fa42757916
* add staging ios app build script * feat(api): add OpenTelemetry LGTM stack for local observability Wire OTel traces, metrics, and logs through a collector to Tempo, Prometheus, and Loki, with custom LLM instrumentation, dev compose overlay, Grafana provisioning, env templates, and development.sh auto-start. Co-authored-by: Cursor <cursoragent@cursor.com> * feat: expand observability, harden dev tooling, and fix expo staging UX Add business and LLM Prometheus metrics with Grafana dashboards, alerting, and a metrics verification script. Wire telemetry through adapters and core LLM paths, and document the local LGTM workflow. Fix development.sh for macOS bash 3.2, open Grafana and eval-web in Chrome, and repair eval-web auto-open (unbound EVAL_WEB_BROWSER_SCHEDULED). Merge internal-eval into the main dev script with improved compose handling. Require EXPO_PUBLIC_* at build time, improve iOS HTTP ATS for staging IPs, show memoir empty state instead of load errors when no chapters exist, and add jest env setup plus chapter list response normalization. Co-authored-by: Cursor <cursoragent@cursor.com> * chore: enable Grafana Assistant Cursor plugin Co-authored-by: Cursor <cursoragent@cursor.com> * fix: memoir empty state and repair withdrawn 0020_chapters_book_id stamp Show empty memoir UI when the chapter list succeeds with no items; treat auth/404 as non-fatal. Extend alembic revision repair so local dev DBs stamped with the removed 0020_chapters_book_id migration can roll back and upgrade to 0019. Co-authored-by: Cursor <cursoragent@cursor.com> --------- Co-authored-by: Kevin <kevin@brighteng.org> Co-authored-by: Cursor <cursoragent@cursor.com>
82 lines
2.3 KiB
Python
82 lines
2.3 KiB
Python
"""
|
||
业务链路 OpenTelemetry span（回忆录阶段、WS、外部依赖等）。
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import time
|
||
from contextlib import contextmanager
|
||
from typing import Any, Iterator
|
||
|
||
from opentelemetry import trace
|
||
from opentelemetry.trace import Status, StatusCode
|
||
|
||
from app.core.config import settings
|
||
from app.core.telemetry import get_meter, get_tracer
|
||
|
||
_meter = None
|
||
_duration_hist = None
|
||
|
||
# 仅低基数字段进入 span attribute（禁止 user_id / conversation_id 等）
|
||
_ALLOWED_SPAN_ATTRS = frozenset(
|
||
{"provider", "chapter_category", "segment_count", "batch_size", "hours"}
|
||
)
|
||
|
||
|
||
def _ensure_instruments() -> None:
|
||
global _meter, _duration_hist
|
||
if _meter is not None or not settings.otel_enabled:
|
||
return
|
||
_meter = get_meter("app.business")
|
||
_duration_hist = _meter.create_histogram(
|
||
"business.operation.duration",
|
||
unit="ms",
|
||
description="Business operation wall time",
|
||
)
|
||
|
||
|
||
def _normalize_attr_value(value: Any) -> str | int | float | bool:
|
||
if isinstance(value, (str, int, float, bool)):
|
||
return value
|
||
return str(value)
|
||
|
||
|
||
@contextmanager
|
||
def business_span(
|
||
name: str,
|
||
/,
|
||
**attributes: Any,
|
||
) -> Iterator[trace.Span]:
|
||
if not settings.otel_enabled:
|
||
yield trace.INVALID_SPAN
|
||
return
|
||
|
||
tracer = get_tracer("app.business")
|
||
otel_attrs = {
|
||
f"business.{k}": _normalize_attr_value(v)
|
||
for k, v in attributes.items()
|
||
if k in _ALLOWED_SPAN_ATTRS and v is not None and v != ""
|
||
}
|
||
t0 = time.perf_counter()
|
||
outcome = "ok"
|
||
with tracer.start_as_current_span(name, attributes=otel_attrs) as span:
|
||
try:
|
||
yield span
|
||
except Exception:
|
||
outcome = "error"
|
||
if span.is_recording():
|
||
span.set_status(Status(StatusCode.ERROR))
|
||
raise
|
||
finally:
|
||
duration_ms = (time.perf_counter() - t0) * 1000
|
||
if span.is_recording():
|
||
span.set_attribute("business.duration_ms", round(duration_ms, 2))
|
||
if outcome == "ok":
|
||
span.set_status(Status(StatusCode.OK))
|
||
_ensure_instruments()
|
||
if _duration_hist is not None:
|
||
_duration_hist.record(
|
||
duration_ms,
|
||
{"operation": name, "outcome": outcome},
|
||
)
|