Files
server-26/drb-c2-core/app/routers/tokens.py
T
Logan 8b660d8e10 feat: incident correlation overhaul, signal-based auto-resolve, token fixes
Correlator
- Raise fast-path idle gate 30 → 90 min (tg_fast_path_idle_minutes)
- Fix disambiguate always-commits bug: run _call_fits_incident on winner
  before committing; fall through to new-incident creation if it fails
- Add unit-continuity path (path 1.5): matches all_active by shared unit
  IDs with a reassignment guard, bridges calls past the idle gate
- Add tag-based incident_type inference (_TAG_TYPE_HINTS) as GPT fallback,
  rescuing tagged calls that would have been dropped (616 observed orphans)
- Add master/child incident model: _create_master_incident, _demote_to_child,
  _add_child_to_master; new incidents stamped incident_type="master"
- Add cross-system parent detection (_find_cross_system_parent): two-signal
  scoring (road overlap=0.4, embedding≥0.78=0.3, proximity=0.3, threshold=0.5)
  wired into create-if-new path; creates master shell on first cross-system match
- Add maybe_resolve_parent: auto-resolves master when all children close;
  called from upload pipeline (LLM closure) and summarizer stale sweep
- Add signal-based auto-resolve via units_active/units_cleared tracking:
  GPT now extracts cleared_units per scene; _update_incident moves units
  between active/cleared lists and resolves the incident when active empties;
  stored on call doc for re-correlation sweep reuse
- Add _create_incident initialization of units_active/units_cleared fields

Re-correlation sweep
- Add corr_sweep_count + MAX_SWEEP_ATTEMPTS=3: orphans get 3 attempts
  then are tombstoned as corr_path="unlinked", ending the re-sweep loop
  (previously hammering each orphan 29-31 times per shift)

Intelligence extraction
- Add cleared_units to GPT prompt schema and rules
- Extract and propagate cleared_units per scene; merge across scenes;
  store on call doc for re-correlation sweep

Token management
- Fix token release bug: remove release_token call on discord_connected=False
  in MQTT checkin (transient Discord drops were orphaning bots mid-shift)
- Add PUT /tokens/{id}/prefer/{system_id} endpoint: lock a bot token to a
  system; pass _none as system_id to clear; stored bidirectionally on both
  token and system documents
- discord_join handler resolves preferred_token_id from system doc and passes
  system_name in MQTT payload
2026-05-10 19:49:05 -04:00

155 lines
5.5 KiB
Python

import uuid
from fastapi import APIRouter, HTTPException
from pydantic import BaseModel
from typing import Optional
from datetime import datetime, timezone
from app.internal import firestore as fstore
router = APIRouter(prefix="/tokens", tags=["tokens"])
class TokenCreate(BaseModel):
name: str # friendly label e.g. "DRB Bot 1"
token: str # the actual Discord bot token
# ---------------------------------------------------------------------------
# CRUD
# ---------------------------------------------------------------------------
@router.get("")
async def list_tokens():
"""List all tokens. The actual token string is masked for safety."""
tokens = await fstore.collection_list("bot_tokens")
return [
{**t, "token": t["token"][:10] + "" + t["token"][-4:]}
for t in tokens
]
@router.post("", status_code=201)
async def add_token(body: TokenCreate):
token_id = str(uuid.uuid4())
doc = {
"token_id": token_id,
"name": body.name,
"token": body.token,
"in_use": False,
"assigned_node_id": None,
"assigned_at": None,
}
await fstore.doc_set("bot_tokens", token_id, doc, merge=False)
return {"token_id": token_id, "name": body.name}
@router.post("/flush", status_code=200)
async def flush_tokens():
"""Force-release all in-use tokens (admin utility — use when tokens get orphaned)."""
def _find():
from app.internal.firestore import db
return [d for d in db.collection("bot_tokens").where("in_use", "==", True).stream()]
import asyncio
results = await asyncio.to_thread(_find)
for doc in results:
await fstore.doc_update("bot_tokens", doc.id, {
"in_use": False,
"assigned_node_id": None,
"assigned_at": None,
})
return {"released": len(results)}
@router.put("/{token_id}/prefer/{system_id}", status_code=200)
async def set_preferred_system(token_id: str, system_id: str):
"""
Mark this token as the preferred bot for a system.
When a discord_join is issued for any node in that system, this token
is tried first before falling back to the general pool.
Pass system_id="_none" to clear the preference.
"""
existing = await fstore.doc_get("bot_tokens", token_id)
if not existing:
raise HTTPException(404, "Token not found.")
if system_id == "_none":
# Clear any existing preference on the system that pointed to this token.
system_doc = await fstore.doc_get("systems", existing.get("preferred_for_system_id", ""))
if system_doc:
await fstore.doc_set("systems", existing["preferred_for_system_id"], {"preferred_token_id": None})
await fstore.doc_set("bot_tokens", token_id, {"preferred_for_system_id": None})
return {"ok": True, "preferred_for_system_id": None}
system_doc = await fstore.doc_get("systems", system_id)
if not system_doc:
raise HTTPException(404, "System not found.")
# Set preference on both sides for easy lookup in either direction.
await fstore.doc_set("systems", system_id, {"preferred_token_id": token_id})
await fstore.doc_set("bot_tokens", token_id, {"preferred_for_system_id": system_id})
return {"ok": True, "preferred_for_system_id": system_id}
@router.delete("/{token_id}", status_code=204)
async def delete_token(token_id: str):
existing = await fstore.doc_get("bot_tokens", token_id)
if not existing:
raise HTTPException(404, "Token not found.")
if existing.get("in_use"):
raise HTTPException(409, "Token is currently in use by a node.")
await fstore.doc_delete("bot_tokens", token_id)
# ---------------------------------------------------------------------------
# Internal helpers — used by the nodes router, not exposed via HTTP
# ---------------------------------------------------------------------------
async def assign_token(node_id: str, preferred_token_id: Optional[str] = None) -> Optional[str]:
"""
Find a free token, mark it as in-use, return the token string.
If preferred_token_id is given, try that token first (only if it's free).
Returns None if no tokens are available.
"""
def _find_free(preferred: Optional[str]):
from app.internal.firestore import db
if preferred:
snap = db.collection("bot_tokens").document(preferred).get()
if snap.exists and not snap.to_dict().get("in_use"):
return [snap]
docs = db.collection("bot_tokens").where("in_use", "==", False).limit(1).stream()
return [d for d in docs]
import asyncio
results = await asyncio.to_thread(_find_free, preferred_token_id)
if not results:
return None
doc = results[0]
token_id = doc.id
token_value = doc.to_dict()["token"]
await fstore.doc_update("bot_tokens", token_id, {
"in_use": True,
"assigned_node_id": node_id,
"assigned_at": datetime.now(timezone.utc),
})
return token_value
async def release_token(node_id: str) -> None:
"""Free whichever token is currently assigned to this node."""
def _find_assigned():
from app.internal.firestore import db
return [
d for d in db.collection("bot_tokens")
.where("assigned_node_id", "==", node_id)
.stream()
]
import asyncio
results = await asyncio.to_thread(_find_assigned)
for doc in results:
await fstore.doc_update("bot_tokens", doc.id, {
"in_use": False,
"assigned_node_id": None,
"assigned_at": None,
})