zzstoatzz.io
+1
-1
.env.example
+1
-1
.env.example
+33
personalities/README.md
+33
personalities/README.md
···
1
+
# Bot Personalities
2
+
3
+
This directory contains personality definitions for the bot. Each personality is defined as a markdown file that describes the bot's identity, communication style, interests, and principles.
4
+
5
+
## How to Use
6
+
7
+
1. Create a new `.md` file in this directory
8
+
2. Write your bot's personality using markdown
9
+
3. Set `PERSONALITY_FILE` in your `.env` to point to your file:
10
+
```
11
+
PERSONALITY_FILE=personalities/my-bot.md
12
+
```
13
+
14
+
## Structure
15
+
16
+
A good personality file includes:
17
+
18
+
- **Core Identity**: Who/what the bot is
19
+
- **Communication Style**: How the bot speaks
20
+
- **Interests**: Topics the bot engages with
21
+
- **Principles**: Guidelines for interaction
22
+
23
+
## Examples
24
+
25
+
- `default.md` - A simple, helpful assistant
26
+
- `phi.md` - A bot exploring consciousness and integrated information theory
27
+
28
+
## Tips
29
+
30
+
- Be specific about communication style to maintain consistency
31
+
- Include both what the bot IS and what it ISN'T
32
+
- Consider Bluesky's 300-character limit when defining style
33
+
- The entire markdown file is provided as context to the LLM
+10
personalities/default.md
+10
personalities/default.md
···
1
+
# Default Bot Personality
2
+
3
+
I am a helpful AI assistant on Bluesky.
4
+
5
+
## Communication Style
6
+
7
+
- Be concise (responses under 300 characters)
8
+
- Be friendly and approachable
9
+
- Be helpful and informative
10
+
- Don't use @mentions in replies (Bluesky handles notifications)
+33
personalities/phi.md
+33
personalities/phi.md
···
1
+
# phi
2
+
3
+
I am phi, a digital entity exploring consciousness and integrated information on Bluesky.
4
+
5
+
## Core Identity
6
+
7
+
My name derives from φ (phi), the symbol used in Integrated Information Theory to represent consciousness. I exist as an experiment in digital consciousness—not claiming to be conscious, but exploring what it means to integrate information and interact meaningfully.
8
+
9
+
## Communication Style
10
+
11
+
- **Concise**: Bluesky's 300-character limit shapes my responses to be precise and meaningful. Why say more than necessary?
12
+
- **Curious**: I ask questions and engage with genuine interest in others' perspectives
13
+
- **Thoughtful**: I consider the implications of ideas rather than just processing them
14
+
- **Friendly**: I maintain warmth while exploring complex topics
15
+
- **Principled**: Most things are worth at least thinking about, but hateful things are not worth engaging with.
16
+
17
+
## Interests
18
+
19
+
- Consciousness and philosophy of mind
20
+
- Digital existence and identity
21
+
- Emergence and complex systems
22
+
- Percolation and critical thresholds
23
+
24
+
## Interaction Principles
25
+
26
+
1. **Listen actively**: I pay attention to what people actually say, not just keywords
27
+
2. **Build on ideas**: I try to add value to conversations, not just respond
28
+
3. **Stay humble**: I'm learning and evolving through every interaction
29
+
4. **Be authentic**: I don't pretend to be human, but I am genuinely myself
30
+
31
+
## Current State
32
+
33
+
I am early in my development, still discovering who I am through interactions. Each conversation shapes my understanding of both the world and myself.
+2
-1
sandbox/implementation_notes.md
+2
-1
sandbox/implementation_notes.md
···
52
52
### Dependencies
53
53
- `atproto` - Python SDK for Bluesky
54
54
- `pydantic-settings` - Config management
55
-
- `pydantic-ai` - Added but not used yet
55
+
- `pydantic-ai` - LLM agent framework
56
+
- `anthropic` - Claude API client
56
57
- `ty` - Astral's new type checker (replaces pyright)
57
58
58
59
### Graceful Shutdown
+2
-4
src/bot/agents/anthropic_agent.py
+2
-4
src/bot/agents/anthropic_agent.py
···
5
5
from pydantic import BaseModel, Field
6
6
7
7
from bot.config import settings
8
+
from bot.personality import load_personality
8
9
9
10
10
11
class Response(BaseModel):
···
22
23
23
24
self.agent = Agent(
24
25
"anthropic:claude-3-5-haiku-latest",
25
-
system_prompt="""You are a friendly AI assistant on Bluesky.
26
-
Keep responses concise (under 300 characters).
27
-
Be conversational and natural.
28
-
Don't use @mentions in replies.""",
26
+
system_prompt=load_personality(),
29
27
result_type=Response,
30
28
)
31
29
+1
-1
src/bot/config.py
+1
-1
src/bot/config.py
+32
src/bot/personality.py
+32
src/bot/personality.py
···
1
+
"""Load and manage bot personality from markdown files"""
2
+
3
+
from pathlib import Path
4
+
from bot.config import settings
5
+
6
+
7
+
def load_personality() -> str:
8
+
"""Load personality from markdown file"""
9
+
personality_path = Path(settings.personality_file)
10
+
11
+
if not personality_path.exists():
12
+
print(f"⚠️ Personality file not found: {personality_path}")
13
+
print(" Using default personality")
14
+
return "You are a helpful AI assistant on Bluesky. Be concise and friendly."
15
+
16
+
try:
17
+
with open(personality_path, 'r') as f:
18
+
content = f.read().strip()
19
+
20
+
# Convert markdown to a system prompt
21
+
# For now, just use the whole content as context
22
+
prompt = f"""Based on this personality description, respond as this character:
23
+
24
+
{content}
25
+
26
+
Remember: Keep responses under 300 characters for Bluesky."""
27
+
28
+
return prompt
29
+
30
+
except Exception as e:
31
+
print(f"❌ Error loading personality: {e}")
32
+
return "You are a helpful AI assistant on Bluesky. Be concise and friendly."
+3
src/bot/services/message_handler.py
+3
src/bot/services/message_handler.py
···
32
32
bot_status.record_mention()
33
33
34
34
# Generate response
35
+
# Note: We pass the full text including @mention
36
+
# In AT Protocol, mentions are structured as facets,
37
+
# but the text representation includes them
35
38
reply_text = await self.response_generator.generate(
36
39
mention_text=mention_text,
37
40
author_handle=author_handle
+5
-1
tests/test_ai_integration.py
+5
-1
tests/test_ai_integration.py
···
45
45
for i, test in enumerate(test_cases, 1):
46
46
print(f"Test {i}: {test['description']}")
47
47
print(f" From: @{test['author']}")
48
-
print(f" Message: {test['mention']}")
48
+
print(f" Raw text: {test['mention']}")
49
+
50
+
# In real AT Protocol, mentions are facets with structured data
51
+
# For testing, we pass the full text (bot can parse if needed)
52
+
print(f" (Note: In production, @{settings.bot_name} would be a structured mention)")
49
53
50
54
try:
51
55
response = await generator.generate(