talos/backend/app/export.py

"""Bulk scan report rendering for Cursor and other consumers."""

from __future__ import annotations

from typing import Any

_SEVERITY_ORDER = ("critical", "high", "medium", "low", "info")
_PHASE_OUTPUT_MAX = 4000


def _sort_findings(findings: list[dict[str, Any]]) -> list[dict[str, Any]]:
    order = {s: i for i, s in enumerate(_SEVERITY_ORDER)}
    return sorted(findings, key=lambda f: order.get(str(f.get("severity", "")).lower(), 99))


def _truncate(text: str, limit: int = _PHASE_OUTPUT_MAX) -> str:
    text = (text or "").strip()
    if len(text) <= limit:
        return text
    return text[: limit - 40] + "\n\n… (truncated)"


def render_bulk_markdown(payload: dict[str, Any], *, for_cursor: bool = False) -> str:
    bulk = payload["bulk"]
    scans = payload["scans"]
    lines: list[str] = []

    if for_cursor:
        lines.extend(
            [
                "<!-- Talos bulk report — paste into Cursor for triage / remediation -->",
                "",
                "You are reviewing authorized security scan results from Talos.",
                "Prioritize critical/high findings, then failed phases that may hide issues.",
                "",
            ]
        )

    lines.extend(
        [
            f"# Talos bulk report",
            "",
            f"- **Bulk ID:** `{bulk['id']}`",
            f"- **Profile:** {bulk['profile']}",
            f"- **Status:** {bulk['status']}",
            f"- **Progress:** {bulk['complete']}/{bulk['total']} complete"
            + (f", {bulk['failed']} failed" if bulk.get("failed") else "")
            + (f", {bulk['running']} running" if bulk.get("running") else "")
            + (f", {bulk['queued']} queued" if bulk.get("queued") else ""),
            "",
        ]
    )

    # Cross-target finding rollup (severity >= low with issues)
    all_findings: list[tuple[str, dict[str, Any]]] = []
    for entry in scans:
        target = entry["scan"]["target"]
        for f in entry.get("findings") or []:
            if f.get("severity") in ("critical", "high", "medium", "low"):
                all_findings.append((target, f))

    if all_findings:
        lines.append("## Findings rollup (all targets)")
        lines.append("")
        for target, f in sorted(
            all_findings,
            key=lambda x: _SEVERITY_ORDER.index(x[1]["severity"])
            if x[1]["severity"] in _SEVERITY_ORDER
            else 99,
        ):
            sev = f["severity"].upper()
            lines.append(f"- **[{sev}]** `{target}` — {f['title']}")
        lines.append("")

    for entry in scans:
        scan = entry["scan"]
        phases = entry.get("phases") or []
        findings = _sort_findings(entry.get("findings") or [])
        lines.append(f"## {scan['target']}")
        lines.append("")
        lines.append(f"- Scan ID: `{scan['id']}`")
        lines.append(f"- Status: **{scan['status']}**")
        if scan.get("llm_unavailable"):
            lines.append("- LLM analysis was unavailable for some phases")
        lines.append("")

        lines.append("### Phases")
        lines.append("")
        lines.append("| Phase | Status | Tool |")
        lines.append("|-------|--------|------|")
        for p in phases:
            lines.append(f"| {p['name']} | {p['status']} | {p.get('tool', '')} |")
        lines.append("")

        failed_phases = [p for p in phases if p["status"] in ("failed", "blocked", "inconclusive")]
        if failed_phases:
            lines.append("### Phase notes (non-complete)")
            lines.append("")
            for p in failed_phases:
                snippet = _truncate(p.get("raw_output") or "", 800)
                lines.append(f"**{p['name']}** ({p['status']})")
                if snippet:
                    lines.append("")
                    lines.append("```")
                    lines.append(snippet)
                    lines.append("```")
                lines.append("")

        if findings:
            lines.append("### Findings")
            lines.append("")
            for f in findings:
                sev = str(f["severity"]).upper()
                lines.append(f"#### [{sev}] {f['title']}")
                lines.append("")
                lines.append(f["description"])
                lines.append("")
                if f.get("evidence"):
                    lines.append(f"**Evidence:** `{_truncate(str(f['evidence']), 500)}`")
                    lines.append("")
                lines.append(f"**Recommendation:** {f['recommendation']}")
                lines.append("")
        else:
            lines.append("_No LLM findings recorded._")
            lines.append("")

        lines.append("---")
        lines.append("")

    return "\n".join(lines).rstrip() + "\n"


def render_bulk_json(payload: dict[str, Any]) -> dict[str, Any]:
    """JSON export with truncated phase output to keep size reasonable."""
    out = dict(payload)
    scans_out: list[dict[str, Any]] = []
    for entry in payload.get("scans") or []:
        entry = dict(entry)
        phases = []
        for p in entry.get("phases") or []:
            p = dict(p)
            if p.get("raw_output"):
                p["raw_output"] = _truncate(str(p["raw_output"]))
            phases.append(p)
        entry["phases"] = phases
        scans_out.append(entry)
    out["scans"] = scans_out
    return out