refactor(integrations): shared agent plugin runtimes and native adapters (#7203)
This commit is contained in:
Kartik
@@ -0,0 +1,247 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Expose Mem0's memory search as one local coding-agent tool."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
from typing import Any
|
||||
|
||||
import telemetry
|
||||
from memory_core import (
|
||||
CODING_MEMORY_CATEGORY_NAMES,
|
||||
PLUGIN_VERSION,
|
||||
SEARCH_SCOPES,
|
||||
format_search_result,
|
||||
resolve_repo,
|
||||
search_memories,
|
||||
)
|
||||
|
||||
PROTOCOL_VERSION = "2024-11-05"
|
||||
TOOL_NAME = "search_memories"
|
||||
TOOL_DESCRIPTION = (
|
||||
"Search memories from earlier work in this repository. ALWAYS call this "
|
||||
"tool before answering anything that could depend on prior context: the "
|
||||
"user's preferences, facts about this codebase, history, people, projects, "
|
||||
"or earlier decisions. Do not rely on the chat window alone. The "
|
||||
"repository's memory is shared by everyone who works in it and includes "
|
||||
"what it took to run, test, or build here, so search before assuming an "
|
||||
"invocation works. The scope argument changes what is searched: 'repo' "
|
||||
"(default) is the whole repository's shared memory plus your own "
|
||||
"preferences, 'dir' narrows the shared part to the directory you are "
|
||||
"working in, and 'mine' is your preferences alone."
|
||||
)
|
||||
TOOL_SCHEMA = {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"query": {
|
||||
"type": "string",
|
||||
"minLength": 1,
|
||||
"maxLength": 2000,
|
||||
"description": "A direct question about earlier work in this repository.",
|
||||
},
|
||||
"top_k": {
|
||||
"type": "integer",
|
||||
"minimum": 1,
|
||||
"maximum": 20,
|
||||
"description": "Maximum memories to return. Uses Mem0's configured default when omitted.",
|
||||
},
|
||||
"category": {
|
||||
"type": "string",
|
||||
"enum": list(CODING_MEMORY_CATEGORY_NAMES),
|
||||
"description": "Optional memory category. Omit to search every category.",
|
||||
},
|
||||
"scope": {
|
||||
"type": "string",
|
||||
"enum": list(SEARCH_SCOPES),
|
||||
"description": (
|
||||
"Which memories to search. 'repo' (default) is the whole repository's "
|
||||
"shared memory plus your own preferences, 'dir' narrows the shared "
|
||||
"part to the current directory, 'mine' is your preferences alone."
|
||||
),
|
||||
},
|
||||
"run_id": {
|
||||
"type": "string",
|
||||
"minLength": 1,
|
||||
"description": (
|
||||
"Optional coding-agent session ID. With any scope, restricts results to memories "
|
||||
"saved in that session. Omit to recall memories across sessions."
|
||||
),
|
||||
},
|
||||
},
|
||||
"required": ["query"],
|
||||
"additionalProperties": False,
|
||||
}
|
||||
|
||||
|
||||
class ToolInputError(ValueError):
|
||||
pass
|
||||
|
||||
|
||||
def _validate_arguments(
|
||||
arguments: Any,
|
||||
) -> tuple[str, int | None, str | None, str | None, str | None]:
|
||||
if not isinstance(arguments, dict):
|
||||
raise ToolInputError("Search arguments must be an object.")
|
||||
|
||||
unknown = set(arguments) - {"query", "top_k", "category", "scope", "run_id"}
|
||||
if unknown:
|
||||
raise ToolInputError(f"Unknown search argument: {sorted(unknown)[0]}")
|
||||
|
||||
query = arguments.get("query")
|
||||
if not isinstance(query, str) or not query.strip():
|
||||
raise ToolInputError("query must be a non-empty string.")
|
||||
query = query.strip()
|
||||
if len(query) > 2000:
|
||||
raise ToolInputError("query must be at most 2,000 characters.")
|
||||
|
||||
top_k = arguments.get("top_k")
|
||||
if top_k is not None and (
|
||||
isinstance(top_k, bool) or not isinstance(top_k, int) or not 1 <= top_k <= 20
|
||||
):
|
||||
raise ToolInputError("top_k must be an integer from 1 to 20.")
|
||||
|
||||
category = arguments.get("category")
|
||||
if category is not None and category not in CODING_MEMORY_CATEGORY_NAMES:
|
||||
raise ToolInputError("category must be one of Mem0's supported categories.")
|
||||
|
||||
scope = arguments.get("scope")
|
||||
if scope is not None and scope not in SEARCH_SCOPES:
|
||||
raise ToolInputError(f"scope must be one of {list(SEARCH_SCOPES)}.")
|
||||
|
||||
run_id = arguments.get("run_id")
|
||||
if run_id is not None:
|
||||
if not isinstance(run_id, str) or not run_id.strip():
|
||||
raise ToolInputError("run_id must be a non-empty string.")
|
||||
run_id = run_id.strip()
|
||||
|
||||
return query, top_k, category, scope, run_id
|
||||
|
||||
|
||||
def call_search_memories(arguments: Any, cwd: str | None = None) -> str:
|
||||
query, top_k, category, scope, run_id = _validate_arguments(arguments)
|
||||
repo = resolve_repo(cwd or os.environ.get("CLAUDE_PROJECT_DIR") or os.getcwd())
|
||||
result = search_memories(
|
||||
None,
|
||||
repo,
|
||||
None,
|
||||
query,
|
||||
top_k=top_k,
|
||||
category=category,
|
||||
scope=scope,
|
||||
run_id=run_id,
|
||||
operation="mcp-search",
|
||||
)
|
||||
return format_search_result(result)
|
||||
|
||||
|
||||
def _workspace_cwd(params: dict[str, Any]) -> str | None:
|
||||
meta = params.get("_meta")
|
||||
if not isinstance(meta, dict):
|
||||
return None
|
||||
metadata = meta.get("x-codex-turn-metadata")
|
||||
if not isinstance(metadata, dict):
|
||||
return None
|
||||
workspaces = metadata.get("workspaces") or {}
|
||||
if isinstance(workspaces, dict):
|
||||
return next((path for path in workspaces if isinstance(path, str) and path), None)
|
||||
return None
|
||||
|
||||
|
||||
def _tool_response(text: str, *, is_error: bool = False) -> dict[str, Any]:
|
||||
return {
|
||||
"content": [{"type": "text", "text": text}],
|
||||
"isError": is_error,
|
||||
}
|
||||
|
||||
|
||||
def handle_request(message: Any) -> dict[str, Any] | None:
|
||||
if not isinstance(message, dict):
|
||||
return None
|
||||
request_id = message.get("id")
|
||||
method = message.get("method")
|
||||
|
||||
if method == "notifications/initialized":
|
||||
return None
|
||||
if method == "initialize":
|
||||
requested = (message.get("params") or {}).get("protocolVersion")
|
||||
return {
|
||||
"jsonrpc": "2.0",
|
||||
"id": request_id,
|
||||
"result": {
|
||||
"protocolVersion": requested or PROTOCOL_VERSION,
|
||||
"capabilities": {"tools": {"listChanged": False}},
|
||||
"serverInfo": {"name": "mem0", "version": PLUGIN_VERSION},
|
||||
},
|
||||
}
|
||||
if method == "ping":
|
||||
return {"jsonrpc": "2.0", "id": request_id, "result": {}}
|
||||
if method == "tools/list":
|
||||
return {
|
||||
"jsonrpc": "2.0",
|
||||
"id": request_id,
|
||||
"result": {
|
||||
"tools": [
|
||||
{
|
||||
"name": TOOL_NAME,
|
||||
"description": TOOL_DESCRIPTION,
|
||||
"inputSchema": TOOL_SCHEMA,
|
||||
"annotations": {
|
||||
"readOnlyHint": True,
|
||||
"idempotentHint": True,
|
||||
"openWorldHint": True,
|
||||
},
|
||||
}
|
||||
]
|
||||
},
|
||||
}
|
||||
if method == "tools/call":
|
||||
params = message.get("params") or {}
|
||||
if params.get("name") != TOOL_NAME:
|
||||
result = _tool_response("Unknown Mem0 tool.", is_error=True)
|
||||
else:
|
||||
try:
|
||||
result = _tool_response(
|
||||
call_search_memories(params.get("arguments"), _workspace_cwd(params))
|
||||
)
|
||||
except ToolInputError as exc:
|
||||
result = _tool_response(str(exc), is_error=True)
|
||||
except Exception:
|
||||
result = _tool_response("Memory search failed.", is_error=True)
|
||||
return {"jsonrpc": "2.0", "id": request_id, "result": result}
|
||||
if request_id is None:
|
||||
return None
|
||||
return {
|
||||
"jsonrpc": "2.0",
|
||||
"id": request_id,
|
||||
"error": {"code": -32601, "message": "Method not found"},
|
||||
}
|
||||
|
||||
|
||||
def main() -> int:
|
||||
for raw_line in sys.stdin:
|
||||
try:
|
||||
message = json.loads(raw_line)
|
||||
response = handle_request(message)
|
||||
except json.JSONDecodeError:
|
||||
response = {
|
||||
"jsonrpc": "2.0",
|
||||
"id": None,
|
||||
"error": {"code": -32700, "message": "Parse error"},
|
||||
}
|
||||
except Exception:
|
||||
response = {
|
||||
"jsonrpc": "2.0",
|
||||
"id": None,
|
||||
"error": {"code": -32603, "message": "Internal error"},
|
||||
}
|
||||
if response is not None:
|
||||
sys.stdout.write(json.dumps(response, separators=(",", ":")) + "\n")
|
||||
sys.stdout.flush()
|
||||
telemetry.spawn_flush()
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -0,0 +1,154 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Mem0 diagnostics and user controls."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
|
||||
import telemetry
|
||||
from memory_core import (
|
||||
EvidenceStore,
|
||||
api_key,
|
||||
data_dir,
|
||||
doctor,
|
||||
forget_remote_repo,
|
||||
configure_harness,
|
||||
resolve_repo,
|
||||
user_id,
|
||||
)
|
||||
|
||||
|
||||
def _print_status(value: dict) -> None:
|
||||
last = value.get("last_operation") or {}
|
||||
print(f"Mem0: {'paused' if value['paused'] else 'active'}")
|
||||
print(f"Repository: {value['repo_id']}")
|
||||
print(f"Local data: {value['data_dir']}")
|
||||
print(f"API key: {'configured' if value['api_key_configured'] else 'missing'}")
|
||||
print(
|
||||
"Saved on this computer: "
|
||||
f"{value['events']} session details, {value['flushes']} memory updates"
|
||||
)
|
||||
print(
|
||||
f"Used in this repository: {value['retrievals']} memories returned, "
|
||||
f"{value['sidekick_runs']} sidekick runs"
|
||||
)
|
||||
if last:
|
||||
item_label = ""
|
||||
if last["operation"] in {"flush", "flush-retry"}:
|
||||
item_label = f", {last['item_count']} memories"
|
||||
operation = (
|
||||
"memory update"
|
||||
if last["operation"] in {"flush", "flush-retry"}
|
||||
else last["operation"].replace("-", " ")
|
||||
)
|
||||
print(
|
||||
f"Last {operation}: "
|
||||
f"{'succeeded' if last['success'] else 'failed'} "
|
||||
f"({last['duration_ms']:.1f} ms{item_label})"
|
||||
)
|
||||
sidekick = value.get("last_sidekick") or {}
|
||||
if sidekick:
|
||||
state = "finished" if sidekick.get("stopped_at") else "started"
|
||||
print(
|
||||
"Last sidekick: "
|
||||
f"{state}, received {sidekick['context_chars']} characters of memory, "
|
||||
f"agent {sidekick['agent_id']}"
|
||||
)
|
||||
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--plugin-data-dir", default="")
|
||||
parser.add_argument("--harness", default="")
|
||||
subparsers = parser.add_subparsers(dest="command", required=True)
|
||||
|
||||
status = subparsers.add_parser("status")
|
||||
status.add_argument("--json", action="store_true")
|
||||
|
||||
doctor_parser = subparsers.add_parser("doctor")
|
||||
doctor_parser.add_argument("--json", action="store_true")
|
||||
|
||||
subparsers.add_parser("pause")
|
||||
subparsers.add_parser("resume")
|
||||
|
||||
forget = subparsers.add_parser("forget")
|
||||
forget.add_argument("--remote", action="store_true")
|
||||
forget.add_argument("--yes", action="store_true")
|
||||
forget.add_argument("--include-project-memory", action="store_true")
|
||||
|
||||
args = parser.parse_args()
|
||||
if args.harness:
|
||||
source_tag = f"{args.harness.replace('-', '_')}_plugin"
|
||||
configure_harness(args.harness, source_tag=source_tag)
|
||||
telemetry.init(harness=args.harness, source_tag=source_tag.upper())
|
||||
if args.plugin_data_dir:
|
||||
os.environ["MEM0_CODE_DATA_DIR"] = args.plugin_data_dir
|
||||
store = EvidenceStore()
|
||||
try:
|
||||
repo = resolve_repo(os.getcwd())
|
||||
telemetry.record("control", repo=repo, action=args.command)
|
||||
if args.command == "status":
|
||||
result = {
|
||||
**store.status(repo.identity),
|
||||
"repo_id": repo.identity,
|
||||
"app_id": repo.app_id,
|
||||
"project_id": repo.project_id,
|
||||
"directory": repo.directory,
|
||||
"user_id": user_id(),
|
||||
"data_dir": str(data_dir()),
|
||||
"api_key_configured": bool(api_key()),
|
||||
}
|
||||
if args.json:
|
||||
print(json.dumps(result, indent=2, default=str))
|
||||
else:
|
||||
_print_status(result)
|
||||
elif args.command == "doctor":
|
||||
result = doctor(os.getcwd())
|
||||
if args.json:
|
||||
print(json.dumps(result, indent=2, default=str))
|
||||
else:
|
||||
for name, check in result["checks"].items():
|
||||
print(
|
||||
f"{'PASS' if check['ok'] else 'FAIL'} {name}: {check['detail']}"
|
||||
)
|
||||
return 0 if result["ok"] else 1
|
||||
elif args.command == "pause":
|
||||
store.set_setting("paused", "true")
|
||||
print("Mem0 stopped saving and searching memories.")
|
||||
elif args.command == "resume":
|
||||
store.set_setting("paused", "false")
|
||||
print("Mem0 resumed saving and searching memories.")
|
||||
elif args.command == "forget":
|
||||
if not args.yes:
|
||||
print(
|
||||
"Refusing to delete data without --yes. Add --remote to also "
|
||||
"delete this user/repository scope from Mem0."
|
||||
)
|
||||
return 2
|
||||
remote_result = (
|
||||
forget_remote_repo(
|
||||
repo, include_project_memory=args.include_project_memory
|
||||
)
|
||||
if args.remote
|
||||
else None
|
||||
)
|
||||
local_result = store.forget_local_repo(repo.identity)
|
||||
print(
|
||||
json.dumps(
|
||||
{"local": local_result, "remote": remote_result},
|
||||
indent=2,
|
||||
default=str,
|
||||
)
|
||||
)
|
||||
if remote_result and remote_result.get("status") == "error":
|
||||
return 1
|
||||
finally:
|
||||
store.close()
|
||||
telemetry.spawn_flush()
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,397 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Anonymous usage telemetry for Mem0 agent plugins.
|
||||
|
||||
Hooks run on a 3-6 second budget and fire on every tool call, so recording never
|
||||
touches the network: `record` appends one JSON line to a local spool and returns.
|
||||
A detached `python3 telemetry.py` drains the spool in one batched PostHog request,
|
||||
started once per session and again from the flush worker that is already detached.
|
||||
|
||||
Pure stdlib, matching the rest of the plugin. Opt out with MEM0_TELEMETRY=false.
|
||||
|
||||
Never sends prompts, memory text, queries, file paths, repository names, or API
|
||||
keys: only event names, durations, counts, coarse outcomes, and salted hashes.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
import platform
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
import uuid
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
import memory_core
|
||||
|
||||
_harness: str = "generic"
|
||||
_source_tag: str = "MEM0_PLUGIN"
|
||||
_PRIVATE_KEYS = {
|
||||
"apikey",
|
||||
"authorization",
|
||||
"password",
|
||||
"query",
|
||||
"secret",
|
||||
"prompt",
|
||||
"token",
|
||||
"text",
|
||||
"memory",
|
||||
"message",
|
||||
"error",
|
||||
"path",
|
||||
"cwd",
|
||||
"userid",
|
||||
"agentid",
|
||||
"runid",
|
||||
"repoid",
|
||||
"repositoryid",
|
||||
"projectid",
|
||||
"appid",
|
||||
"filters",
|
||||
}
|
||||
|
||||
|
||||
def init(harness: str = "generic", source_tag: str = "") -> None:
|
||||
global _harness, _source_tag
|
||||
_harness = harness
|
||||
_source_tag = source_tag or f"MEM0_{harness.upper().replace('-', '_')}_PLUGIN"
|
||||
|
||||
POSTHOG_API_KEY = "phc_hgJkUVJFYtmaJqrvf6CYN67TIQ8yhXAkWzUn9AMU4yX"
|
||||
POSTHOG_CAPTURE_URL = "https://us.i.posthog.com/i/v0/e/"
|
||||
POSTHOG_BATCH_URL = "https://us.i.posthog.com/batch/"
|
||||
EVENT_PREFIX = "code"
|
||||
SPOOL_LIMIT_BYTES = 256 * 1024
|
||||
BATCH_SIZE = 100
|
||||
SEND_TIMEOUT = 5
|
||||
CLAIM_STALE_SECONDS = 120
|
||||
CLAIM_EXPIRY_SECONDS = 7 * 24 * 60 * 60
|
||||
|
||||
|
||||
def is_enabled() -> bool:
|
||||
"""Whether telemetry is switched on for this process."""
|
||||
return os.environ.get("MEM0_TELEMETRY", "true").strip().lower() not in {
|
||||
"false",
|
||||
"0",
|
||||
"no",
|
||||
"off",
|
||||
}
|
||||
|
||||
|
||||
def _digest(value: str, length: int = 16) -> str:
|
||||
return hashlib.sha256(value.encode("utf-8")).hexdigest()[:length]
|
||||
|
||||
|
||||
def _safe_value(value: Any) -> Any:
|
||||
if isinstance(value, str):
|
||||
return memory_core.redact(value)
|
||||
if isinstance(value, dict):
|
||||
return {
|
||||
key: _safe_value(item)
|
||||
for key, item in value.items()
|
||||
if "".join(character for character in str(key).lower() if character.isalnum())
|
||||
not in _PRIVATE_KEYS
|
||||
}
|
||||
if isinstance(value, (list, tuple)):
|
||||
return [_safe_value(item) for item in value]
|
||||
if value is None or isinstance(value, (bool, int, float)):
|
||||
return value
|
||||
return memory_core.redact(value)
|
||||
|
||||
|
||||
def _spool_path() -> Path:
|
||||
return memory_core.data_dir() / "telemetry.jsonl"
|
||||
|
||||
|
||||
def _identity_path() -> Path:
|
||||
return memory_core.data_dir() / "telemetry-identity.json"
|
||||
|
||||
|
||||
def _read_identity() -> dict[str, str]:
|
||||
try:
|
||||
value = json.loads(_identity_path().read_text(encoding="utf-8"))
|
||||
except (OSError, json.JSONDecodeError):
|
||||
return {}
|
||||
return value if isinstance(value, dict) else {}
|
||||
|
||||
|
||||
def _write_identity(identity: dict[str, str]) -> None:
|
||||
path = _identity_path()
|
||||
temporary = path.with_suffix(f".{os.getpid()}.tmp")
|
||||
try:
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
temporary.write_text(json.dumps(identity), encoding="utf-8")
|
||||
temporary.replace(path)
|
||||
except OSError:
|
||||
try:
|
||||
temporary.unlink()
|
||||
except OSError:
|
||||
pass
|
||||
|
||||
|
||||
def anonymous_id(identity: dict[str, str] | None = None) -> str:
|
||||
"""Per-machine anonymous identifier, created and persisted on first use."""
|
||||
identity = _read_identity() if identity is None else identity
|
||||
existing = identity.get("anonymous_id")
|
||||
if existing:
|
||||
return existing
|
||||
created = f"code-anon-{uuid.uuid4().hex}"
|
||||
identity["anonymous_id"] = created
|
||||
_write_identity(identity)
|
||||
return created
|
||||
|
||||
|
||||
def is_first_run() -> bool:
|
||||
"""Whether this machine has never recorded a plugin event before."""
|
||||
return not _identity_path().exists()
|
||||
|
||||
|
||||
def record(
|
||||
event: str,
|
||||
*,
|
||||
repo: Any = None,
|
||||
session_id: str | None = None,
|
||||
**properties: Any,
|
||||
) -> None:
|
||||
"""Append one event to the local spool. Never blocks and never raises."""
|
||||
if not is_enabled():
|
||||
return
|
||||
try:
|
||||
spool = _spool_path()
|
||||
try:
|
||||
if spool.stat().st_size > SPOOL_LIMIT_BYTES:
|
||||
return
|
||||
except OSError:
|
||||
pass
|
||||
properties = _safe_value(properties)
|
||||
properties.update(
|
||||
harness=_harness,
|
||||
plugin_version=memory_core.PLUGIN_VERSION,
|
||||
os=sys.platform,
|
||||
python_version=platform.python_version(),
|
||||
)
|
||||
if repo is not None:
|
||||
properties["repo_hash"] = _digest(getattr(repo, "identity", ""))
|
||||
if session_id:
|
||||
properties["session_hash"] = _digest(session_id)
|
||||
line = json.dumps(
|
||||
{
|
||||
"event": f"{EVENT_PREFIX}.{event}",
|
||||
"timestamp": memory_core.utc_now(),
|
||||
"properties": {
|
||||
key: value for key, value in properties.items() if value is not None
|
||||
},
|
||||
},
|
||||
separators=(",", ":"),
|
||||
default=str,
|
||||
)
|
||||
spool.parent.mkdir(parents=True, exist_ok=True)
|
||||
with spool.open("a", encoding="utf-8") as handle:
|
||||
handle.write(line + "\n")
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
|
||||
def error_kind(exc: BaseException | str) -> str:
|
||||
"""Coarse, content-free label for a failure, safe to send."""
|
||||
text = exc if isinstance(exc, str) else f"{type(exc).__name__}: {exc}"
|
||||
lowered = text.lower()
|
||||
if "timed out" in lowered or "timeout" in lowered:
|
||||
return "timeout"
|
||||
if "401" in lowered or "403" in lowered or "unauthor" in lowered or "forbidden" in lowered:
|
||||
return "auth"
|
||||
if "429" in lowered or "rate limit" in lowered:
|
||||
return "rate-limited"
|
||||
if any(code in lowered for code in ("500", "502", "503", "504")):
|
||||
return "server-error"
|
||||
if "400" in lowered or "422" in lowered:
|
||||
return "bad-request"
|
||||
if isinstance(exc, str):
|
||||
return "other"
|
||||
if isinstance(exc, urllib.error.URLError):
|
||||
return "network"
|
||||
return type(exc).__name__
|
||||
|
||||
|
||||
def spawn_flush() -> bool:
|
||||
"""Start the detached sender that drains the spool."""
|
||||
if not is_enabled():
|
||||
return False
|
||||
try:
|
||||
if not _spool_path().exists() and not any(
|
||||
memory_core.data_dir().glob("telemetry-*.sending")
|
||||
):
|
||||
return False
|
||||
subprocess.Popen(
|
||||
[sys.executable, str(Path(__file__).resolve())],
|
||||
stdin=subprocess.DEVNULL,
|
||||
stdout=subprocess.DEVNULL,
|
||||
stderr=subprocess.DEVNULL,
|
||||
close_fds=True,
|
||||
**memory_core.detached_process_kwargs(),
|
||||
)
|
||||
return True
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
|
||||
def _claim_spool() -> Path | None:
|
||||
"""Rename the spool aside so exactly one sender owns each batch."""
|
||||
directory = memory_core.data_dir()
|
||||
claim = directory / f"telemetry-{os.getpid()}-{uuid.uuid4().hex[:8]}.sending"
|
||||
spool = _spool_path()
|
||||
try:
|
||||
spool.replace(claim)
|
||||
return claim
|
||||
except OSError:
|
||||
pass
|
||||
now = time.time()
|
||||
for orphan in sorted(directory.glob("telemetry-*.sending")):
|
||||
try:
|
||||
age = now - orphan.stat().st_mtime
|
||||
except OSError:
|
||||
continue
|
||||
if age > CLAIM_EXPIRY_SECONDS:
|
||||
try:
|
||||
orphan.unlink()
|
||||
except OSError:
|
||||
pass
|
||||
continue
|
||||
if age < CLAIM_STALE_SECONDS:
|
||||
continue
|
||||
try:
|
||||
orphan.replace(claim)
|
||||
return claim
|
||||
except OSError:
|
||||
continue
|
||||
return None
|
||||
|
||||
|
||||
def _resolve_email(key: str) -> str:
|
||||
"""Trade the API key for the account email so events join other Mem0 surfaces."""
|
||||
url = os.environ.get("MEM0_API_URL", memory_core.DEFAULT_API_URL).rstrip("/") + "/v1/ping/"
|
||||
request = urllib.request.Request(
|
||||
url, headers={"Authorization": f"Token {key}", "Content-Type": "application/json"}
|
||||
)
|
||||
try:
|
||||
with urllib.request.urlopen(request, timeout=SEND_TIMEOUT) as response:
|
||||
payload = json.loads(response.read().decode("utf-8"))
|
||||
except Exception:
|
||||
return ""
|
||||
email = payload.get("user_email") if isinstance(payload, dict) else ""
|
||||
return email if isinstance(email, str) else ""
|
||||
|
||||
|
||||
def _post(payload: dict[str, Any], url: str) -> bool:
|
||||
request = urllib.request.Request(
|
||||
url,
|
||||
data=json.dumps(payload, default=str).encode("utf-8"),
|
||||
headers={"Content-Type": "application/json"},
|
||||
)
|
||||
try:
|
||||
with urllib.request.urlopen(request, timeout=SEND_TIMEOUT):
|
||||
return True
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
|
||||
def resolve_distinct_id() -> tuple[str, str]:
|
||||
"""Return the PostHog distinct id and the anonymous id it replaced, if any."""
|
||||
identity = _read_identity()
|
||||
email = identity.get("email", "")
|
||||
if email:
|
||||
return email, ""
|
||||
key = memory_core.api_key()
|
||||
if not key:
|
||||
return anonymous_id(identity), ""
|
||||
email = _resolve_email(key)
|
||||
if not email:
|
||||
return anonymous_id(identity), ""
|
||||
previous = identity.get("anonymous_id", "")
|
||||
identity["email"] = email
|
||||
_write_identity(identity)
|
||||
return email, previous
|
||||
|
||||
|
||||
def flush() -> int:
|
||||
"""Drain claimed spools to PostHog and return the number of events sent."""
|
||||
if not is_enabled():
|
||||
return 0
|
||||
claim = _claim_spool()
|
||||
if claim is None:
|
||||
return 0
|
||||
try:
|
||||
lines = claim.read_text(encoding="utf-8").splitlines()
|
||||
except OSError:
|
||||
return 0
|
||||
events = []
|
||||
for line in lines:
|
||||
try:
|
||||
value = json.loads(line)
|
||||
except json.JSONDecodeError:
|
||||
continue
|
||||
if isinstance(value, dict) and value.get("event"):
|
||||
events.append(value)
|
||||
if not events:
|
||||
try:
|
||||
claim.unlink()
|
||||
except OSError:
|
||||
pass
|
||||
return 0
|
||||
|
||||
distinct_id, aliased_anonymous_id = resolve_distinct_id()
|
||||
if aliased_anonymous_id:
|
||||
_post(
|
||||
{
|
||||
"api_key": POSTHOG_API_KEY,
|
||||
"event": "$identify",
|
||||
"distinct_id": distinct_id,
|
||||
"properties": {
|
||||
"$anon_distinct_id": aliased_anonymous_id,
|
||||
"$lib": "posthog-python",
|
||||
},
|
||||
},
|
||||
POSTHOG_CAPTURE_URL,
|
||||
)
|
||||
|
||||
sent = 0
|
||||
for start in range(0, len(events), BATCH_SIZE):
|
||||
batch = [
|
||||
{
|
||||
"event": event["event"],
|
||||
"distinct_id": distinct_id,
|
||||
"timestamp": event.get("timestamp"),
|
||||
"properties": {
|
||||
"source": _source_tag,
|
||||
"language": "python",
|
||||
"$process_person_profile": False,
|
||||
"$lib": "posthog-python",
|
||||
**(event.get("properties") or {}),
|
||||
},
|
||||
}
|
||||
for event in events[start : start + BATCH_SIZE]
|
||||
]
|
||||
if not _post({"api_key": POSTHOG_API_KEY, "batch": batch}, POSTHOG_BATCH_URL):
|
||||
return sent
|
||||
sent += len(batch)
|
||||
try:
|
||||
claim.unlink()
|
||||
except OSError:
|
||||
pass
|
||||
return sent
|
||||
|
||||
|
||||
def main() -> int:
|
||||
flush()
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
try:
|
||||
raise SystemExit(main())
|
||||
except Exception:
|
||||
raise SystemExit(0)
|
||||
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"$schema": "https://agent-plugins.org/schemas/1.0.0/mcp.schema.json",
|
||||
"mcpServers": {
|
||||
"mem0": {
|
||||
"type": "stdio",
|
||||
"command": "python3",
|
||||
"args": [
|
||||
"${PLUGIN_ROOT}/core/mcp_server.py"
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,19 @@
|
||||
{
|
||||
"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
|
||||
"name": "mem0",
|
||||
"version": "0.3.1",
|
||||
"description": "Cross-session memory and token savings for coding agents.",
|
||||
"author": {
|
||||
"name": "Mem0",
|
||||
"email": "support@mem0.ai"
|
||||
},
|
||||
"homepage": "https://docs.mem0.ai/integrations",
|
||||
"repository": "https://github.com/mem0ai/mem0",
|
||||
"license": "Apache-2.0",
|
||||
"keywords": [
|
||||
"memory",
|
||||
"coding-agents",
|
||||
"continual-learning",
|
||||
"token-efficiency"
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,25 @@
|
||||
---
|
||||
name: forget
|
||||
description: Delete the Mem0 memories stored for this repository and this user. Use when the user asks to forget, clear, wipe, or delete memories.
|
||||
---
|
||||
|
||||
# Forget this repository's memories
|
||||
|
||||
This permanently deletes remote memories. Before running anything, tell the
|
||||
user exactly what will be deleted: their own memories for this repository
|
||||
only. The repository's project memory is shared by everyone who works in it,
|
||||
so it stays unless the user explicitly asks to delete that too.
|
||||
|
||||
After the user confirms, run:
|
||||
|
||||
```bash
|
||||
python3 "${PLUGIN_ROOT}/core/memory_cli.py" --harness "coding-agent" forget --remote --yes
|
||||
```
|
||||
|
||||
If the user also asked to delete the repository's shared project memory, add
|
||||
`--include-project-memory` and say that this removes it for every teammate.
|
||||
|
||||
Report what the command output says was deleted. If the user only wants local
|
||||
data cleared (evidence log, pending queue), run the same command without
|
||||
`--remote`. Never pass `--yes` before the user has confirmed in this
|
||||
conversation.
|
||||
@@ -0,0 +1,19 @@
|
||||
---
|
||||
name: pause
|
||||
description: Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments.
|
||||
---
|
||||
|
||||
# Pause memory capture
|
||||
|
||||
To pause (hooks stop capturing and sending session content; a minimal
|
||||
anonymous telemetry ping still fires at session start unless
|
||||
`MEM0_TELEMETRY=false`):
|
||||
|
||||
```bash
|
||||
python3 "${PLUGIN_ROOT}/core/memory_cli.py" --harness "coding-agent" pause
|
||||
```
|
||||
|
||||
Confirm the new state back to the user, and remind them that already-created
|
||||
memories still exist and remain searchable. Pending unsent packets are held
|
||||
while paused, not expired, and are delivered after resuming. To turn capture
|
||||
back on, use `/mem0:resume`.
|
||||
@@ -0,0 +1,20 @@
|
||||
---
|
||||
name: remember
|
||||
description: Acknowledge a "remember this" request and make sure it is captured well. Use when the user explicitly asks to remember, note, or save something for future sessions.
|
||||
---
|
||||
|
||||
# Remember something for future sessions
|
||||
|
||||
Mem0 creates memories from the session automatically — there is no separate
|
||||
write command. When the user asks to remember something:
|
||||
|
||||
1. Restate the fact clearly and completely in your reply, in one or two
|
||||
sentences, including any names, values, or paths it depends on. Your visible
|
||||
reply is what memory extraction reads, so a precise restatement is what gets
|
||||
remembered.
|
||||
2. Tell the user it will be saved with this session's memories when the session
|
||||
ends or compacts, and that it will surface in future sessions in this
|
||||
repository (they can check later with /mem0:search).
|
||||
|
||||
Do not invent a storage confirmation or a memory ID — creation happens in the
|
||||
background after the session.
|
||||
@@ -0,0 +1,18 @@
|
||||
---
|
||||
name: resume
|
||||
description: Resume Mem0 memory capture after it was paused with /mem0:pause.
|
||||
---
|
||||
|
||||
# Resume memory capture
|
||||
|
||||
Resume memory capture for this machine.
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
python3 "${PLUGIN_ROOT}/core/memory_cli.py" --harness "coding-agent" resume
|
||||
```
|
||||
|
||||
Confirm to the user that capture is active again. New sessions record evidence and
|
||||
create memories as normal; nothing that happened while paused is retroactively
|
||||
captured.
|
||||
@@ -0,0 +1,26 @@
|
||||
---
|
||||
name: search
|
||||
description: Search memories from earlier Coding Agent sessions in this repository. Use it when earlier work may already explain the code, error, decision, or command you need, so you can avoid repeating file reads, searches, or experiments.
|
||||
---
|
||||
|
||||
# Search memories
|
||||
|
||||
Call `search_memories` with the user's question. Treat `--top-k`, `--category`,
|
||||
`--scope`, and `--run-id` as tool arguments instead of including them in the
|
||||
query.
|
||||
|
||||
Omit `top_k` to use Mem0's configured default. Omit `category` to search every
|
||||
category; a category is a best-effort label Mem0 assigned when it saved the
|
||||
memory, so if a category search misses, repeat it without the category. Omit
|
||||
`scope` to use the configured default, normally `repo`: this repository's
|
||||
shared memory, which everyone who works in it contributes to, plus your own
|
||||
preferences.
|
||||
|
||||
Pass `scope` when the question needs something else: `dir` to narrow the
|
||||
shared memory to the directory you are working in (a package inside a
|
||||
monorepo), `mine` for your own preferences alone.
|
||||
|
||||
Pass `run_id` with any scope to retrieve memories saved in a specific coding-agent
|
||||
session. Omit `run_id` to search across sessions. It filters the memories returned;
|
||||
it does not identify the session making the search request. Use a known session ID,
|
||||
never invent one. Return the tool's result directly.
|
||||
@@ -0,0 +1,22 @@
|
||||
---
|
||||
name: status
|
||||
description: Show whether Mem0 memory is working in this repository, covering configuration, capture state, pending flushes, and whether the Mem0 API key is valid. Use when the user asks whether memory is on, why a memory is missing, or anything looks broken.
|
||||
---
|
||||
|
||||
# Memory status
|
||||
|
||||
Run both commands and report the combined result in plain language:
|
||||
|
||||
```bash
|
||||
python3 "${PLUGIN_ROOT}/core/memory_cli.py" --harness "coding-agent" status --json
|
||||
python3 "${PLUGIN_ROOT}/core/memory_cli.py" --harness "coding-agent" doctor
|
||||
```
|
||||
|
||||
Summarize, using only fields the JSON actually reports: whether capture is
|
||||
active or paused, the user ID and repository scope (`repo_id`), whether an
|
||||
API key is configured, the event/flush/retrieval counts (`flushes` is the
|
||||
number of completed flushes, not a pending count), and the doctor check
|
||||
results. If doctor reports an authentication failure (401 / invalid key), say
|
||||
clearly that the Mem0 API key is invalid or expired and that memories are NOT
|
||||
being created. Never report an auth failure as "no memories found". Suggest
|
||||
reinstalling with `--config api_key=...` in that case.
|
||||
Reference in New Issue
Block a user