mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
505d12f662
Salvages the event-spine foundation from feat/telemetry-observability (emitter, typed events, OTLP streaming, redaction — authorship preserved in the preceding commits) and scopes it to the plane enterprise operators need today: gateway Service Health Monitoring plus redacted Operational Diagnostics, exported over OTLP. Dropped from the salvaged branch, deliberately: - run/model/tool trajectory capture (plugins/telemetry hooks, tel_spans) - the local JSONL + state.db tel_* store (monitoring is egress, not storage) - usage rollups/metrics, /insights integration, bulk export - hermes telemetry CLI (replaced by hermes monitoring status) Those planes — shared client usage metrics and enterprise trace telemetry — are being designed on the NeMo Relay integration with distinct consent, policy, and export boundaries; this keeps the monitoring plane content-free and independently enableable. Renames agent/telemetry -> agent/monitoring, config telemetry.* -> monitoring.*, and pins the otlp extra at OpenTelemetry 1.39.1 (matching uv.lock; 1.30.0 conflicts with mistralai>=2.4 on opentelemetry-api).
69 lines
1.9 KiB
Python
69 lines
1.9 KiB
Python
"""Typed gateway monitoring events.
|
|
|
|
Content-free service-health and redacted diagnostic events for the gateway
|
|
daemon. These are the only event shapes the monitoring plane emits: no
|
|
prompts, messages, tool args/results, session history, or usage analytics.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import time
|
|
from dataclasses import dataclass, field, asdict
|
|
from typing import Any, Dict, Optional
|
|
|
|
|
|
def _now_ns() -> int:
|
|
return time.time_ns()
|
|
|
|
|
|
@dataclass(slots=True)
|
|
class GatewayHealthEvent:
|
|
"""Content-free gateway health snapshot or lifecycle event."""
|
|
|
|
name: str
|
|
gateway_state: Optional[str] = None
|
|
old_state: Optional[str] = None
|
|
new_state: Optional[str] = None
|
|
exit_reason: Optional[str] = None
|
|
restart_requested: Optional[bool] = None
|
|
active_agents: int = 0
|
|
gateway_busy: bool = False
|
|
gateway_drainable: bool = False
|
|
platform_count: int = 0
|
|
fatal_platform_count: int = 0
|
|
profile: Optional[str] = None
|
|
install_id: Optional[str] = None
|
|
version: Optional[str] = None
|
|
supervision_mode: Optional[str] = None
|
|
pid: Optional[int] = None
|
|
ts_ns: int = field(default_factory=_now_ns)
|
|
|
|
def to_dict(self) -> Dict[str, Any]:
|
|
return {"event": "gateway_health", **asdict(self)}
|
|
|
|
|
|
@dataclass(slots=True)
|
|
class GatewayDiagnosticEvent:
|
|
"""Redacted gateway diagnostic event for operator-owned observability."""
|
|
|
|
name: str
|
|
subsystem: str
|
|
error_class: str = "unknown"
|
|
error_code: Optional[str] = None
|
|
redacted_message: Optional[str] = None
|
|
platform: Optional[str] = None
|
|
old_state: Optional[str] = None
|
|
new_state: Optional[str] = None
|
|
profile: Optional[str] = None
|
|
version: Optional[str] = None
|
|
severity: str = "warning"
|
|
ts_ns: int = field(default_factory=_now_ns)
|
|
|
|
def to_dict(self) -> Dict[str, Any]:
|
|
return {"event": "gateway_diagnostic", **asdict(self)}
|
|
|
|
|
|
__all__ = [
|
|
"GatewayHealthEvent",
|
|
"GatewayDiagnosticEvent",
|
|
]
|