Files
Cortex-Inara/cortex/routers/nextcloud_talk.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

169 lines
5.8 KiB
Python

import asyncio
import json
import logging
from fastapi import APIRouter, BackgroundTasks, HTTPException, Request, Response
from auth_utils import get_user_channels
from context_loader import load_context
from llm_client import complete
from notification import _send_nct_message
from persona import set_context
from session_logger import log_turn
from session_store import load as load_session, save as save_session
from config import settings
import event_bus
logger = logging.getLogger(__name__)
logger.setLevel(logging.DEBUG)
if not logger.handlers:
_h = logging.StreamHandler()
_h.setFormatter(logging.Formatter("%(levelname)s:%(name)s: %(message)s"))
logger.addHandler(_h)
logger.propagate = False
router = APIRouter()
def _verify_signature(body: bytes, random_header: str, sig_header: str, secret: str) -> bool:
"""Nextcloud signs requests with HMAC-SHA256(key=secret, msg=random+body)."""
expected = hmac.new(
secret.encode(),
(random_header + body.decode("utf-8", errors="replace")).encode(),
hashlib.sha256,
).hexdigest()
return hmac.compare_digest(expected, sig_header.lower())
async def _send_reply(conversation_token: str, message: str, nextcloud_url: str, secret: str) -> None:
"""Post a message to Nextcloud Talk as the bot."""
logger.info("NCT _send_reply → room %s (%d chars)", conversation_token, len(message))
await _send_nct_message(nextcloud_url, secret, conversation_token, message)
async def _process_message(
conversation_token: str,
user_text: str,
actor_name: str,
username: str,
persona_name: str,
nextcloud_url: str,
secret: str,
timeout: int,
) -> None:
logger.info("NCT process: token=%s user=%s text=%r", conversation_token, actor_name, user_text)
set_context(username, persona_name)
session_id = f"nct_{username}_{conversation_token}"
system_prompt = load_context(settings.default_tier)
history = load_session(session_id)
history.append({"role": "user", "content": user_text})
await event_bus.publish({
"type": "nct_message",
"session_id": session_id,
"role": "user",
"content": user_text,
"actor": actor_name,
})
try:
response_text, backend = await asyncio.wait_for(
complete(system_prompt=system_prompt, messages=history),
timeout=timeout,
)
except asyncio.TimeoutError:
logger.warning("NCT timeout for %s", conversation_token)
await _send_reply(conversation_token, "⏳ Still thinking — this is taking longer than usual.", nextcloud_url, secret)
return
except Exception as e:
logger.error("NCT LLM error for %s: %s", conversation_token, e)
await _send_reply(conversation_token, "⚠️ Something went wrong on my end.", nextcloud_url, secret)
return
logger.info("NCT LLM responded via %s (%d chars)", backend, len(response_text))
history.append({"role": "assistant", "content": response_text})
save_session(session_id, history)
log_turn(session_id, user_text, response_text)
await event_bus.publish({
"type": "nct_response",
"session_id": session_id,
"role": "assistant",
"content": response_text,
"backend": backend,
})
await _send_reply(conversation_token, response_text, nextcloud_url, secret)
@router.post("/webhook/nextcloud/{username}")
async def nextcloud_talk_webhook(username: str, request: Request, background_tasks: BackgroundTasks):
channels = get_user_channels(username)
cfg = channels.get("nextcloud")
if not cfg:
logger.warning("NCT webhook: no channel config for user %r", username)
raise HTTPException(status_code=404, detail="Channel not configured for this user")
persona_name = cfg.get("persona", "inara")
nextcloud_url = cfg.get("url", "")
secret = cfg.get("bot_secret", "")
timeout = cfg.get("timeout", 55)
if not secret:
logger.error("NCT webhook: bot_secret missing for user %r", username)
return Response(status_code=500)
body = await request.body()
random_header = request.headers.get("X-Nextcloud-Talk-Random", "")
sig_header = request.headers.get("X-Nextcloud-Talk-Signature", "")
if not _verify_signature(body, random_header, sig_header, secret):
logger.warning("NCT webhook: signature mismatch for %s", username)
raise HTTPException(status_code=401, detail="Invalid signature")
try:
payload = json.loads(body)
except json.JSONDecodeError:
raise HTTPException(status_code=400, detail="Invalid JSON")
if payload.get("type") != "Create":
return Response(status_code=200)
obj = payload.get("object", {})
if obj.get("type") != "Note":
return Response(status_code=200)
actor = payload.get("actor", {})
target = payload.get("target", {})
if actor.get("type") == "bots":
return Response(status_code=200)
conversation_token = target.get("id", "")
try:
content = json.loads(obj.get("content", "{}"))
user_text = content.get("message", "").strip()
except (json.JSONDecodeError, AttributeError):
user_text = (obj.get("name") or obj.get("content", "")).strip()
mention_prefix = f"@{persona_name.lower()}"
if user_text.lower().startswith(mention_prefix):
user_text = user_text[len(mention_prefix):].strip()
if not user_text:
return Response(status_code=200)
actor_name = actor.get("name", "User")
logger.info("NCT message from %s in %s: %r", actor_name, conversation_token, user_text[:60])
background_tasks.add_task(
_process_message,
conversation_token, user_text, actor_name,
username, persona_name, nextcloud_url, secret, timeout,
)
return Response(status_code=200)