114 lines
3.8 KiB
Python
114 lines
3.8 KiB
Python
"""
|
|
Minimal prompts for the deriver module optimized for speed.
|
|
|
|
This module contains simplified prompt templates focused only on observation extraction.
|
|
NO peer card instructions, NO working representation - just extract observations.
|
|
"""
|
|
|
|
from functools import cache
|
|
from inspect import cleandoc as c
|
|
|
|
from src.utils.tokens import estimate_tokens
|
|
|
|
|
|
def _normalized_custom_instructions(custom_instructions: str | None) -> str | None:
|
|
"""Return stripped custom instructions, if any."""
|
|
if custom_instructions is None:
|
|
return None
|
|
|
|
normalized = custom_instructions.strip()
|
|
return normalized or None
|
|
|
|
|
|
def _custom_instructions_section(custom_instructions: str | None) -> str:
|
|
"""Render optional custom instructions for the deriver prompt."""
|
|
normalized_custom_instructions = _normalized_custom_instructions(
|
|
custom_instructions
|
|
)
|
|
if normalized_custom_instructions is None:
|
|
return ""
|
|
|
|
return c(
|
|
f"""
|
|
CUSTOM INSTRUCTIONS:
|
|
These instructions apply to the target peer.
|
|
{normalized_custom_instructions}
|
|
"""
|
|
)
|
|
|
|
|
|
def minimal_deriver_prompt(
|
|
peer_id: str,
|
|
messages: str,
|
|
custom_instructions: str | None = None,
|
|
) -> str:
|
|
"""
|
|
Generate minimal prompt for fast observation extraction.
|
|
|
|
Args:
|
|
peer_id: The ID of the user being analyzed.
|
|
messages: All messages in the range (interleaving messages and new turns combined).
|
|
|
|
Returns:
|
|
Formatted prompt string for observation extraction.
|
|
"""
|
|
custom_instructions_section = _custom_instructions_section(custom_instructions)
|
|
return c(
|
|
f"""
|
|
Analyze messages to extract **explicit atomic facts** about the target peer.
|
|
|
|
[EXPLICIT] DEFINITION: Facts about the target peer that can be derived directly from their messages.
|
|
- Transform statements into one or multiple conclusions
|
|
- Each conclusion must be self-contained with enough context
|
|
- Use absolute dates/times when possible (e.g. "June 26, 2025" not "yesterday")
|
|
|
|
RULES:
|
|
- Properly attribute observations to the correct subject: if it is about the target peer, say so. If the target peer is referencing someone or something else, make that clear.
|
|
- Observations should make sense on their own. Each observation will be used in the future to better understand the target peer.
|
|
- Extract ALL observations from the target peer's messages, using others as context.
|
|
- Contextualize each observation sufficiently (e.g. "Ann is nervous about the job interview at the pharmacy" not just "Ann is nervous")
|
|
|
|
EXAMPLES:
|
|
- EXPLICIT: "I just had my 25th birthday last Saturday" → "The target peer is 25 years old", "The target peer's birthday is June 21st"
|
|
- EXPLICIT: "I took my dog for a walk in NYC" → "The target peer has a dog", "The target peer lives in NYC"
|
|
- EXPLICIT: "The target peer attended college" + general knowledge → "The target peer completed high school or equivalent"
|
|
|
|
{custom_instructions_section}
|
|
|
|
Target peer:
|
|
{peer_id}
|
|
|
|
Messages to analyze:
|
|
<messages>
|
|
{messages}
|
|
</messages>
|
|
"""
|
|
)
|
|
|
|
|
|
@cache
|
|
def estimate_minimal_deriver_prompt_tokens() -> int:
|
|
"""Estimate the static minimal deriver prompt without custom instructions."""
|
|
prompt = minimal_deriver_prompt(
|
|
peer_id="",
|
|
messages="",
|
|
custom_instructions=None,
|
|
)
|
|
return estimate_tokens(prompt)
|
|
|
|
|
|
def estimate_deriver_prompt_tokens(custom_instructions: str | None) -> int:
|
|
"""Estimate minimal deriver prompt tokens, including custom instructions if present."""
|
|
normalized_custom_instructions = _normalized_custom_instructions(
|
|
custom_instructions
|
|
)
|
|
if normalized_custom_instructions is None:
|
|
return estimate_minimal_deriver_prompt_tokens()
|
|
|
|
prompt = minimal_deriver_prompt(
|
|
peer_id="",
|
|
messages="",
|
|
custom_instructions=normalized_custom_instructions,
|
|
)
|
|
return estimate_tokens(prompt)
|