feat: complete OTEL tracing across all services with pipeline bridge and docs

Extends tracing to every remaining module: all 23 API route handlers,
correlation engine, sniffer (fingerprint/p0f/syslog), prober (jarm/hassh/tcpfp),
profiler behavioral analysis, logging subsystem, engine, and mutator.

Bridges the ingester→SSE trace gap by persisting trace_id/span_id columns on
the logs table and creating OTEL span links in the SSE endpoint. Adds log-trace
correlation via _TraceContextFilter injecting otel_trace_id into Python LogRecords.

Includes development/docs/TRACING.md with full span reference (76 spans),
pipeline propagation architecture, quick start guide, and troubleshooting.
This commit is contained in:
2026-04-16 00:58:08 -04:00
parent 04db13afae
commit 70d8ffc607
38 changed files with 577 additions and 124 deletions

View File

@@ -7,6 +7,7 @@ from fastapi.responses import StreamingResponse
from decnet.env import DECNET_DEVELOPER
from decnet.logging import get_logger
from decnet.telemetry import traced as _traced, get_tracer as _get_tracer
from decnet.web.dependencies import require_stream_viewer, repo
log = get_logger("api")
@@ -14,6 +15,34 @@ log = get_logger("api")
router = APIRouter()
def _build_trace_links(logs: list[dict]) -> list:
"""Build OTEL span links from persisted trace_id/span_id in log rows.
Returns an empty list when tracing is disabled (no OTEL imports).
"""
try:
from opentelemetry.trace import Link, SpanContext, TraceFlags
except ImportError:
return []
links: list[Link] = []
for entry in logs:
tid = entry.get("trace_id")
sid = entry.get("span_id")
if not tid or not sid or tid == "0":
continue
try:
ctx = SpanContext(
trace_id=int(tid, 16),
span_id=int(sid, 16),
is_remote=True,
trace_flags=TraceFlags(TraceFlags.SAMPLED),
)
links.append(Link(ctx))
except (ValueError, TypeError):
continue
return links
@router.get("/stream", tags=["Observability"],
responses={
200: {
@@ -24,6 +53,7 @@ router = APIRouter()
422: {"description": "Validation error"}
},
)
@_traced("api.stream_events")
async def stream_events(
request: Request,
last_event_id: int = Query(0, alias="lastEventId"),
@@ -75,7 +105,15 @@ async def stream_events(
)
if new_logs:
last_id = max(entry["id"] for entry in new_logs)
yield f"event: message\ndata: {json.dumps({'type': 'logs', 'data': new_logs})}\n\n"
# Create a span linking back to the ingestion traces
# stored in each log row, closing the pipeline gap.
_links = _build_trace_links(new_logs)
_tracer = _get_tracer("sse")
with _tracer.start_as_current_span(
"sse.emit_logs", links=_links,
attributes={"log_count": len(new_logs)},
):
yield f"event: message\ndata: {json.dumps({'type': 'logs', 'data': new_logs})}\n\n"
loops_since_stats = stats_interval_sec
if loops_since_stats >= stats_interval_sec: