bunware.org
Compare changes
Choose any two refs to compare.
+2
-2
README.md
+2
-2
README.md
···
32
32
33
33
Before continuing, you must:
34
34
35
-
1. Create a project on [Letta Cloud](https://cloud.letta.com) (or your own Letta instance)
35
+
1. Create a project on [Letta Cloud](https://app.letta.com) (or your own Letta instance)
36
36
2. Have a Bluesky account
37
37
3. Have Python 3.8+ installed
38
38
···
40
40
41
41
#### 1. Letta Setup
42
42
43
-
- Sign up for [Letta Cloud](https://cloud.letta.com)
43
+
- Sign up for [Letta Cloud](https://app.letta.com)
44
44
- Create a new project
45
45
- Note your Project ID and create an API key
46
46
+1
-1
bsky.py
+1
-1
bsky.py
···
371
371
logger.info(f"Mention from @{author_handle}: {mention_text}")
372
372
373
373
# Log prompt details to separate logger
374
-
prompt_logger.debug(f"Full prompt being sent:\n{prompt}")
374
+
logger.debug(f"Full prompt being sent:\n{prompt}")
375
375
376
376
# Log concise prompt info to main logger
377
377
thread_handles_count = len(unique_handles)
+18
tools/dummy_reply.py
+18
tools/dummy_reply.py
···
1
+
"""Dummy reply tool for Bluesky responses."""
2
+
from typing import Optional
3
+
from pydantic import BaseModel, Field
4
+
5
+
6
+
class BlueskyReplyArgs(BaseModel):
7
+
message: str = Field(
8
+
...,
9
+
description="The message to reply with (max 300 characters)"
10
+
)
11
+
12
+
13
+
def bluesky_reply(message: str) -> str:
14
+
"""
15
+
Dummy function that just returns success. The actual reply is handled in the bsky.py process_mention function.
16
+
This exists only to make the agent think it has a bluesky_reply tool available.
17
+
"""
18
+
return "Reply will be sent"