🔧 Initial dev copy from live

api/__init__.py

@@ -0,0 +1 @@
+"""Hermes Web UI -- API modules."""

api/agents.py

@@ -0,0 +1,150 @@
+"""
+Rose Agents Panel API — Data layer for Hermes WebUI Agents extension.
+Provides Rose + Tier-2 agent status, inbox management, and configuration.
+"""
+
+import json
+import os
+import subprocess
+import threading
+import time
+from pathlib import Path
+from typing import Any
+
+from api.helpers import j
+
+# ── Paths ──────────────────────────────────────────────────────────────────────
+_HERMES_DIR = Path.home() / ".hermes"
+_AGENTS_DIR = _HERMES_DIR / "agents"
+_INBOX_BUS = _HERMES_DIR / "scripts" / "message_bus.py"
+
+# ── Tier-2 Agent Registry ──────────────────────────────────────────────────────
+TIER2_AGENTS = {
+    "lotus":         {"name": "Lotus",         "emoji": "🪷", "domain": "Health, Fitness & Recovery",    "color": "#e91e63"},
+    "forget-me-not": {"name": "Forget-me-not", "emoji": "🌼", "domain": "Calendar, Time & Social",       "color": "#ff9800"},
+    "sunflower":     {"name": "Sunflower",     "emoji": "🌻", "domain": "Finance, Wealth & Subscriptions","color": "#ffeb3b"},
+    "iris":          {"name": "Iris",          "emoji": "⚜️",  "domain": "Career, Learning & Focus",       "color": "#9c27b0"},
+    "ivy":           {"name": "Ivy",           "emoji": "🌿", "domain": "Smart Home & Environment",      "color": "#4caf50"},
+    "dandelion":     {"name": "Dandelion",     "emoji": "🛡️", "domain": "Communication Triage",          "color": "#03a9f4"},
+    "root":          {"name": "Root",           "emoji": "🌳", "domain": "DevOps, Logs & System Health",  "color": "#795548"},
+}
+
+ROSE_META = {
+    "name": "Rose",
+    "emoji": "🌹",
+    "domain": "Orchestrator & Main Interface",
+    "color": "#f44336",
+}
+
+# ── Helpers ───────────────────────────────────────────────────────────────────
+
+def _get_process_status(agent_name: str) -> dict:
+    """Check if an agent process is running via ps."""
+    try:
+        result = subprocess.run(
+            ["pgrep", "-f", f"hermes.*--agent\\s+{agent_name}|message_bus.*--agent\\s+{agent_name}"],
+            capture_output=True, text=True
+        )
+        running = bool(result.stdout.strip())
+        pid = int(result.stdout.strip().split()[0]) if running else None
+        return {"running": running, "pid": pid}
+    except Exception:
+        return {"running": False, "pid": None}
+
+def _get_inbox_count(agent_name: str) -> int:
+    """Count messages in agent inbox via message_bus.py."""
+    try:
+        result = subprocess.run(
+            ["/usr/bin/python3", str(_INBOX_BUS), "check", "--agent", agent_name],
+            capture_output=True, text=True, timeout=5
+        )
+        if result.returncode == 0:
+            data = json.loads(result.stdout)
+            return data.get("pending", 0)
+    except Exception:
+        pass
+    return 0
+
+def _read_inbox(agent_name: str, limit: int = 20) -> list[dict]:
+    """Read messages from agent inbox."""
+    inbox_path = _AGENTS_DIR / agent_name / "inbox.json"
+    if not inbox_path.exists():
+        return []
+    try:
+        with open(inbox_path, "r") as f:
+            data = json.load(f)
+        messages = data if isinstance(data, list) else data.get("messages", [])
+        return messages[-limit:]
+    except (json.JSONDecodeError, IOError):
+        return []
+
+# ── API Functions ─────────────────────────────────────────────────────────────
+
+def list_agents() -> dict:
+    """Return status for Rose + all Tier-2 agents."""
+    agents = []
+
+    # Rose (the orchestrator)
+    rose_running = True  # Rose IS the gateway/webui
+    rose_inbox_count = _get_inbox_count("rose")
+    agents.append({
+        "id": "rose",
+        "name": ROSE_META["name"],
+        "emoji": ROSE_META["emoji"],
+        "domain": ROSE_META["domain"],
+        "color": ROSE_META["color"],
+        "tier": "orchestrator",
+        "running": rose_running,
+        "pid": None,
+        "inbox_count": rose_inbox_count,
+    })
+
+    # Tier-2 agents
+    for agent_id, meta in TIER2_AGENTS.items():
+        status = _get_process_status(agent_id)
+        inbox_count = _get_inbox_count(agent_id) if status["running"] else 0
+        agents.append({
+            "id": agent_id,
+            "name": meta["name"],
+            "emoji": meta["emoji"],
+            "domain": meta["domain"],
+            "color": meta["color"],
+            "tier": "tier2",
+            "running": status["running"],
+            "pid": status["pid"],
+            "inbox_count": inbox_count,
+        })
+
+    return {"agents": agents}
+
+def get_agent_inbox(agent_id: str, limit: int = 20) -> dict:
+    """Return inbox messages for a specific agent."""
+    if agent_id not in TIER2_AGENTS and agent_id != "rose":
+        return {"error": f"Unknown agent: {agent_id}"}
+
+    messages = _read_inbox(agent_id, limit)
+    return {
+        "agent_id": agent_id,
+        "agent_name": TIER2_AGENTS.get(agent_id, {}).get("name", "Rose"),
+        "messages": messages,
+    }
+
+def get_agent_config(agent_id: str) -> dict:
+    """Return configuration for a specific agent (soul.md path, etc)."""
+    if agent_id == "rose":
+        return {
+            "id": "rose",
+            "name": "Rose",
+            "soul_path": str(_HERMES_DIR / "rose.md"),
+            "memory_path": str(_HERMES_DIR / "memory.json"),
+        }
+    elif agent_id in TIER2_AGENTS:
+        soul_path = _AGENTS_DIR / agent_id / "soul.md"
+        inbox_path = _AGENTS_DIR / agent_id / "inbox.json"
+        return {
+            "id": agent_id,
+            "name": TIER2_AGENTS[agent_id]["name"],
+            "soul_path": str(soul_path) if soul_path.exists() else None,
+            "inbox_path": str(inbox_path),
+        }
+    return {"error": f"Unknown agent: {agent_id}"}

api/auth.py

@@ -0,0 +1,204 @@
+"""
+Hermes Web UI -- Optional password authentication.
+Off by default. Enable by setting HERMES_WEBUI_PASSWORD env var
+or configuring a password in the Settings panel.
+"""
+import hashlib
+import hmac
+import http.cookies
+import logging
+import os
+import secrets
+import time
+
+from api.config import STATE_DIR, load_settings
+
+logger = logging.getLogger(__name__)
+
+# ── Public paths (no auth required) ─────────────────────────────────────────
+PUBLIC_PATHS = frozenset({
+    '/login', '/health', '/favicon.ico',
+    '/api/auth/login', '/api/auth/status',
+})
+
+COOKIE_NAME = 'hermes_session'
+SESSION_TTL = 86400  # 24 hours
+
+# Active sessions: token -> expiry timestamp
+_sessions = {}
+
+# ── Login rate limiter ──────────────────────────────────────────────────────
+_login_attempts = {}  # ip -> [timestamp, ...]
+_LOGIN_MAX_ATTEMPTS = 5
+_LOGIN_WINDOW = 60  # seconds
+
+def _check_login_rate(ip: str) -> bool:
+    """Return True if the IP is allowed to attempt login."""
+    now = time.time()
+    attempts = _login_attempts.get(ip, [])
+    # Prune old attempts
+    attempts = [t for t in attempts if now - t < _LOGIN_WINDOW]
+    _login_attempts[ip] = attempts
+    return len(attempts) < _LOGIN_MAX_ATTEMPTS
+
+def _record_login_attempt(ip: str) -> None:
+    now = time.time()
+    attempts = _login_attempts.get(ip, [])
+    attempts.append(now)
+    _login_attempts[ip] = attempts
+
+
+def _signing_key():
+    """Return a random signing key, generating and persisting one on first call."""
+    key_file = STATE_DIR / '.signing_key'
+    if key_file.exists():
+        try:
+            raw = key_file.read_bytes()
+            if len(raw) >= 32:
+                return raw[:32]
+        except Exception:
+            logger.debug("Failed to read signing key from file, generating new key")
+    # Generate a new random key
+    key = secrets.token_bytes(32)
+    try:
+        STATE_DIR.mkdir(parents=True, exist_ok=True)
+        key_file.write_bytes(key)
+        key_file.chmod(0o600)
+    except Exception:
+        logger.debug("Failed to persist signing key, using in-memory key only")
+    return key
+
+
+def _hash_password(password):
+    """PBKDF2-SHA256 with 600k iterations (OWASP recommendation).
+    Salt is the persisted random signing key, which is secret and unique per
+    installation. This keeps the stored hash format a plain hex string
+    (no format change to settings.json) while replacing the predictable
+    STATE_DIR-derived salt from the original implementation."""
+    salt = _signing_key()
+    dk = hashlib.pbkdf2_hmac('sha256', password.encode(), salt, 600_000)
+    return dk.hex()
+
+
+def get_password_hash() -> str | None:
+    """Return the active password hash, or None if auth is disabled.
+    Priority: env var > settings.json."""
+    env_pw = os.getenv('HERMES_WEBUI_PASSWORD', '').strip()
+    if env_pw:
+        return _hash_password(env_pw)
+    settings = load_settings()
+    return settings.get('password_hash') or None
+
+
+def is_auth_enabled() -> bool:
+    """True if a password is configured (env var or settings)."""
+    return get_password_hash() is not None
+
+
+def verify_password(plain) -> bool:
+    """Verify a plaintext password against the stored hash."""
+    expected = get_password_hash()
+    if not expected:
+        return False
+    return hmac.compare_digest(_hash_password(plain), expected)
+
+
+def create_session() -> str:
+    """Create a new auth session. Returns signed cookie value."""
+    token = secrets.token_hex(32)
+    _sessions[token] = time.time() + SESSION_TTL
+    sig = hmac.new(_signing_key(), token.encode(), hashlib.sha256).hexdigest()[:32]
+    return f"{token}.{sig}"
+
+
+def _prune_expired_sessions():
+    """Remove all expired session entries to prevent unbounded memory growth."""
+    now = time.time()
+    for token in [t for t, exp in _sessions.items() if now > exp]:
+        _sessions.pop(token, None)
+
+
+def verify_session(cookie_value) -> bool:
+    """Verify a signed session cookie. Returns True if valid and not expired."""
+    if not cookie_value or '.' not in cookie_value:
+        return False
+    _prune_expired_sessions()  # lazy cleanup on every verification attempt
+    token, sig = cookie_value.rsplit('.', 1)
+    expected_sig = hmac.new(_signing_key(), token.encode(), hashlib.sha256).hexdigest()[:32]
+    if not hmac.compare_digest(sig, expected_sig):
+        return False
+    expiry = _sessions.get(token)
+    if not expiry or time.time() > expiry:
+        _sessions.pop(token, None)
+        return False
+    return True
+
+
+def invalidate_session(cookie_value) -> None:
+    """Remove a session token."""
+    if cookie_value and '.' in cookie_value:
+        token = cookie_value.rsplit('.', 1)[0]
+        _sessions.pop(token, None)
+
+
+def parse_cookie(handler) -> str | None:
+    """Extract the auth cookie from the request headers."""
+    cookie_header = handler.headers.get('Cookie', '')
+    if not cookie_header:
+        return None
+    cookie = http.cookies.SimpleCookie()
+    try:
+        cookie.load(cookie_header)
+    except http.cookies.CookieError:
+        return None
+    morsel = cookie.get(COOKIE_NAME)
+    return morsel.value if morsel else None
+
+
+def check_auth(handler, parsed) -> bool:
+    """Check if request is authorized. Returns True if OK.
+    If not authorized, sends 401 (API) or 302 redirect (page) and returns False."""
+    if not is_auth_enabled():
+        return True
+    # Public paths don't require auth
+    if parsed.path in PUBLIC_PATHS or parsed.path.startswith('/static/'):
+        return True
+    # Check session cookie
+    cookie_val = parse_cookie(handler)
+    if cookie_val and verify_session(cookie_val):
+        return True
+    # Not authorized
+    if parsed.path.startswith('/api/'):
+        handler.send_response(401)
+        handler.send_header('Content-Type', 'application/json')
+        handler.end_headers()
+        handler.wfile.write(b'{"error":"Authentication required"}')
+    else:
+        handler.send_response(302)
+        handler.send_header('Location', '/login')
+        handler.end_headers()
+    return False
+
+
+def set_auth_cookie(handler, cookie_value) -> None:
+    """Set the auth cookie on the response."""
+    cookie = http.cookies.SimpleCookie()
+    cookie[COOKIE_NAME] = cookie_value
+    cookie[COOKIE_NAME]['httponly'] = True
+    cookie[COOKIE_NAME]['samesite'] = 'Lax'
+    cookie[COOKIE_NAME]['path'] = '/'
+    cookie[COOKIE_NAME]['max-age'] = str(SESSION_TTL)
+    # Set Secure flag when connection is HTTPS
+    if getattr(handler.request, 'getpeercert', None) is not None or handler.headers.get('X-Forwarded-Proto', '') == 'https':
+        cookie[COOKIE_NAME]['secure'] = True
+    handler.send_header('Set-Cookie', cookie[COOKIE_NAME].OutputString())
+
+
+def clear_auth_cookie(handler) -> None:
+    """Clear the auth cookie on the response."""
+    cookie = http.cookies.SimpleCookie()
+    cookie[COOKIE_NAME] = ''
+    cookie[COOKIE_NAME]['httponly'] = True
+    cookie[COOKIE_NAME]['path'] = '/'
+    cookie[COOKIE_NAME]['max-age'] = '0'
+    handler.send_header('Set-Cookie', cookie[COOKIE_NAME].OutputString())

api/clarify.py

@@ -0,0 +1,128 @@
+"""Clarify prompt state for the WebUI.
+
+This mirrors the approval flow structure, but the response is a free-form
+clarification string instead of an approval decision.
+"""
+
+from __future__ import annotations
+
+import threading
+from typing import Optional
+
+
+_lock = threading.Lock()
+_pending: dict[str, dict] = {}
+_gateway_queues: dict[str, list] = {}
+_gateway_notify_cbs: dict[str, object] = {}
+
+
+class _ClarifyEntry:
+    """One pending clarify request inside a session."""
+
+    __slots__ = ("event", "data", "result")
+
+    def __init__(self, data: dict):
+        self.event = threading.Event()
+        self.data = data
+        self.result: Optional[str] = None
+
+
+def register_gateway_notify(session_key: str, cb) -> None:
+    """Register a per-session callback for sending clarify requests to the UI."""
+    with _lock:
+        _gateway_notify_cbs[session_key] = cb
+
+
+def _clear_queue_locked(session_key: str) -> list[_ClarifyEntry]:
+    entries = _gateway_queues.pop(session_key, [])
+    _pending.pop(session_key, None)
+    return entries
+
+
+def unregister_gateway_notify(session_key: str) -> None:
+    """Unregister the per-session callback and unblock any waiting clarify prompt."""
+    with _lock:
+        _gateway_notify_cbs.pop(session_key, None)
+        entries = _clear_queue_locked(session_key)
+    for entry in entries:
+        entry.event.set()
+
+
+def clear_pending(session_key: str) -> int:
+    """Clear any pending clarify prompts for the session without removing the callback."""
+    with _lock:
+        entries = _clear_queue_locked(session_key)
+    for entry in entries:
+        entry.event.set()
+    return len(entries)
+
+
+def submit_pending(session_key: str, data: dict) -> _ClarifyEntry:
+    """Queue a pending clarify request and notify the UI callback if registered."""
+    with _lock:
+        queue = _gateway_queues.setdefault(session_key, [])
+        # De-duplicate while unresolved: if the most recent pending clarify is
+        # semantically identical, reuse it instead of stacking duplicates.
+        if queue:
+            last = queue[-1]
+            if (
+                str(last.data.get("question", "")) == str(data.get("question", ""))
+                and list(last.data.get("choices_offered") or [])
+                == list(data.get("choices_offered") or [])
+            ):
+                entry = last
+                cb = _gateway_notify_cbs.get(session_key)
+                # Keep _pending aligned to the oldest unresolved entry.
+                _pending[session_key] = queue[0].data
+                if cb:
+                    try:
+                        cb(dict(entry.data))
+                    except Exception:
+                        pass
+                return entry
+
+        entry = _ClarifyEntry(data)
+        queue.append(entry)
+        _pending[session_key] = queue[0].data
+        cb = _gateway_notify_cbs.get(session_key)
+    if cb:
+        try:
+            cb(data)
+        except Exception:
+            pass
+    return entry
+
+
+def get_pending(session_key: str) -> dict | None:
+    """Return the oldest pending clarify request for this session, if any."""
+    with _lock:
+        queue = _gateway_queues.get(session_key) or []
+        if queue:
+            return dict(queue[0].data)
+        pending = _pending.get(session_key)
+        return dict(pending) if pending else None
+
+
+def has_pending(session_key: str) -> bool:
+    with _lock:
+        return bool(_gateway_queues.get(session_key))
+
+
+def resolve_clarify(session_key: str, response: str, resolve_all: bool = False) -> int:
+    """Resolve the oldest pending clarify request for a session."""
+    with _lock:
+        queue = _gateway_queues.get(session_key)
+        if not queue:
+            _pending.pop(session_key, None)
+            return 0
+        entries = list(queue) if resolve_all else [queue.pop(0)]
+        if queue:
+            _pending[session_key] = queue[0].data
+        else:
+            _clear_queue_locked(session_key)
+    count = 0
+    for entry in entries:
+        entry.result = response
+        entry.event.set()
+        count += 1
+    return count

api/commands.py

@@ -0,0 +1,56 @@
+"""Expose hermes-agent's COMMAND_REGISTRY to the webui frontend.
+
+This module is the single integration point with hermes_cli.commands.
+If hermes-agent is unavailable the endpoint degrades to an empty list
+so the frontend can still load with WEBUI_ONLY commands.
+"""
+from __future__ import annotations
+import logging
+from typing import Any
+
+logger = logging.getLogger(__name__)
+
+# Commands that are gateway_only in the agent registry -- webui never
+# wants to expose them (sethome, restart, update etc.) even if a future
+# agent version drops the gateway_only flag. /commands is the agent's
+# own command-listing command; webui has its own /help that calls
+# cmdHelp() locally, so /commands would be redundant and confusing.
+_NEVER_EXPOSE: frozenset[str] = frozenset({
+    'sethome', 'restart', 'update', 'commands',
+})
+
+
+def list_commands(_registry=None) -> list[dict[str, Any]]:
+    """Return COMMAND_REGISTRY entries as JSON-friendly dicts.
+
+    Returns empty list if hermes_cli is not installed (graceful
+    degradation -- the frontend has its own fallback minimum set).
+
+    Args:
+        _registry: Optional injected registry for testing. When None
+            (production), imports COMMAND_REGISTRY from hermes_cli.
+    """
+    if _registry is None:
+        try:
+            from hermes_cli.commands import COMMAND_REGISTRY as _registry
+        except ImportError:
+            logger.warning("hermes_cli.commands not importable -- /api/commands returns []")
+            return []
+
+    out: list[dict[str, Any]] = []
+    for cmd in _registry:
+        if cmd.gateway_only:
+            continue
+        if cmd.name in _NEVER_EXPOSE:
+            continue
+        out.append({
+            'name': cmd.name,
+            'description': cmd.description,
+            'category': cmd.category,
+            'aliases': list(cmd.aliases),
+            'args_hint': cmd.args_hint,
+            'subcommands': list(cmd.subcommands),
+            'cli_only': bool(cmd.cli_only),
+            'gateway_only': bool(cmd.gateway_only),
+        })
+    return out

api/gateway_watcher.py

@@ -0,0 +1,229 @@
+"""
+Hermes Web UI -- Gateway session watcher.
+
+Background daemon thread that polls state.db every 5 seconds for changes
+to gateway sessions (telegram, discord, slack, etc.). When changes are
+detected, it pushes notifications to all subscribed SSE clients.
+
+This enables real-time session list updates in the sidebar without
+requiring any changes to hermes-agent.
+"""
+import hashlib
+import json
+import logging
+import os
+import queue
+import sqlite3
+import threading
+import time
+from pathlib import Path
+
+from api.config import HOME
+
+logger = logging.getLogger(__name__)
+
+
+# ── State hash tracking ─────────────────────────────────────────────────────
+
+def _snapshot_hash(sessions: list) -> str:
+    """Create a lightweight hash of session IDs and timestamps for change detection."""
+    key = '|'.join(
+        f"{s['session_id']}:{s.get('updated_at', 0)}:{s.get('message_count', 0)}"
+        for s in sorted(sessions, key=lambda x: x['session_id'])
+    )
+    return hashlib.md5(key.encode(), usedforsecurity=False).hexdigest()
+
+
+# ── DB resolution (shared pattern with state_sync.py) ──────────────────────
+
+def _get_state_db_path() -> Path:
+    """Resolve state.db path for the active profile."""
+    try:
+        from api.profiles import get_active_hermes_home
+        hermes_home = Path(get_active_hermes_home()).expanduser().resolve()
+    except Exception:
+        hermes_home = Path(os.getenv('HERMES_HOME', str(HOME / '.hermes'))).expanduser().resolve()
+    return hermes_home / 'state.db'
+
+
+def _get_agent_sessions_from_db() -> list:
+    """Read all non-webui sessions from state.db.
+    Returns list of session dicts, or empty list on any error.
+    """
+    db_path = _get_state_db_path()
+    if not db_path.exists():
+        return []
+
+    try:
+        with sqlite3.connect(str(db_path)) as conn:
+            conn.row_factory = sqlite3.Row
+            cur = conn.cursor()
+            cur.execute("""
+                SELECT s.id, s.title, s.model, s.message_count,
+                       s.started_at, s.source,
+                       MAX(m.timestamp) AS last_activity
+                FROM sessions s
+                LEFT JOIN messages m ON m.session_id = s.id
+                WHERE s.source IS NOT NULL AND s.source != 'webui'
+                GROUP BY s.id
+                HAVING COUNT(m.id) > 0
+                ORDER BY COALESCE(MAX(m.timestamp), s.started_at) DESC
+                LIMIT 200
+            """)
+            sessions = []
+            for row in cur.fetchall():
+                sessions.append({
+                    'session_id': row['id'],
+                    'title': row['title'] or 'Agent Session',
+                    'model': row['model'] or None,
+                    'message_count': row['message_count'] or 0,
+                    'created_at': row['started_at'],
+                    'updated_at': row['last_activity'] or row['started_at'],
+                    'source': row['source'] or 'cli',
+                })
+            return sessions
+    except Exception:
+        return []
+
+
+# ── GatewayWatcher ──────────────────────────────────────────────────────────
+
+class GatewayWatcher:
+    """Background thread that polls state.db for agent session changes.
+
+    Usage:
+        watcher = GatewayWatcher()
+        watcher.start()
+        q = watcher.subscribe()
+        # ... receive change events via q.get() ...
+        watcher.unsubscribe(q)
+        watcher.stop()
+    """
+
+    POLL_INTERVAL = 5  # seconds between polls
+    SUBSCRIBER_TIMEOUT = 30  # seconds before sending keepalive comment
+
+    def __init__(self):
+        self._subscribers: list[queue.Queue] = []
+        self._sub_lock = threading.Lock()
+        self._stop_event = threading.Event()
+        self._thread: threading.Thread | None = None
+        self._last_hash: str = ''
+        self._last_sessions: list = []
+
+    def start(self):
+        """Start the watcher daemon thread."""
+        if self._thread and self._thread.is_alive():
+            return
+        self._stop_event.clear()
+        self._thread = threading.Thread(target=self._poll_loop, daemon=True, name='gateway-watcher')
+        self._thread.start()
+
+    def stop(self):
+        """Stop the watcher thread."""
+        self._stop_event.set()
+        # Wake up any subscribers
+        with self._sub_lock:
+            for q in self._subscribers:
+                try:
+                    q.put(None)  # sentinel
+                except Exception:
+                    logger.debug("Failed to send sentinel to subscriber")
+        if self._thread:
+            self._thread.join(timeout=3)
+            self._thread = None
+
+    def subscribe(self) -> queue.Queue:
+        """Subscribe to change events. Returns a queue.Queue.
+        Events are dicts: {'type': 'sessions_changed', 'sessions': [...]}
+        A None sentinel means the watcher is stopping.
+        """
+        q = queue.Queue(maxsize=10)
+        with self._sub_lock:
+            self._subscribers.append(q)
+        return q
+
+    def unsubscribe(self, q: queue.Queue):
+        """Remove a subscriber queue."""
+        with self._sub_lock:
+            try:
+                self._subscribers.remove(q)
+            except ValueError:
+                pass
+
+    def _notify_subscribers(self, sessions: list):
+        """Push change event to all subscribers."""
+        event = {
+            'type': 'sessions_changed',
+            'sessions': sessions,
+        }
+        with self._sub_lock:
+            dead = []
+            for q in self._subscribers:
+                try:
+                    q.put_nowait(event)
+                except queue.Full:
+                    dead.append(q)  # remove slow consumers
+                except Exception:
+                    dead.append(q)
+            for q in dead:
+                try:
+                    self._subscribers.remove(q)
+                except ValueError:
+                    pass
+                # Send a None sentinel so the SSE handler unblocks, closes,
+                # and lets the browser's EventSource auto-reconnect.
+                try:
+                    q.put_nowait(None)
+                except Exception:
+                    logger.debug("Failed to send sentinel to dead subscriber")
+
+    def _poll_loop(self):
+        """Main polling loop. Runs in a daemon thread."""
+        while not self._stop_event.is_set():
+            try:
+                sessions = _get_agent_sessions_from_db()
+                current_hash = _snapshot_hash(sessions)
+
+                if current_hash != self._last_hash:
+                    self._last_hash = current_hash
+                    self._last_sessions = sessions
+                    self._notify_subscribers(sessions)
+            except Exception:
+                logger.debug("Error in gateway watcher poll loop", exc_info=True)
+
+            # Sleep in small increments so we can stop promptly
+            for _ in range(self.POLL_INTERVAL * 10):
+                if self._stop_event.is_set():
+                    return
+                time.sleep(0.1)
+
+
+# ── Module-level singleton ─────────────────────────────────────────────────
+
+_watcher: GatewayWatcher | None = None
+_watcher_lock = threading.Lock()
+
+
+def start_watcher():
+    """Start the global gateway watcher (idempotent)."""
+    global _watcher
+    with _watcher_lock:
+        if _watcher is None:
+            _watcher = GatewayWatcher()
+            _watcher.start()
+
+
+def stop_watcher():
+    """Stop the global gateway watcher."""
+    global _watcher
+    with _watcher_lock:
+        if _watcher is not None:
+            _watcher.stop()
+            _watcher = None
+
+
+def get_watcher() -> GatewayWatcher | None:
+    """Get the global watcher instance (or None if not started)."""
+    with _watcher_lock:
+        return _watcher

api/gateways.py

@@ -0,0 +1,265 @@
+"""
+Gateway management API for Hermes WebUI.
+
+Provides endpoints to list, start, stop, restart, and add gateway connections
+like Telegram, OpenClaw, and other Hermes gateway types.
+"""
+
+import os
+import re
+import subprocess
+import threading
+import time
+from pathlib import Path
+from typing import Optional
+
+# In-memory gateway registry (gateway_name -> info)
+_gateways: dict[str, dict] = {}
+_gateways_lock = threading.Lock()
+
+# Track running gateway processes (gateway_name -> PID)
+_gateway_pids: dict[str, int] = {}
+
+
+def _get_hermes_home() -> Path:
+    """Get the Hermes home directory."""
+    hermes_home = os.environ.get("HERMES_HOME", "")
+    if hermes_home and str(Path(hermes_home).parent) != "profiles":
+        return Path(hermes_home)
+    return Path.home() / ".hermes"
+
+
+def _get_gateway_pid(name: str) -> Optional[int]:
+    """Get PID of a running gateway process by name."""
+    try:
+        result = subprocess.run(
+            ["pgrep", "-f", f"hermes.*gateway.*{name}"],
+            capture_output=True, text=True
+        )
+        if result.returncode == 0 and result.stdout.strip():
+            pids = result.stdout.strip().split("\n")
+            return int(pids[0]) if pids else None
+    except Exception:
+        pass
+    return _gateway_pids.get(name)
+
+
+def _is_gateway_running(name: str) -> bool:
+    """Check if a gateway process is running."""
+    pid = _get_gateway_pid(name)
+    if pid:
+        try:
+            os.kill(pid, 0)
+            return True
+        except OSError:
+            pass
+    return False
+
+
+def _get_gateway_info(name: str) -> str:
+    """Get additional info about a gateway."""
+    pid = _get_gateway_pid(name)
+    if pid:
+        try:
+            result = subprocess.run(
+                ["ps", "-p", str(pid), "-o", "etime=", "-o", "args="],
+                capture_output=True, text=True
+            )
+            if result.returncode == 0:
+                parts = result.stdout.strip().split(None, 1)
+                if len(parts) >= 2:
+                    elapsed = parts[0]
+                    return f"PID {pid} · running {elapsed}"
+        except Exception:
+            pass
+        return f"PID {pid}"
+    return ""
+
+
+def _detect_telegram_gateway() -> dict:
+    """Detect if Telegram gateway is configured and running."""
+    hermes_home = _get_hermes_home()
+    gateway_running = False
+    info = ""
+
+    # Check if there's a telegram gateway config
+    config_paths = [
+        hermes_home / "gateways" / "telegram",
+        hermes_home / "gateway" / "telegram",
+        hermes_home / ".env",
+    ]
+
+    has_config = False
+    for p in config_paths:
+        if p.exists():
+            has_config = True
+            break
+
+    if has_config:
+        gateway_running = _is_gateway_running("telegram")
+        if gateway_running:
+            info = _get_gateway_info("telegram")
+
+    return {
+        "name": "telegram",
+        "type": "telegram",
+        "running": gateway_running,
+        "info": info,
+        "has_config": has_config,
+    }
+
+
+def _detect_openclaw_gateway() -> dict:
+    """Detect if OpenClaw gateway is configured and running."""
+    hermes_home = _get_hermes_home()
+    gateway_running = False
+    info = ""
+
+    config_paths = [
+        hermes_home / "gateways" / "openclaw",
+        hermes_home / "gateway" / "openclaw",
+    ]
+
+    has_config = False
+    for p in config_paths:
+        if p.exists():
+            has_config = True
+            break
+
+    if has_config:
+        gateway_running = _is_gateway_running("openclaw")
+        if gateway_running:
+            info = _get_gateway_info("openclaw")
+
+    return {
+        "name": "openclaw",
+        "type": "openclaw",
+        "running": gateway_running,
+        "info": info,
+        "has_config": has_config,
+    }
+
+
+def _discover_gateways() -> list[dict]:
+    """Discover all available and configured gateways."""
+    gateways = []
+
+    # Always show telegram if detected
+    telegram = _detect_telegram_gateway()
+    gateways.append(telegram)
+
+    # Check for openclaw
+    openclaw = _detect_openclaw_gateway()
+    gateways.append(openclaw)
+
+    # Add any manually registered gateways
+    with _gateways_lock:
+        for name, info in _gateways.items():
+            if not any(g["name"] == name for g in gateways):
+                running = _is_gateway_running(name)
+                gw_info = _get_gateway_info(name) if running else ""
+                gateways.append({
+                    "name": name,
+                    "type": info.get("type", "unknown"),
+                    "running": running,
+                    "info": gw_info,
+                    "has_config": True,
+                })
+
+    return gateways
+
+
+def list_gateways_api() -> list[dict]:
+    """List all gateways with their status."""
+    return _discover_gateways()
+
+
+def start_gateway_api(name: str) -> dict:
+    """Start a gateway by name."""
+    # Check if already running
+    if _is_gateway_running(name):
+        raise RuntimeError(f"Gateway '{name}' is already running")
+
+    hermes_home = _get_hermes_home()
+
+    # Determine the gateway type and command
+    if name == "telegram":
+        cmd = ["hermes", "gateway", "run", "--type", "telegram"]
+    elif name == "openclaw":
+        cmd = ["hermes", "gateway", "run", "--type", "openclaw"]
+    else:
+        cmd = ["hermes", "gateway", "run", "--name", name]
+
+    # Start the gateway process
+    try:
+        proc = subprocess.Popen(
+            cmd,
+            cwd=str(hermes_home),
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+            start_new_session=True
+        )
+        _gateway_pids[name] = proc.pid
+
+        # Give it a moment to start
+        time.sleep(1)
+
+        if proc.poll() is not None:
+            # Process already terminated
+            stdout, stderr = proc.communicate()
+            raise RuntimeError(f"Gateway failed to start: {stderr.decode()[:200]}")
+
+        return {"ok": True, "message": f"Gateway '{name}' started", "pid": proc.pid}
+
+    except FileNotFoundError:
+        raise RuntimeError("hermes CLI not found in PATH. Is Hermes installed?")
+    except Exception as e:
+        raise RuntimeError(f"Failed to start gateway: {e}")
+
+
+def stop_gateway_api(name: str) -> dict:
+    """Stop a gateway by name."""
+    pid = _get_gateway_pid(name)
+
+    if not pid:
+        raise RuntimeError(f"Gateway '{name}' is not running")
+
+    try:
+        os.kill(pid, 9)  # SIGKILL
+        time.sleep(0.5)
+        if name in _gateway_pids:
+            del _gateway_pids[name]
+        return {"ok": True, "message": f"Gateway '{name}' stopped"}
+    except OSError as e:
+        raise RuntimeError(f"Failed to stop gateway: {e}")
+
+
+def restart_gateway_api(name: str) -> dict:
+    """Restart a gateway by name."""
+    # Check if running first
+    if not _is_gateway_running(name):
+        raise RuntimeError(f"Gateway '{name}' is not running")
+
+    # Stop it
+    stop_gateway_api(name)
+    time.sleep(1)
+
+    # Start it again
+    return start_gateway_api(name)
+
+
+def add_gateway_api(name: str, gw_type: str = "telegram") -> dict:
+    """Register a new gateway."""
+    # Validate name
+    if not re.match(r"^[a-zA-Z0-9][a-zA-Z0-9_-]{0,63}$", name):
+        raise ValueError("Invalid gateway name")
+
+    # Check if already exists
+    for g in _discover_gateways():
+        if g["name"] == name:
+            raise FileExistsError(f"Gateway '{name}' already exists")
+
+    with _gateways_lock:
+        _gateways[name] = {"type": gw_type, "registered_at": time.time()}
+
+    return {"ok": True, "message": f"Gateway '{name}' added as {gw_type}"}

api/helpers.py

@@ -0,0 +1,175 @@
+"""
+Hermes Web UI -- HTTP helper functions.
+"""
+import json as _json
+import re as _re
+from pathlib import Path
+from api.config import IMAGE_EXTS, MD_EXTS
+
+
+def require(body: dict, *fields) -> None:
+    """Phase D: Validate required fields. Raises ValueError with clean message."""
+    missing = [f for f in fields if not body.get(f) and body.get(f) != 0]
+    if missing:
+        raise ValueError(f"Missing required field(s): {', '.join(missing)}")
+
+
+def bad(handler, msg, status: int=400):
+    """Return a clean JSON error response."""
+    return j(handler, {'error': msg}, status=status)
+
+
+def _sanitize_error(e: Exception) -> str:
+    """Strip filesystem paths from exception messages before returning to client."""
+    import re
+    msg = str(e)
+    # Remove absolute paths (Unix and Windows)
+    msg = re.sub(r'(?:(?:/[a-zA-Z0-9_.-]+)+|(?:[A-Z]:\\[^\s]+))', '<path>', msg)
+    return msg
+
+
+def safe_resolve(root: Path, requested: str) -> Path:
+    """Resolve a relative path inside root, raising ValueError on traversal."""
+    resolved = (root / requested).resolve()
+    resolved.relative_to(root.resolve())  # raises ValueError if outside root
+    return resolved
+
+
+def _security_headers(handler):
+    """Add security headers to every response."""
+    handler.send_header('X-Content-Type-Options', 'nosniff')
+    handler.send_header('X-Frame-Options', 'DENY')
+    handler.send_header('Referrer-Policy', 'same-origin')
+    handler.send_header(
+        'Content-Security-Policy',
+        "default-src 'self'; "
+        "script-src 'self' 'unsafe-inline' https://cdn.jsdelivr.net; "
+        "style-src 'self' 'unsafe-inline' https://cdn.jsdelivr.net; "
+        "img-src 'self' data: https: blob:; font-src 'self' data: https://cdn.jsdelivr.net; connect-src 'self'; "
+        "base-uri 'self'; form-action 'self'"
+    )
+    handler.send_header(
+        'Permissions-Policy',
+        'camera=(), microphone=(self), geolocation=()'
+    )
+
+
+def j(handler, payload, status: int=200) -> None:
+    """Send a JSON response."""
+    body = _json.dumps(payload, ensure_ascii=False, indent=2).encode('utf-8')
+    handler.send_response(status)
+    handler.send_header('Content-Type', 'application/json; charset=utf-8')
+    handler.send_header('Content-Length', str(len(body)))
+    handler.send_header('Cache-Control', 'no-store')
+    _security_headers(handler)
+    handler.end_headers()
+    handler.wfile.write(body)
+
+
+def t(handler, payload, status: int=200, content_type: str='text/plain; charset=utf-8') -> None:
+    """Send a plain text or HTML response."""
+    body = payload if isinstance(payload, bytes) else str(payload).encode('utf-8')
+    handler.send_response(status)
+    handler.send_header('Content-Type', content_type)
+    handler.send_header('Content-Length', str(len(body)))
+    handler.send_header('Cache-Control', 'no-store')
+    _security_headers(handler)
+    handler.end_headers()
+    handler.wfile.write(body)
+
+
+MAX_BODY_BYTES = 20 * 1024 * 1024  # 20MB limit for non-upload POST bodies
+
+
+# ── Credential redaction ──────────────────────────────────────────────────────
+
+def _build_redact_fn():
+    """Return redact_sensitive_text from hermes-agent if available, else a fallback."""
+    try:
+        from agent.redact import redact_sensitive_text
+        return redact_sensitive_text
+    except ImportError:
+        pass
+
+    # Minimal fallback covering the most common credential prefixes
+    _CRED_RE = _re.compile(
+        r"(?<![A-Za-z0-9_-])("
+        r"sk-[A-Za-z0-9_-]{10,}"          # OpenAI / Anthropic / OpenRouter
+        r"|ghp_[A-Za-z0-9]{10,}"          # GitHub PAT (classic)
+        r"|github_pat_[A-Za-z0-9_]{10,}"  # GitHub PAT (fine-grained)
+        r"|gho_[A-Za-z0-9]{10,}"          # GitHub OAuth token
+        r"|ghu_[A-Za-z0-9]{10,}"          # GitHub user-to-server token
+        r"|ghs_[A-Za-z0-9]{10,}"          # GitHub server-to-server token
+        r"|ghr_[A-Za-z0-9]{10,}"          # GitHub refresh token
+        r"|AKIA[A-Z0-9]{16}"              # AWS Access Key ID
+        r"|xox[baprs]-[A-Za-z0-9-]{10,}" # Slack tokens
+        r"|hf_[A-Za-z0-9]{10,}"          # HuggingFace token
+        r"|SG\.[A-Za-z0-9_-]{10,}"       # SendGrid API key
+        r")(?![A-Za-z0-9_-])"
+    )
+    _AUTH_HDR_RE = _re.compile(r"(Authorization:\s*Bearer\s+)(\S+)", _re.IGNORECASE)
+    _ENV_RE = _re.compile(
+        r"([A-Z0-9_]{0,50}(?:API_?KEY|TOKEN|SECRET|PASSWORD|PASSWD|CREDENTIAL|AUTH)[A-Z0-9_]{0,50})"
+        r"\s*=\s*(['\"]?)(\S+)\2"
+    )
+    _PRIVKEY_RE = _re.compile(
+        r"-----BEGIN[A-Z ]*PRIVATE KEY-----[\s\S]*?-----END[A-Z ]*PRIVATE KEY-----"
+    )
+
+    def _mask(token: str) -> str:
+        return f"{token[:6]}...{token[-4:]}" if len(token) >= 18 else "***"
+
+    def _fallback_redact(text: str) -> str:
+        if not isinstance(text, str) or not text:
+            return text
+        text = _CRED_RE.sub(lambda m: _mask(m.group(1)), text)
+        text = _AUTH_HDR_RE.sub(lambda m: m.group(1) + _mask(m.group(2)), text)
+        text = _ENV_RE.sub(
+            lambda m: f"{m.group(1)}={m.group(2)}{_mask(m.group(3))}{m.group(2)}", text
+        )
+        text = _PRIVKEY_RE.sub("[REDACTED PRIVATE KEY]", text)
+        return text
+
+    return _fallback_redact
+
+
+_redact_text = _build_redact_fn()
+
+
+def _redact_value(v):
+    """Recursively redact credentials from strings, dicts, and lists."""
+    if isinstance(v, str):
+        return _redact_text(v)
+    if isinstance(v, dict):
+        return {k: _redact_value(val) for k, val in v.items()}
+    if isinstance(v, list):
+        return [_redact_value(item) for item in v]
+    return v
+
+
+def redact_session_data(session_dict: dict) -> dict:
+    """Redact credentials from message content and tool_call data before API response.
+
+    Applies to: messages[], tool_calls[], and title.
+    The underlying session file is not modified; redaction is response-layer only.
+    """
+    result = dict(session_dict)
+    if isinstance(result.get('title'), str):
+        result['title'] = _redact_text(result['title'])
+    if 'messages' in result:
+        result['messages'] = _redact_value(result['messages'])
+    if 'tool_calls' in result:
+        result['tool_calls'] = _redact_value(result['tool_calls'])
+    return result
+
+
+def read_body(handler) -> dict:
+    """Read and JSON-parse a POST request body (capped at 20MB)."""
+    length = int(handler.headers.get('Content-Length', 0))
+    if length > MAX_BODY_BYTES:
+        raise ValueError(f'Request body too large ({length} bytes, max {MAX_BODY_BYTES})')
+    raw = handler.rfile.read(length) if length else b'{}'
+    try:
+        return _json.loads(raw)
+    except Exception:
+        return {}

api/mc.py

@@ -0,0 +1,218 @@
+"""
+Mission Control API — Data layer for Hermes WebUI Mission Control extension.
+Provides priorities, tasks, feed, and dashboard status management.
+"""
+
+import json
+import threading
+import time
+from pathlib import Path
+from typing import Any
+
+from api.helpers import j
+
+# ── State file ────────────────────────────────────────────────────────────────
+_MC_DATA_FILE = Path.home() / ".hermes" / "data" / "mc-data.json"
+_MC_LOCK = threading.RLock()
+
+# ── Default structure ─────────────────────────────────────────────────────────
+DEFAULT_MC_DATA = {
+    "priorities": [],
+    "tasks": [],
+    "feed": [],
+}
+
+
+def _load_mc_data() -> dict:
+    """Load Mission Control data from disk."""
+    with _MC_LOCK:
+        if not _MC_DATA_FILE.exists():
+            return DEFAULT_MC_DATA.copy()
+        try:
+            with open(_MC_DATA_FILE, "r") as f:
+                return json.load(f)
+        except (json.JSONDecodeError, IOError):
+            return DEFAULT_MC_DATA.copy()
+
+
+def _save_mc_data(data: dict) -> None:
+    """Save Mission Control data to disk."""
+    with _MC_LOCK:
+        _MC_DATA_FILE.parent.mkdir(parents=True, exist_ok=True)
+        with open(_MC_DATA_FILE, "w") as f:
+            json.dump(data, f, indent=2)
+
+
+# ── Priority helpers ──────────────────────────────────────────────────────────
+
+def get_priorities() -> list[dict]:
+    """Return all priorities sorted by id."""
+    data = _load_mc_data()
+    return sorted(data.get("priorities", []), key=lambda p: p.get("id", 0))
+
+
+def create_priority(name: str, color: str = "#808080") -> dict:
+    """Add a new priority. Returns the created priority."""
+    data = _load_mc_data()
+    priorities = data.get("priorities", [])
+    new_id = max([p.get("id", 0) for p in priorities], default=0) + 1
+    priority = {"id": new_id, "name": name, "color": color}
+    priorities.append(priority)
+    data["priorities"] = priorities
+    _save_mc_data(data)
+    _add_feed_event(f"Priority created: {name}")
+    return priority
+
+
+def update_priority(priority_id: int, name: str = None, color: str = None, done: bool = None) -> dict | None:
+    """Update an existing priority. Returns updated priority or None if not found."""
+    data = _load_mc_data()
+    priorities = data.get("priorities", [])
+    for p in priorities:
+        if p.get("id") == priority_id:
+            if name is not None:
+                p["name"] = name
+            if color is not None:
+                p["color"] = color
+            if done is not None:
+                p["done"] = done
+                if done:
+                    _add_feed_event(f"Priority completed: {p['name']}")
+            data["priorities"] = priorities
+            _save_mc_data(data)
+            return p
+    return None
+
+
+def delete_priority(priority_id: int) -> bool:
+    """Delete a priority. Returns True if found and deleted."""
+    data = _load_mc_data()
+    priorities = data.get("priorities", [])
+    original_len = len(priorities)
+    priorities = [p for p in priorities if p.get("id") != priority_id]
+    if len(priorities) < original_len:
+        data["priorities"] = priorities
+        _save_mc_data(data)
+        return True
+    return False
+
+
+# ── Task helpers ──────────────────────────────────────────────────────────────
+
+def get_tasks() -> list[dict]:
+    """Return all tasks sorted by priority then id."""
+    data = _load_mc_data()
+    return sorted(data.get("tasks", []), key=lambda t: (t.get("priority", 999), t.get("id", 0)))
+
+
+def create_task(title: str, priority: int = 1, status: str = "backlog") -> dict:
+    """Create a new task. Returns the created task."""
+    data = _load_mc_data()
+    tasks = data.get("tasks", [])
+    new_id = max([t.get("id", 0) for t in tasks], default=0) + 1
+    task = {"id": new_id, "title": title, "priority": priority, "status": status}
+    tasks.append(task)
+    data["tasks"] = tasks
+    _save_mc_data(data)
+    _add_feed_event(f"Task created: {title}")
+    return task
+
+
+def update_task(task_id: int, **kwargs) -> dict | None:
+    """Update a task by id. kwargs: title, priority, status. Returns updated task or None."""
+    data = _load_mc_data()
+    tasks = data.get("tasks", [])
+    for t in tasks:
+        if t.get("id") == task_id:
+            old_status = t.get("status")
+            for key in ("title", "priority", "status"):
+                if key in kwargs:
+                    t[key] = kwargs[key]
+            new_status = t.get("status")
+            # Feed events for status transitions
+            if old_status != new_status:
+                if new_status == "done":
+                    _add_feed_event(f"Task completed: {t['title']}")
+                elif new_status == "progress":
+                    _add_feed_event(f"Task started: {t['title']}")
+            data["tasks"] = tasks
+            _save_mc_data(data)
+            return t
+    return None
+
+
+def delete_task(task_id: int) -> bool:
+    """Delete a task. Returns True if found and deleted."""
+    data = _load_mc_data()
+    tasks = data.get("tasks", [])
+    original_len = len(tasks)
+    tasks = [t for t in tasks if t.get("id") != task_id]
+    if len(tasks) < original_len:
+        data["tasks"] = tasks
+        _save_mc_data(data)
+        return True
+    return False
+
+
+# ── Feed helpers ──────────────────────────────────────────────────────────────
+
+def get_feed(limit: int = 50) -> list[dict]:
+    """Return recent feed events, newest first."""
+    data = _load_mc_data()
+    feed = data.get("feed", [])
+    return sorted(feed, key=lambda f: f.get("timestamp", ""), reverse=True)[:limit]
+
+
+def _add_feed_event(event: str) -> None:
+    """Add a timestamped feed event."""
+    data = _load_mc_data()
+    feed = data.get("feed", [])
+    feed.append({
+        "timestamp": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()),
+        "event": event,
+    })
+    # Keep only last 200 events
+    data["feed"] = feed[-200:]
+    _save_mc_data(data)
+
+
+# ── Dashboard status ──────────────────────────────────────────────────────────
+
+def get_dashboard_status() -> dict:
+    """Return aggregated dashboard status for Mission Control."""
+    data = _load_mc_data()
+    priorities = data.get("priorities", [])
+    tasks = data.get("tasks", [])
+
+    priorities_total = len(priorities)
+    priorities_done = sum(1 for p in priorities if p.get("done"))
+
+    tasks_backlog = sum(1 for t in tasks if t.get("status") == "backlog")
+    tasks_progress = sum(1 for t in tasks if t.get("status") == "progress")
+    tasks_done = sum(1 for t in tasks if t.get("status") == "done")
+
+    feed = get_feed(limit=5)
+    latest_event = feed[0]["event"] if feed else "No recent activity"
+
+    # Health assessment
+    if tasks_done == 0 and tasks_backlog == 0 and tasks_progress == 0:
+        health = "empty"
+    elif tasks_progress > 0 and tasks_done > 0:
+        health = "healthy"
+    elif tasks_progress > 0:
+        health = "active"
+    elif tasks_backlog > 0:
+        health = "warning"
+    else:
+        health = "ok"
+
+    return {
+        "priorities_total": priorities_total,
+        "priorities_done": priorities_done,
+        "tasks_backlog": tasks_backlog,
+        "tasks_progress": tasks_progress,
+        "tasks_done": tasks_done,
+        "latest_feed_event": latest_event,
+        "dashboard_health": health,
+        "timestamp": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()),
+    }

api/models.py

@@ -0,0 +1,405 @@
+"""
+Hermes Web UI -- Session model and in-memory session store.
+"""
+import collections
+import json
+import logging
+import time
+import uuid
+from pathlib import Path
+
+import api.config as _cfg
+from api.config import (
+    SESSION_DIR, SESSION_INDEX_FILE, SESSIONS, SESSIONS_MAX,
+    LOCK, DEFAULT_WORKSPACE, DEFAULT_MODEL, PROJECTS_FILE, HOME
+)
+from api.workspace import get_last_workspace
+
+logger = logging.getLogger(__name__)
+
+
+def _write_session_index():
+    """Rebuild the session index file for O(1) future reads."""
+    entries = []
+    for p in SESSION_DIR.glob('*.json'):
+        if p.name.startswith('_'): continue
+        try:
+            s = Session.load(p.stem)
+            if s: entries.append(s.compact())
+        except Exception:
+            logger.debug("Failed to load session from %s", p)
+    with LOCK:
+        for s in SESSIONS.values():
+            if not any(e['session_id'] == s.session_id for e in entries):
+                entries.append(s.compact())
+    entries.sort(key=lambda s: s['updated_at'], reverse=True)
+    SESSION_INDEX_FILE.write_text(json.dumps(entries, ensure_ascii=False, indent=2), encoding='utf-8')
+
+
+class Session:
+    def __init__(self, session_id: str=None, title: str='Untitled',
+                 workspace=str(DEFAULT_WORKSPACE), model=DEFAULT_MODEL,
+                 messages=None, created_at=None, updated_at=None,
+                 tool_calls=None, pinned: bool=False, archived: bool=False,
+                 project_id: str=None, profile=None,
+                 input_tokens: int=0, output_tokens: int=0, estimated_cost=None,
+                 personality=None,
+                 active_stream_id: str=None,
+                 pending_user_message: str=None,
+                 pending_attachments=None,
+                 pending_started_at=None,
+                 compression_anchor_visible_idx=None,
+                 compression_anchor_message_key=None,
+                 **kwargs):
+        self.session_id = session_id or uuid.uuid4().hex[:12]
+        self.title = title
+        self.workspace = str(Path(workspace).expanduser().resolve())
+        self.model = model
+        self.messages = messages or []
+        self.tool_calls = tool_calls or []
+        self.created_at = created_at or time.time()
+        self.updated_at = updated_at or time.time()
+        self.pinned = bool(pinned)
+        self.archived = bool(archived)
+        self.project_id = project_id or None
+        self.profile = profile
+        self.input_tokens = input_tokens or 0
+        self.output_tokens = output_tokens or 0
+        self.estimated_cost = estimated_cost
+        self.personality = personality
+        self.active_stream_id = active_stream_id
+        self.pending_user_message = pending_user_message
+        self.pending_attachments = pending_attachments or []
+        self.pending_started_at = pending_started_at
+        self.compression_anchor_visible_idx = compression_anchor_visible_idx
+        self.compression_anchor_message_key = compression_anchor_message_key
+
+    @property
+    def path(self):
+        return SESSION_DIR / f'{self.session_id}.json'
+
+    def save(self, touch_updated_at: bool = True) -> None:
+        if touch_updated_at:
+            self.updated_at = time.time()
+        self.path.write_text(
+            json.dumps(self.__dict__, ensure_ascii=False, indent=2),
+            encoding='utf-8',
+        )
+        _write_session_index()
+
+    @classmethod
+    def load(cls, sid):
+        # Validate session ID format to prevent path traversal
+        if not sid or not all(c in '0123456789abcdefghijklmnopqrstuvwxyz_' for c in sid):
+            return None
+        p = SESSION_DIR / f'{sid}.json'
+        if not p.exists():
+            return None
+        return cls(**json.loads(p.read_text(encoding='utf-8')))
+
+    def compact(self) -> dict:
+        return {
+            'session_id': self.session_id,
+            'title': self.title,
+            'workspace': self.workspace,
+            'model': self.model,
+            'message_count': len(self.messages),
+            'created_at': self.created_at,
+            'updated_at': self.updated_at,
+            'pinned': self.pinned,
+            'archived': self.archived,
+            'project_id': self.project_id,
+            'profile': self.profile,
+            'input_tokens': self.input_tokens,
+            'output_tokens': self.output_tokens,
+            'estimated_cost': self.estimated_cost,
+            'personality': self.personality,
+            'compression_anchor_visible_idx': self.compression_anchor_visible_idx,
+            'compression_anchor_message_key': self.compression_anchor_message_key,
+        }
+
+def get_session(sid):
+    with LOCK:
+        if sid in SESSIONS:
+            SESSIONS.move_to_end(sid)  # LRU: mark as recently used
+            return SESSIONS[sid]
+    s = Session.load(sid)
+    if s:
+        with LOCK:
+            SESSIONS[sid] = s
+            SESSIONS.move_to_end(sid)
+            while len(SESSIONS) > SESSIONS_MAX:
+                SESSIONS.popitem(last=False)  # evict least recently used
+        return s
+    raise KeyError(sid)
+
+def new_session(workspace=None, model=None):
+    # Use _cfg.DEFAULT_MODEL (not the import-time snapshot) so save_settings() changes take effect
+    try:
+        from api.profiles import get_active_profile_name
+        _profile = get_active_profile_name()
+    except ImportError:
+        _profile = None
+    s = Session(workspace=workspace or get_last_workspace(), model=model or _cfg.DEFAULT_MODEL, profile=_profile)
+    with LOCK:
+        SESSIONS[s.session_id] = s
+        SESSIONS.move_to_end(s.session_id)
+        while len(SESSIONS) > SESSIONS_MAX:
+            SESSIONS.popitem(last=False)
+    s.save()
+    return s
+
+def all_sessions():
+    # Phase C: try index first for O(1) read; fall back to full scan
+    if SESSION_INDEX_FILE.exists():
+        try:
+            index = json.loads(SESSION_INDEX_FILE.read_text(encoding='utf-8'))
+            # Overlay any in-memory sessions that may be newer than the index
+            index_map = {s['session_id']: s for s in index}
+            with LOCK:
+                for s in SESSIONS.values():
+                    index_map[s.session_id] = s.compact()
+            result = sorted(index_map.values(), key=lambda s: (s.get('pinned', False), s['updated_at']), reverse=True)
+            # Hide empty Untitled sessions from the UI (created by tests, page refreshes, etc.)
+            result = [s for s in result if not (s.get('title','Untitled')=='Untitled' and s.get('message_count',0)==0)]
+            # Backfill: sessions created before Sprint 22 have no profile tag.
+            # Attribute them to 'default' so the client profile filter works correctly.
+            for s in result:
+                if not s.get('profile'):
+                    s['profile'] = 'default'
+            return result
+        except Exception:
+            logger.debug("Failed to load session index, falling back to full scan")
+    # Full scan fallback
+    out = []
+    for p in SESSION_DIR.glob('*.json'):
+        if p.name.startswith('_'): continue
+        try:
+            s = Session.load(p.stem)
+            if s: out.append(s)
+        except Exception:
+            logger.debug("Failed to load session from %s", p)
+    for s in SESSIONS.values():
+        if all(s.session_id != x.session_id for x in out): out.append(s)
+    out.sort(key=lambda s: (getattr(s, 'pinned', False), s.updated_at), reverse=True)
+    result = [s.compact() for s in out if not (s.title=='Untitled' and len(s.messages)==0)]
+    for s in result:
+        if not s.get('profile'):
+            s['profile'] = 'default'
+    return result
+
+
+def title_from(messages, fallback: str='Untitled'):
+    """Derive a session title from the first user message."""
+    for m in messages:
+        if m.get('role') == 'user':
+            c = m.get('content', '')
+            if isinstance(c, list):
+                c = ' '.join(p.get('text', '') for p in c if isinstance(p, dict) and p.get('type') == 'text')
+            text = str(c).strip()
+            if text:
+                return text[:64]
+    return fallback
+
+
+# ── Project helpers ──────────────────────────────────────────────────────────
+
+def load_projects() -> list:
+    """Load project list from disk. Returns list of project dicts."""
+    if not PROJECTS_FILE.exists():
+        return []
+    try:
+        return json.loads(PROJECTS_FILE.read_text(encoding='utf-8'))
+    except Exception:
+        return []
+
+def save_projects(projects) -> None:
+    """Write project list to disk."""
+    PROJECTS_FILE.write_text(json.dumps(projects, ensure_ascii=False, indent=2), encoding='utf-8')
+
+
+def import_cli_session(
+    session_id: str,
+    title: str,
+    messages,
+    model: str='unknown',
+    profile=None,
+    created_at=None,
+    updated_at=None,
+):
+    """Create a new WebUI session populated with CLI messages.
+    Returns the Session object.
+    """
+    s = Session(
+        session_id=session_id,
+        title=title,
+        workspace=get_last_workspace(),
+        model=model,
+        messages=messages,
+        profile=profile,
+        created_at=created_at,
+        updated_at=updated_at,
+    )
+    s.save(touch_updated_at=False)
+    return s
+
+
+# ── CLI session bridge ──────────────────────────────────────────────────────
+
+def get_cli_sessions() -> list:
+    """Read CLI sessions from the agent's SQLite store and return them as
+    dicts in a format the WebUI sidebar can render alongside local sessions.
+
+    Returns empty list if the SQLite DB is missing, the sqlite3 module is
+    unavailable, or any error occurs -- the bridge is purely additive and never
+    crashes the WebUI.
+    """
+    import os
+    cli_sessions = []
+    try:
+        import sqlite3
+    except ImportError:
+        return cli_sessions
+
+    # Use the active WebUI profile's HERMES_HOME to find state.db.
+    # The active profile is determined by what the user has selected in the UI
+    # (stored in the server's runtime config). This means:
+    #   - default profile  -> ~/.hermes/state.db
+    #   - named profile X  -> ~/.hermes/profiles/X/state.db
+    # We resolve the active profile's home directory rather than just using
+    # HERMES_HOME (which is the server's launch profile, not necessarily the
+    # active one after a profile switch).
+    try:
+        from api.profiles import get_active_hermes_home
+        hermes_home = Path(get_active_hermes_home()).expanduser().resolve()
+    except Exception:
+        hermes_home = Path(os.getenv('HERMES_HOME', str(HOME / '.hermes'))).expanduser().resolve()
+
+    db_path = hermes_home / 'state.db'
+    if not db_path.exists():
+        return cli_sessions
+
+    # Try to resolve the active CLI profile so imported sessions integrate
+    # with the WebUI profile filter (available since Sprint 22).
+    try:
+        from api.profiles import get_active_profile_name
+        _cli_profile = get_active_profile_name()
+    except ImportError:
+        _cli_profile = None  # older agent -- fall back to no profile
+
+    try:
+        with sqlite3.connect(str(db_path)) as conn:
+            conn.row_factory = sqlite3.Row
+            cur = conn.cursor()
+            cur.execute("""
+                SELECT s.id, s.title, s.model, s.message_count,
+                       s.started_at, s.source,
+                       MAX(m.timestamp) AS last_activity
+                FROM sessions s
+                LEFT JOIN messages m ON m.session_id = s.id
+                WHERE s.source IS NOT NULL AND s.source != 'webui'
+                GROUP BY s.id
+                ORDER BY COALESCE(MAX(m.timestamp), s.started_at) DESC
+                LIMIT 200
+            """)
+            for row in cur.fetchall():
+                sid = row['id']
+                raw_ts = row['last_activity'] or row['started_at']
+                # Prefer the CLI session's own profile from the DB; fall back to
+                # the active CLI profile so sidebar filtering works either way.
+                profile = _cli_profile  # CLI DB has no profile column; use active profile
+
+                _source = row['source'] or 'cli'
+                _display_title = row['title'] or f'{_source.title()} Session'
+                cli_sessions.append({
+                    'session_id': sid,
+                    'title': _display_title,
+                    'workspace': str(get_last_workspace()),
+                    'model': row['model'] or None,
+                    'message_count': row['message_count'] or 0,
+                    'created_at': row['started_at'],
+                    'updated_at': raw_ts,
+                    'pinned': False,
+                    'archived': False,
+                    'project_id': None,
+                    'profile': profile,
+                    'source_tag': _source,
+                    'is_cli_session': True,
+                })
+    except Exception:
+        # DB schema changed, locked, or corrupted -- silently degrade
+        return []
+
+    return cli_sessions
+
+
+def get_cli_session_messages(sid) -> list:
+    """Read messages for a single CLI session from the SQLite store.
+    Returns a list of {role, content, timestamp} dicts.
+    Returns empty list on any error.
+    """
+    import os
+    try:
+        import sqlite3
+    except ImportError:
+        return []
+
+    try:
+        from api.profiles import get_active_hermes_home
+        hermes_home = Path(get_active_hermes_home()).expanduser().resolve()
+    except Exception:
+        hermes_home = Path(os.getenv('HERMES_HOME', str(HOME / '.hermes'))).expanduser().resolve()
+    db_path = hermes_home / 'state.db'
+    if not db_path.exists():
+        return []
+
+    try:
+        with sqlite3.connect(str(db_path)) as conn:
+            conn.row_factory = sqlite3.Row
+            cur = conn.cursor()
+            cur.execute("""
+                SELECT role, content, timestamp
+                FROM messages
+                WHERE session_id = ?
+                ORDER BY timestamp ASC
+            """, (sid,))
+            msgs = []
+            for row in cur.fetchall():
+                msgs.append({
+                    'role': row['role'],
+                    'content': row['content'],
+                    'timestamp': row['timestamp'],
+                })
+    except Exception:
+        return []
+    return msgs
+
+
+def delete_cli_session(sid) -> bool:
+    """Delete a CLI session from state.db (messages + session row).
+    Returns True if deleted, False if not found or error.
+    """
+    import os
+    try:
+        import sqlite3
+    except ImportError:
+        return False
+
+    try:
+        from api.profiles import get_active_hermes_home
+        hermes_home = Path(get_active_hermes_home()).expanduser().resolve()
+    except Exception:
+        hermes_home = Path(os.getenv('HERMES_HOME', str(HOME / '.hermes'))).expanduser().resolve()
+    db_path = hermes_home / 'state.db'
+    if not db_path.exists():
+        return False
+
+    try:
+        with sqlite3.connect(str(db_path)) as conn:
+            cur = conn.cursor()
+            cur.execute("DELETE FROM messages WHERE session_id = ?", (sid,))
+            cur.execute("DELETE FROM sessions WHERE id = ?", (sid,))
+            conn.commit()
+            return cur.rowcount > 0
+    except Exception:
+        return False

api/onboarding.py

@@ -0,0 +1,555 @@
+"""Hermes Web UI -- first-run onboarding helpers."""
+
+from __future__ import annotations
+
+import logging
+import os
+from pathlib import Path
+from urllib.parse import urlparse
+
+from api.auth import is_auth_enabled
+from api.config import (
+    DEFAULT_MODEL,
+    DEFAULT_WORKSPACE,
+    _FALLBACK_MODELS,
+    _HERMES_FOUND,
+    _PROVIDER_DISPLAY,
+    _PROVIDER_MODELS,
+    _get_config_path,
+    get_available_models,
+    get_config,
+    load_settings,
+    reload_config,
+    save_settings,
+    verify_hermes_imports,
+)
+from api.workspace import get_last_workspace, load_workspaces
+
+logger = logging.getLogger(__name__)
+
+
+_SUPPORTED_PROVIDER_SETUPS = {
+    "openrouter": {
+        "label": "OpenRouter",
+        "env_var": "OPENROUTER_API_KEY",
+        "default_model": "anthropic/claude-sonnet-4.6",
+        "requires_base_url": False,
+        "models": [
+            {"id": model["id"], "label": model["label"]} for model in _FALLBACK_MODELS
+        ],
+    },
+    "anthropic": {
+        "label": "Anthropic",
+        "env_var": "ANTHROPIC_API_KEY",
+        "default_model": "claude-sonnet-4.6",
+        "requires_base_url": False,
+        "models": list(_PROVIDER_MODELS.get("anthropic", [])),
+    },
+    "openai": {
+        "label": "OpenAI",
+        "env_var": "OPENAI_API_KEY",
+        "default_model": "gpt-4o",
+        "default_base_url": "https://api.openai.com/v1",
+        "requires_base_url": False,
+        "models": list(_PROVIDER_MODELS.get("openai", [])),
+    },
+    "custom": {
+        "label": "Custom OpenAI-compatible",
+        "env_var": "OPENAI_API_KEY",
+        "default_model": "gpt-4o-mini",
+        "requires_base_url": True,
+        "models": [],
+    },
+}
+
+_UNSUPPORTED_PROVIDER_NOTE = (
+    "OAuth and advanced provider flows such as Nous Portal, OpenAI Codex, and GitHub "
+    "Copilot are still terminal-first. Use `hermes model` for those flows."
+)
+
+
+def _get_active_hermes_home() -> Path:
+    try:
+        from api.profiles import get_active_hermes_home
+
+        return get_active_hermes_home()
+    except ImportError:
+        return Path.home() / ".hermes"
+
+
+def _load_env_file(env_path: Path) -> dict[str, str]:
+    values: dict[str, str] = {}
+    if not env_path.exists():
+        return values
+    try:
+        for raw in env_path.read_text(encoding="utf-8").splitlines():
+            line = raw.strip()
+            if not line or line.startswith("#") or "=" not in line:
+                continue
+            key, value = line.split("=", 1)
+            values[key.strip()] = value.strip().strip('"').strip("'")
+    except Exception:
+        return {}
+    return values
+
+
+def _write_env_file(env_path: Path, updates: dict[str, str]) -> None:
+    current = _load_env_file(env_path)
+    for key, value in updates.items():
+        if value is None:
+            current.pop(key, None)
+            os.environ.pop(key, None)
+            continue
+        clean = str(value).strip()
+        if not clean:
+            continue
+        # Reject embedded newlines/carriage returns to prevent .env injection
+        if "\n" in clean or "\r" in clean:
+            raise ValueError("API key must not contain newline characters.")
+        current[key] = clean
+        os.environ[key] = clean
+
+    env_path.parent.mkdir(parents=True, exist_ok=True)
+    lines = [f"{key}={current[key]}" for key in sorted(current)]
+    env_path.write_text("\n".join(lines) + ("\n" if lines else ""), encoding="utf-8")
+
+
+def _load_yaml_config(config_path: Path) -> dict:
+    try:
+        import yaml as _yaml
+    except ImportError:
+        return {}
+
+    if not config_path.exists():
+        return {}
+    try:
+        loaded = _yaml.safe_load(config_path.read_text(encoding="utf-8"))
+        return loaded if isinstance(loaded, dict) else {}
+    except Exception:
+        return {}
+
+
+def _save_yaml_config(config_path: Path, config: dict) -> None:
+    try:
+        import yaml as _yaml
+    except ImportError as exc:
+        raise RuntimeError("PyYAML is required to write Hermes config.yaml") from exc
+
+    config_path.parent.mkdir(parents=True, exist_ok=True)
+    config_path.write_text(
+        _yaml.safe_dump(config, sort_keys=False, allow_unicode=True),
+        encoding="utf-8",
+    )
+
+
+def _normalize_model_for_provider(provider: str, model: str) -> str:
+    clean = (model or "").strip()
+    if not clean:
+        return ""
+    if provider in {"anthropic", "openai"} and clean.startswith(provider + "/"):
+        return clean.split("/", 1)[1]
+    return clean
+
+
+def _normalize_base_url(base_url: str) -> str:
+    return (base_url or "").strip().rstrip("/")
+
+
+def _extract_current_provider(cfg: dict) -> str:
+    model_cfg = cfg.get("model", {})
+    if isinstance(model_cfg, dict):
+        provider = str(model_cfg.get("provider") or "").strip().lower()
+        if provider:
+            return provider
+    return ""
+
+
+def _extract_current_model(cfg: dict) -> str:
+    model_cfg = cfg.get("model", {})
+    if isinstance(model_cfg, str):
+        return model_cfg.strip()
+    if isinstance(model_cfg, dict):
+        return str(model_cfg.get("default") or "").strip()
+    return ""
+
+
+def _extract_current_base_url(cfg: dict) -> str:
+    model_cfg = cfg.get("model", {})
+    if isinstance(model_cfg, dict):
+        return _normalize_base_url(str(model_cfg.get("base_url") or ""))
+    return ""
+
+
+def _provider_api_key_present(
+    provider: str, cfg: dict, env_values: dict[str, str]
+) -> bool:
+    provider = (provider or "").strip().lower()
+    if not provider:
+        return False
+
+    env_var = _SUPPORTED_PROVIDER_SETUPS.get(provider, {}).get("env_var")
+    if env_var and env_values.get(env_var):
+        return True
+
+    model_cfg = cfg.get("model", {})
+    if isinstance(model_cfg, dict) and str(model_cfg.get("api_key") or "").strip():
+        return True
+
+    providers_cfg = cfg.get("providers", {})
+    if isinstance(providers_cfg, dict):
+        provider_cfg = providers_cfg.get(provider, {})
+        if (
+            isinstance(provider_cfg, dict)
+            and str(provider_cfg.get("api_key") or "").strip()
+        ):
+            return True
+        if provider == "custom":
+            custom_cfg = providers_cfg.get("custom", {})
+            if (
+                isinstance(custom_cfg, dict)
+                and str(custom_cfg.get("api_key") or "").strip()
+            ):
+                return True
+
+    # For providers not in _SUPPORTED_PROVIDER_SETUPS (e.g. minimax-cn, deepseek,
+    # xai, etc.), ask the hermes_cli auth registry — it knows every provider's env
+    # var names and can check os.environ for a valid key.
+    # Exclude known OAuth/token-flow providers — those are handled separately by
+    # _provider_oauth_authenticated() and should not be short-circuited here.
+    _known_oauth = {"openai-codex", "copilot", "copilot-acp", "qwen-oauth", "nous"}
+    if provider not in _SUPPORTED_PROVIDER_SETUPS and provider not in _known_oauth:
+        try:
+            from hermes_cli.auth import get_auth_status as _gas
+            status = _gas(provider)
+            if isinstance(status, dict) and status.get("logged_in"):
+                return True
+        except Exception:
+            pass
+
+    return False
+
+
+
+def _provider_oauth_authenticated(provider: str, hermes_home: "Path") -> bool:
+    """Return True if the provider has valid OAuth credentials.
+
+    Checks via hermes_cli.auth.get_auth_status() when available, then falls
+    back to reading auth.json directly for the known OAuth provider IDs
+    (openai-codex, copilot, copilot-acp, qwen-oauth, nous).
+
+    This covers users who authenticated via 'hermes auth' or 'hermes model'
+    but whose provider is not in _SUPPORTED_PROVIDER_SETUPS because it does
+    not use a plain API key.
+    """
+    provider = (provider or "").strip().lower()
+    if not provider:
+        return False
+
+    # Check auth.json for known OAuth provider IDs.
+    # hermes_home scopes the check — callers must pass the correct home directory.
+    # (A prior CLI fast path via hermes_cli.auth.get_auth_status() was removed
+    # because it ignored hermes_home and read from the real system home, breaking
+    # both test isolation and deployments with multiple profiles.)
+    _known_oauth_providers = {"openai-codex", "copilot", "copilot-acp", "qwen-oauth", "nous"}
+    if provider not in _known_oauth_providers:
+        return False
+
+    try:
+        import json as _j
+
+        auth_path = hermes_home / "auth.json"
+        if not auth_path.exists():
+            return False
+        store = _j.loads(auth_path.read_text(encoding="utf-8"))
+        providers_store = store.get("providers")
+        if not isinstance(providers_store, dict):
+            return False
+        state = providers_store.get(provider)
+        if not isinstance(state, dict):
+            return False
+        # Any non-empty token is enough to confirm the user has credentials.
+        # Token refresh happens at runtime inside the agent.
+        has_token = bool(
+            str(state.get("access_token") or "").strip()
+            or str(state.get("api_key") or "").strip()
+            or str(state.get("refresh_token") or "").strip()
+        )
+        return has_token
+    except Exception:
+        return False
+
+
+def _status_from_runtime(cfg: dict, imports_ok: bool) -> dict:
+    provider = _extract_current_provider(cfg)
+    model = _extract_current_model(cfg)
+    base_url = _extract_current_base_url(cfg)
+    env_values = _load_env_file(_get_active_hermes_home() / ".env")
+
+    provider_configured = bool(provider and model)
+    provider_ready = False
+
+    if provider_configured:
+        if provider == "custom":
+            provider_ready = bool(
+                base_url and _provider_api_key_present(provider, cfg, env_values)
+            )
+        elif provider in _SUPPORTED_PROVIDER_SETUPS:
+            provider_ready = _provider_api_key_present(provider, cfg, env_values)
+        else:
+            # Unknown provider — may be an OAuth flow (openai-codex, copilot, etc.)
+            # OR an API-key provider not in the quick-setup list (minimax-cn, deepseek,
+            # xai, etc.).  Check both: api key presence first (covers the majority of
+            # third-party providers), then OAuth auth.json.
+            provider_ready = (
+                _provider_api_key_present(provider, cfg, env_values)
+                or _provider_oauth_authenticated(provider, _get_active_hermes_home())
+            )
+
+    chat_ready = bool(_HERMES_FOUND and imports_ok and provider_ready)
+
+    if not _HERMES_FOUND or not imports_ok:
+        state = "agent_unavailable"
+        note = (
+            "Hermes is not fully importable from the Web UI yet. Finish bootstrap or fix the "
+            "agent install before provider setup will work."
+        )
+    elif chat_ready:
+        state = "ready"
+        provider_name = _PROVIDER_DISPLAY.get(
+            provider, provider.title() if provider else "Hermes"
+        )
+        note = f"Hermes is minimally configured and ready to chat via {provider_name}."
+    elif provider_configured:
+        state = "provider_incomplete"
+        if provider == "custom" and not base_url:
+            note = (
+                "Hermes has a saved provider/model selection but still needs the "
+                "base URL and API key required to chat."
+            )
+        elif provider not in _SUPPORTED_PROVIDER_SETUPS:
+            # OAuth / unsupported provider: avoid misleading "API key" wording.
+            note = (
+                f"Provider '{provider}' is configured but not yet authenticated. "
+                "Run 'hermes auth' or 'hermes model' in a terminal to complete "
+                "setup, then reload the Web UI."
+            )
+        else:
+            note = (
+                "Hermes has a saved provider/model selection but still needs the "
+                "API key required to chat."
+            )
+    else:
+        state = "needs_provider"
+        note = "Hermes is installed, but you still need to choose a provider and save working credentials."
+
+    return {
+        "provider_configured": provider_configured,
+        "provider_ready": provider_ready,
+        "chat_ready": chat_ready,
+        "setup_state": state,
+        "provider_note": note,
+        "current_provider": provider or None,
+        "current_model": model or None,
+        "current_base_url": base_url or None,
+        "env_path": str(_get_active_hermes_home() / ".env"),
+    }
+
+
+def _build_setup_catalog(cfg: dict) -> dict:
+    current_provider = _extract_current_provider(cfg) or "openrouter"
+    current_model = _extract_current_model(cfg)
+    current_base_url = _extract_current_base_url(cfg)
+
+    providers = []
+    for provider_id, meta in _SUPPORTED_PROVIDER_SETUPS.items():
+        providers.append(
+            {
+                "id": provider_id,
+                "label": meta["label"],
+                "env_var": meta["env_var"],
+                "default_model": meta["default_model"],
+                "default_base_url": meta.get("default_base_url") or "",
+                "requires_base_url": bool(meta.get("requires_base_url")),
+                "models": list(meta.get("models", [])),
+                "quick": provider_id == "openrouter",
+            }
+        )
+
+    # Flag whether the currently-configured provider is OAuth-based (not in the
+    # API-key flow).  The frontend uses this to show a confirmation card instead
+    # of a key input when the user has already authenticated via 'hermes auth'.
+    current_is_oauth = current_provider not in _SUPPORTED_PROVIDER_SETUPS and bool(
+        current_provider
+    )
+
+    return {
+        "providers": providers,
+        "unsupported_note": _UNSUPPORTED_PROVIDER_NOTE,
+        "current_is_oauth": current_is_oauth,
+        "current": {
+            "provider": current_provider,
+            "model": current_model
+            or _SUPPORTED_PROVIDER_SETUPS.get(current_provider, {}).get(
+                "default_model", ""
+            ),
+            "base_url": current_base_url,
+        },
+    }
+
+
+def get_onboarding_status() -> dict:
+    settings = load_settings()
+    cfg = get_config()
+    imports_ok, missing, errors = verify_hermes_imports()
+    runtime = _status_from_runtime(cfg, imports_ok)
+    workspaces = load_workspaces()
+    last_workspace = get_last_workspace()
+    available_models = get_available_models()
+
+    # HERMES_WEBUI_SKIP_ONBOARDING=1 lets hosting providers (e.g. Agent37) ship
+    # a pre-configured instance without the wizard blocking the first load.
+    # This is an operator-level override and is honoured unconditionally —
+    # the operator knows their deployment is configured; we must not second-guess
+    # it by requiring chat_ready to also be true.
+    skip_env = os.environ.get("HERMES_WEBUI_SKIP_ONBOARDING", "").strip()
+    skip_requested = skip_env in {"1", "true", "yes"}
+    auto_completed = skip_requested  # unconditional: operator says skip, we skip
+
+    # Auto-complete for existing Hermes users: if config.yaml already exists
+    # AND the system is chat_ready, treat onboarding as done.  These users
+    # configured Hermes via the CLI before the Web UI existed; they must never
+    # be shown the first-run wizard — it would silently overwrite their config.
+    config_exists = Path(_get_config_path()).exists()
+    config_auto_completed = config_exists and bool(runtime.get("chat_ready"))
+
+    return {
+        "completed": bool(settings.get("onboarding_completed")) or auto_completed or config_auto_completed,
+        "settings": {
+            "default_model": settings.get("default_model") or DEFAULT_MODEL,
+            "default_workspace": settings.get("default_workspace")
+            or str(DEFAULT_WORKSPACE),
+            "password_enabled": is_auth_enabled(),
+            "bot_name": settings.get("bot_name") or "Hermes",
+        },
+        "system": {
+            "hermes_found": bool(_HERMES_FOUND),
+            "imports_ok": bool(imports_ok),
+            "missing_modules": missing,
+            "import_errors": errors,
+            "config_path": str(_get_config_path()),
+            "config_exists": Path(_get_config_path()).exists(),
+            **runtime,
+        },
+        "setup": _build_setup_catalog(cfg),
+        "workspaces": {
+            "items": workspaces,
+            "last": last_workspace,
+        },
+        "models": available_models,
+    }
+
+
+def apply_onboarding_setup(body: dict) -> dict:
+    # Hard guard: if the operator set SKIP_ONBOARDING, the wizard should never
+    # have appeared.  Even if the frontend somehow calls this endpoint anyway
+    # (e.g. a stale JS bundle or a curious user), we must not overwrite the
+    # operator's config.yaml or .env files.  Just mark onboarding complete and
+    # return the current status — no file writes.
+    skip_env = os.environ.get("HERMES_WEBUI_SKIP_ONBOARDING", "").strip()
+    if skip_env in {"1", "true", "yes"}:
+        save_settings({"onboarding_completed": True})
+        return get_onboarding_status()
+
+    provider = str(body.get("provider") or "").strip().lower()
+    model = str(body.get("model") or "").strip()
+    api_key = str(body.get("api_key") or "").strip()
+    base_url = _normalize_base_url(str(body.get("base_url") or ""))
+
+    if provider not in _SUPPORTED_PROVIDER_SETUPS:
+        # Unsupported providers (openai-codex, copilot, nous, etc.) are already
+        # configured via the CLI. Just mark onboarding as complete and let the
+        # user through — the agent is already set up, no further setup needed.
+        save_settings({"onboarding_completed": True})
+        return get_onboarding_status()
+    if not model:
+        raise ValueError("model is required")
+
+    provider_meta = _SUPPORTED_PROVIDER_SETUPS[provider]
+    if provider_meta.get("requires_base_url"):
+        if not base_url:
+            raise ValueError("base_url is required for custom endpoints")
+        parsed = urlparse(base_url)
+        if parsed.scheme not in {"http", "https"}:
+            raise ValueError("base_url must start with http:// or https://")
+
+    config_path = _get_config_path()
+    # Guard: if config.yaml already exists and the caller did not explicitly
+    # acknowledge the overwrite, refuse to proceed.  The frontend must pass
+    # confirm_overwrite=True after showing the user a confirmation step.
+    if Path(config_path).exists() and not body.get("confirm_overwrite"):
+        return {
+            "error": "config_exists",
+            "message": (
+                "Hermes is already configured (config.yaml exists). "
+                "Pass confirm_overwrite=true to overwrite it."
+            ),
+            "requires_confirm": True,
+        }
+
+    cfg = _load_yaml_config(config_path)
+    env_path = _get_active_hermes_home() / ".env"
+    env_values = _load_env_file(env_path)
+
+    if not api_key and not _provider_api_key_present(provider, cfg, env_values):
+        raise ValueError(f"{provider_meta['env_var']} is required")
+
+    model_cfg = cfg.get("model", {})
+    if not isinstance(model_cfg, dict):
+        model_cfg = {}
+
+    model_cfg["provider"] = provider
+    model_cfg["default"] = _normalize_model_for_provider(provider, model)
+
+    if provider == "custom":
+        model_cfg["base_url"] = base_url
+    elif provider == "openai":
+        model_cfg["base_url"] = (
+            provider_meta.get("default_base_url") or "https://api.openai.com/v1"
+        )
+    else:
+        model_cfg.pop("base_url", None)
+
+    cfg["model"] = model_cfg
+    _save_yaml_config(config_path, cfg)
+
+    if api_key:
+        _write_env_file(env_path, {provider_meta["env_var"]: api_key})
+
+    # Reload the hermes_cli provider/config cache so the next streaming call
+    # picks up the new key without requiring a server restart.
+    try:
+        from api.profiles import _reload_dotenv
+        _reload_dotenv(_get_active_hermes_home())
+    except Exception:
+        logger.debug("Failed to reload dotenv")
+
+    # Belt-and-braces: set directly on os.environ AFTER _reload_dotenv so the
+    # value survives even if _reload_dotenv cleared it (e.g. when _write_env_file
+    # wrote to disk but the profile isolation tracking hasn't seen it yet).
+    if api_key:
+        os.environ[provider_meta["env_var"]] = api_key
+
+    try:
+        # hermes_cli may cache config at import time; ask it to reload if possible.
+        from hermes_cli.config import reload as _cli_reload
+        _cli_reload()
+    except Exception:
+        logger.debug("Failed to reload hermes_cli config")
+
+    reload_config()
+    return get_onboarding_status()
+
+
+def complete_onboarding() -> dict:
+    save_settings({"onboarding_completed": True})
+    return get_onboarding_status()

api/profiles.py

@@ -0,0 +1,450 @@
+"""
+Hermes Web UI -- Profile state management.
+Wraps hermes_cli.profiles to provide profile switching for the web UI.
+
+The web UI maintains a process-level "active profile" that determines which
+HERMES_HOME directory is used for config, skills, memory, cron, and API keys.
+Profile switches update os.environ['HERMES_HOME'] and monkey-patch module-level
+cached paths in hermes-agent modules (skills_tool, cron/jobs) that snapshot
+HERMES_HOME at import time.
+"""
+import json
+import logging
+import os
+import re
+import shutil
+import threading
+from pathlib import Path
+
+logger = logging.getLogger(__name__)
+
+# ── Constants (match hermes_cli.profiles upstream) ─────────────────────────
+_PROFILE_ID_RE = re.compile(r'^[a-z0-9][a-z0-9_-]{0,63}$')
+_PROFILE_DIRS = [
+    'memories', 'sessions', 'skills', 'skins',
+    'logs', 'plans', 'workspace', 'cron',
+]
+_CLONE_CONFIG_FILES = ['config.yaml', '.env', 'SOUL.md']
+
+# ── Module state ────────────────────────────────────────────────────────────
+_active_profile = 'default'
+_profile_lock = threading.Lock()
+_loaded_profile_env_keys: set[str] = set()
+
+def _resolve_base_hermes_home() -> Path:
+    """Return the BASE ~/.hermes directory — the root that contains profiles/.
+
+    This is intentionally distinct from HERMES_HOME, which tracks the *active
+    profile's* home and changes on every profile switch.  The base dir must
+    always point to the top-level .hermes regardless of which profile is active.
+
+    Resolution order:
+      1. HERMES_BASE_HOME env var (set explicitly, highest priority)
+      2. HERMES_HOME env var — but only if it does NOT look like a profile subdir
+         (i.e. its parent is not named 'profiles').  This handles test isolation
+         where HERMES_HOME is set to an isolated test state dir.
+      3. ~/.hermes (always-correct default)
+
+    The bug this prevents: if HERMES_HOME has already been mutated to
+    /home/user/.hermes/profiles/webui (by init_profile_state at startup),
+    reading it here would make _DEFAULT_HERMES_HOME point to that subdir,
+    causing switch_profile('webui') to look for
+    /home/user/.hermes/profiles/webui/profiles/webui — which doesn't exist.
+    """
+    # Explicit override for tests or unusual setups
+    base_override = os.getenv('HERMES_BASE_HOME', '').strip()
+    if base_override:
+        return Path(base_override).expanduser()
+
+    hermes_home = os.getenv('HERMES_HOME', '').strip()
+    if hermes_home:
+        p = Path(hermes_home).expanduser()
+        # If HERMES_HOME points to a profiles/ subdir, walk up two levels to the base
+        if p.parent.name == 'profiles':
+            return p.parent.parent
+        # Otherwise trust it (e.g. test isolation sets HERMES_HOME to TEST_STATE_DIR)
+        return p
+
+    return Path.home() / '.hermes'
+
+_DEFAULT_HERMES_HOME = _resolve_base_hermes_home()
+
+
+def _read_active_profile_file() -> str:
+    """Read the sticky active profile from ~/.hermes/active_profile."""
+    ap_file = _DEFAULT_HERMES_HOME / 'active_profile'
+    if ap_file.exists():
+        try:
+            name = ap_file.read_text(encoding="utf-8").strip()
+            if name:
+                return name
+        except Exception:
+            logger.debug("Failed to read active profile file")
+    return 'default'
+
+
+# ── Public API ──────────────────────────────────────────────────────────────
+
+def get_active_profile_name() -> str:
+    """Return the currently active profile name."""
+    return _active_profile
+
+
+def get_active_hermes_home() -> Path:
+    """Return the HERMES_HOME path for the currently active profile."""
+    if _active_profile == 'default':
+        return _DEFAULT_HERMES_HOME
+    profile_dir = _DEFAULT_HERMES_HOME / 'profiles' / _active_profile
+    if profile_dir.is_dir():
+        return profile_dir
+    return _DEFAULT_HERMES_HOME
+
+
+def _set_hermes_home(home: Path):
+    """Set HERMES_HOME env var and monkey-patch cached module-level paths."""
+    os.environ['HERMES_HOME'] = str(home)
+
+    # Patch skills_tool module-level cache (snapshots HERMES_HOME at import)
+    try:
+        import tools.skills_tool as _sk
+        _sk.HERMES_HOME = home
+        _sk.SKILLS_DIR = home / 'skills'
+    except (ImportError, AttributeError):
+        logger.debug("Failed to patch skills_tool module")
+
+    # Patch cron/jobs module-level cache
+    try:
+        import cron.jobs as _cj
+        _cj.HERMES_DIR = home
+        _cj.CRON_DIR = home / 'cron'
+        _cj.JOBS_FILE = _cj.CRON_DIR / 'jobs.json'
+        _cj.OUTPUT_DIR = _cj.CRON_DIR / 'output'
+    except (ImportError, AttributeError):
+        logger.debug("Failed to patch cron.jobs module")
+
+
+def _reload_dotenv(home: Path):
+    """Load .env from the profile dir into os.environ with profile isolation.
+
+    Clears env vars that were loaded from the previously active profile before
+    applying the current profile's .env. This prevents API keys and other
+    profile-scoped secrets from leaking across profile switches.
+    """
+    global _loaded_profile_env_keys
+
+    # Remove keys loaded from the previous profile first.
+    for key in list(_loaded_profile_env_keys):
+        os.environ.pop(key, None)
+    _loaded_profile_env_keys = set()
+
+    env_path = home / '.env'
+    if not env_path.exists():
+        return
+    try:
+        loaded_keys: set[str] = set()
+        for line in env_path.read_text(encoding="utf-8").splitlines():
+            line = line.strip()
+            if line and not line.startswith('#') and '=' in line:
+                k, v = line.split('=', 1)
+                k = k.strip()
+                v = v.strip().strip('"').strip("'")
+                if k and v:
+                    os.environ[k] = v
+                    loaded_keys.add(k)
+        _loaded_profile_env_keys = loaded_keys
+    except Exception:
+        _loaded_profile_env_keys = set()
+        logger.debug("Failed to reload dotenv from %s", env_path)
+
+
+def init_profile_state() -> None:
+    """Initialize profile state at server startup.
+
+    Reads ~/.hermes/active_profile, sets HERMES_HOME env var, patches
+    module-level cached paths.  Called once from config.py after imports.
+    """
+    global _active_profile
+    _active_profile = _read_active_profile_file()
+    home = get_active_hermes_home()
+    _set_hermes_home(home)
+    _reload_dotenv(home)
+
+
+def switch_profile(name: str) -> dict:
+    """Switch the active profile.
+
+    Validates the profile exists, updates process state, patches module caches,
+    reloads .env, and reloads config.yaml.
+
+    Returns: {'profiles': [...], 'active': name}
+    Raises ValueError if profile doesn't exist or agent is busy.
+    """
+    global _active_profile
+
+    # Import here to avoid circular import at module load
+    from api.config import STREAMS, STREAMS_LOCK, reload_config
+
+    # Block if agent is running
+    with STREAMS_LOCK:
+        if len(STREAMS) > 0:
+            raise RuntimeError(
+                'Cannot switch profiles while an agent is running. '
+                'Cancel or wait for it to finish.'
+            )
+
+    # Resolve profile directory
+    if name == 'default':
+        home = _DEFAULT_HERMES_HOME
+    else:
+        home = _resolve_named_profile_home(name)
+        if not home.is_dir():
+            raise ValueError(f"Profile '{name}' does not exist.")
+
+    with _profile_lock:
+        _active_profile = name
+        _set_hermes_home(home)
+        _reload_dotenv(home)
+
+    # Write sticky default for CLI consistency
+    try:
+        ap_file = _DEFAULT_HERMES_HOME / 'active_profile'
+        ap_file.write_text(name if name != 'default' else '')
+    except Exception:
+        logger.debug("Failed to write active profile file")
+
+    # Reload config.yaml from the new profile
+    reload_config()
+
+    # Return profile-specific defaults so frontend can apply them
+    from api.workspace import get_last_workspace
+    from api.config import get_config
+    cfg = get_config()
+    model_cfg = cfg.get('model', {})
+    default_model = None
+    if isinstance(model_cfg, str):
+        default_model = model_cfg
+    elif isinstance(model_cfg, dict):
+        default_model = model_cfg.get('default')
+
+    return {
+        'profiles': list_profiles_api(),
+        'active': name,
+        'default_model': default_model,
+        'default_workspace': get_last_workspace(),
+    }
+
+
+def list_profiles_api() -> list:
+    """List all profiles with metadata, serialized for JSON response."""
+    try:
+        from hermes_cli.profiles import list_profiles
+        infos = list_profiles()
+    except ImportError:
+        # hermes_cli not available -- return just the default
+        return [_default_profile_dict()]
+
+    active = _active_profile
+    result = []
+    for p in infos:
+        result.append({
+            'name': p.name,
+            'path': str(p.path),
+            'is_default': p.is_default,
+            'is_active': p.name == active,
+            'gateway_running': p.gateway_running,
+            'model': p.model,
+            'provider': p.provider,
+            'has_env': p.has_env,
+            'skill_count': p.skill_count,
+        })
+    return result
+
+
+def _default_profile_dict() -> dict:
+    """Fallback profile dict when hermes_cli is not importable."""
+    return {
+        'name': 'default',
+        'path': str(_DEFAULT_HERMES_HOME),
+        'is_default': True,
+        'is_active': True,
+        'gateway_running': False,
+        'model': None,
+        'provider': None,
+        'has_env': (_DEFAULT_HERMES_HOME / '.env').exists(),
+        'skill_count': 0,
+    }
+
+
+def _validate_profile_name(name: str):
+    """Validate profile name format (matches hermes_cli.profiles upstream)."""
+    if name == 'default':
+        raise ValueError("Cannot create a profile named 'default' -- it is the built-in profile.")
+    # Use fullmatch (not match) so a trailing newline can't sneak past the $ anchor
+    if not _PROFILE_ID_RE.fullmatch(name):
+        raise ValueError(
+            f"Invalid profile name {name!r}. "
+            "Must match [a-z0-9][a-z0-9_-]{0,63}"
+        )
+
+
+def _profiles_root() -> Path:
+    """Return the canonical root that contains named profiles."""
+    return (_DEFAULT_HERMES_HOME / 'profiles').resolve()
+
+
+def _resolve_named_profile_home(name: str) -> Path:
+    """Resolve a named profile to a directory under the profiles root.
+
+    Validates *name* as a logical profile identifier first, then resolves the
+    final filesystem path and enforces containment under ~/.hermes/profiles.
+    """
+    _validate_profile_name(name)
+    profiles_root = _profiles_root()
+    candidate = (profiles_root / name).resolve()
+    candidate.relative_to(profiles_root)
+    return candidate
+
+
+def _create_profile_fallback(name: str, clone_from: str = None,
+                              clone_config: bool = False) -> Path:
+    """Create a profile directory without hermes_cli (Docker/standalone fallback)."""
+    profile_dir = _DEFAULT_HERMES_HOME / 'profiles' / name
+    if profile_dir.exists():
+        raise FileExistsError(f"Profile '{name}' already exists.")
+
+    # Bootstrap directory structure (exist_ok=False so a concurrent create raises)
+    profile_dir.mkdir(parents=True, exist_ok=False)
+    for subdir in _PROFILE_DIRS:
+        (profile_dir / subdir).mkdir(parents=True, exist_ok=True)
+
+    # Clone config files from source profile if requested
+    if clone_config and clone_from:
+        if clone_from == 'default':
+            source_dir = _DEFAULT_HERMES_HOME
+        else:
+            source_dir = _DEFAULT_HERMES_HOME / 'profiles' / clone_from
+        if source_dir.is_dir():
+            for filename in _CLONE_CONFIG_FILES:
+                src = source_dir / filename
+                if src.exists():
+                    shutil.copy2(src, profile_dir / filename)
+
+    return profile_dir
+
+
+def _write_endpoint_to_config(profile_dir: Path, base_url: str = None, api_key: str = None) -> None:
+    """Write custom endpoint fields into config.yaml for a profile."""
+    if not base_url and not api_key:
+        return
+    config_path = profile_dir / 'config.yaml'
+    try:
+        import yaml as _yaml
+    except ImportError:
+        return
+    cfg = {}
+    if config_path.exists():
+        try:
+            loaded = _yaml.safe_load(config_path.read_text(encoding="utf-8"))
+            if isinstance(loaded, dict):
+                cfg = loaded
+        except Exception:
+            logger.debug("Failed to load config from %s", config_path)
+    model_section = cfg.get('model', {})
+    if not isinstance(model_section, dict):
+        model_section = {}
+    if base_url:
+        model_section['base_url'] = base_url
+    if api_key:
+        model_section['api_key'] = api_key
+    cfg['model'] = model_section
+    config_path.write_text(_yaml.dump(cfg, default_flow_style=False, allow_unicode=True))
+
+
+def create_profile_api(name: str, clone_from: str = None,
+                       clone_config: bool = False,
+                       base_url: str = None,
+                       api_key: str = None) -> dict:
+    """Create a new profile. Returns the new profile info dict."""
+    _validate_profile_name(name)
+    # Defense-in-depth: validate clone_from here too, even though routes.py
+    # also validates it. Any caller that bypasses the HTTP layer gets protection.
+    if clone_from is not None and clone_from != 'default':
+        _validate_profile_name(clone_from)
+
+    try:
+        from hermes_cli.profiles import create_profile
+        create_profile(
+            name,
+            clone_from=clone_from,
+            clone_config=clone_config,
+            clone_all=False,
+            no_alias=True,
+        )
+    except ImportError:
+        _create_profile_fallback(name, clone_from, clone_config)
+
+    # Resolve the profile directory from the profile list when possible.
+    # hermes_cli and the webui runtime do not always agree on the exact root,
+    # so we prefer the path returned by list_profiles_api() and fall back to the
+    # standard profile location only if the profile cannot be found there yet.
+    profile_path = _DEFAULT_HERMES_HOME / 'profiles' / name
+    for p in list_profiles_api():
+        if p['name'] == name:
+            try:
+                profile_path = Path(p.get('path') or profile_path)
+            except Exception:
+                logger.debug("Failed to parse profile path")
+            break
+
+    profile_path.mkdir(parents=True, exist_ok=True)
+    _write_endpoint_to_config(profile_path, base_url=base_url, api_key=api_key)
+
+    # Find and return the newly created profile info.
+    # When hermes_cli is not importable, list_profiles_api() also falls back
+    # to the stub default-only list and won't find the new profile by name.
+    # In that case, return a complete profile dict directly.
+    for p in list_profiles_api():
+        if p['name'] == name:
+            return p
+    return {
+        'name': name,
+        'path': str(profile_path),
+        'is_default': False,
+        'is_active': _active_profile == name,
+        'gateway_running': False,
+        'model': None,
+        'provider': None,
+        'has_env': (profile_path / '.env').exists(),
+        'skill_count': 0,
+    }
+
+
+def delete_profile_api(name: str) -> dict:
+    """Delete a profile. Switches to default first if it's the active one."""
+    if name == 'default':
+        raise ValueError("Cannot delete the default profile.")
+    _validate_profile_name(name)
+
+    # If deleting the active profile, switch to default first
+    if _active_profile == name:
+        try:
+            switch_profile('default')
+        except RuntimeError:
+            raise RuntimeError(
+                f"Cannot delete active profile '{name}' while an agent is running. "
+                "Cancel or wait for it to finish."
+            )
+
+    try:
+        from hermes_cli.profiles import delete_profile
+        delete_profile(name, yes=True)
+    except ImportError:
+        # Manual fallback: just remove the directory
+        import shutil
+        profile_dir = _resolve_named_profile_home(name)
+        if profile_dir.is_dir():
+            shutil.rmtree(str(profile_dir))
+        else:
+            raise ValueError(f"Profile '{name}' does not exist.")
+
+    return {'ok': True, 'name': name}

api/session_ops.py

@@ -0,0 +1,151 @@
+"""Session-mutation operations for slash commands (/retry, /undo) and
+read-only aggregators (/status, /usage). Operates on the webui's own
+JSON Session store (api/models.py), not on hermes-agent's SQLite.
+
+Behavior parity reference: gateway/run.py:_handle_*_command in
+the hermes-agent repo.
+"""
+from __future__ import annotations
+import logging
+from typing import Any
+
+from api.config import LOCK
+from api.models import get_session, SESSIONS
+
+logger = logging.getLogger(__name__)
+
+
+def retry_last(session_id: str) -> dict[str, Any]:
+    """Truncate the session to before the last user message, return its text.
+
+    Mirrors gateway/run.py:_handle_retry_command. Caller (webui frontend)
+    is expected to put the returned text back in the composer and call
+    send() to resume the conversation -- the agent's gateway calls its own
+    _handle_message; the webui has no equivalent in-process pipeline.
+
+    Raises:
+        KeyError: session not found
+        ValueError: no user message in transcript
+    """
+    # get_session() and Session.save() both acquire the module-level LOCK
+    # internally (the latter via _write_session_index()), and LOCK is a
+    # non-reentrant threading.Lock — so they MUST be called outside our
+    # own `with LOCK:` block to avoid self-deadlocking.
+    #
+    # The race we close is the read-modify-write of s.messages: two
+    # concurrent /api/session/retry calls could otherwise both compute the
+    # same last_user_idx from the same history and double-truncate. We
+    # serialize just the in-memory mutation; persistence happens outside
+    # the lock and is naturally last-write-wins on a consistent state.
+    #
+    # Stale-object guard: on a cache miss, two concurrent get_session()
+    # calls can each load and cache a *different* Session instance for the
+    # same session_id (the second store_clobbers the first). Re-bind to
+    # the canonical cached instance inside the lock so the mutation lands
+    # on the object the next reader will see, not a stale parallel copy.
+    s = get_session(session_id)  # raises KeyError if missing
+    with LOCK:
+        s = SESSIONS.get(session_id, s)
+        history = s.messages or []
+        last_user_idx = None
+        for i in range(len(history) - 1, -1, -1):
+            if history[i].get('role') == 'user':
+                last_user_idx = i
+                break
+        if last_user_idx is None:
+            raise ValueError('No previous message to retry.')
+
+        last_user_text = _extract_text(history[last_user_idx].get('content', ''))
+        removed_count = len(history) - last_user_idx
+        s.messages = history[:last_user_idx]
+    s.save()
+    return {'last_user_text': last_user_text, 'removed_count': removed_count}
+
+
+def undo_last(session_id: str) -> dict[str, Any]:
+    """Remove the most recent user message and everything after it.
+
+    Mirrors gateway/run.py:_handle_undo_command. Returns a preview of the
+    removed text so the UI can confirm to the user.
+
+    Raises:
+        KeyError: session not found
+        ValueError: no user message in transcript
+    """
+    s = get_session(session_id)  # acquires LOCK transiently
+    with LOCK:
+        # Stale-object guard — see retry_last for the rationale.
+        s = SESSIONS.get(session_id, s)
+        history = s.messages or []
+        last_user_idx = None
+        for i in range(len(history) - 1, -1, -1):
+            if history[i].get('role') == 'user':
+                last_user_idx = i
+                break
+        if last_user_idx is None:
+            raise ValueError('Nothing to undo.')
+
+        removed_text = _extract_text(history[last_user_idx].get('content', ''))
+        removed_count = len(history) - last_user_idx
+        s.messages = history[:last_user_idx]
+    s.save()  # outside LOCK -- save() re-acquires LOCK via _write_session_index()
+    preview = (removed_text[:40] + '...') if len(removed_text) > 40 else removed_text
+    return {
+        'removed_count': removed_count,
+        'removed_preview': preview,
+    }
+
+
+def session_status(session_id: str) -> dict[str, Any]:
+    """Return a snapshot of session state for /status.
+
+    Webui equivalent of gateway/run.py:_handle_status_command. The agent's
+    "agent_running" comes from `session_key in self._running_agents`; the
+    webui equivalent is whether the session has an active stream
+    (active_stream_id is set).
+    """
+    s = get_session(session_id)
+    return {
+        'session_id': s.session_id,
+        'title': s.title,
+        'model': s.model,
+        'workspace': s.workspace,
+        'personality': s.personality,
+        'message_count': len(s.messages or []),
+        'created_at': s.created_at,
+        'updated_at': s.updated_at,
+        'agent_running': bool(getattr(s, 'active_stream_id', None)),
+    }
+
+
+def session_usage(session_id: str) -> dict[str, Any]:
+    """Return token usage and cost for /usage.
+
+    Mirrors gateway/run.py:_handle_usage_command's basic counters. The
+    agent shows additional fields (rate-limit headroom etc.) that depend
+    on provider API responses we don't have in webui -- those are deferred.
+    """
+    s = get_session(session_id)
+    inp = int(s.input_tokens or 0)
+    out = int(s.output_tokens or 0)
+    return {
+        'input_tokens': inp,
+        'output_tokens': out,
+        'total_tokens': inp + out,
+        'estimated_cost': s.estimated_cost,
+        'model': s.model,
+    }
+
+
+def _extract_text(content: Any) -> str:
+    """Flatten message content to plain text. Agent stores either a string
+    or a list of {type, text|...} parts; webui needs the user-typed text."""
+    if isinstance(content, str):
+        return content
+    if isinstance(content, list):
+        parts = []
+        for p in content:
+            if isinstance(p, dict) and p.get('type') == 'text':
+                parts.append(p.get('text', ''))
+        return ' '.join(parts)
+    return str(content)

api/startup.py

@@ -0,0 +1,74 @@
+"""Hermes Web UI -- startup helpers."""
+from __future__ import annotations
+import os, stat, subprocess, sys
+from pathlib import Path
+
+# Credential files that should never be world-readable
+_SENSITIVE_FILES = (
+    '.env',
+    'google_token.json',
+    'google_client_secret.json',
+    '.signing_key',
+    'auth.json',
+)
+
+
+def fix_credential_permissions() -> None:
+    """Ensure sensitive files in HERMES_HOME are chmod 600 (owner-only)."""
+    hermes_home = Path(os.environ.get('HERMES_HOME', str(Path.home() / '.hermes')))
+    if not hermes_home.is_dir():
+        return
+    for name in _SENSITIVE_FILES:
+        fpath = hermes_home / name
+        if not fpath.exists():
+            continue
+        try:
+            current = stat.S_IMODE(fpath.stat().st_mode)
+            if current & 0o077:  # group or other bits set
+                fpath.chmod(0o600)
+                print(f'  [security] fixed permissions on {fpath.name} ({oct(current)} -> 0600)', flush=True)
+        except OSError:
+            pass  # best-effort; don't abort startup
+
+
+def _agent_dir() -> Path | None:
+    hermes_home = Path(os.environ.get('HERMES_HOME', str(Path.home() / '.hermes')))
+    for raw in [os.environ.get('HERMES_WEBUI_AGENT_DIR', '').strip(), str(hermes_home / 'hermes-agent')]:
+        if not raw:
+            continue
+        p = Path(raw).expanduser()
+        if p.is_dir():
+            return p.resolve()
+    return None
+
+def auto_install_agent_deps() -> bool:
+    agent_dir = _agent_dir()
+    if agent_dir is None:
+        print('[!!] Auto-install skipped: agent directory not found.', flush=True)
+        return False
+    req_file = agent_dir / 'requirements.txt'
+    pyproject = agent_dir / 'pyproject.toml'
+    if req_file.exists():
+        install_args = [sys.executable, '-m', 'pip', 'install', '--quiet', '-r', str(req_file)]
+        print(f'     Installing from {req_file} ...', flush=True)
+    elif pyproject.exists():
+        install_args = [sys.executable, '-m', 'pip', 'install', '--quiet', str(agent_dir)]
+        print(f'     Installing from {agent_dir} (pyproject.toml) ...', flush=True)
+    else:
+        print('[!!] Auto-install skipped: no requirements.txt or pyproject.toml in agent dir.', flush=True)
+        return False
+    try:
+        result = subprocess.run(install_args, capture_output=True, text=True, timeout=120)
+        if result.returncode != 0:
+            print(f'[!!] pip install failed (exit {result.returncode}):', flush=True)
+            for line in (result.stderr or '').splitlines()[-10:]:
+                print(f'     {line}', flush=True)
+            return False
+        print('[ok] pip install completed.', flush=True)
+        return True
+    except subprocess.TimeoutExpired:
+        print('[!!] Auto-install timed out after 120s.', flush=True)
+        return False
+    except Exception as e:
+        print(f'[!!] Auto-install error: {e}', flush=True)
+        return False

api/state_sync.py

@@ -0,0 +1,118 @@
+"""
+Hermes Web UI -- Optional state.db sync bridge.
+
+Mirrors WebUI session metadata (token usage, title, model) into the
+hermes-agent state.db so that /insights, session lists, and cost
+tracking include WebUI activity.
+
+This is opt-in via the 'sync_to_insights' setting (default: off).
+All operations are wrapped in try/except -- if state.db is unavailable,
+locked, or the schema doesn't match, the WebUI continues normally.
+
+The bridge uses absolute token counts (not deltas) because the WebUI
+Session object already accumulates totals across turns. This avoids
+any double-counting risk.
+"""
+import logging
+import os
+from pathlib import Path
+
+logger = logging.getLogger(__name__)
+
+
+def _get_state_db():
+    """Get a SessionDB instance for the active profile's state.db.
+    Returns None if hermes_state is not importable or DB is unavailable.
+    Each caller is responsible for calling db.close() when done.
+    """
+    try:
+        from hermes_state import SessionDB
+    except ImportError:
+        return None
+
+    try:
+        from api.profiles import get_active_hermes_home
+        hermes_home = Path(get_active_hermes_home()).expanduser().resolve()
+    except Exception:
+        logger.debug("Failed to resolve hermes home, using default")
+        hermes_home = Path(os.getenv('HERMES_HOME', str(Path.home() / '.hermes')))
+
+    db_path = hermes_home / 'state.db'
+    if not db_path.exists():
+        return None
+
+    try:
+        return SessionDB(db_path)
+    except Exception:
+        logger.debug("Failed to open state.db")
+        return None
+
+
+def sync_session_start(session_id: str, model=None) -> None:
+    """Register a WebUI session in state.db (idempotent).
+    Called when a session's first message is sent.
+    """
+    db = _get_state_db()
+    if not db:
+        return
+    try:
+        db.ensure_session(
+            session_id=session_id,
+            source='webui',
+            model=model,
+        )
+    except Exception:
+        logger.debug("Failed to sync session start to state.db")
+    finally:
+        try:
+            db.close()
+        except Exception:
+            logger.debug("Failed to close state.db")
+
+
+def sync_session_usage(session_id: str, input_tokens: int=0, output_tokens: int=0,
+                       estimated_cost=None, model=None, title: str=None,
+                       message_count: int=None) -> None:
+    """Update token usage and title for a WebUI session in state.db.
+    Called after each turn completes. Uses absolute=True to set totals
+    (the WebUI Session already accumulates across turns).
+    """
+    db = _get_state_db()
+    if not db:
+        return
+    try:
+        # Ensure session exists first (idempotent)
+        db.ensure_session(session_id=session_id, source='webui', model=model)
+        # Set absolute token counts
+        db.update_token_counts(
+            session_id=session_id,
+            input_tokens=input_tokens,
+            output_tokens=output_tokens,
+            estimated_cost_usd=estimated_cost,
+            model=model,
+            absolute=True,
+        )
+        # Update title if we have one, using the public API
+        if title:
+            try:
+                db.set_session_title(session_id, title)
+            except Exception:
+                logger.debug("Failed to sync session title to state.db")
+        # Update message count
+        if message_count is not None:
+            try:
+                def _set_msg_count(conn):
+                    conn.execute(
+                        "UPDATE sessions SET message_count = ? WHERE id = ?",
+                        (message_count, session_id),
+                    )
+                db._execute_write(_set_msg_count)
+            except Exception:
+                logger.debug("Failed to sync message count to state.db")
+    except Exception:
+        logger.debug("Failed to sync session usage to state.db")
+    finally:
+        try:
+            db.close()
+        except Exception:
+            logger.debug("Failed to close state.db")

api/updates.py

@@ -0,0 +1,257 @@
+"""
+Hermes Web UI -- Self-update checker.
+
+Checks if the webui and hermes-agent git repos are behind their upstream
+branches. Results are cached server-side (30-min TTL) so git fetch runs
+at most twice per hour regardless of client count.
+
+Skips repos that are not git checkouts (e.g. Docker baked images where
+.git does not exist).
+"""
+import subprocess
+import threading
+import time
+from pathlib import Path
+
+from api.config import REPO_ROOT
+
+# Lazy -- may be None if agent not found
+try:
+    from api.config import _AGENT_DIR
+except ImportError:
+    _AGENT_DIR = None
+
+_update_cache = {'webui': None, 'agent': None, 'checked_at': 0}
+_cache_lock = threading.Lock()
+_check_in_progress = False
+_apply_lock = threading.Lock()   # prevents concurrent stash/pull/pop on same repo
+CACHE_TTL = 1800  # 30 minutes
+
+
+def _run_git(args, cwd, timeout=10):
+    """Run a git command and return (useful output, ok).
+
+    On failure, returns stderr (or stdout as fallback) so callers can
+    surface actionable git error messages instead of empty strings.
+    """
+    try:
+        r = subprocess.run(
+            ['git'] + args, cwd=str(cwd), capture_output=True,
+            text=True, timeout=timeout,
+        )
+        stdout = r.stdout.strip()
+        stderr = r.stderr.strip()
+        if r.returncode == 0:
+            return stdout, True
+        return stderr or stdout or f"git exited with status {r.returncode}", False
+    except subprocess.TimeoutExpired as exc:
+        detail = (getattr(exc, 'stderr', None) or getattr(exc, 'stdout', None) or '').strip()
+        return detail or f"git {' '.join(args)} timed out after {timeout}s", False
+    except FileNotFoundError:
+        return 'git executable not found', False
+    except OSError as exc:
+        return f'git failed to start: {exc}', False
+
+
+def _split_remote_ref(ref):
+    """Split 'origin/branch-name' into ('origin', 'branch-name').
+
+    Returns (None, ref) if ref contains no slash.
+    """
+    if '/' not in ref:
+        return None, ref
+    remote, branch = ref.split('/', 1)
+    return remote, branch
+
+
+def _detect_default_branch(path):
+    """Detect the remote default branch (master or main)."""
+    out, ok = _run_git(['symbolic-ref', 'refs/remotes/origin/HEAD'], path)
+    if ok and out:
+        # refs/remotes/origin/master -> master
+        return out.split('/')[-1]
+    # Fallback: try master, then main
+    for branch in ('master', 'main'):
+        _, ok = _run_git(['rev-parse', '--verify', f'origin/{branch}'], path)
+        if ok:
+            return branch
+    return 'master'
+
+
+def _check_repo(path, name):
+    """Check if a git repo is behind its upstream. Returns dict or None."""
+    if path is None or not (path / '.git').exists():
+        return None
+
+    # Fetch latest from origin (network call, cached by TTL)
+    _, fetch_ok = _run_git(['fetch', 'origin', '--quiet'], path, timeout=15)
+    if not fetch_ok:
+        return {'name': name, 'behind': 0, 'error': 'fetch failed'}
+
+    # Use the current branch's upstream tracking branch, not the repo default.
+    # This avoids false "N updates behind" alerts when the user is on a feature
+    # branch and master/main has moved forward with unrelated commits.
+    # If no upstream is set (brand-new local branch), fall back to the default branch.
+    upstream, ok = _run_git(['rev-parse', '--abbrev-ref', '@{upstream}'], path)
+    if ok and upstream:
+        # upstream is like "origin/feat/foo" — use it directly in rev-list
+        compare_ref = upstream
+    else:
+        branch = _detect_default_branch(path)
+        compare_ref = f'origin/{branch}'
+
+    # Count commits behind
+    out, ok = _run_git(['rev-list', '--count', f'HEAD..{compare_ref}'], path)
+    behind = int(out) if ok and out.isdigit() else 0
+
+    # Get short SHAs for display
+    current, _ = _run_git(['rev-parse', '--short', 'HEAD'], path)
+    latest, _ = _run_git(['rev-parse', '--short', compare_ref], path)
+
+    return {
+        'name': name,
+        'behind': behind,
+        'current_sha': current,
+        'latest_sha': latest,
+        'branch': compare_ref,
+    }
+
+
+def check_for_updates(force=False):
+    """Return cached update status for webui and agent repos."""
+    global _check_in_progress
+    with _cache_lock:
+        if not force and time.time() - _update_cache['checked_at'] < CACHE_TTL:
+            return dict(_update_cache)
+        if _check_in_progress:
+            return dict(_update_cache)  # another thread is already checking
+        _check_in_progress = True
+
+    try:
+        # Run checks outside the lock (network I/O)
+        webui_info = _check_repo(REPO_ROOT, 'webui')
+        agent_info = _check_repo(_AGENT_DIR, 'agent')
+
+        with _cache_lock:
+            _update_cache['webui'] = webui_info
+            _update_cache['agent'] = agent_info
+            _update_cache['checked_at'] = time.time()
+            return dict(_update_cache)
+    finally:
+        _check_in_progress = False
+
+
+def apply_update(target):
+    """Stash, pull --ff-only, pop for the given target repo."""
+    if not _apply_lock.acquire(blocking=False):
+        return {'ok': False, 'message': 'Update already in progress'}
+    try:
+        return _apply_update_inner(target)
+    finally:
+        _apply_lock.release()
+
+
+def _apply_update_inner(target):
+    """Inner implementation of apply_update, called under _apply_lock."""
+    if target == 'webui':
+        path = REPO_ROOT
+    elif target == 'agent':
+        path = _AGENT_DIR
+    else:
+        return {'ok': False, 'message': f'Unknown target: {target}'}
+
+    if path is None or not (path / '.git').exists():
+        return {'ok': False, 'message': 'Not a git repository'}
+
+    # Use the current branch's upstream for pull, matching the behaviour
+    # of _check_repo. Falls back to default branch if no upstream is set.
+    upstream, ok = _run_git(['rev-parse', '--abbrev-ref', '@{upstream}'], path)
+    if ok and upstream:
+        compare_ref = upstream
+    else:
+        branch = _detect_default_branch(path)
+        compare_ref = f'origin/{branch}'
+
+    # Fetch before attempting pull, so the remote ref is current.
+    _, fetch_ok = _run_git(['fetch', 'origin', '--quiet'], path, timeout=15)
+    if not fetch_ok:
+        return {
+            'ok': False,
+            'message': (
+                'Could not reach the remote repository. '
+                'Check your internet connection and try again.'
+            ),
+        }
+
+    # Check for dirty working tree (ignore untracked files — git stash
+    # doesn't include them, so stashing on '??' alone leaves nothing to pop)
+    status_out, status_ok = _run_git(
+        ['status', '--porcelain', '--untracked-files=no'], path
+    )
+    if not status_ok:
+        return {'ok': False, 'message': f'Failed to inspect repo status: {status_out[:200]}'}
+    # Fail early on unresolved merge conflicts
+    if any(line[:2] in {'DD', 'AU', 'UD', 'UA', 'DU', 'AA', 'UU'}
+           for line in status_out.splitlines()):
+        return {'ok': False, 'message': 'Repository has unresolved merge conflicts'}
+    stashed = False
+    if status_out:
+        _, ok = _run_git(['stash'], path)
+        if not ok:
+            return {'ok': False, 'message': 'Failed to stash local changes'}
+        stashed = True
+
+    # Pull with ff-only (no merge commits).
+    # Split tracking refs like 'origin/main' into separate remote + branch
+    # arguments — git treats 'origin/main' as a repository name otherwise.
+    remote, branch = _split_remote_ref(compare_ref)
+    pull_args = ['pull', '--ff-only']
+    if remote:
+        pull_args.extend([remote, branch])
+    else:
+        pull_args.append(compare_ref)
+    pull_out, pull_ok = _run_git(pull_args, path, timeout=30)
+    if not pull_ok:
+        if stashed:
+            _run_git(['stash', 'pop'], path)
+
+        # Diagnose the most common failure modes and surface actionable messages.
+        pull_lower = pull_out.lower()
+        if 'not possible to fast-forward' in pull_lower or 'diverged' in pull_lower:
+            return {
+                'ok': False,
+                'message': (
+                    f'The local {target} repo has commits that are not on the remote '
+                    'branch, so a fast-forward update is not possible. '
+                    'Run: git -C ' + str(path) + ' fetch origin && '
+                    'git -C ' + str(path) + ' reset --hard ' + compare_ref
+                ),
+                'diverged': True,
+            }
+        if 'does not track' in pull_lower or 'no tracking information' in pull_lower:
+            return {
+                'ok': False,
+                'message': (
+                    f'The local {target} branch has no upstream tracking branch configured. '
+                    'Run: git -C ' + str(path) + ' branch --set-upstream-to=' + compare_ref
+                ),
+            }
+        # Generic fallback — include the raw git output for debugging.
+        detail = pull_out.strip()[:300] if pull_out.strip() else '(no output from git)'
+        return {'ok': False, 'message': f'Pull failed: {detail}'}
+
+    # Pop stash if we stashed
+    if stashed:
+        _, pop_ok = _run_git(['stash', 'pop'], path)
+        if not pop_ok:
+            return {
+                'ok': False,
+                'message': 'Updated but stash pop failed -- manual merge needed',
+                'stash_conflict': True,
+            }
+
+    # Invalidate cache
+    with _cache_lock:
+        _update_cache['checked_at'] = 0
+
+    return {'ok': True, 'message': f'{target} updated successfully', 'target': target}

api/upload.py

@@ -0,0 +1,131 @@
+"""
+Hermes Web UI -- File upload: multipart parser and upload handler.
+"""
+import re as _re
+import email.parser
+import tempfile
+from pathlib import Path
+
+from api.config import MAX_UPLOAD_BYTES
+from api.helpers import j, bad
+from api.models import get_session
+from api.workspace import safe_resolve_ws
+
+
+def parse_multipart(rfile, content_type, content_length) -> tuple:
+    import re as _re, email.parser as _ep
+    m = _re.search(r'boundary=([^;\s]+)', content_type)
+    if not m:
+        raise ValueError('No boundary in Content-Type')
+    boundary = m.group(1).strip('"').encode()
+    raw = rfile.read(content_length)
+    fields = {}
+    files = {}
+    delimiter = b'--' + boundary
+    end_marker = b'--' + boundary + b'--'
+    parts = raw.split(delimiter)
+    for part in parts[1:]:
+        stripped = part.lstrip(b'\r\n')
+        if stripped.startswith(b'--'):
+            break
+        sep = b'\r\n\r\n' if b'\r\n\r\n' in part else b'\n\n'
+        if sep not in part:
+            continue
+        header_raw, body = part.split(sep, 1)
+        if body.endswith(b'\r\n'):
+            body = body[:-2]
+        elif body.endswith(b'\n'):
+            body = body[:-1]
+        header_text = header_raw.lstrip(b'\r\n').decode('utf-8', errors='replace')
+        msg = _ep.HeaderParser().parsestr(header_text)
+        disp = msg.get('Content-Disposition', '')
+        name_m = _re.search(r'name="([^"]*)"', disp)
+        file_m = _re.search(r'filename="([^"]*)"', disp)
+        if not name_m:
+            continue
+        name = name_m.group(1)
+        if file_m:
+            files[name] = (file_m.group(1), body)
+        else:
+            fields[name] = body.decode('utf-8', errors='replace')
+    return fields, files
+
+
+def _sanitize_upload_name(filename: str) -> str:
+    safe_name = _re.sub(r'[^\w.\-]', '_', Path(filename).name)[:200]
+    if not safe_name or safe_name.strip('.') == '':
+        raise ValueError('Invalid filename')
+    return safe_name
+
+
+def handle_upload(handler):
+    import traceback as _tb
+    try:
+        content_type = handler.headers.get('Content-Type', '')
+        content_length = int(handler.headers.get('Content-Length', 0) or 0)
+        if content_length > MAX_UPLOAD_BYTES:
+            return j(handler, {'error': f'File too large (max {MAX_UPLOAD_BYTES//1024//1024}MB)'}, status=413)
+        fields, files = parse_multipart(handler.rfile, content_type, content_length)
+        session_id = fields.get('session_id', '')
+        if 'file' not in files:
+            return j(handler, {'error': 'No file field in request'}, status=400)
+        filename, file_bytes = files['file']
+        if not filename:
+            return j(handler, {'error': 'No filename in upload'}, status=400)
+        try:
+            s = get_session(session_id)
+        except KeyError:
+            return j(handler, {'error': 'Session not found'}, status=404)
+        workspace = Path(s.workspace)
+        safe_name = _sanitize_upload_name(filename)
+        dest = safe_resolve_ws(workspace, safe_name)
+        dest.write_bytes(file_bytes)
+        return j(handler, {'filename': safe_name, 'path': str(dest), 'size': dest.stat().st_size})
+    except ValueError as e:
+        return j(handler, {'error': str(e)}, status=400)
+    except Exception:
+        print('[webui] upload error: ' + _tb.format_exc(), flush=True)
+        return j(handler, {'error': 'Upload failed'}, status=500)
+
+
+def handle_transcribe(handler):
+    import traceback as _tb
+    temp_path = None
+    try:
+        content_type = handler.headers.get('Content-Type', '')
+        content_length = int(handler.headers.get('Content-Length', 0) or 0)
+        if content_length > MAX_UPLOAD_BYTES:
+            return j(handler, {'error': f'File too large (max {MAX_UPLOAD_BYTES//1024//1024}MB)'}, status=413)
+        fields, files = parse_multipart(handler.rfile, content_type, content_length)
+        if 'file' not in files:
+            return j(handler, {'error': 'No file field in request'}, status=400)
+        filename, file_bytes = files['file']
+        if not filename:
+            return j(handler, {'error': 'No filename in upload'}, status=400)
+        safe_name = _sanitize_upload_name(filename)
+        suffix = Path(safe_name).suffix or '.webm'
+        with tempfile.NamedTemporaryFile(prefix='webui-stt-', suffix=suffix, delete=False) as tmp:
+            temp_path = tmp.name
+            tmp.write(file_bytes)
+        try:
+            from tools.transcription_tools import transcribe_audio
+        except ImportError:
+            return j(handler, {'error': 'Speech-to-text is unavailable on this server'}, status=503)
+        result = transcribe_audio(temp_path)
+        if not result.get('success'):
+            msg = str(result.get('error') or 'Transcription failed')
+            status = 503 if 'unavailable' in msg.lower() or 'not configured' in msg.lower() else 400
+            return j(handler, {'error': msg}, status=status)
+        transcript = str(result.get('transcript') or '').strip()
+        return j(handler, {'ok': True, 'transcript': transcript})
+    except ValueError as e:
+        return j(handler, {'error': str(e)}, status=400)
+    except Exception:
+        print('[webui] transcribe error: ' + _tb.format_exc(), flush=True)
+        return j(handler, {'error': 'Transcription failed'}, status=500)
+    finally:
+        if temp_path:
+            try:
+                Path(temp_path).unlink(missing_ok=True)
+            except Exception:
+                pass

api/workspace.py

@@ -0,0 +1,379 @@
+"""
+Hermes Web UI -- Workspace and file system helpers.
+
+Workspace lists and last-used workspace are stored per-profile so each
+profile has its own workspace configuration.  State files live at
+``{profile_home}/webui_state/workspaces.json`` and
+``{profile_home}/webui_state/last_workspace.txt``.  The global STATE_DIR
+paths are used as fallback when no profile module is available.
+"""
+import json
+import logging
+import os
+import subprocess
+from pathlib import Path
+
+logger = logging.getLogger(__name__)
+
+from api.config import (
+    WORKSPACES_FILE as _GLOBAL_WS_FILE,
+    LAST_WORKSPACE_FILE as _GLOBAL_LW_FILE,
+    DEFAULT_WORKSPACE as _BOOT_DEFAULT_WORKSPACE,
+    MAX_FILE_BYTES, IMAGE_EXTS, MD_EXTS
+)
+
+
+# ── Profile-aware path resolution ───────────────────────────────────────────
+
+def _profile_state_dir() -> Path:
+    """Return the webui_state directory for the active profile.
+
+    For the default profile, returns the global STATE_DIR (respects
+    HERMES_WEBUI_STATE_DIR env var for test isolation).
+    For named profiles, returns {profile_home}/webui_state/.
+    """
+    try:
+        from api.profiles import get_active_profile_name, get_active_hermes_home
+        name = get_active_profile_name()
+        if name and name != 'default':
+            d = get_active_hermes_home() / 'webui_state'
+            d.mkdir(parents=True, exist_ok=True)
+            return d
+    except ImportError:
+        logger.debug("Failed to import profiles module, using global state dir")
+    return _GLOBAL_WS_FILE.parent
+
+
+def _workspaces_file() -> Path:
+    """Return the workspaces.json path for the active profile."""
+    return _profile_state_dir() / 'workspaces.json'
+
+
+def _last_workspace_file() -> Path:
+    """Return the last_workspace.txt path for the active profile."""
+    return _profile_state_dir() / 'last_workspace.txt'
+
+
+def _profile_default_workspace() -> str:
+    """Read the profile's default workspace from its config.yaml.
+
+    Checks keys in priority order:
+      1. 'workspace'         — explicit webui workspace key
+      2. 'default_workspace' — alternate explicit key
+      3. 'terminal.cwd'      — hermes-agent terminal working dir (most common)
+
+    Falls back to the boot-time DEFAULT_WORKSPACE constant.
+    """
+    try:
+        from api.config import get_config
+        cfg = get_config()
+        # Explicit webui workspace keys first
+        for key in ('workspace', 'default_workspace'):
+            ws = cfg.get(key)
+            if ws:
+                p = Path(str(ws)).expanduser().resolve()
+                if p.is_dir():
+                    return str(p)
+        # Fall through to terminal.cwd — the agent's configured working directory
+        terminal_cfg = cfg.get('terminal', {})
+        if isinstance(terminal_cfg, dict):
+            cwd = terminal_cfg.get('cwd', '')
+            if cwd and str(cwd) not in ('.', ''):
+                p = Path(str(cwd)).expanduser().resolve()
+                if p.is_dir():
+                    return str(p)
+    except (ImportError, Exception):
+        logger.debug("Failed to load profile default workspace config")
+    return str(_BOOT_DEFAULT_WORKSPACE)
+
+
+# ── Public API ──────────────────────────────────────────────────────────────
+
+def _clean_workspace_list(workspaces: list) -> list:
+    """Sanitize a workspace list:
+    - Remove entries whose paths no longer exist on disk.
+    - Remove entries whose paths live inside another profile's directory
+      (e.g. ~/.hermes/profiles/X/... should not appear on a different profile).
+    - Rename any entry whose name is literally 'default' to 'Home' (avoids
+      confusion with the 'default' profile name).
+    Returns the cleaned list (may be empty).
+    """
+    hermes_profiles = (Path.home() / '.hermes' / 'profiles').resolve()
+    result = []
+    for w in workspaces:
+        path = w.get('path', '')
+        name = w.get('name', '')
+        p = Path(path).resolve() if path else Path('/')
+        # Skip paths that no longer exist
+        if not p.is_dir():
+            continue
+        # Skip paths inside a DIFFERENT profile's directory (cross-profile leak).
+        # Allow paths inside the CURRENT profile's own directory (e.g. test workspaces
+        # created under ~/.hermes/profiles/webui/webui-mvp-test/).
+        try:
+            p.relative_to(hermes_profiles)
+            # p is under ~/.hermes/profiles/ — only skip if it's under a DIFFERENT profile
+            try:
+                from api.profiles import get_active_hermes_home
+                own_profile_dir = get_active_hermes_home().resolve()
+                p.relative_to(own_profile_dir)
+                # p is under our own profile dir — keep it
+            except (ValueError, Exception):
+                continue  # under profiles/ but not our own — cross-profile leak, skip
+        except ValueError:
+            pass  # not under profiles/ at all — keep it
+        # Rename confusing 'default' label to 'Home'
+        if name.lower() == 'default':
+            name = 'Home'
+        result.append({'path': str(p), 'name': name})
+    return result
+
+
+def _migrate_global_workspaces() -> list:
+    """Read the legacy global workspaces.json, clean it, and return the result.
+
+    This is the migration path for users upgrading from a pre-profile version:
+    their global file may contain cross-profile entries, test artifacts, and
+    stale paths accumulated over time.  We clean it in-place and rewrite it.
+    """
+    if not _GLOBAL_WS_FILE.exists():
+        return []
+    try:
+        raw = json.loads(_GLOBAL_WS_FILE.read_text(encoding='utf-8'))
+        cleaned = _clean_workspace_list(raw)
+        if len(cleaned) != len(raw):
+            # Rewrite the cleaned version so future reads are already clean
+            _GLOBAL_WS_FILE.write_text(
+                json.dumps(cleaned, ensure_ascii=False, indent=2), encoding='utf-8'
+            )
+        return cleaned
+    except Exception:
+        return []
+
+
+def load_workspaces() -> list:
+    ws_file = _workspaces_file()
+    if ws_file.exists():
+        try:
+            raw = json.loads(ws_file.read_text(encoding='utf-8'))
+            cleaned = _clean_workspace_list(raw)
+            if len(cleaned) != len(raw):
+                # Persist the cleaned version so stale entries don't keep reappearing
+                try:
+                    ws_file.write_text(
+                        json.dumps(cleaned, ensure_ascii=False, indent=2), encoding='utf-8'
+                    )
+                except Exception:
+                    logger.debug("Failed to persist cleaned workspace list")
+            return cleaned or [{'path': _profile_default_workspace(), 'name': 'Home'}]
+        except Exception:
+            logger.debug("Failed to load workspaces from %s", ws_file)
+    # No profile-local file yet.
+    # For the DEFAULT profile: migrate from the legacy global file (one-time cleanup).
+    # For NAMED profiles: always start clean with just their own workspace.
+    try:
+        from api.profiles import get_active_profile_name
+        is_default = get_active_profile_name() in ('default', None)
+    except ImportError:
+        is_default = True
+    if is_default:
+        migrated = _migrate_global_workspaces()
+        if migrated:
+            return migrated
+    # Fresh start: single entry from the profile's configured workspace, labeled "Home"
+    return [{'path': _profile_default_workspace(), 'name': 'Home'}]
+
+
+def save_workspaces(workspaces: list) -> None:
+    ws_file = _workspaces_file()
+    ws_file.parent.mkdir(parents=True, exist_ok=True)
+    ws_file.write_text(json.dumps(workspaces, ensure_ascii=False, indent=2), encoding='utf-8')
+
+
+def get_last_workspace() -> str:
+    lw_file = _last_workspace_file()
+    if lw_file.exists():
+        try:
+            p = lw_file.read_text(encoding='utf-8').strip()
+            if p and Path(p).is_dir():
+                return p
+        except Exception:
+            logger.debug("Failed to read last workspace from %s", lw_file)
+    # Fallback: try global file
+    if _GLOBAL_LW_FILE.exists():
+        try:
+            p = _GLOBAL_LW_FILE.read_text(encoding='utf-8').strip()
+            if p and Path(p).is_dir():
+                return p
+        except Exception:
+            logger.debug("Failed to read global last workspace")
+    return _profile_default_workspace()
+
+
+def set_last_workspace(path: str) -> None:
+    try:
+        lw_file = _last_workspace_file()
+        lw_file.parent.mkdir(parents=True, exist_ok=True)
+        lw_file.write_text(str(path), encoding='utf-8')
+    except Exception:
+        logger.debug("Failed to set last workspace")
+
+
+def resolve_trusted_workspace(path: str | Path | None = None) -> Path:
+    """Resolve and validate a workspace path.
+
+    A path is trusted if it satisfies at least one of:
+      (A) It is under the user's home directory (Path.home()).
+          Works cross-platform: ~/... on Linux/macOS, C:\\Users\\... on Windows.
+      (B) It is already in the profile's saved workspace list.
+          This covers self-hosted deployments where workspaces live outside home
+          (e.g. /data/projects, /opt/workspace) — once a workspace is saved by
+          an admin, it can be reused without re-validation.
+
+    Additionally enforced regardless of (A)/(B):
+      1. The path must exist.
+      2. The path must be a directory.
+      3. The path must not be a known system root (/etc, /usr, /var, /bin, /sbin,
+         /boot, /proc, /sys, /dev, /root on Linux/macOS; Windows system dirs).
+         This prevents even admin-saved workspaces from pointing at OS internals.
+
+    None/empty path falls back to the boot-time DEFAULT_WORKSPACE, which is always
+    trusted (it was validated at server startup).
+    """
+    _BLOCKED_SYSTEM_ROOTS = {
+        # Linux / macOS
+        Path('/etc'), Path('/usr'), Path('/var'), Path('/bin'), Path('/sbin'),
+        Path('/boot'), Path('/proc'), Path('/sys'), Path('/dev'),
+        Path('/lib'), Path('/lib64'), Path('/opt/homebrew'),
+    }
+
+    if path in (None, ""):
+        return Path(_BOOT_DEFAULT_WORKSPACE).expanduser().resolve()
+
+    candidate = Path(path).expanduser().resolve()
+
+    if not candidate.exists():
+        raise ValueError(f"Path does not exist: {candidate}")
+    if not candidate.is_dir():
+        raise ValueError(f"Path is not a directory: {candidate}")
+
+    # Block known system roots and their children
+    for blocked in _BLOCKED_SYSTEM_ROOTS:
+        try:
+            candidate.relative_to(blocked)
+            raise ValueError(f"Path points to a system directory: {candidate}")
+        except ValueError as e:
+            if "system directory" in str(e):
+                raise
+            # relative_to raised ValueError = candidate is NOT under blocked = safe
+
+    # (A) Trusted if under the user's home directory — cross-platform via Path.home()
+    try:
+        candidate.relative_to(Path.home().resolve())
+        return candidate
+    except ValueError:
+        pass
+
+    # (B) Trusted if already in the saved workspace list — covers non-home installs
+    try:
+        saved = load_workspaces()
+        saved_paths = {Path(w["path"]).resolve() for w in saved if w.get("path")}
+        if candidate in saved_paths:
+            return candidate
+    except Exception:
+        pass
+
+    # (C) Trusted if it is equal to or under the boot-time DEFAULT_WORKSPACE.
+    #     In Docker deployments HERMES_WEBUI_DEFAULT_WORKSPACE is often set to a
+    #     volume mount outside the user's home (e.g. /data/workspace).  That path
+    #     was already validated at server startup, so any sub-path of it is safe
+    #     without requiring the user to add it to the workspace list manually.
+    try:
+        boot_default = Path(_BOOT_DEFAULT_WORKSPACE).expanduser().resolve()
+        candidate.relative_to(boot_default)
+        return candidate
+    except ValueError:
+        pass
+
+    raise ValueError(
+        f"Path is outside the user home directory, not in the saved workspace "
+        f"list, and not under the default workspace: {candidate}. "
+        f"Add it via Settings → Workspaces first."
+    )
+
+
+def safe_resolve_ws(root: Path, requested: str) -> Path:
+    """Resolve a relative path inside a workspace root, raising ValueError on traversal."""
+    resolved = (root / requested).resolve()
+    resolved.relative_to(root.resolve())
+    return resolved
+
+
+def list_dir(workspace: Path, rel: str='.'):
+    target = safe_resolve_ws(workspace, rel)
+    if not target.is_dir():
+        raise FileNotFoundError(f"Not a directory: {rel}")
+    entries = []
+    for item in sorted(target.iterdir(), key=lambda p: (p.is_file(), p.name.lower())):
+        entries.append({
+            'name': item.name,
+            'path': str(item.relative_to(workspace)),
+            'type': 'dir' if item.is_dir() else 'file',
+            'size': item.stat().st_size if item.is_file() else None,
+        })
+        if len(entries) >= 200:
+            break
+    return entries
+
+
+def read_file_content(workspace: Path, rel: str) -> dict:
+    target = safe_resolve_ws(workspace, rel)
+    if not target.is_file():
+        raise FileNotFoundError(f"Not a file: {rel}")
+    size = target.stat().st_size
+    if size > MAX_FILE_BYTES:
+        raise ValueError(f"File too large ({size} bytes, max {MAX_FILE_BYTES})")
+    content = target.read_text(encoding='utf-8', errors='replace')
+    return {'path': rel, 'content': content, 'size': size, 'lines': content.count('\n') + 1}
+
+
+# ── Git detection ──────────────────────────────────────────────────────────
+
+def _run_git(args, cwd, timeout=3):
+    """Run a git command and return stdout, or None on failure."""
+    try:
+        r = subprocess.run(
+            ['git'] + args, cwd=str(cwd), capture_output=True,
+            text=True, timeout=timeout,
+        )
+        return r.stdout.strip() if r.returncode == 0 else None
+    except (subprocess.TimeoutExpired, FileNotFoundError, OSError):
+        return None
+
+
+def git_info_for_workspace(workspace: Path) -> dict:
+    """Return git info for a workspace directory, or None if not a git repo."""
+    if not (workspace / '.git').exists():
+        return None
+    branch = _run_git(['rev-parse', '--abbrev-ref', 'HEAD'], workspace)
+    if branch is None:
+        return None
+    # Status counts
+    status_out = _run_git(['status', '--porcelain'], workspace) or ''
+    lines = [l for l in status_out.splitlines() if l]
+    # git status --porcelain: XY format where X=index, Y=worktree
+    modified = sum(1 for l in lines if len(l) >= 2 and (l[0] in 'MAR' or l[1] in 'MAR'))
+    untracked = sum(1 for l in lines if l.startswith('??'))
+    dirty = len(lines)
+    # Ahead/behind
+    ahead = _run_git(['rev-list', '--count', '@{u}..HEAD'], workspace)
+    behind = _run_git(['rev-list', '--count', 'HEAD..@{u}'], workspace)
+    return {
+        'branch': branch,
+        'dirty': dirty,
+        'modified': modified,
+        'untracked': untracked,
+        'ahead': int(ahead) if ahead and ahead.isdigit() else 0,
+        'behind': int(behind) if behind and behind.isdigit() else 0,
+        'is_git': True,
+    }