Introduces model_registry.py as the single source of truth for all LLM
backend configuration. Replaces scattered backend settings across user_settings,
config distill_backend_*, and the UI toggle.
model_registry.py:
- Per-user home/{user}/model_registry.json with version, hosts, models, roles
- Models have: type (local_openai|claude_cli|gemini_cli|gemini_api), label,
model_name, host_id, context_k (tokens), tags (capability labels)
- Roles map to priority chains: primary, backup_1..backup_4
- Built-in IDs (claude_cli, gemini_cli, gemini_api) always resolvable
- Auto-migrates existing local_llm.json on first access
- CRUD: save_host, remove_host, save_model, remove_model, set_role
- get_model_for_role(): registry → .env default → hardcoded fallback
config.py:
- role_chat/orchestrator/distill/coder/research .env defaults
- defined_roles: comma-separated standard role list (extensible)
- get_defined_roles() and get_role_default() helper methods
llm_client.complete():
- New role= parameter (default "chat") for registry-based routing
- model= still accepted for explicit UI toggle override
- _claude() and _local() accept model_cfg dict instead of raw string
- _local() uses pre-resolved config from registry
memory_distiller.py:
- distill_mid/long now use role="distill" (no more distill_backend_* .env vars needed)
cron_runner.py:
- brief jobs use role="chat"
routers/chat.py + auth.py:
- Use model_registry instead of user_settings for local model info
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
129 lines
5.8 KiB
Python
129 lines
5.8 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 = ""
|
|
|
|
# Model registry: default backend type per role when user registry has no entry.
|
|
# Values: "claude_cli" | "gemini_cli" | "gemini_api" (builtin IDs)
|
|
# Override in .env: ROLE_CHAT=claude_cli ROLE_DISTILL=gemini_api etc.
|
|
role_chat: str = "claude_cli"
|
|
role_orchestrator: str = "gemini_api"
|
|
role_distill: str = "claude_cli"
|
|
role_coder: str = "claude_cli"
|
|
role_research: str = "gemini_api"
|
|
|
|
# Comma-separated list of standard roles shown in the model settings UI.
|
|
# Add custom roles here to extend the UI without code changes.
|
|
# Example: DEFINED_ROLES=chat,orchestrator,distill,coder,research,medical
|
|
defined_roles: str = "chat,orchestrator,distill,coder,research"
|
|
|
|
# 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 get_defined_roles(self) -> list[str]:
|
|
"""Return the ordered list of standard roles from the defined_roles setting."""
|
|
return [r.strip() for r in self.defined_roles.split(",") if r.strip()]
|
|
|
|
def get_role_default(self, role: str) -> str:
|
|
"""Return the .env default backend type for a role (e.g. 'claude_cli')."""
|
|
return getattr(self, f"role_{role.replace('-', '_')}", "claude_cli")
|
|
|
|
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()
|