Add web auth, infinite-scroll, agent admission and review fixes across agent/server/web

server/monlet_server/api/events.py

@@ -7,8 +7,10 @@ from fastapi import APIRouter, Depends, HTTPException, Query, status
 from sqlalchemy import and_, or_, select
 from sqlalchemy.ext.asyncio import AsyncSession
 
+from .. import metrics
 from ..agent_auth import AgentCredential, get_agent_credential
 from ..db import get_session
+from ..logging_config import get_logger
 from ..models import Event
 from ..schemas import (
     ID_PATTERN,
@@ -22,6 +24,8 @@ from ..timeutil import to_utc
 
 router = APIRouter()
 
+log = get_logger("monlet.events")
+
 
 def _encode_cursor(received_at: datetime, event_id) -> str:
     raw = f"{to_utc(received_at).isoformat()}|{event_id}".encode()
@@ -52,12 +56,24 @@ async def events(
 ) -> EventBatchAcceptedResponse:
     agent = await accepted_agent_for_key(session, credential)
     if agent is None:
-        await session.commit()
-        return EventBatchAcceptedResponse(accepted=0, deduplicated=0)
+        raise HTTPException(status_code=403, detail="agent not accepted")
     accepted = 0
     deduplicated = 0
     for ev in body.events:
-        ok = await ingest_event(session, agent.agent_id, ev)
+        try:
+            async with session.begin_nested():
+                ok = await ingest_event(session, agent.agent_id, ev)
+        except HTTPException as exc:
+            if exc.status_code != 400:
+                raise
+            log.warning(
+                "event_rejected",
+                check_id=ev.check_id,
+                agent_id=agent.agent_id,
+                code=exc.detail,
+            )
+            metrics.events_total.labels(result="rejected").inc()
+            continue
         if ok:
             accepted += 1
         else:

server/monlet_server/errors.py

@@ -46,11 +46,12 @@ def install_error_handlers(app: FastAPI) -> None:
 
     @app.exception_handler(StarletteHTTPException)
     async def _http(request: Request, exc: StarletteHTTPException):
-        code = (
-            "agent_blocked"
-            if exc.status_code == 403 and exc.detail == "agent blocked"
-            else _STATUS_TO_CODE.get(exc.status_code, "internal")
-        )
+        code: ErrorCode = _STATUS_TO_CODE.get(exc.status_code, "internal")
+        if exc.status_code == 403:
+            if exc.detail == "agent blocked":
+                code = "agent_blocked"
+            elif exc.detail == "agent not accepted":
+                code = "agent_not_accepted"
         msg = exc.detail if isinstance(exc.detail, str) else code
         return error_response(request, exc.status_code, code, msg)
 

server/monlet_server/metrics.py

@@ -1,4 +1,4 @@
-from prometheus_client import CollectorRegistry, Counter, Gauge, Histogram, generate_latest
+from prometheus_client import CollectorRegistry, Counter, Gauge, generate_latest
 from prometheus_client.exposition import CONTENT_TYPE_LATEST
 
 REGISTRY = CollectorRegistry()
@@ -42,12 +42,6 @@ notifications_total = Counter(
     ["notifier", "result"],
     registry=REGISTRY,
 )
-request_duration = Histogram(
-    "monlet_server_request_duration_seconds",
-    "Request duration seconds.",
-    ["path"],
-    registry=REGISTRY,
-)
 
 
 def render() -> tuple[bytes, str]:

server/monlet_server/schemas.py

@@ -1,7 +1,6 @@
 import re
 from datetime import datetime
 from typing import Literal
-from uuid import UUID
 
 from pydantic import BaseModel, ConfigDict, Field, field_validator
 
@@ -39,6 +38,7 @@ ErrorCode = Literal[
     "internal",
     "not_ready",
     "agent_blocked",
+    "agent_not_accepted",
 ]
 
 
@@ -233,12 +233,6 @@ class OutboxPage(PageEnvelope):
     items: list[NotificationOutboxItem]
 
 
-class UUIDStr(BaseModel):
-    """Helper to validate generated UUIDs."""
-
-    value: UUID
-
-
 class SystemSummaryResponse(BaseModel):
     agents_online: int
     agents_offline: int

server/monlet_server/services/ingestion.py

@@ -53,13 +53,7 @@ async def _blacklist_row(session: AsyncSession, cred: AgentCredential) -> AgentB
     return res.scalar_one_or_none()
 
 
-async def reject_if_blocked(
-    session: AsyncSession,
-    cred: AgentCredential,
-    agent_id: str,
-    hostname: str,
-    observed: datetime | None = None,
-) -> None:
+async def reject_if_blocked(session: AsyncSession, cred: AgentCredential) -> None:
     row = await _blacklist_row(session, cred)
     if row is None:
         return
@@ -108,7 +102,7 @@ async def upsert_agent_heartbeat(
     session: AsyncSession, hb: HeartbeatRequest, cred: AgentCredential
 ) -> str:
     observed = to_utc(hb.observed_at)
-    await reject_if_blocked(session, cred, hb.agent_id, hb.hostname, observed)
+    await reject_if_blocked(session, cred)
 
     features = hb.features.model_dump()
     res = await session.execute(select(Agent).where(Agent.accepted_key_hash == cred.key_hash))
@@ -330,7 +324,6 @@ async def ingest_event(
             incident_key=incident_key,
         )
         await session.execute(stmt)
-        metrics.events_total.labels(result="accepted").inc()
     else:
         metrics.events_total.labels(result="unchanged").inc()
 
@@ -366,6 +359,9 @@ async def ingest_event(
         return False
 
     transition, inc = await _apply_incident(session, agent_id, ev, incident_key)
+    # Count accepted only after _apply_incident: an incident_key collision raises
+    # 400 and the savepoint rollback discards the Event insert above.
+    metrics.events_total.labels(result="accepted").inc()
     if transition and inc is not None and ev.notifications_enabled:
         event_type = "resolved" if ev.status == "ok" else "firing"
         await _enqueue_outbox(

server/monlet_server/services/notifier_worker.py

@@ -208,9 +208,16 @@ async def tick(
         await session.commit()
     if not rows:
         return 0
-    await asyncio.gather(
-        *(_process_row(sm, registry, r, settings.notifier_max_attempts) for r in rows)
-    )
+
+    # Bound concurrent DB sessions: each _process_row opens its own session, so an
+    # unbounded gather over a large batch can exhaust the connection pool.
+    sem = asyncio.Semaphore(settings.notifier_concurrency)
+
+    async def _guarded(row: dict) -> None:
+        async with sem:
+            await _process_row(sm, registry, row, settings.notifier_max_attempts)
+
+    await asyncio.gather(*(_guarded(r) for r in rows))
     return len(rows)
 
 

server/monlet_server/services/notifiers/http.py

@@ -1,7 +1,5 @@
 from __future__ import annotations
 
-import httpx
-
 
 def classify_response(status: int) -> tuple[bool, bool]:
     """Return (ok, permanent_failure)."""
@@ -10,9 +8,3 @@ def classify_response(status: int) -> tuple[bool, bool]:
     if 400 <= status < 500 and status not in (408, 425, 429):
         return False, True
     return False, False
-
-
-def classify_exception(exc: Exception) -> tuple[bool, bool]:
-    if isinstance(exc, httpx.TimeoutException | httpx.NetworkError):
-        return False, False
-    return False, False

server/monlet_server/settings.py

@@ -1,4 +1,4 @@
-from pydantic import field_validator
+from pydantic import Field, field_validator
 from pydantic_settings import BaseSettings, SettingsConfigDict
 
 from .timeutil import validate_time_zone
@@ -40,6 +40,7 @@ class Settings(BaseSettings):
     notifier_batch_size: int = 20
     notifier_max_attempts: int = 8
     notifier_lease_sec: int = 300
+    notifier_concurrency: int = Field(default=4, ge=1)
     notifier_http_timeout_sec: float = 10.0
     notification_time_zone: str = "UTC"