ce3c1f5f7f
- config.py: memory_budget_long/mid/short settings (overridable in .env)
- memory_distiller.py: distill_short (no LLM), distill_mid, distill_long (LLM)
- routers/distill.py: POST /distill/{short,mid,long,all} endpoints
- context_loader.py: rewrote to load long→mid→short order with include_* toggles
- routers/chat.py: ChatRequest gains include_long/mid/short fields
- routers/files.py: MEMORY_LONG/MID/SHORT.md added to ALLOWED set
- main.py: register distill router
- static/index.html: context bar — tier selector, L/M/S memory toggles,
distill buttons with status feedback; send includes tier + memory flags
- inara/MEMORY_LONG.md: migrated from MEMORY.md + Cortex/Talk bot notes
- inara/MEMORY_MID.md, MEMORY_SHORT.md: stubs ready for distillation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
54 lines
2.0 KiB
Python
54 lines
2.0 KiB
Python
from pathlib import Path
|
|
from pydantic_settings import BaseSettings, SettingsConfigDict
|
|
|
|
|
|
class Settings(BaseSettings):
|
|
anthropic_api_key: str | None = None # not used — claude CLI handles auth
|
|
inara_dir: Path = Path("../inara")
|
|
sessions_dir: Path = Path("./data/sessions")
|
|
default_model: str = "claude-sonnet-4-6"
|
|
default_tier: int = 2
|
|
max_history_messages: int = 40 # rolling window — 20 turns (user + assistant)
|
|
primary_backend: str = "claude" # "claude" or "gemini" — other is always fallback
|
|
|
|
# Per-backend timeouts in seconds
|
|
timeout_claude: int = 60
|
|
timeout_gemini: int = 120 # frequently slow under load
|
|
timeout_local: int = 300 # local models may need to load first
|
|
|
|
# Google Chat must receive a response within 30s or shows an error to the user
|
|
google_chat_timeout: int = 25
|
|
# Backend forced for Google Chat — Claude is more reliable within the 25s deadline
|
|
google_chat_backend: str = "claude"
|
|
|
|
# Nextcloud Talk bot
|
|
nextcloud_url: str = "https://cloud.dgrzone.com"
|
|
nextcloud_talk_bot_secret: str = "" # set in .env
|
|
nextcloud_talk_timeout: int = 55
|
|
|
|
# Memory tier token budgets — soft caps used during distillation
|
|
# Override in .env: MEMORY_BUDGET_LONG=4000 etc.
|
|
memory_budget_long: int = 2000
|
|
memory_budget_mid: int = 2000
|
|
memory_budget_short: int = 3000
|
|
|
|
host: str = "0.0.0.0"
|
|
port: int = 8000
|
|
|
|
model_config = SettingsConfigDict(env_file=".env", env_file_encoding="utf-8", extra="ignore")
|
|
|
|
def inara_path(self) -> Path:
|
|
"""Resolve inara_dir relative to this file's location if not absolute."""
|
|
if self.inara_dir.is_absolute():
|
|
return self.inara_dir
|
|
return (Path(__file__).parent / self.inara_dir).resolve()
|
|
|
|
def sessions_path(self) -> Path:
|
|
"""Resolve sessions_dir relative to this file's location if not absolute."""
|
|
if self.sessions_dir.is_absolute():
|
|
return self.sessions_dir
|
|
return (Path(__file__).parent / self.sessions_dir).resolve()
|
|
|
|
|
|
settings = Settings()
|