Hermes-agent

This commit is contained in:
Zakaria
2026-06-14 14:30:48 -04:00
commit dac4b88b94
5058 changed files with 1884848 additions and 0 deletions
+54
View File
@@ -0,0 +1,54 @@
"""Remote 'node host' primitive for the google_meet plugin.
Lets the Meet bot (Playwright + Chrome) run on a different machine than
the hermes-agent gateway. The gateway speaks a small JSON-over-WebSocket
RPC protocol to the remote node; the node wraps the existing
``plugins.google_meet.process_manager`` API.
Topology
--------
gateway (Linux) ── ws://mac.local:18789 ──▶ node server (Mac)
└─ process_manager
└─ meet_bot (Playwright)
Why: Google sign-in + Chrome profile live on the user's laptop. Running
the bot there reuses that profile without shipping credentials to the
server.
Public surface
--------------
NodeClient — gateway-side RPC client (short-lived sync WS per call)
NodeServer — long-running server that hosts the bot
NodeRegistry — local JSON registry of approved nodes (name → url+token)
protocol — message envelope helpers (make_request, encode, decode, ...)
"""
from __future__ import annotations
from plugins.google_meet.node import protocol
from plugins.google_meet.node.client import NodeClient
from plugins.google_meet.node.protocol import (
VALID_REQUEST_TYPES,
decode,
encode,
make_error,
make_request,
make_response,
validate_request,
)
from plugins.google_meet.node.registry import NodeRegistry
from plugins.google_meet.node.server import NodeServer
__all__ = [
"NodeClient",
"NodeServer",
"NodeRegistry",
"protocol",
"make_request",
"make_response",
"make_error",
"encode",
"decode",
"validate_request",
"VALID_REQUEST_TYPES",
]
+125
View File
@@ -0,0 +1,125 @@
"""`hermes meet node ...` subcommand tree.
Wired into the existing ``hermes meet`` parser by the plugin's top-level
CLI. This module only defines the subparsers and their dispatch — it
does not mutate the existing cli.py.
"""
from __future__ import annotations
import argparse
import asyncio
import json
import sys
from typing import Any
from plugins.google_meet.node.client import NodeClient
from plugins.google_meet.node.registry import NodeRegistry
from plugins.google_meet.node.server import NodeServer
def register_cli(subparser: argparse.ArgumentParser) -> None:
"""Add ``run / list / approve / remove / status / ping`` subparsers.
*subparser* is the ``hermes meet node`` argparse object — typically
the result of ``meet_parser.add_parser('node', ...)``.
"""
sp = subparser.add_subparsers(dest="node_cmd", required=True)
run = sp.add_parser("run", help="Start a node server on this machine.")
run.add_argument("--host", default="0.0.0.0")
run.add_argument("--port", type=int, default=18789)
run.add_argument("--display-name", default="hermes-meet-node")
run.set_defaults(func=node_command)
lst = sp.add_parser("list", help="List approved remote nodes.")
lst.set_defaults(func=node_command)
app = sp.add_parser("approve", help="Register a remote node on the gateway.")
app.add_argument("name")
app.add_argument("url")
app.add_argument("token")
app.set_defaults(func=node_command)
rm = sp.add_parser("remove", help="Forget a registered node.")
rm.add_argument("name")
rm.set_defaults(func=node_command)
st = sp.add_parser("status", help="Ping a registered node.")
st.add_argument("name")
st.set_defaults(func=node_command)
pg = sp.add_parser("ping", help="Alias for status.")
pg.add_argument("name")
pg.set_defaults(func=node_command)
def node_command(args: argparse.Namespace) -> int:
"""Dispatch for ``hermes meet node ...``.
Returns a process exit code. Side-effects print to stdout/stderr.
"""
cmd = getattr(args, "node_cmd", None)
if cmd == "run":
server = NodeServer(
host=args.host,
port=args.port,
display_name=args.display_name,
)
token = server.ensure_token()
print(f"[meet-node] display_name={server.display_name}")
print(f"[meet-node] listening on ws://{args.host}:{args.port}")
print(f"[meet-node] token (copy to gateway): {token}")
print(f"[meet-node] approve with:")
print(f" hermes meet node approve <name> ws://<host>:{args.port} {token}")
try:
asyncio.run(server.serve())
except KeyboardInterrupt:
return 0
except RuntimeError as exc:
print(f"[meet-node] error: {exc}", file=sys.stderr)
return 2
return 0
reg = NodeRegistry()
if cmd == "list":
nodes = reg.list_all()
if not nodes:
print("no nodes registered")
return 0
for n in nodes:
print(f"{n['name']}\t{n['url']}\ttoken={n['token'][:6]}")
return 0
if cmd == "approve":
reg.add(args.name, args.url, args.token)
print(f"approved node {args.name!r} at {args.url}")
return 0
if cmd == "remove":
ok = reg.remove(args.name)
print(f"removed {args.name!r}" if ok else f"no such node: {args.name!r}")
return 0 if ok else 1
if cmd in {"status", "ping"}:
entry = reg.get(args.name)
if entry is None:
print(f"no such node: {args.name!r}", file=sys.stderr)
return 1
client = NodeClient(entry["url"], entry["token"])
try:
result = client.ping()
except Exception as exc: # noqa: BLE001 — surface any connection error
print(json.dumps({"ok": False, "error": str(exc)}))
return 1
print(json.dumps({"ok": True, "node": args.name, **_coerce_dict(result)}))
return 0
print(f"unknown node command: {cmd!r}", file=sys.stderr)
return 2
def _coerce_dict(value: Any) -> dict:
return value if isinstance(value, dict) else {"result": value}
+107
View File
@@ -0,0 +1,107 @@
"""Gateway-side RPC client for a remote meet node.
Each call opens a short-lived synchronous WebSocket to the node, sends
exactly one request, reads exactly one response, and closes. This keeps
the client trivial to use from non-async tool handlers and avoids
maintaining persistent connection state across agent turns.
The ``websockets`` package is an optional dep — we import it lazily so
plugin load doesn't require it.
"""
from __future__ import annotations
from typing import Any, Dict, Optional
from plugins.google_meet.node import protocol as _proto
class NodeClient:
"""Thin synchronous WS client matching the server's request surface."""
def __init__(self, url: str, token: str, timeout: float = 10.0) -> None:
if not isinstance(url, str) or not url:
raise ValueError("url must be a non-empty string")
if not isinstance(token, str) or not token:
raise ValueError("token must be a non-empty string")
self.url = url
self.token = token
self.timeout = float(timeout)
# ----- core RPC -----------------------------------------------------
def _rpc(self, type: str, payload: Dict[str, Any]) -> Dict[str, Any]:
"""Send one request, return the response payload dict.
Raises RuntimeError when the server sends an ``error`` envelope
or the response id doesn't match.
"""
try:
from websockets.sync.client import connect # type: ignore
except ImportError as exc:
raise RuntimeError(
"NodeClient requires the 'websockets' package. "
"Install it with: pip install websockets"
) from exc
req = _proto.make_request(type, self.token, payload)
raw_out = _proto.encode(req)
with connect(self.url, open_timeout=self.timeout,
close_timeout=self.timeout) as ws:
ws.send(raw_out)
raw_in = ws.recv(timeout=self.timeout)
if isinstance(raw_in, (bytes, bytearray)):
raw_in = raw_in.decode("utf-8")
resp = _proto.decode(raw_in)
if resp.get("type") == "error":
raise RuntimeError(f"node error: {resp.get('error', '<unknown>')}")
if resp.get("id") != req["id"]:
raise RuntimeError(
f"response id mismatch: sent {req['id']}, got {resp.get('id')!r}"
)
payload_out = resp.get("payload")
if not isinstance(payload_out, dict):
# Ping returns {"type": "pong", "payload": {...}} — still a dict.
raise RuntimeError("response missing payload dict")
return payload_out
# ----- convenience methods -----------------------------------------
def start_bot(
self,
url: str,
guest_name: str = "Hermes Agent",
duration: Optional[str] = None,
headed: bool = False,
mode: str = "transcribe",
) -> Dict[str, Any]:
payload: Dict[str, Any] = {
"url": url,
"guest_name": guest_name,
"headed": bool(headed),
"mode": mode,
}
if duration is not None:
payload["duration"] = duration
return self._rpc("start_bot", payload)
def stop(self) -> Dict[str, Any]:
return self._rpc("stop", {})
def status(self) -> Dict[str, Any]:
return self._rpc("status", {})
def transcript(self, last: Optional[int] = None) -> Dict[str, Any]:
payload: Dict[str, Any] = {}
if last is not None:
payload["last"] = int(last)
return self._rpc("transcript", payload)
def say(self, text: str) -> Dict[str, Any]:
return self._rpc("say", {"text": str(text)})
def ping(self) -> Dict[str, Any]:
return self._rpc("ping", {})
+124
View File
@@ -0,0 +1,124 @@
"""Wire protocol for gateway ↔ node RPC.
Everything is a JSON object with the same envelope shape:
Request: {"type": <str>, "id": <str>, "token": <str>, "payload": <dict>}
Response: {"type": "<req-type>_res", "id": <req-id>, "payload": <dict>}
Error: {"type": "error", "id": <req-id>, "error": <str>}
Requests must carry the shared bearer token (set up via
``hermes meet node approve`` on the gateway and read off disk on the
server). Mismatched tokens are rejected before dispatch.
"""
from __future__ import annotations
import json
import uuid
from typing import Any, Dict, Tuple
VALID_REQUEST_TYPES = frozenset({
"start_bot",
"stop",
"status",
"transcript",
"say",
"ping",
})
def make_request(
type: str,
token: str,
payload: Dict[str, Any],
req_id: str | None = None,
) -> Dict[str, Any]:
"""Construct a request envelope.
``req_id`` is auto-generated (uuid4 hex) when not supplied so callers
can correlate async responses.
"""
if not isinstance(type, str) or not type:
raise ValueError("type must be a non-empty string")
if type not in VALID_REQUEST_TYPES:
raise ValueError(f"unknown request type: {type!r}")
if not isinstance(token, str):
raise ValueError("token must be a string")
if not isinstance(payload, dict):
raise ValueError("payload must be a dict")
return {
"type": type,
"id": req_id or uuid.uuid4().hex,
"token": token,
"payload": payload,
}
def make_response(req_id: str, payload: Dict[str, Any]) -> Dict[str, Any]:
"""Build a success response. The caller supplies the *request* type;
we suffix it with ``_res`` so clients can assert they got the right
reply.
For simplicity we don't require the type here — clients usually just
key off ``id``. But we still emit a generic ``*_res`` envelope.
"""
if not isinstance(payload, dict):
raise ValueError("payload must be a dict")
return {"type": "response", "id": req_id, "payload": payload}
def make_error(req_id: str, error: str) -> Dict[str, Any]:
return {"type": "error", "id": req_id, "error": str(error)}
def encode(msg: Dict[str, Any]) -> str:
"""Serialize a message envelope to a JSON string."""
return json.dumps(msg, separators=(",", ":"), ensure_ascii=False)
def decode(raw: str) -> Dict[str, Any]:
"""Parse a JSON envelope, raising ValueError on anything malformed.
Minimal type validation: must be an object, must contain ``type`` and
``id``. Heavier validation (token match, payload shape) happens in
:func:`validate_request` on the server side.
"""
try:
obj = json.loads(raw)
except (TypeError, json.JSONDecodeError) as exc:
raise ValueError(f"malformed JSON: {exc}") from exc
if not isinstance(obj, dict):
raise ValueError("envelope must be a JSON object")
if "type" not in obj or not isinstance(obj["type"], str):
raise ValueError("envelope missing string 'type'")
if "id" not in obj or not isinstance(obj["id"], str):
raise ValueError("envelope missing string 'id'")
return obj
def validate_request(msg: Dict[str, Any], expected_token: str) -> Tuple[bool, str]:
"""Check a decoded request against the server's shared token.
Returns ``(True, "")`` when the envelope is acceptable or
``(False, <reason>)`` otherwise. Reason strings are safe to surface
back to the client in an error envelope.
"""
if not isinstance(msg, dict):
return False, "envelope must be a dict"
t = msg.get("type")
if not isinstance(t, str) or not t:
return False, "missing or non-string 'type'"
if t not in VALID_REQUEST_TYPES:
return False, f"unknown request type: {t!r}"
if not isinstance(msg.get("id"), str) or not msg.get("id"):
return False, "missing or non-string 'id'"
token = msg.get("token")
if not isinstance(token, str) or not token:
return False, "missing token"
if token != expected_token:
return False, "token mismatch"
payload = msg.get("payload")
if not isinstance(payload, dict):
return False, "payload must be a dict"
return True, ""
+112
View File
@@ -0,0 +1,112 @@
"""Local JSON registry of approved remote meet nodes.
Lives at ``$HERMES_HOME/workspace/meetings/nodes.json``. The gateway
consults it to resolve a ``chrome_node`` name to a ``(url, token)`` pair
before opening a WebSocket to the remote bot host.
Schema
------
{
"nodes": {
"<name>": {
"url": "ws://host:port",
"token": "...",
"added_at": <epoch_float>
}
}
}
"""
from __future__ import annotations
import json
import time
from pathlib import Path
from typing import Any, Dict, List, Optional
from hermes_constants import get_hermes_home
def _default_path() -> Path:
return Path(get_hermes_home()) / "workspace" / "meetings" / "nodes.json"
class NodeRegistry:
"""Simple file-backed registry. Not concurrent-safe across processes
— single writer assumed (the gateway CLI)."""
def __init__(self, path: Optional[Path] = None) -> None:
self.path = Path(path) if path is not None else _default_path()
# ----- storage ------------------------------------------------------
def _load(self) -> Dict[str, Any]:
if not self.path.is_file():
return {"nodes": {}}
try:
data = json.loads(self.path.read_text(encoding="utf-8"))
except (OSError, json.JSONDecodeError):
return {"nodes": {}}
if not isinstance(data, dict) or not isinstance(data.get("nodes"), dict):
return {"nodes": {}}
return data
def _save(self, data: Dict[str, Any]) -> None:
self.path.parent.mkdir(parents=True, exist_ok=True)
tmp = self.path.with_suffix(".json.tmp")
tmp.write_text(json.dumps(data, indent=2), encoding="utf-8")
tmp.replace(self.path)
# ----- public API ---------------------------------------------------
def get(self, name: str) -> Optional[Dict[str, Any]]:
data = self._load()
entry = data["nodes"].get(name)
if entry is None:
return None
return {"name": name, **entry}
def add(self, name: str, url: str, token: str) -> None:
if not isinstance(name, str) or not name:
raise ValueError("node name must be a non-empty string")
if not isinstance(url, str) or not url:
raise ValueError("url must be a non-empty string")
if not isinstance(token, str) or not token:
raise ValueError("token must be a non-empty string")
data = self._load()
data["nodes"][name] = {
"url": url,
"token": token,
"added_at": time.time(),
}
self._save(data)
def remove(self, name: str) -> bool:
data = self._load()
if name in data["nodes"]:
del data["nodes"][name]
self._save(data)
return True
return False
def list_all(self) -> List[Dict[str, Any]]:
data = self._load()
out: List[Dict[str, Any]] = []
for name, entry in sorted(data["nodes"].items()):
out.append({"name": name, **entry})
return out
def resolve(self, chrome_node: Optional[str]) -> Optional[Dict[str, Any]]:
"""Resolve a node name to its entry.
If ``chrome_node`` is provided, return that named node (or None).
If ``chrome_node`` is None, return the sole registered node when
exactly one is registered; otherwise return None (ambiguous or
empty).
"""
if chrome_node:
return self.get(chrome_node)
nodes = self.list_all()
if len(nodes) == 1:
return nodes[0]
return None
+200
View File
@@ -0,0 +1,200 @@
"""Remote node server.
Runs on the machine that will host the Meet bot (typically the user's
Mac laptop with a signed-in Chrome). Exposes a WebSocket endpoint that
accepts signed RPC requests and dispatches them to the existing
``plugins.google_meet.process_manager`` module.
Launched by ``hermes meet node run``.
Token handling
--------------
On first boot we mint 32 hex chars of entropy and persist them at
``$HERMES_HOME/workspace/meetings/node_token.json``. Subsequent boots
reuse the same token so previously-approved gateways don't need to be
re-paired. The operator copies this token out-of-band to the gateway
via ``hermes meet node approve <name> <url> <token>``.
Dependencies
------------
``websockets`` is an optional dep. We import it lazily inside
:meth:`serve` so installing the plugin doesn't require it unless you
actually host a node.
"""
from __future__ import annotations
import json
import secrets
import time
from pathlib import Path
from typing import Any, Dict, Optional
from hermes_constants import get_hermes_home
from plugins.google_meet.node import protocol as _proto
def _default_token_path() -> Path:
return Path(get_hermes_home()) / "workspace" / "meetings" / "node_token.json"
class NodeServer:
"""WebSocket server that executes meet bot RPCs locally."""
def __init__(
self,
host: str = "127.0.0.1",
port: int = 18789,
token_path: Optional[Path] = None,
display_name: str = "hermes-meet-node",
) -> None:
self.host = host
self.port = port
self.display_name = display_name
self.token_path = Path(token_path) if token_path is not None else _default_token_path()
self._token: Optional[str] = None
# ----- token management --------------------------------------------
def ensure_token(self) -> str:
"""Return the persisted shared secret, generating one on first use."""
if self._token:
return self._token
if self.token_path.is_file():
try:
data = json.loads(self.token_path.read_text(encoding="utf-8"))
tok = data.get("token")
if isinstance(tok, str) and tok:
self._token = tok
return tok
except (OSError, json.JSONDecodeError):
pass
tok = secrets.token_hex(16) # 32 hex chars
self.token_path.parent.mkdir(parents=True, exist_ok=True)
tmp = self.token_path.with_suffix(".json.tmp")
tmp.write_text(
json.dumps({"token": tok, "generated_at": time.time()}, indent=2),
encoding="utf-8",
)
# Restrict to owner-read-write only — the token grants full RPC
# access to the meet bot (start, transcribe, speak in meetings).
try:
tmp.chmod(0o600)
except (OSError, NotImplementedError):
# Best-effort on non-POSIX filesystems; mode is set on POSIX.
pass
tmp.replace(self.token_path)
self._token = tok
return tok
def get_token(self) -> str:
"""Alias for :meth:`ensure_token`; does not mutate on subsequent calls."""
return self.ensure_token()
# ----- dispatch -----------------------------------------------------
async def _handle_request(self, msg: Dict[str, Any]) -> Dict[str, Any]:
"""Validate + dispatch a single decoded request envelope.
Always returns a response envelope (success or error); never
raises. Errors from inside the process_manager are wrapped into
the response payload's ``ok``/``error`` keys (which pm already
does) rather than being re-encoded as error envelopes — the
envelope-level error channel is reserved for auth / protocol
failures.
"""
expected = self.ensure_token()
ok, reason = _proto.validate_request(msg, expected)
if not ok:
return _proto.make_error(str(msg.get("id") or ""), reason)
req_id = msg["id"]
t = msg["type"]
payload = msg["payload"]
# Import lazily so test mocks can monkeypatch freely.
from plugins.google_meet import process_manager as pm
try:
if t == "ping":
return {"type": "pong", "id": req_id,
"payload": {"display_name": self.display_name,
"ts": time.time()}}
if t == "start_bot":
# Whitelist kwargs we pass through to pm.start.
kwargs = {
k: payload[k]
for k in ("url", "guest_name", "duration", "headed",
"auth_state", "session_id", "out_dir")
if k in payload
}
if "url" not in kwargs:
return _proto.make_error(req_id, "missing 'url' in payload")
result = pm.start(**kwargs)
return _proto.make_response(req_id, result)
if t == "stop":
reason_arg = payload.get("reason", "requested")
result = pm.stop(reason=reason_arg)
return _proto.make_response(req_id, result)
if t == "status":
return _proto.make_response(req_id, pm.status())
if t == "transcript":
last = payload.get("last")
result = pm.transcript(last=last)
return _proto.make_response(req_id, result)
if t == "say":
# v2 wiring: enqueue into say_queue.jsonl inside the
# active meeting's out_dir when present. The bot-side
# consumer is v3+ (for v1 this is a stub returning ok).
text = payload.get("text", "")
active = pm._read_active() # type: ignore[attr-defined]
enqueued = False
if active and active.get("out_dir"):
queue = Path(active["out_dir"]) / "say_queue.jsonl"
try:
queue.parent.mkdir(parents=True, exist_ok=True)
with queue.open("a", encoding="utf-8") as fh:
fh.write(json.dumps({"text": text, "ts": time.time()}) + "\n")
enqueued = True
except OSError:
enqueued = False
return _proto.make_response(
req_id,
{"ok": True, "enqueued": enqueued, "text": text},
)
except Exception as exc: # noqa: BLE001 — surface any pm crash to client
return _proto.make_error(req_id, f"{type(exc).__name__}: {exc}")
return _proto.make_error(req_id, f"unhandled type: {t!r}")
# ----- server loop --------------------------------------------------
async def serve(self) -> None:
"""Run the WebSocket server until cancelled.
Blocks forever. Callers typically wrap this in ``asyncio.run``.
"""
try:
import websockets # type: ignore
except ImportError as exc:
raise RuntimeError(
"NodeServer.serve requires the 'websockets' package. "
"Install it with: pip install websockets"
) from exc
self.ensure_token()
async def _handler(ws):
async for raw in ws:
try:
msg = _proto.decode(raw if isinstance(raw, str) else raw.decode("utf-8"))
except ValueError as exc:
await ws.send(_proto.encode(_proto.make_error("", f"decode: {exc}")))
continue
reply = await self._handle_request(msg)
await ws.send(_proto.encode(reply))
async with websockets.serve(_handler, self.host, self.port):
# Run until cancelled.
import asyncio
await asyncio.Future()