Files
Cortex-Inara/cortex/config.py
Scott Idem a4daebdc9b feat: local LLM multi-model, session search, cron proactive types, notifications, docs overhaul
Local LLM:
- user_settings.py: per-user hosts/models config (local_llm.json)
- routers/local_llm.py + static/local_llm.html: dedicated settings page
- llm_client.py: local OpenAI-compatible backend via httpx
- config.py: LOCAL_API_URL/KEY/MODEL + per-backend timeouts
- Active model shown near backend toggle (amber hint text)

Memory distillation:
- memory_distiller.py: DISTILL_BACKEND_MID/LONG .env overrides
- scheduler.py + notification.py: notify NC Talk after mid/long distill
- notification.py: outbound channel abstraction (NC Talk, extensible)

Session search:
- routers/files.py: GET /sessions/search?q= with excerpts grouped by date
- static/index.html + app.js: search UI in file sidebar with highlight
- _esc() helper to prevent XSS in search results

Proactive cron:
- cron_runner.py: new job types — message (send directly) and brief (LLM + send)
- Both support optional per-job channel override

Channels:
- routers/nextcloud_talk.py: consolidated using notification._send_nct_message()
- routers/auth.py: local backend status in /auth/status
- routers/chat.py: /backend returns {primary, fallback, local_model} object

UI / UX:
- Copy button for user messages (matching assistant)
- Autocomplete disabled on sensitive form fields
- settings.html: local model section replaced with link to /settings/local

Docs overhaul:
- MASTER.md hub + ARCH__SYSTEM/BACKENDS/PERSONA/CHANNELS/FUTURE.md
- ARCH__Intelligence_Layer.md replaced with redirect table
- CORTEX.md trimmed to vision only; README updated
- OPEN_WEBUI_API.md added to docs/

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-05 20:53:06 -04:00

107 lines
4.7 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
# Google OAuth — "Sign in with Google" for all users
# Create credentials at console.cloud.google.com → APIs & Services → Credentials
# Add https://<your-domain>/auth/google/callback as an authorised redirect URI
google_client_id: str | None = None
google_client_secret: str | None = None
# Orchestrator (Gemini API — separate from Gemini CLI)
# Get a key at: https://aistudio.google.com/apikey (free tier is sufficient)
gemini_api_key: str | None = None
orchestrator_model: str = "gemini-2.5-flash" # model used for tool loop
orchestrator_max_rounds: int = 10 # safety cap on tool iterations
# DuckDuckGo search (used by orchestrator web_search tool)
# Leave blank to use the free unauthenticated tier; set to your API key for higher limits
ddg_api_key: str | None = None
ddg_max_results: int = 5
# Aether Platform API (used by orchestrator ae_journal_* and ae_task_list tools)
ae_api_url: str = "https://dev-api.oneskyit.com"
ae_api_key: str = "" # x-aether-api-key header
ae_account_id: str = "" # x-account-id header
ae_api_timeout: int = 15 # per-request timeout in seconds
# Agent identity — used in prompts, session logs, and memory distillation
# Override in .env for each instance (e.g. AGENT_NAME=Holly, USER_NAME=Holly)
agent_name: str = "Inara"
user_name: str = "Scott"
home_dir: Path = Path("../home")
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
# Local model backend — OpenAI-compatible API (Open WebUI / Ollama)
# Set LOCAL_API_URL in .env to enable; leave blank to disable
local_api_url: str = "" # e.g. http://192.168.32.19:3000
local_api_key: str = "" # sk-... from Open WebUI → Settings → Account → API Keys
local_model: str = "" # workspace or model name, e.g. test-agent-simple
# 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
# Auto-distillation schedule — override in .env
# AUTO_DISTILL=false disables entirely
scheduler_timezone: str = "America/New_York" # IANA tz — override in .env if needed
auto_distill: bool = True
auto_distill_short: bool = True # daily at 03:00 — rolls session logs → MEMORY_SHORT
auto_distill_mid: bool = True # weekly Sunday at 03:30 — LLM summarizes short → mid
auto_distill_long: bool = False # monthly 1st at 04:00 — off by default (manual review recommended)
# Which backend to use for distillation LLM calls.
# "" = use primary_backend (default); "local" = use local model (saves API credits).
# "long" stays on default (claude/gemini) for best quality.
distill_backend_mid: str = ""
distill_backend_long: str = ""
# 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
# Session auth
jwt_secret: str = "change-me-in-dotenv" # override in .env: JWT_SECRET=<random>
jwt_expire_days: int = 30
# SMTP — for sending invite emails
smtp_server: str = ""
smtp_port: int = 465
smtp_username: str = ""
smtp_password: str = ""
smtp_from_email: str = "noreply@oneskyit.com"
smtp_from_name: str = "Cortex"
# Base URL used in invite links (no trailing slash)
cortex_base_url: str = "https://cortex.dgrzone.com"
host: str = "0.0.0.0"
port: int = 8000
model_config = SettingsConfigDict(env_file=".env", env_file_encoding="utf-8", extra="ignore")
def home_root(self) -> Path:
"""Resolve home_dir relative to this file's location if not absolute."""
if self.home_dir.is_absolute():
return self.home_dir
return (Path(__file__).parent / self.home_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()