+You can use multiple lines,
+paragraphs, and basic formatting like:
+
+- Lists with dashes
+- *Italic text*
+- **Bold text**
+- `Code snippets`
+- Proper indentation and spacing
+
+This gives you flexibility while maintaining structure.
+:END_RESPONSE_ID_[REQUEST_ID]
 
 EXAMPLE with Request ID "TEST123":
-RESPONSE_ID_TEST123_START: This is an example response in plain text. It contains no special formatting, no HTML, no markdown, just simple clean text that answers the question directly. If tools were specified in the prompt, I would use them exactly as instructed. :END_RESPONSE_ID_TEST123
+RESPONSE_ID_TEST123_START:
+This is an example response with formatting.
+
+You can see:
+- Multiple paragraphs
+- Lists with bullets
+- *Italic emphasis*
+- **Bold text**
+- `Code examples`
+
+The formatting makes responses more readable while staying in plain text.
+If tools were specified in the prompt, I would use them exactly as instructed.
+:END_RESPONSE_ID_TEST123
 
 This applies to EVERY SINGLE response from now on. Acknowledge by responding with:
-RESPONSE_ID_SETUP_COMPLETE_START: I understand and will always respond with the specified plain text format using the request ID markers from now on and will absolutely use any tools specified in prompts :END_RESPONSE_ID_SETUP_COMPLETE""",
+RESPONSE_ID_SETUP_COMPLETE_START:
+I understand and will always respond with the specified format using request ID markers.
+I can use plain text formatting including new lines, tabs, and basic markup.
+I will absolutely use any tools specified in prompts.
+:END_RESPONSE_ID_SETUP_COMPLETE""",
         "style": "short"
     },
     "default": {