chore: uptick

cli.py

@@ -15,7 +15,6 @@ Usage:
 
 import logging
 import os
-import re
 import shutil
 import sys
 import json
@@ -86,7 +85,7 @@ from hermes_cli.browser_connect import (
     try_launch_chrome_debug,
 )
 from hermes_cli.env_loader import load_hermes_dotenv
-from utils import base_url_host_matches
+from utils import base_url_host_matches, is_truthy_value
 
 _hermes_home = get_hermes_home()
 _project_env = Path(__file__).parent / '.env'
@@ -600,6 +599,7 @@ def load_cli_config() -> Dict[str, Any]:
 # Load configuration at module startup
 CLI_CONFIG = load_cli_config()
 
+
 # Initialize centralized logging early — agent.log + errors.log in ~/.hermes/logs/.
 # This ensures CLI sessions produce a log trail even before AIAgent is instantiated.
 try:
@@ -934,6 +934,20 @@ def _run_state_db_auto_maintenance(session_db) -> None:
     try:
         from hermes_cli.config import load_config as _load_full_config
         from hermes_constants import get_hermes_home as _get_hermes_home
+        _hermes_home_maint = _get_hermes_home()
+
+        # One-time prune of empty TUI ghost sessions.
+        try:
+            if not session_db.get_meta("ghost_session_prune_v1"):
+                pruned = session_db.prune_empty_ghost_sessions(
+                    sessions_dir=_hermes_home_maint / "sessions"
+                )
+                session_db.set_meta("ghost_session_prune_v1", "1")
+                if pruned:
+                    logger.info("Pruned %d empty TUI ghost sessions", pruned)
+        except Exception as _prune_exc:
+            logger.debug("Ghost session prune skipped: %s", _prune_exc)
+
         cfg = (_load_full_config().get("sessions") or {})
         if not cfg.get("auto_prune", False):
             return
@@ -941,7 +955,7 @@ def _run_state_db_auto_maintenance(session_db) -> None:
             retention_days=int(cfg.get("retention_days", 90)),
             min_interval_hours=int(cfg.get("min_interval_hours", 24)),
             vacuum=bool(cfg.get("vacuum_after_prune", True)),
-            sessions_dir=_get_hermes_home() / "sessions",
+            sessions_dir=_hermes_home_maint / "sessions",
         )
     except Exception as exc:
         logger.debug("state.db auto-maintenance skipped: %s", exc)
@@ -2118,6 +2132,8 @@ class HermesCLI:
         
         # Parse and validate toolsets
         self.enabled_toolsets = toolsets
+        self.disabled_toolsets = CLI_CONFIG["agent"].get("disabled_toolsets") or []
+
         if toolsets and "all" not in toolsets and "*" not in toolsets:
             # Validate each toolset — MCP server names are resolved via
             # live registry aliases (registered during discover_mcp_tools),
@@ -3568,6 +3584,7 @@ class HermesCLI:
                 credential_pool=runtime.get("credential_pool"),
                 max_iterations=self.max_turns,
                 enabled_toolsets=self.enabled_toolsets,
+                disabled_toolsets=self.disabled_toolsets,
                 verbose_logging=self.verbose,
                 quiet_mode=not self.verbose,
                 ephemeral_system_prompt=self.system_prompt if self.system_prompt else None,
@@ -3615,14 +3632,18 @@ class HermesCLI:
                 tuple(runtime.get("args") or ()),
             )
 
-            if self._pending_title and self._session_db:
+            # Force-create DB row on /title intent, then apply title.
+            if self._pending_title and self._session_db and self.agent:
                 try:
-                    self._session_db.set_session_title(self.session_id, self._pending_title)
-                    _cprint(f"  Session title applied: {self._pending_title}")
-                    self._pending_title = None
+                    self.agent._ensure_db_session()
+                    if self.agent._session_db_created:
+                        self._session_db.set_session_title(self.session_id, self._pending_title)
+                        _cprint(f"  Session title applied: {self._pending_title}")
+                        self._pending_title = None
+                    # else: row creation failed transiently — keep _pending_title for retry
                 except (ValueError, Exception) as e:
                     _cprint(f"  Could not apply pending title: {e}")
-                    self._pending_title = None
+                    # Keep _pending_title so it can be retried after row creation succeeds
             return True
         except Exception as e:
             ChatConsole().print(f"[bold red]Failed to initialize agent: {e}[/]")
@@ -4950,6 +4971,7 @@ class HermesCLI:
 
             if self._session_db:
                 try:
+                    self.agent._session_db_created = False
                     self._session_db.create_session(
                         session_id=self.session_id,
                         source=os.environ.get("HERMES_SESSION_SOURCE", "cli"),
@@ -4959,6 +4981,7 @@ class HermesCLI:
                             "reasoning_config": self.reasoning_config,
                         },
                     )
+                    self.agent._session_db_created = True
                 except Exception:
                     pass
             # Notify memory providers that session_id rotated to a fresh
@@ -6537,6 +6560,8 @@ class HermesCLI:
                 # No active run — treat as a normal next-turn message.
                 self._pending_input.put(payload)
                 _cprint(f"  No agent running; queued as next turn: {payload[:80]}{'...' if len(payload) > 80 else ''}")
+        elif canonical == "goal":
+            self._handle_goal_command(cmd_original)
         elif canonical == "skin":
             self._handle_skin_command(cmd_original)
         elif canonical == "voice":
@@ -6582,12 +6607,17 @@ class HermesCLI:
                     self._console_print(f"[bold red]Quick command '{base_cmd}' has unsupported type (supported: 'exec', 'alias')[/]")
             # Check for plugin-registered slash commands
             elif base_cmd.lstrip("/") in _get_plugin_cmd_handler_names():
-                from hermes_cli.plugins import get_plugin_command_handler
+                from hermes_cli.plugins import (
+                    get_plugin_command_handler,
+                    resolve_plugin_command_result,
+                )
                 plugin_handler = get_plugin_command_handler(base_cmd.lstrip("/"))
                 if plugin_handler:
                     user_args = cmd_original[len(base_cmd):].strip()
                     try:
-                        result = plugin_handler(user_args)
+                        result = resolve_plugin_command_result(
+                            plugin_handler(user_args)
+                        )
                         if result:
                             _cprint(str(result))
                     except Exception as e:
@@ -7012,6 +7042,166 @@ class HermesCLI:
             print("   status       Show current browser mode")
             print()
 
+    # ────────────────────────────────────────────────────────────────
+    # /goal — persistent cross-turn goals (Ralph-style loop)
+    # ────────────────────────────────────────────────────────────────
+    def _get_goal_manager(self):
+        """Return the GoalManager bound to the current session_id.
+
+        Cached on ``self._goal_manager`` and rebound lazily when
+        ``session_id`` changes (e.g. after /new or a compression-driven
+        session split).
+        """
+        try:
+            from hermes_cli.goals import GoalManager
+            from hermes_cli.config import load_config
+        except Exception as exc:
+            logging.debug("goal manager unavailable: %s", exc)
+            return None
+
+        sid = getattr(self, "session_id", None) or ""
+        if not sid:
+            return None
+
+        existing = getattr(self, "_goal_manager", None)
+        if existing is not None and getattr(existing, "session_id", None) == sid:
+            return existing
+
+        try:
+            cfg = load_config() or {}
+            goals_cfg = cfg.get("goals") or {}
+            max_turns = int(goals_cfg.get("max_turns", 20) or 20)
+        except Exception:
+            max_turns = 20
+
+        mgr = GoalManager(session_id=sid, default_max_turns=max_turns)
+        self._goal_manager = mgr
+        return mgr
+
+    def _handle_goal_command(self, cmd: str) -> None:
+        """Dispatch /goal subcommands: set / status / pause / resume / clear."""
+        parts = (cmd or "").strip().split(None, 1)
+        arg = parts[1].strip() if len(parts) > 1 else ""
+
+        mgr = self._get_goal_manager()
+        if mgr is None:
+            _cprint(f"  {_DIM}Goals unavailable (no active session).{_RST}")
+            return
+
+        lower = arg.lower()
+
+        # Bare /goal or /goal status → show current state
+        if not arg or lower == "status":
+            _cprint(f"  {mgr.status_line()}")
+            return
+
+        if lower == "pause":
+            state = mgr.pause(reason="user-paused")
+            if state is None:
+                _cprint(f"  {_DIM}No goal set.{_RST}")
+            else:
+                _cprint(f"  ⏸ Goal paused: {state.goal}")
+            return
+
+        if lower == "resume":
+            state = mgr.resume()
+            if state is None:
+                _cprint(f"  {_DIM}No goal to resume.{_RST}")
+            else:
+                _cprint(f"  ▶ Goal resumed: {state.goal}")
+                _cprint(
+                    f"  {_DIM}Send any message (or press Enter on an empty prompt "
+                    f"is a no-op; type 'continue' to kick it off).{_RST}"
+                )
+            return
+
+        if lower in ("clear", "stop", "done"):
+            had = mgr.has_goal()
+            mgr.clear()
+            if had:
+                _cprint("  ✓ Goal cleared.")
+            else:
+                _cprint(f"  {_DIM}No active goal.{_RST}")
+            return
+
+        # Otherwise treat the arg as the goal text.
+        try:
+            state = mgr.set(arg)
+        except ValueError as exc:
+            _cprint(f"  Invalid goal: {exc}")
+            return
+
+        _cprint(f"  ⊙ Goal set ({state.max_turns}-turn budget): {state.goal}")
+        _cprint(
+            f"  {_DIM}After each turn, a judge model will check if the goal is done. "
+            f"Hermes keeps working until it is, you pause/clear it, or the budget is "
+            f"exhausted. Use /goal status, /goal pause, /goal resume, /goal clear.{_RST}"
+        )
+        # Kick the loop off immediately so the user doesn't have to send a
+        # separate message after setting the goal.
+        try:
+            self._pending_input.put(state.goal)
+        except Exception:
+            pass
+
+    def _maybe_continue_goal_after_turn(self) -> None:
+        """Hook run after every CLI turn. Judges + maybe re-queues.
+
+        Safe to call when no goal is set — returns quickly.
+
+        Preemption is automatic: if a real user message is already in
+        ``_pending_input`` we skip judging (the user's new input takes
+        priority and we'll re-judge after that turn). If judge says done,
+        mark it done and tell the user. If judge says continue and we're
+        under budget, push the continuation prompt onto the queue.
+        """
+        mgr = self._get_goal_manager()
+        if mgr is None or not mgr.is_active():
+            return
+
+        # If a real user message is already queued, don't inject a
+        # continuation prompt on top — let the user's turn go first.
+        try:
+            if getattr(self, "_pending_input", None) is not None \
+                    and not self._pending_input.empty():
+                return
+        except Exception:
+            pass
+
+        # Extract the agent's final response for this turn.
+        last_response = ""
+        try:
+            hist = self.conversation_history or []
+            for msg in reversed(hist):
+                if msg.get("role") == "assistant":
+                    content = msg.get("content", "")
+                    if isinstance(content, list):
+                        # Multimodal content — flatten text parts.
+                        parts = [
+                            p.get("text", "")
+                            for p in content
+                            if isinstance(p, dict) and p.get("type") in ("text", "output_text")
+                        ]
+                        last_response = "\n".join(t for t in parts if t)
+                    else:
+                        last_response = str(content or "")
+                    break
+        except Exception:
+            last_response = ""
+
+        decision = mgr.evaluate_after_turn(last_response, user_initiated=True)
+        msg = decision.get("message") or ""
+        if msg:
+            _cprint(f"  {msg}")
+
+        if decision.get("should_continue"):
+            prompt = decision.get("continuation_prompt")
+            if prompt:
+                try:
+                    self._pending_input.put(prompt)
+                except Exception as exc:
+                    logging.debug("goal continuation enqueue failed: %s", exc)
+
     def _handle_skin_command(self, cmd: str):
         """Handle /skin [name] — show or change the display skin."""
         try:
@@ -7138,7 +7328,7 @@ class HermesCLI:
         import os
         from hermes_cli.colors import Colors as _Colors
 
-        current = bool(os.environ.get("HERMES_YOLO_MODE"))
+        current = is_truthy_value(os.environ.get("HERMES_YOLO_MODE"))
         if current:
             os.environ.pop("HERMES_YOLO_MODE", None)
             _cprint(
@@ -7335,10 +7525,20 @@ class HermesCLI:
         original_count = len(self.conversation_history)
         with self._busy_command("Compressing context..."):
             try:
-                from agent.model_metadata import estimate_messages_tokens_rough
+                from agent.model_metadata import estimate_request_tokens_rough
                 from agent.manual_compression_feedback import summarize_manual_compression
                 original_history = list(self.conversation_history)
-                approx_tokens = estimate_messages_tokens_rough(original_history)
+                # Include system prompt + tool schemas in the estimate —
+                # a transcript-only number understates real request pressure
+                # and can even appear to grow after compression because a
+                # dense handoff summary replaces many short turns (#6217).
+                _sys_prompt = getattr(self.agent, "_cached_system_prompt", "") or ""
+                _tools = getattr(self.agent, "tools", None) or None
+                approx_tokens = estimate_request_tokens_rough(
+                    original_history,
+                    system_prompt=_sys_prompt,
+                    tools=_tools,
+                )
                 if focus_topic:
                     print(f"🗜️  Compressing {original_count} messages (~{approx_tokens:,} tokens), "
                           f"focus: \"{focus_topic}\"...")
@@ -7370,7 +7570,11 @@ class HermesCLI:
                 ):
                     self.session_id = self.agent.session_id
                     self._pending_title = None
-                new_tokens = estimate_messages_tokens_rough(self.conversation_history)
+                new_tokens = estimate_request_tokens_rough(
+                    self.conversation_history,
+                    system_prompt=_sys_prompt,
+                    tools=_tools,
+                )
                 summary = summarize_manual_compression(
                     original_history,
                     self.conversation_history,
@@ -11336,6 +11540,17 @@ class HermesCLI:
 
                         app.invalidate()  # Refresh status line
 
+                        # Goal continuation: if a standing goal is active, ask
+                        # the judge whether the turn satisfied it. If not, and
+                        # there's no real user message already queued, push the
+                        # continuation prompt back into _pending_input so the
+                        # next loop iteration picks it up naturally (and any
+                        # user input that arrives in between still preempts).
+                        try:
+                            self._maybe_continue_goal_after_turn()
+                        except Exception as _goal_exc:
+                            logging.debug("goal continuation hook failed: %s", _goal_exc)
+
                         # Continuous voice: auto-restart recording after agent responds.
                         # Dispatch to a daemon thread so play_beep (sd.wait) and
                         # AudioRecorder.start (lock acquire) never block process_loop —