"""Seed the knowledge graph with archetypes, sink classes, and the P1 impact

families (the severity gate). Idempotent."""

import os, sys

sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "memory"))

from memory import Memory

ARCHETYPES = {

    "ml-model-loaders": "Model-file & inference parsers (GGUF/ONNX/safetensors/pickle/joblib) - load-time RCE. Headline.",

    "ai-agent-mcp":     "Agent/tool-runners & MCP servers - tool-abuse, sandbox escape, SSRF->RCE.",

    "devops-infra":     "Self-hosted infra (Jenkins/Grafana/Redis/Jupyter/Argo) - unauth RCE, SSRF->metadata.",

    "electron-desktop": "Electron apps (Obsidian/Cursor/Discord) - renderer-XSS->node, protocol-handler RCE.",

    "cicd-supplychain": "CI/CD & supply chain - workflow injection, runner takeover, dependency confusion.",

    "memory-unsafe-parsers": "Image/archive/font/serialization C/C++ libs - fuzz->memory corruption->RCE.",

}

SINKCLASSES = [

    ("memory-corruption",  "CWE-787", "RCE via Memory Corruption"),

    ("deserialization",    "CWE-502", "RCE via Deserialization"),

    ("command-injection",  "CWE-78",  "RCE via Command Injection"),

    ("template-injection", "CWE-1336","RCE via Template Injection"),

    ("sql-injection",      "CWE-89",  "RCE/Data via SQL Injection"),

    ("path-traversal",     "CWE-22",  "Arbitrary File Read/Write -> Secrets/RCE"),

    ("ssrf",               "CWE-918", "SSRF -> Metadata/Internal/RCE"),

    ("xxe",                "CWE-611", "XXE -> Internal File Read"),

    ("auth-bypass",        "CWE-287", "Authentication Bypass / ATO"),

    ("electron-rce",       "CWE-94",  "One-Click/Zero-Click RCE"),

    ("container-escape",   "CWE-269", "Container/VM/Sandbox Escape"),

    ("ssti-upload-rce",    "CWE-434", "RCE via File Upload"),

]

def main():

    m = Memory()

    for name, desc in ARCHETYPES.items():

        m.upsert_archetype(name, desc)

    for name, cwe, fam in SINKCLASSES:

        m._exec("""MERGE (s:SinkClass {name:$n})

                   SET s.cwe=$c, s.impact_family=$f""",

                {"n": name, "c": cwe, "f": fam})

    print("seeded archetypes:", len(ARCHETYPES), "sink classes:", len(SINKCLASSES))

    print("graph:", m.stats())

if __name__ == "__main__":

    main()