memory-gateway/plugins/memory-gateway-agent/scripts/cleanup_test_memories.py

#!/usr/bin/env python3
from __future__ import annotations

import json
import os
import sys
import urllib.error
import urllib.parse
import urllib.request
from pathlib import Path
from typing import Any

PLUGIN_ROOT = Path(__file__).resolve().parents[1]
if str(PLUGIN_ROOT) not in sys.path:
    sys.path.insert(0, str(PLUGIN_ROOT))

from memory_gateway_plugin.output import dumps_safe, short_id, summarize_data


USER_ID = "test_user_memory_gateway_plugin"
AGENT_ID = "test_hermes_memory_gateway_plugin"
WORKSPACE_ID = "test_workspace_memory_gateway_plugin"
SESSION_ID = "test_session_memory_gateway_plugin_001"


def _assert_test_user(user_id: str) -> None:
    if not user_id.startswith("test_user_"):
        raise ValueError("cleanup_refuses_non_test_user")


def _gateway_url() -> str:
    return os.environ.get("MEMORY_GATEWAY_URL", "http://127.0.0.1:1934").rstrip("/")


def _api_key() -> str:
    return os.environ.get("MEMORY_GATEWAY_API_KEY", "")


def _request(method: str, endpoint: str, payload: dict[str, Any] | None = None) -> dict[str, Any]:
    headers = {"Content-Type": "application/json"}
    if _api_key():
        headers["X-API-Key"] = _api_key()
    body = None if payload is None else json.dumps(payload, ensure_ascii=False).encode("utf-8")
    req = urllib.request.Request(_gateway_url() + endpoint, data=body, headers=headers, method=method)
    try:
        with urllib.request.urlopen(req, timeout=15) as response:
            raw = response.read().decode("utf-8")
            return {"ok": True, "status_code": getattr(response, "status", 200), "data": json.loads(raw) if raw else {}}
    except urllib.error.HTTPError as exc:
        return {"ok": False, "status_code": exc.code, "error": str(exc.reason)[:300]}
    except Exception as exc:
        return {"ok": False, "status_code": None, "error": str(exc)[:300]}


def _search_candidates() -> dict[str, Any]:
    return _request(
        "POST",
        "/v1/memory/search",
        {
            "query": "integration_test plugin safe_to_delete Memory Gateway plugin",
            "user_id": USER_ID,
            "agent_id": AGENT_ID,
            "workspace_id": WORKSPACE_ID,
            "session_id": SESSION_ID,
            "tags": ["integration_test"],
            "limit": 100,
        },
    )


def _audit_candidate_ids() -> list[str]:
    result = _request("GET", "/v1/audit?limit=1000")
    if not result.get("ok"):
        return []
    ids: list[str] = []
    for row in result.get("data") or []:
        if row.get("actor_user_id") != USER_ID:
            continue
        if row.get("actor_agent_id") not in {AGENT_ID, None, ""}:
            continue
        if row.get("target_type") == "memory" and row.get("action") in {"upsert_memory", "feedback:incorrect", "feedback:duplicate", "feedback:outdated"}:
            target_id = row.get("target_id")
            if target_id and target_id not in ids:
                ids.append(target_id)
    return ids


def _memory_from_result(item: dict[str, Any]) -> dict[str, Any] | None:
    memory = item.get("memory")
    if isinstance(memory, dict) and memory.get("id"):
        return memory
    return None


def _is_cleanup_candidate(memory: dict[str, Any]) -> bool:
    if memory.get("user_id") != USER_ID:
        return False
    tags = set(memory.get("tags") or [])
    return bool(tags.intersection({"integration_test", "safe_to_delete", "plugin"}))


def _delete_memory(memory_id: str) -> dict[str, Any]:
    query = urllib.parse.urlencode({"user_id": USER_ID, "agent_id": AGENT_ID, "workspace_id": WORKSPACE_ID, "session_id": SESSION_ID})
    return _request("DELETE", f"/v1/memory/{urllib.parse.quote(memory_id)}?{query}")


def _feedback_memory(memory_id: str) -> dict[str, Any]:
    return _request(
        "POST",
        f"/v1/memory/{urllib.parse.quote(memory_id)}/feedback",
        {
            "user_id": USER_ID,
            "agent_id": AGENT_ID,
            "workspace_id": WORKSPACE_ID,
            "session_id": SESSION_ID,
            "feedback": "incorrect",
            "comment": "cleanup marker for integration test memory",
        },
    )


def run(user_id: str = USER_ID) -> dict[str, Any]:
    _assert_test_user(user_id)
    if user_id != USER_ID:
        return {"ok": False, "error": "script_is_scoped_to_fixed_test_user", "user_id": user_id}

    search = _search_candidates()
    if not search.get("ok"):
        return {"ok": False, "search": {"ok": False, "status_code": search.get("status_code"), "error": search.get("error")}, "deleted": 0, "feedback_marked": 0, "skipped": 0}

    rows = (search.get("data") or {}).get("results") or []
    memory_ids = _audit_candidate_ids()
    deleted = 0
    feedback_marked = 0
    skipped = 0
    unable: list[dict[str, Any]] = []
    touched: list[str] = []

    for item in rows:
        memory = _memory_from_result(item)
        if not memory or not _is_cleanup_candidate(memory):
            skipped += 1
            continue
        memory_id = memory["id"]
        if memory_id not in memory_ids:
            memory_ids.append(memory_id)

    for memory_id in memory_ids:
        deletion = _delete_memory(memory_id)
        if deletion.get("ok"):
            deleted += 1
            touched.append(short_id(memory_id))
            continue
        if deletion.get("status_code") == 404:
            skipped += 1
            continue
        feedback = _feedback_memory(memory_id)
        if feedback.get("ok"):
            feedback_marked += 1
            touched.append(short_id(memory_id))
        else:
            unable.append({"memory_id": short_id(memory_id), "delete_status": deletion.get("status_code"), "feedback_status": feedback.get("status_code"), "reason": feedback.get("error") or deletion.get("error")})

    return {
        "ok": not unable,
        "search": {"ok": True, "status_code": search.get("status_code"), "data": summarize_data(search.get("data"))},
        "deleted": deleted,
        "feedback_marked": feedback_marked,
        "skipped": skipped,
        "unable_count": len(unable),
        "unable": unable,
        "touched_memory_ids": touched,
        "limitation": "search API returns local MemoryRecord rows plus OpenViking context; cleanup only deletes local MemoryRecord rows for the fixed test user.",
    }


def main() -> int:
    try:
        result = run(os.environ.get("MEMORY_GATEWAY_CLEANUP_USER_ID", USER_ID))
    except ValueError as exc:
        result = {"ok": False, "error": str(exc), "deleted": 0, "feedback_marked": 0, "skipped": 0}
    print(dumps_safe(result))
    return 0 if result.get("ok") else 1


if __name__ == "__main__":
    sys.exit(main())