feat(browser): add persistent Camofox sessions and VNC URL discovery (salvage #4400) (#4419)

Adds two Camofox features:

1. Persistent browser sessions: new `browser.camofox.managed_persistence`
   config option. When enabled, Hermes sends a deterministic profile-scoped
   userId to Camofox so the server maps it to a persistent browser profile
   directory. Cookies, logins, and browser state survive across restarts.
   Default remains ephemeral (random userId per session).

2. VNC URL discovery: Camofox /health endpoint returns vncPort when running
   in headed mode. Hermes constructs the VNC URL and includes it in navigate
   responses so the agent can share it with users.

Also fixes camofox_vision bug where call_llm response object was passed
directly to json.dumps instead of extracting .choices[0].message.content.

Changes from original PR:
- Removed browser_evaluate tool (separate feature, needs own PR)
- Removed snapshot truncation limit change (unrelated)
- Config.yaml only for managed_persistence (no env var, no version bump)
- Rewrote tests to use config mock instead of env var
- Reverted package-lock.json churn

Co-authored-by: analista <psikonetik@gmail.com.com>
This commit is contained in:
Teknium 2026-04-01 04:18:50 -07:00 committed by GitHub
parent 85e96a4638
commit 70744add15
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 485 additions and 10 deletions

View file

@ -34,6 +34,9 @@ from typing import Any, Dict, Optional
import requests
from hermes_cli.config import load_config
from tools.browser_camofox_state import get_camofox_identity
logger = logging.getLogger(__name__)
# ---------------------------------------------------------------------------
@ -42,6 +45,8 @@ logger = logging.getLogger(__name__)
_DEFAULT_TIMEOUT = 30 # seconds per HTTP request
_SNAPSHOT_MAX_CHARS = 80_000 # camofox paginates at this limit
_vnc_url: Optional[str] = None # cached from /health response
_vnc_url_checked = False # only probe once per process
def get_camofox_url() -> str:
@ -56,16 +61,52 @@ def is_camofox_mode() -> bool:
def check_camofox_available() -> bool:
"""Verify the Camofox server is reachable."""
global _vnc_url, _vnc_url_checked
url = get_camofox_url()
if not url:
return False
try:
resp = requests.get(f"{url}/health", timeout=5)
if resp.status_code == 200 and not _vnc_url_checked:
try:
data = resp.json()
vnc_port = data.get("vncPort")
if isinstance(vnc_port, int) and 1 <= vnc_port <= 65535:
from urllib.parse import urlparse
parsed = urlparse(url)
host = parsed.hostname or "localhost"
_vnc_url = f"http://{host}:{vnc_port}"
except (ValueError, KeyError):
pass
_vnc_url_checked = True
return resp.status_code == 200
except Exception:
return False
def get_vnc_url() -> Optional[str]:
"""Return the VNC URL if the Camofox server exposes one, or None."""
if not _vnc_url_checked:
check_camofox_available()
return _vnc_url
def _managed_persistence_enabled() -> bool:
"""Return whether Hermes-managed persistence is enabled for Camofox.
When enabled, sessions use a stable profile-scoped userId so the
Camofox server can map it to a persistent browser profile directory.
When disabled (default), each session gets a random userId (ephemeral).
Controlled by ``browser.camofox.managed_persistence`` in config.yaml.
"""
try:
camofox_cfg = load_config().get("browser", {}).get("camofox", {})
except Exception:
return False
return bool(camofox_cfg.get("managed_persistence"))
# ---------------------------------------------------------------------------
# Session management
# ---------------------------------------------------------------------------
@ -75,16 +116,31 @@ _sessions_lock = threading.Lock()
def _get_session(task_id: Optional[str]) -> Dict[str, Any]:
"""Get or create a camofox session for the given task."""
"""Get or create a camofox session for the given task.
When managed persistence is enabled, uses a deterministic userId
derived from the Hermes profile so the Camofox server can map it
to the same persistent browser profile across restarts.
"""
task_id = task_id or "default"
with _sessions_lock:
if task_id in _sessions:
return _sessions[task_id]
session = {
"user_id": f"hermes_{uuid.uuid4().hex[:10]}",
"tab_id": None,
"session_key": f"task_{task_id[:16]}",
}
if _managed_persistence_enabled():
identity = get_camofox_identity(task_id)
session = {
"user_id": identity["user_id"],
"tab_id": None,
"session_key": identity["session_key"],
"managed": True,
}
else:
session = {
"user_id": f"hermes_{uuid.uuid4().hex[:10]}",
"tab_id": None,
"session_key": f"task_{task_id[:16]}",
"managed": False,
}
_sessions[task_id] = session
return session
@ -172,11 +228,19 @@ def camofox_navigate(url: str, task_id: Optional[str] = None) -> str:
{"userId": session["user_id"], "url": url},
timeout=60,
)
return json.dumps({
result = {
"success": True,
"url": data.get("url", url),
"title": data.get("title", ""),
})
}
vnc = get_vnc_url()
if vnc:
result["vnc_url"] = vnc
result["vnc_hint"] = (
"Browser is visible via VNC. "
"Share this link with the user so they can watch the browser live."
)
return json.dumps(result)
except requests.HTTPError as e:
return json.dumps({"success": False, "error": f"Navigation failed: {e}"})
except requests.ConnectionError:
@ -436,7 +500,7 @@ def camofox_vision(question: str, annotate: bool = False,
except Exception:
_vision_timeout = 120
analysis = call_llm(
response = call_llm(
messages=[{
"role": "user",
"content": [
@ -452,6 +516,7 @@ def camofox_vision(question: str, annotate: bool = False,
task="vision",
timeout=_vision_timeout,
)
analysis = response.choices[0].message.content if response.choices else ""
return json.dumps({
"success": True,

View file

@ -0,0 +1,47 @@
"""Hermes-managed Camofox state helpers.
Provides profile-scoped identity and state directory paths for Camofox
persistent browser profiles. When managed persistence is enabled, Hermes
sends a deterministic userId derived from the active profile so that
Camofox can map it to the same persistent browser profile directory
across restarts.
"""
from __future__ import annotations
import uuid
from pathlib import Path
from typing import Dict, Optional
from hermes_constants import get_hermes_home
CAMOFOX_STATE_DIR_NAME = "browser_auth"
CAMOFOX_STATE_SUBDIR = "camofox"
def get_camofox_state_dir() -> Path:
"""Return the profile-scoped root directory for Camofox persistence."""
return get_hermes_home() / CAMOFOX_STATE_DIR_NAME / CAMOFOX_STATE_SUBDIR
def get_camofox_identity(task_id: Optional[str] = None) -> Dict[str, str]:
"""Return the stable Hermes-managed Camofox identity for this profile.
The user identity is profile-scoped (same Hermes profile = same userId).
The session key is scoped to the logical browser task so newly created
tabs within the same profile reuse the same identity contract.
"""
scope_root = str(get_camofox_state_dir())
logical_scope = task_id or "default"
user_digest = uuid.uuid5(
uuid.NAMESPACE_URL,
f"camofox-user:{scope_root}",
).hex[:10]
session_digest = uuid.uuid5(
uuid.NAMESPACE_URL,
f"camofox-session:{scope_root}:{logical_scope}",
).hex[:16]
return {
"user_id": f"hermes_{user_digest}",
"session_key": f"task_{session_digest}",
}