Simplify mention prompt and make replying optional

Streamlined the prompt agents receive when mentioned:
- Removed prescriptive guidance about when to use threads
- Removed redundant explanation of YAML structure
- Made replying feel optional ("If you choose to reply...")
- Kept essential info: who mentioned them, the post, thread context, and tool usage

This gives agents more autonomy to decide whether and how to respond,
rather than implying they must reply to every mention.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <[e-mail]>

bsky.py

···
         # Create a prompt for the Letta agent with thread context
         prompt = f"""You received a mention on Bluesky from @{author_handle} ({author_name or author_handle}).
 
-MOST RECENT POST (the mention you're responding to):
+MOST RECENT POST:
 "{mention_text}"
 
-FULL THREAD CONTEXT:
+THREAD CONTEXT:
 ```yaml
 {thread_context}
 ```
 
-The YAML above shows the complete conversation thread. The most recent post is the one mentioned above that you should respond to, but use the full thread context to understand the conversation flow.
-
-To reply, use the add_post_to_bluesky_reply_thread tool:
-- Each call creates one post (max 300 characters)
-- For most responses, a single call is sufficient
-- Only use multiple calls for threaded replies when:
-  * The topic requires extended explanation that cannot fit in 300 characters
-  * You're explicitly asked for a detailed/long response
-  * The conversation naturally benefits from a structured multi-part answer
-- Avoid unnecessary threads - be concise when possible"""
+If you choose to reply, use the add_post_to_bluesky_reply_thread tool. Each call creates one post (max 300 characters). You may use multiple calls to create a thread if needed."""
 
         # Extract all handles from notification and thread data
         all_handles = set()