hermes-agent/plugins/mem0-memory/__init__.py

"""Mem0 memory plugin — MemoryProvider interface.

Server-side LLM fact extraction, semantic search with reranking, and
automatic deduplication via the Mem0 Platform API.

Original PR #2933 by kartik-mem0, adapted to MemoryProvider ABC.

Config via environment variables:
  MEM0_API_KEY       — Mem0 Platform API key (required)
  MEM0_USER_ID       — User identifier (default: hermes-user)
  MEM0_AGENT_ID      — Agent identifier (default: hermes)

Or via $HERMES_HOME/mem0.json.
"""

from __future__ import annotations

import json
import logging
import os
import threading
from pathlib import Path
from typing import Any, Dict, List

from agent.memory_provider import MemoryProvider

logger = logging.getLogger(__name__)


# ---------------------------------------------------------------------------
# Config
# ---------------------------------------------------------------------------

def _load_config() -> dict:
    """Load config from $HERMES_HOME/mem0.json or env vars."""
    hermes_home = os.environ.get("HERMES_HOME", os.path.expanduser("~/.hermes"))
    config_path = Path(hermes_home) / "mem0.json"

    if config_path.exists():
        try:
            return json.loads(config_path.read_text(encoding="utf-8"))
        except Exception:
            pass

    return {
        "api_key": os.environ.get("MEM0_API_KEY", ""),
        "user_id": os.environ.get("MEM0_USER_ID", "hermes-user"),
        "agent_id": os.environ.get("MEM0_AGENT_ID", "hermes"),
        "rerank": True,
        "keyword_search": False,
    }


# ---------------------------------------------------------------------------
# Tool schemas
# ---------------------------------------------------------------------------

PROFILE_SCHEMA = {
    "name": "mem0_profile",
    "description": (
        "Retrieve all stored memories about the user — preferences, facts, "
        "project context. Fast, no reranking. Use at conversation start."
    ),
    "parameters": {"type": "object", "properties": {}, "required": []},
}

SEARCH_SCHEMA = {
    "name": "mem0_search",
    "description": (
        "Search memories by meaning. Returns relevant facts ranked by similarity. "
        "Set rerank=true for higher accuracy (+150ms)."
    ),
    "parameters": {
        "type": "object",
        "properties": {
            "query": {"type": "string", "description": "What to search for."},
            "rerank": {"type": "boolean", "description": "Enable reranking for precision (default: false)."},
            "top_k": {"type": "integer", "description": "Max results (default: 10, max: 50)."},
        },
        "required": ["query"],
    },
}

CONTEXT_SCHEMA = {
    "name": "mem0_context",
    "description": (
        "Deep retrieval with forced reranking. Use when you need the most "
        "relevant memories for a specific topic."
    ),
    "parameters": {
        "type": "object",
        "properties": {
            "query": {"type": "string", "description": "What to search for."},
        },
        "required": ["query"],
    },
}

CONCLUDE_SCHEMA = {
    "name": "mem0_conclude",
    "description": (
        "Store a durable fact about the user. Stored verbatim (no LLM extraction). "
        "Use for explicit preferences, corrections, or decisions."
    ),
    "parameters": {
        "type": "object",
        "properties": {
            "conclusion": {"type": "string", "description": "The fact to store."},
        },
        "required": ["conclusion"],
    },
}


# ---------------------------------------------------------------------------
# MemoryProvider implementation
# ---------------------------------------------------------------------------

class Mem0MemoryProvider(MemoryProvider):
    """Mem0 Platform memory with server-side extraction and semantic search."""

    def __init__(self):
        self._config = None
        self._client = None
        self._api_key = ""
        self._user_id = "hermes-user"
        self._agent_id = "hermes"
        self._rerank = True
        self._prefetch_result = ""
        self._prefetch_lock = threading.Lock()
        self._prefetch_thread = None

    @property
    def name(self) -> str:
        return "mem0"

    def is_available(self) -> bool:
        cfg = _load_config()
        return bool(cfg.get("api_key"))

    def _get_client(self):
        if self._client is not None:
            return self._client
        try:
            from mem0 import MemoryClient
            self._client = MemoryClient(api_key=self._api_key)
            return self._client
        except ImportError:
            raise RuntimeError("mem0 package not installed. Run: pip install mem0ai")

    def initialize(self, session_id: str, **kwargs) -> None:
        self._config = _load_config()
        self._api_key = self._config.get("api_key", "")
        self._user_id = self._config.get("user_id", "hermes-user")
        self._agent_id = self._config.get("agent_id", "hermes")
        self._rerank = self._config.get("rerank", True)

    def system_prompt_block(self) -> str:
        return (
            "# Mem0 Memory\n"
            f"Active. User: {self._user_id}.\n"
            "Use mem0_search to find memories, mem0_conclude to store facts, "
            "mem0_profile for a full overview."
        )

    def prefetch(self, query: str) -> str:
        if self._prefetch_thread and self._prefetch_thread.is_alive():
            self._prefetch_thread.join(timeout=3.0)
        with self._prefetch_lock:
            result = self._prefetch_result
            self._prefetch_result = ""
        if not result:
            return ""
        return f"## Mem0 Memory\n{result}"

    def queue_prefetch(self, query: str) -> None:
        def _run():
            try:
                client = self._get_client()
                results = client.search(
                    query=query,
                    user_id=self._user_id,
                    rerank=self._rerank,
                    top_k=5,
                )
                if results:
                    lines = [r.get("memory", "") for r in results if r.get("memory")]
                    with self._prefetch_lock:
                        self._prefetch_result = "\n".join(f"- {l}" for l in lines)
            except Exception as e:
                logger.debug("Mem0 prefetch failed: %s", e)

        self._prefetch_thread = threading.Thread(target=_run, daemon=True, name="mem0-prefetch")
        self._prefetch_thread.start()

    def sync_turn(self, user_content: str, assistant_content: str) -> None:
        """Send the turn to Mem0 for server-side fact extraction."""
        try:
            client = self._get_client()
            messages = [
                {"role": "user", "content": user_content},
                {"role": "assistant", "content": assistant_content},
            ]
            client.add(messages, user_id=self._user_id, agent_id=self._agent_id)
        except Exception as e:
            logger.warning("Mem0 sync failed: %s", e)

    def get_tool_schemas(self) -> List[Dict[str, Any]]:
        return [PROFILE_SCHEMA, SEARCH_SCHEMA, CONTEXT_SCHEMA, CONCLUDE_SCHEMA]

    def handle_tool_call(self, tool_name: str, args: dict, **kwargs) -> str:
        try:
            client = self._get_client()
        except Exception as e:
            return json.dumps({"error": str(e)})

        if tool_name == "mem0_profile":
            try:
                memories = client.get_all(user_id=self._user_id)
                if not memories:
                    return json.dumps({"result": "No memories stored yet."})
                lines = [m.get("memory", "") for m in memories if m.get("memory")]
                return json.dumps({"result": "\n".join(lines), "count": len(lines)})
            except Exception as e:
                return json.dumps({"error": f"Failed to fetch profile: {e}"})

        elif tool_name == "mem0_search":
            query = args.get("query", "")
            if not query:
                return json.dumps({"error": "Missing required parameter: query"})
            rerank = args.get("rerank", False)
            top_k = min(int(args.get("top_k", 10)), 50)
            try:
                results = client.search(
                    query=query, user_id=self._user_id,
                    rerank=rerank, top_k=top_k,
                )
                if not results:
                    return json.dumps({"result": "No relevant memories found."})
                items = [{"memory": r.get("memory", ""), "score": r.get("score", 0)} for r in results]
                return json.dumps({"results": items, "count": len(items)})
            except Exception as e:
                return json.dumps({"error": f"Search failed: {e}"})

        elif tool_name == "mem0_context":
            query = args.get("query", "")
            if not query:
                return json.dumps({"error": "Missing required parameter: query"})
            try:
                results = client.search(
                    query=query, user_id=self._user_id,
                    rerank=True, top_k=5,
                )
                if not results:
                    return json.dumps({"result": "No relevant memories found."})
                items = [{"memory": r.get("memory", ""), "score": r.get("score", 0)} for r in results]
                return json.dumps({"results": items, "count": len(items)})
            except Exception as e:
                return json.dumps({"error": f"Context retrieval failed: {e}"})

        elif tool_name == "mem0_conclude":
            conclusion = args.get("conclusion", "")
            if not conclusion:
                return json.dumps({"error": "Missing required parameter: conclusion"})
            try:
                client.add(
                    [{"role": "user", "content": conclusion}],
                    user_id=self._user_id,
                    agent_id=self._agent_id,
                    infer=False,
                )
                return json.dumps({"result": "Fact stored."})
            except Exception as e:
                return json.dumps({"error": f"Failed to store: {e}"})

        return json.dumps({"error": f"Unknown tool: {tool_name}"})

    def shutdown(self) -> None:
        if self._prefetch_thread and self._prefetch_thread.is_alive():
            self._prefetch_thread.join(timeout=5.0)
        self._client = None


def register(ctx) -> None:
    """Register Mem0 as a memory provider plugin."""
    ctx.register_memory_provider(Mem0MemoryProvider())