refactor(telemetry): extract scan artifact I/O into `strix.io.scan_artifacts`

The 150-line ``Tracer.save_run_data`` mashed three concerns together:
opening file handles, formatting Markdown for vulnerabilities, and
writing the executive penetration-test report. None of that is
telemetry — it's pure on-disk artifact emission.

Extract to :class:`ScanArtifactWriter` in ``strix/io/scan_artifacts.py``:

- One writer per ``run_dir``, owns its own ``_saved_vuln_ids`` dedupe
  set so re-saves only emit new files.
- ``writer.save(vulnerability_reports=, final_scan_result=)`` is the
  only public entry point.
- ``_render_vulnerability_md`` is module-private and unit-testable in
  isolation.

``Tracer`` now lazily creates a single ``ScanArtifactWriter`` per
``run_dir`` and delegates ``save_run_data`` to it (~150 LoC body
collapses to ~10).

Net: tracer.py 422 → 327 LoC; new scan_artifacts.py 196 LoC. About
−95 LoC of mixed concerns, plus telemetry no longer carries file-I/O
responsibilities.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
0xallam
2026-04-25 16:28:07 -07:00
co-authored by Claude Opus 4.7
parent 494e6fab0d
commit 8f1f473eb8
4 changed files with 225 additions and 149 deletions
+17 -149
View File
@@ -5,6 +5,7 @@ from pathlib import Path
from typing import Any, Optional
from uuid import uuid4
from strix.io.scan_artifacts import ScanArtifactWriter
from strix.telemetry import posthog
@@ -67,8 +68,8 @@ class Tracer:
"status": "running",
}
self._run_dir: Path | None = None
self._writer: ScanArtifactWriter | None = None
self._next_message_id = 1
self._saved_vuln_ids: set[str] = set()
self.caido_url: str | None = None
self.vulnerability_found_callback: Callable[[dict[str, Any]], None] | None = None
@@ -79,6 +80,7 @@ class Tracer:
self.run_metadata["run_name"] = run_name
self.run_metadata["run_id"] = run_name
self._run_dir = None
self._writer = None
def get_run_dir(self) -> Path:
if self._run_dir is None:
@@ -91,6 +93,11 @@ class Tracer:
return self._run_dir
def _get_writer(self) -> ScanArtifactWriter:
if self._writer is None:
self._writer = ScanArtifactWriter(self.get_run_dir())
return self._writer
def add_vulnerability_report(
self,
title: str,
@@ -231,155 +238,16 @@ class Tracer:
)
def save_run_data(self, mark_complete: bool = False) -> None:
try:
run_dir = self.get_run_dir()
if mark_complete:
if self.end_time is None:
self.end_time = datetime.now(UTC).isoformat()
self.run_metadata["end_time"] = self.end_time
self.run_metadata["status"] = "completed"
if mark_complete:
if self.end_time is None:
self.end_time = datetime.now(UTC).isoformat()
self.run_metadata["end_time"] = self.end_time
self.run_metadata["status"] = "completed"
if self.final_scan_result:
penetration_test_report_file = run_dir / "penetration_test_report.md"
with penetration_test_report_file.open("w", encoding="utf-8") as f:
f.write("# Security Penetration Test Report\n\n")
f.write(
f"**Generated:** {datetime.now(UTC).strftime('%Y-%m-%d %H:%M:%S UTC')}\n\n"
)
f.write(f"{self.final_scan_result}\n")
logger.info(
"Saved final penetration test report to: %s",
penetration_test_report_file,
)
if self.vulnerability_reports:
vuln_dir = run_dir / "vulnerabilities"
vuln_dir.mkdir(exist_ok=True)
new_reports = [
report
for report in self.vulnerability_reports
if report["id"] not in self._saved_vuln_ids
]
severity_order = {"critical": 0, "high": 1, "medium": 2, "low": 3, "info": 4}
sorted_reports = sorted(
self.vulnerability_reports,
key=lambda report: (
severity_order.get(report["severity"], 5),
report["timestamp"],
),
)
for report in new_reports:
vuln_file = vuln_dir / f"{report['id']}.md"
with vuln_file.open("w", encoding="utf-8") as f:
f.write(f"# {report.get('title', 'Untitled Vulnerability')}\n\n")
f.write(f"**ID:** {report.get('id', 'unknown')}\n")
f.write(f"**Severity:** {report.get('severity', 'unknown').upper()}\n")
f.write(f"**Found:** {report.get('timestamp', 'unknown')}\n")
metadata_fields: list[tuple[str, Any]] = [
("Target", report.get("target")),
("Endpoint", report.get("endpoint")),
("Method", report.get("method")),
("CVE", report.get("cve")),
("CWE", report.get("cwe")),
]
cvss_score = report.get("cvss")
if cvss_score is not None:
metadata_fields.append(("CVSS", cvss_score))
for label, value in metadata_fields:
if value:
f.write(f"**{label}:** {value}\n")
f.write("\n## Description\n\n")
description = report.get("description") or "No description provided."
f.write(f"{description}\n\n")
if report.get("impact"):
f.write("## Impact\n\n")
f.write(f"{report['impact']}\n\n")
if report.get("technical_analysis"):
f.write("## Technical Analysis\n\n")
f.write(f"{report['technical_analysis']}\n\n")
if report.get("poc_description") or report.get("poc_script_code"):
f.write("## Proof of Concept\n\n")
if report.get("poc_description"):
f.write(f"{report['poc_description']}\n\n")
if report.get("poc_script_code"):
f.write("```\n")
f.write(f"{report['poc_script_code']}\n")
f.write("```\n\n")
if report.get("code_locations"):
f.write("## Code Analysis\n\n")
for i, loc in enumerate(report["code_locations"]):
prefix = f"**Location {i + 1}:**"
file_ref = loc.get("file", "unknown")
line_ref = ""
if loc.get("start_line") is not None:
if loc.get("end_line") and loc["end_line"] != loc["start_line"]:
line_ref = f" (lines {loc['start_line']}-{loc['end_line']})"
else:
line_ref = f" (line {loc['start_line']})"
f.write(f"{prefix} `{file_ref}`{line_ref}\n")
if loc.get("label"):
f.write(f" {loc['label']}\n")
if loc.get("snippet"):
f.write(f" ```\n {loc['snippet']}\n ```\n")
if loc.get("fix_before") or loc.get("fix_after"):
f.write("\n **Suggested Fix:**\n")
f.write("```diff\n")
if loc.get("fix_before"):
for line in loc["fix_before"].splitlines():
f.write(f"- {line}\n")
if loc.get("fix_after"):
for line in loc["fix_after"].splitlines():
f.write(f"+ {line}\n")
f.write("```\n")
f.write("\n")
if report.get("remediation_steps"):
f.write("## Remediation\n\n")
f.write(f"{report['remediation_steps']}\n\n")
self._saved_vuln_ids.add(report["id"])
vuln_csv_file = run_dir / "vulnerabilities.csv"
with vuln_csv_file.open("w", encoding="utf-8", newline="") as f:
import csv
fieldnames = ["id", "title", "severity", "timestamp", "file"]
writer = csv.DictWriter(f, fieldnames=fieldnames)
writer.writeheader()
for report in sorted_reports:
writer.writerow(
{
"id": report["id"],
"title": report["title"],
"severity": report["severity"].upper(),
"timestamp": report["timestamp"],
"file": f"vulnerabilities/{report['id']}.md",
}
)
if new_reports:
logger.info(
"Saved %d new vulnerability report(s) to: %s",
len(new_reports),
vuln_dir,
)
logger.info("Updated vulnerability index: %s", vuln_csv_file)
logger.info("📊 Essential scan data saved to: %s", run_dir)
except (OSError, RuntimeError):
logger.exception("Failed to save scan data")
self._get_writer().save(
vulnerability_reports=self.vulnerability_reports,
final_scan_result=self.final_scan_result,
)
def log_tool_start(self, agent_id: str, tool_name: str) -> int:
"""Record a tool invocation in flight. Returns an exec_id."""