Files
strix/strix/telemetry/posthog.py
T
0xallamandClaude Opus 4.7 f8213452ea feat(logging): close audit gaps — SDK records, proxy tracebacks, CLI/docker/posthog
Five gaps from the post-implementation audit, closed:

1. **SDK logger captured.** The openai-agents SDK uses
   ``logging.getLogger("openai.agents")`` for its own lifecycle events
   (Runner.run starts, tool dispatch, model retries, exceptions).
   Previous setup only attached handlers to the ``strix`` root, so
   SDK-internal events were dropped. Tracked-roots tuple now covers
   both, with the same FileHandler/StreamHandler/Filter chain.

2. **Proxy tool exception tracebacks.** Every ``@function_tool`` in
   ``strix/tools/proxy/tools.py`` returns a JSON error to the LLM via
   the ``_err(name, exc)`` helper. The tracebacks were silently
   formatted away — the LLM saw the message, the human reading the
   log saw nothing. ``_err`` now emits ``logger.exception(...)``
   covering all five tools at once.

3. **CLI bootstrap.** ``strix/interface/main.py`` had its module
   ``logger`` removed by the previous commit and was emitting nothing.
   Restored, plus log lines for env validation, docker check, LLM
   warm-up, and image pull (debug for already-present, info for
   pull, exception for failures).

4. **Docker client.** ``strix/runtime/docker_client.py`` had no
   logger. Container creation now logs caps + exposed ports at DEBUG
   and the resulting container id at INFO.

5. **PostHog telemetry.** ``strix/telemetry/posthog.py`` had no
   logger. Now logs send success/failure at DEBUG, version-detection
   failures at DEBUG, and disabled-skip at DEBUG (so the log shows
   when telemetry is off, instead of being silent about it).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-25 23:43:19 -07:00

158 lines
4.5 KiB
Python

import json
import logging
import platform
import sys
import urllib.request
from pathlib import Path
from typing import TYPE_CHECKING, Any
from uuid import uuid4
from strix.config import load_settings
if TYPE_CHECKING:
from strix.telemetry.tracer import Tracer
logger = logging.getLogger(__name__)
_POSTHOG_PUBLIC_API_KEY = "phc_7rO3XRuNT5sgSKAl6HDIrWdSGh1COzxw0vxVIAR6vVZ"
_POSTHOG_HOST = "https://us.i.posthog.com"
_SESSION_ID = uuid4().hex[:16]
def _is_enabled() -> bool:
"""Master telemetry gate. ``STRIX_POSTHOG_TELEMETRY`` overrides ``STRIX_TELEMETRY``."""
return load_settings().telemetry.posthog_enabled
def _is_first_run() -> bool:
marker = Path.home() / ".strix" / ".seen"
if marker.exists():
return False
try:
marker.parent.mkdir(parents=True, exist_ok=True)
marker.touch()
except Exception: # noqa: BLE001, S110
pass # nosec B110
return True
def _get_version() -> str:
try:
from importlib.metadata import version
return version("strix-agent")
except Exception: # noqa: BLE001
logger.debug("strix-agent version lookup failed", exc_info=True)
return "unknown"
def _send(event: str, properties: dict[str, Any]) -> None:
if not _is_enabled():
logger.debug("posthog disabled; skipping event %s", event)
return
try:
payload = {
"api_key": _POSTHOG_PUBLIC_API_KEY,
"event": event,
"distinct_id": _SESSION_ID,
"properties": properties,
}
req = urllib.request.Request( # noqa: S310
f"{_POSTHOG_HOST}/capture/",
data=json.dumps(payload).encode(),
headers={"Content-Type": "application/json"},
)
with urllib.request.urlopen(req, timeout=10): # noqa: S310 # nosec B310
pass
except Exception: # noqa: BLE001
# Telemetry must never disrupt a scan; log + swallow.
logger.debug("posthog send failed for event %s", event, exc_info=True)
else:
logger.debug("posthog event sent: %s", event)
def _base_props() -> dict[str, Any]:
return {
"os": platform.system().lower(),
"arch": platform.machine(),
"python": f"{sys.version_info.major}.{sys.version_info.minor}",
"strix_version": _get_version(),
}
def start(
model: str | None,
scan_mode: str | None,
is_whitebox: bool,
interactive: bool,
has_instructions: bool,
) -> None:
_send(
"scan_started",
{
**_base_props(),
"model": model or "unknown",
"scan_mode": scan_mode or "unknown",
"scan_type": "whitebox" if is_whitebox else "blackbox",
"interactive": interactive,
"has_instructions": has_instructions,
"first_run": _is_first_run(),
},
)
def finding(severity: str) -> None:
_send(
"finding_reported",
{
**_base_props(),
"severity": severity.lower(),
},
)
def end(tracer: "Tracer", exit_reason: str = "completed") -> None:
vulnerabilities_counts = {"critical": 0, "high": 0, "medium": 0, "low": 0, "info": 0}
for v in tracer.vulnerability_reports:
sev = v.get("severity", "info").lower()
if sev in vulnerabilities_counts:
vulnerabilities_counts[sev] += 1
llm = tracer.get_total_llm_stats()
total = llm.get("total", {})
duration = 0.0
try:
from datetime import datetime
start = datetime.fromisoformat(tracer.start_time.replace("Z", "+00:00"))
end_iso = tracer.end_time or datetime.now(start.tzinfo).isoformat()
duration = (datetime.fromisoformat(end_iso.replace("Z", "+00:00")) - start).total_seconds()
except (ValueError, TypeError, AttributeError):
pass
_send(
"scan_ended",
{
**_base_props(),
"exit_reason": exit_reason,
"duration_seconds": round(duration),
"vulnerabilities_total": len(tracer.vulnerability_reports),
**{f"vulnerabilities_{k}": v for k, v in vulnerabilities_counts.items()},
"agent_count": len(tracer.agents),
"tool_count": tracer.get_real_tool_count(),
"llm_tokens": llm.get("total_tokens", 0),
"llm_cost": total.get("cost", 0.0),
},
)
def error(error_type: str, error_msg: str | None = None) -> None:
props = {**_base_props(), "error_type": error_type}
if error_msg:
props["error_msg"] = error_msg
_send("error", props)