strix/strix/telemetry/posthog.py
0xallam 5f31455274 refactor(config): pydantic-settings revamp + drop `is_whitebox` plumbing
Replaces 200+ lines of bespoke env-loader / persist / change-detection
machinery with ``pydantic_settings.BaseSettings`` (already a transitive
of ``openai-agents → mcp``, no new direct dep).

What was wrong with ``Config``:

- 14 knobs flat in one namespace, weak grouping by comment-block.
- ``Config._applied_from_default`` and ``Config._config_file_override``
  were externally mutated from ``interface/main.py:532-534``. Private
  members were part of the public contract.
- Stringly-typed values: every caller had to coerce
  (``int(Config.get("llm_timeout") or "300")``,
  ``... not in {"0", "false", "no", "off"}``).
- Dead knob: ``strix_llm_max_retries`` declared, persisted, listed in
  ``_LLM_CANONICAL_NAMES`` — zero readers (``DEFAULT_RETRY``
  hardcodes ``max_retries=5``). Dropped.
- ``_LLM_CANONICAL_NAMES`` tuple maintained alongside class vars —
  duplicate source of truth.
- ``_tracked_names()`` introspected ``vars(cls).items()`` filtered on
  ``(v is None or isinstance(v, str))`` — fragile.
- Awkward path: ``strix/config/config.py`` inside ``strix/config/``
  with ``__init__.py`` just re-exporting.
- Dual access for the same fact: ``web_search`` read
  ``os.getenv("PERPLEXITY_API_KEY")`` while ``main.py`` read
  ``Config.get("perplexity_api_key")``.

New shape:

- ``strix/config/settings.py`` — typed dataclass tree:
  ``Settings.{llm,runtime,telemetry,integrations}``. Each sub-model is
  its own ``BaseSettings`` so it reads env independently. Field-level
  ``alias=`` and ``validation_alias=AliasChoices(...)`` mirror the
  existing flat env-var names — user-facing env contract is unchanged.
  Bool fields auto-parse ``"0"``/``"false"``/``"no"``/``"off"``;
  int fields auto-coerce.
- ``strix/config/loader.py`` — thin ``load_settings()``,
  ``apply_config_override(path)``, ``persist_current()`` with module
  cache. JSON file reader walks aliases to populate sub-models, dropping
  entries already covered by env (so env still wins).
- 13 callsites migrated from ``Config.get("...")`` to
  ``load_settings().<group>.<field>``.
- ``posthog._is_enabled()`` collapses to one line.
- ``--config <path>`` flow simplified: one
  ``apply_config_override(...)`` call replaces three lines of
  class-private mutation.

Drive-by — drop ``is_whitebox`` from ``scan_config`` dict:

- It was being derived as ``bool(args.local_sources)`` in three places
  (``cli.py``, ``tui.py``, ``main.py``) and stuffed into the dict for
  ``entry.py`` to read back. The fact is fully derivable from
  ``scan_config["targets"]`` — any target with ``type == "local_code"``.
- New helper ``is_whitebox_scan(targets)`` in ``interface/utils.py``
  alongside the other target-classification utilities.
- ``entry.py`` computes once; ``main.py``'s posthog start uses the same
  helper. Triplicate derivation gone.

Verified: ruff at baseline (3), mypy at baseline (69). Six smoke tests
pass — defaults / JSON-only / env-wins-over-JSON / alias-chain
fallback / bool parsing / ``is_whitebox_scan``.
2026-04-25 16:05:40 -07:00

148 lines
4.1 KiB
Python

import json
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
_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
return "unknown"
def _send(event: str, properties: dict[str, Any]) -> None:
if not _is_enabled():
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, S110
pass # nosec B110
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)