mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
Add a built-in telemetry system that records what the agent does — workflows,
model calls, tool calls, errors — to the local machine, powers `/insights`, and
can export to an operator-chosen destination. Default-on locally; nothing leaves
the machine unless the user exports it or opts into the aggregate plane.
Three planes with a hard wall between them:
- local: full-fidelity observability (real model/provider/tool names), on by
default, never leaves the machine.
- aggregate: opt-in metadata, default off. No uploader ships — consent is
recorded via telemetry.consent_state, and `preview` shows what would be
produced, computed locally.
- trajectories: full message content, opt-in, exported only to the operator's
own destination.
Mechanism:
- Bundled `telemetry` plugin registers observational lifecycle hooks
(on_session_start / post_api_request / post_tool_call / on_session_finalize).
No core call sites are edited; hooks already carry the data.
- Fire-and-forget emitter: emit() returns in microseconds, never blocks or
raises into a model/tool call. A daemon thread writes events to an
append-only JSONL log and the tel_* tables in state.db (its own sqlite
connection, separate from SessionDB).
- tel_runs / tel_model_calls / tel_tool_calls live in the declarative
SCHEMA_SQL and are reconciled automatically; SCHEMA_VERSION 16 -> 17.
- metrics derives rollups for /usage and /insights; rollup builds per-run
summaries for `hermes telemetry preview`.
Consent is config, not a parallel command surface. The config file is the root
of trust: set telemetry.consent_state with `hermes config set`, or pin any
telemetry.* key (including allow_aggregate) via managed scope, which overrides
the user's value per key. `hermes telemetry` exposes only what config cannot:
status (report), preview (query), and export.
Export:
- exporter_bulk writes telemetry (and, when the trajectories plane is enabled,
session content) to ndjson/json.
- otlp_exporter streams spans to a configured OpenTelemetry Collector over
OTLP/HTTP. The SDK is an optional extra (hermes-agent[otlp]), lazily
installed via tools.lazy_deps on first use.
- Secrets are always redacted on every export path
(redact_sensitive_text(force=True)); content export is gated by the
trajectories plane, and PII scrubbing follows telemetry.content_redaction.
OTLP auth headers reference environment variable names, never inline values.
No outbound emission to Nous. The aggregate uploader is intentionally not built.
30 lines
1,015 B
Python
30 lines
1,015 B
Python
"""Hermes telemetry & observability.
|
|
|
|
Local-first observability, on by default. The ``telemetry`` plugin registers Hermes
|
|
lifecycle hooks and hands typed events to the fire-and-forget ``emitter`` (queue ->
|
|
background writer -> JSONL + state.db ``tel_*`` index). The emitter never blocks or
|
|
raises into a model/tool call (the hot-path invariant).
|
|
|
|
Events record the observed model ids, provider names, and tool names. ``metrics``
|
|
derives rollups for /usage and /insights; ``rollup`` builds the per-run summaries shown
|
|
by ``hermes telemetry preview``. ``redaction`` + ``exporter_bulk`` + ``otlp_exporter``
|
|
handle export to an operator-chosen destination. ``policy`` holds the consent state
|
|
machine for the opt-in aggregate plane (no uploader ships).
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from . import emitter, events, metrics, policy, spans
|
|
|
|
emit = emitter.emit
|
|
get_emitter = emitter.get_emitter
|
|
|
|
__all__ = [
|
|
"emitter",
|
|
"events",
|
|
"metrics",
|
|
"policy",
|
|
"spans",
|
|
"emit",
|
|
"get_emitter",
|
|
]
|