forked from retoor/devplacepy
retoor
4ae0b0db5d
Implement a multi-agent deep web research subsystem including CLI commands for pruning expired jobs and clearing all artifacts, database tables for sessions/messages/URL cache with indexes, config paths for chroma storage, and internal embed URL for vector operations.
111 lines
3.2 KiB
Python
111 lines
3.2 KiB
Python
# retoor <retoor@molodetz.nl>
|
|
|
|
import logging
|
|
import re
|
|
from datetime import datetime
|
|
from typing import Any, Optional
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
DATE_LABEL = "Current date"
|
|
|
|
_MONTH_NAMES = (
|
|
"january|february|march|april|may|june|july|august|september|october|"
|
|
"november|december|jan|feb|mar|apr|jun|jul|aug|sep|sept|oct|nov|dec"
|
|
)
|
|
|
|
_DATE_PATTERNS: tuple[re.Pattern[str], ...] = (
|
|
re.compile(r"\b\d{4}-\d{1,2}-\d{1,2}\b"),
|
|
re.compile(r"\b\d{1,2}/\d{1,2}/\d{4}\b"),
|
|
re.compile(r"\b\d{1,2}-\d{1,2}-\d{4}\b"),
|
|
re.compile(r"\b\d{1,2}\.\d{1,2}\.\d{4}\b"),
|
|
re.compile(
|
|
rf"\b\d{{1,2}}\s+(?:{_MONTH_NAMES})\.?\s+\d{{4}}\b",
|
|
re.IGNORECASE,
|
|
),
|
|
re.compile(
|
|
rf"\b(?:{_MONTH_NAMES})\.?\s+\d{{1,2}}(?:st|nd|rd|th)?,?\s+\d{{4}}\b",
|
|
re.IGNORECASE,
|
|
),
|
|
)
|
|
|
|
|
|
def contains_date(text: str) -> bool:
|
|
return any(pattern.search(text) for pattern in _DATE_PATTERNS)
|
|
|
|
|
|
def current_date_eu() -> str:
|
|
return datetime.now().strftime("%d/%m/%Y")
|
|
|
|
|
|
def system_message_text(content: Any) -> str:
|
|
if isinstance(content, str):
|
|
return content
|
|
if isinstance(content, list):
|
|
parts: list[str] = []
|
|
for block in content:
|
|
if isinstance(block, dict) and block.get("type") == "text":
|
|
value = block.get("text")
|
|
if isinstance(value, str):
|
|
parts.append(value)
|
|
return "\n".join(parts)
|
|
return ""
|
|
|
|
|
|
def compose_system_content(
|
|
preamble: str, client_content: Any, date_eu: str
|
|
) -> str:
|
|
preamble_text = (preamble or "").strip()
|
|
client_text = system_message_text(client_content)
|
|
sections: list[str] = []
|
|
if preamble_text:
|
|
sections.append(preamble_text)
|
|
combined_for_date = f"{preamble_text}\n{client_text}"
|
|
if not contains_date(combined_for_date):
|
|
sections.append(f"{DATE_LABEL}: {date_eu}")
|
|
if client_text:
|
|
sections.append(client_text)
|
|
return "\n\n".join(sections)
|
|
|
|
|
|
def apply_system_directives(
|
|
messages: list, preamble: str, date_eu: Optional[str] = None
|
|
) -> list:
|
|
date_value = date_eu or current_date_eu()
|
|
preamble_text = (preamble or "").strip()
|
|
result: list = list(messages)
|
|
system_index = next(
|
|
(
|
|
index
|
|
for index, message in enumerate(result)
|
|
if isinstance(message, dict) and message.get("role") == "system"
|
|
),
|
|
None,
|
|
)
|
|
if system_index is not None:
|
|
original = result[system_index]
|
|
composed = compose_system_content(
|
|
preamble_text, original.get("content"), date_value
|
|
)
|
|
updated = dict(original)
|
|
updated["content"] = composed
|
|
result[system_index] = updated
|
|
logger.debug(
|
|
"Gateway composed existing system message (preamble=%s, date=%s)",
|
|
bool(preamble_text),
|
|
date_value,
|
|
)
|
|
return result
|
|
if not preamble_text:
|
|
return result
|
|
composed = compose_system_content(preamble_text, "", date_value)
|
|
if not composed.strip():
|
|
return result
|
|
result.insert(0, {"role": "system", "content": composed})
|
|
logger.info(
|
|
"Gateway injected a system message (preamble=%s, date=%s)",
|
|
bool(preamble_text),
|
|
date_value,
|
|
)
|
|
return result
|