fix: head+tail truncation for execute_code stdout (inspired by openclaw context-pruning)

Previously, _drain() only captured the first MAX_STDOUT_BYTES (50KB) of
stdout, silently dropping all tail output. Scripts that print() their
final results at the end would have those results lost.

Now uses a two-buffer approach: 40% head + 60% tail (rolling window).
This matches the pattern already used in terminal_tool.py (line 1042-1051)
but gives the tail more space since execute_code scripts typically
print() their final results at the end.

Inspired by openclaw's softTrim context-pruning (headChars/tailChars).

agent/auxiliary_client.py

@@ -560,16 +560,12 @@ def get_vision_auxiliary_client() -> Tuple[Optional[OpenAI], Optional[str]]:
     forced = _get_auxiliary_provider("vision")
     if forced != "auto":
         return _resolve_forced_provider(forced)
-    # Auto: try providers known to support multimodal first, then fall
-    # back to the user's custom endpoint.  Many local models (Qwen-VL,
-    # LLaVA, Pixtral, etc.) support vision — skipping them entirely
-    # caused silent failures for local-only users.
-    for try_fn in (_try_openrouter, _try_nous, _try_codex,
-                   _try_custom_endpoint):
+    # Auto: only multimodal-capable providers
+    for try_fn in (_try_openrouter, _try_nous, _try_codex):
         client, model = try_fn()
         if client is not None:
             return client, model
-    logger.debug("Auxiliary vision client: none available")
+    logger.debug("Auxiliary vision client: none available (auto only tries OpenRouter/Nous/Codex)")
     return None, None
 
 

agent/display.py

@@ -16,55 +16,12 @@ _RED = "\033[31m"
 _RESET = "\033[0m"
 
 
-# =========================================================================
-# Skin-aware helpers (lazy import to avoid circular deps)
-# =========================================================================
-
-def _get_skin():
-    """Get the active skin config, or None if not available."""
-    try:
-        from hermes_cli.skin_engine import get_active_skin
-        return get_active_skin()
-    except Exception:
-        return None
-
-
-def get_skin_faces(key: str, default: list) -> list:
-    """Get spinner face list from active skin, falling back to default."""
-    skin = _get_skin()
-    if skin:
-        faces = skin.get_spinner_list(key)
-        if faces:
-            return faces
-    return default
-
-
-def get_skin_verbs() -> list:
-    """Get thinking verbs from active skin."""
-    skin = _get_skin()
-    if skin:
-        verbs = skin.get_spinner_list("thinking_verbs")
-        if verbs:
-            return verbs
-    return KawaiiSpinner.THINKING_VERBS
-
-
-def get_skin_tool_prefix() -> str:
-    """Get tool output prefix character from active skin."""
-    skin = _get_skin()
-    if skin:
-        return skin.tool_prefix
-    return "┊"
-
-
 # =========================================================================
 # Tool preview (one-line summary of a tool call's primary argument)
 # =========================================================================
 
 def build_tool_preview(tool_name: str, args: dict, max_len: int = 40) -> str:
     """Build a short preview of a tool call's primary argument for display."""
-    if not args:
-        return None
     primary_args = {
         "terminal": "command", "web_search": "query", "web_extract": "urls",
         "read_file": "path", "write_file": "path", "patch": "path",
@@ -220,21 +177,13 @@ class KawaiiSpinner:
             pass
 
     def _animate(self):
-        # Cache skin wings at start (avoid per-frame imports)
-        skin = _get_skin()
-        wings = skin.get_spinner_wings() if skin else []
-
         while self.running:
             if os.getenv("HERMES_SPINNER_PAUSE"):
                 time.sleep(0.1)
                 continue
             frame = self.spinner_frames[self.frame_idx % len(self.spinner_frames)]
             elapsed = time.time() - self.start_time
-            if wings:
-                left, right = wings[self.frame_idx % len(wings)]
-                line = f"  {left} {frame} {self.message} {right} ({elapsed:.1f}s)"
-            else:
-                line = f"  {frame} {self.message} ({elapsed:.1f}s)"
+            line = f"  {frame} {self.message} ({elapsed:.1f}s)"
             pad = max(self.last_line_len - len(line), 0)
             self._write(f"\r{line}{' ' * pad}", end='', flush=True)
             self.last_line_len = len(line)
@@ -383,7 +332,6 @@ def get_cute_tool_message(
     """
     dur = f"{duration:.1f}s"
     is_failure, failure_suffix = _detect_tool_failure(tool_name, result)
-    skin_prefix = get_skin_tool_prefix()
 
     def _trunc(s, n=40):
         s = str(s)
@@ -394,9 +342,7 @@ def get_cute_tool_message(
         return ("..." + p[-(n-3):]) if len(p) > n else p
 
     def _wrap(line: str) -> str:
-        """Apply skin tool prefix and failure suffix."""
-        if skin_prefix != "┊":
-            line = line.replace("┊", skin_prefix, 1)
+        """Append failure suffix when the tool failed."""
         if not is_failure:
             return line
         return f"{line}{failure_suffix}"

agent/prompt_builder.py

@@ -195,8 +195,6 @@ def build_skills_system_prompt() -> str:
 
     # Collect skills with descriptions, grouped by category
     # Each entry: (skill_name, description)
-    # Supports sub-categories: skills/mlops/training/axolotl/SKILL.md
-    # → category "mlops/training", skill "axolotl"
     skills_by_category: dict[str, list[tuple[str, str]]] = {}
     for skill_file in skills_dir.rglob("SKILL.md"):
         # Skip skills incompatible with the current OS platform
@@ -205,13 +203,8 @@ def build_skills_system_prompt() -> str:
         rel_path = skill_file.relative_to(skills_dir)
         parts = rel_path.parts
         if len(parts) >= 2:
-            # Category is everything between skills_dir and the skill folder
-            # e.g. parts = ("mlops", "training", "axolotl", "SKILL.md")
-            #   → category = "mlops/training", skill_name = "axolotl"
-            # e.g. parts = ("github", "github-auth", "SKILL.md")
-            #   → category = "github", skill_name = "github-auth"
+            category = parts[0]
             skill_name = parts[-2]
-            category = "/".join(parts[:-2]) if len(parts) > 2 else parts[0]
         else:
             category = "general"
             skill_name = skill_file.parent.name
@@ -222,11 +215,9 @@ def build_skills_system_prompt() -> str:
         return ""
 
     # Read category-level descriptions from DESCRIPTION.md
-    # Checks both the exact category path and parent directories
     category_descriptions = {}
     for category in skills_by_category:
-        cat_path = Path(category)
-        desc_file = skills_dir / cat_path / "DESCRIPTION.md"
+        desc_file = skills_dir / category / "DESCRIPTION.md"
         if desc_file.exists():
             try:
                 content = desc_file.read_text(encoding="utf-8")

cli-config.yaml.example

@@ -402,13 +402,11 @@ agent:
 #     discord: [web, vision, skills, todo]
 #
 # If not set, defaults are:
-#   cli:           hermes-cli            (everything + cronjob management)
-#   telegram:      hermes-telegram       (terminal, file, web, vision, image, tts, browser, skills, todo, cronjob, messaging)
-#   discord:       hermes-discord        (same as telegram)
-#   whatsapp:      hermes-whatsapp       (same as telegram)
-#   slack:         hermes-slack          (same as telegram)
-#   signal:        hermes-signal         (same as telegram)
-#   homeassistant: hermes-homeassistant  (same as telegram)
+#   cli:      hermes-cli      (everything + cronjob management)
+#   telegram: hermes-telegram  (terminal, file, web, vision, image, tts, browser, skills, todo, cronjob, messaging)
+#   discord:  hermes-discord   (same as telegram)
+#   whatsapp: hermes-whatsapp  (same as telegram)
+#   slack:    hermes-slack     (same as telegram)
 #
 platform_toolsets:
   cli: [hermes-cli]
@@ -416,8 +414,6 @@ platform_toolsets:
   discord: [hermes-discord]
   whatsapp: [hermes-whatsapp]
   slack: [hermes-slack]
-  signal: [hermes-signal]
-  homeassistant: [hermes-homeassistant]
 
 # ─────────────────────────────────────────────────────────────────────────────
 # Available toolsets (use these names in platform_toolsets or the toolsets list)
@@ -559,21 +555,6 @@ toolsets:
 #     args: ["-y", "@modelcontextprotocol/server-github"]
 #     env:
 #       GITHUB_PERSONAL_ACCESS_TOKEN: "ghp_..."
-#
-# Sampling (server-initiated LLM requests) — enabled by default.
-# Per-server config under the 'sampling' key:
-#   analysis:
-#     command: npx
-#     args: ["-y", "analysis-server"]
-#     sampling:
-#       enabled: true           # default: true
-#       model: "gemini-3-flash" # override model (optional)
-#       max_tokens_cap: 4096    # max tokens per request
-#       timeout: 30             # LLM call timeout (seconds)
-#       max_rpm: 10             # max requests per minute
-#       allowed_models: []      # model whitelist (empty = all)
-#       max_tool_rounds: 5      # tool loop limit (0 = disable)
-#       log_level: "info"       # audit verbosity
 
 # =============================================================================
 # Voice Transcription (Speech-to-Text)

cli.py

@@ -19,7 +19,6 @@ import sys
 import json
 import atexit
 import uuid
-import textwrap
 from pathlib import Path
 from datetime import datetime
 from typing import List, Dict, Any, Optional
@@ -46,11 +45,6 @@ from prompt_toolkit.widgets import TextArea
 from prompt_toolkit.key_binding import KeyBindings
 from prompt_toolkit import print_formatted_text as _pt_print
 from prompt_toolkit.formatted_text import ANSI as _PT_ANSI
-try:
-    from prompt_toolkit.cursor_shapes import CursorShape
-    _STEADY_CURSOR = CursorShape.BLOCK  # Non-blinking block cursor
-except (ImportError, AttributeError):
-    _STEADY_CURSOR = None
 import threading
 import queue
 
@@ -164,7 +158,6 @@ def load_cli_config() -> Dict[str, Any]:
             "singularity_image": "docker://python:3.11",
             "modal_image": "python:3.11",
             "daytona_image": "nikolaik/python-nodejs:python3.11-nodejs20",
-            "docker_volumes": [],  # host:container volume mounts for Docker backend
         },
         "browser": {
             "inactivity_timeout": 120,  # Auto-cleanup inactive browser sessions after 2 min
@@ -202,7 +195,6 @@ def load_cli_config() -> Dict[str, Any]:
         "display": {
             "compact": False,
             "resume_display": "full",
-            "skin": "default",
         },
         "clarify": {
             "timeout": 120,  # Seconds to wait for a clarify answer before auto-proceeding
@@ -384,13 +376,6 @@ def load_cli_config() -> Dict[str, Any]:
 # Load configuration at module startup
 CLI_CONFIG = load_cli_config()
 
-# Initialize the skin engine from config
-try:
-    from hermes_cli.skin_engine import init_skin_from_config
-    init_skin_from_config(CLI_CONFIG)
-except Exception:
-    pass  # Skin engine is optional — default skin used if unavailable
-
 from rich.console import Console
 from rich.panel import Panel
 from rich.table import Table
@@ -740,7 +725,6 @@ HERMES_CADUCEUS = """[#CD7F32]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢀⣀⡀⠀⣀⣀
 [#B8860B]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠈⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]"""
 
 # Compact banner for smaller terminals (fallback)
-# Note: built dynamically by _build_compact_banner() to fit terminal width
 COMPACT_BANNER = """
 [bold #FFD700]╔══════════════════════════════════════════════════════════════╗[/]
 [bold #FFD700]║[/]  [#FFBF00]⚕ NOUS HERMES[/] [dim #B8860B]- AI Agent Framework[/]              [bold #FFD700]║[/]
@@ -749,26 +733,6 @@ COMPACT_BANNER = """
 """
 
 
-def _build_compact_banner() -> str:
-    """Build a compact banner that fits the current terminal width."""
-    w = min(shutil.get_terminal_size().columns - 2, 64)
-    if w < 30:
-        return "\n[#FFBF00]⚕ NOUS HERMES[/] [dim #B8860B]- Nous Research[/]\n"
-    inner = w - 2  # inside the box border
-    bar = "═" * w
-    line1 = "⚕ NOUS HERMES - AI Agent Framework"
-    line2 = "Messenger of the Digital Gods  ·  Nous Research"
-    # Truncate and pad to fit
-    line1 = line1[:inner - 2].ljust(inner - 2)
-    line2 = line2[:inner - 2].ljust(inner - 2)
-    return (
-        f"\n[bold #FFD700]╔{bar}╗[/]\n"
-        f"[bold #FFD700]║[/] [#FFBF00]{line1}[/] [bold #FFD700]║[/]\n"
-        f"[bold #FFD700]║[/] [dim #B8860B]{line2}[/] [bold #FFD700]║[/]\n"
-        f"[bold #FFD700]╚{bar}╝[/]\n"
-    )
-
-
 def _get_available_skills() -> Dict[str, List[str]]:
     """
     Scan ~/.hermes/skills/ and return skills grouped by category.
@@ -966,12 +930,10 @@ def build_welcome_banner(console: Console, model: str, cwd: str, tools: List[dic
         padding=(0, 2),
     )
     
-    # Print the big HERMES-AGENT logo — skip if terminal is too narrow
+    # Print the big HERMES-AGENT logo first (no panel wrapper for full width)
+    console.print()
+    console.print(HERMES_AGENT_LOGO)
     console.print()
-    term_width = shutil.get_terminal_size().columns
-    if term_width >= 95:
-        console.print(HERMES_AGENT_LOGO)
-        console.print()
     
     # Print the panel with caduceus and info
     console.print(outer_panel)
@@ -1059,7 +1021,6 @@ class HermesCLI:
         verbose: bool = False,
         compact: bool = False,
         resume: str = None,
-        checkpoints: bool = False,
     ):
         """
         Initialize the Hermes CLI.
@@ -1141,13 +1102,6 @@ class HermesCLI:
             if invalid:
                 self.console.print(f"[bold red]Warning: Unknown toolsets: {', '.join(invalid)}[/]")
         
-        # Filesystem checkpoints: CLI flag > config
-        cp_cfg = CLI_CONFIG.get("checkpoints", {})
-        if isinstance(cp_cfg, bool):
-            cp_cfg = {"enabled": cp_cfg}
-        self.checkpoints_enabled = checkpoints or cp_cfg.get("enabled", False)
-        self.checkpoint_max_snapshots = cp_cfg.get("max_snapshots", 50)
-        
         # Ephemeral system prompt: env var takes precedence, then config
         self.system_prompt = (
             os.getenv("HERMES_EPHEMERAL_SYSTEM_PROMPT", "")
@@ -1209,7 +1163,6 @@ class HermesCLI:
         # History file for persistent input recall across sessions
         self._history_file = Path.home() / ".hermes_history"
         self._last_invalidate: float = 0.0  # throttle UI repaints
-        self._spinner_text: str = ""  # thinking spinner text for TUI
 
     def _invalidate(self, min_interval: float = 0.25) -> None:
         """Throttled UI repaint — prevents terminal blinking on slow/SSH connections."""
@@ -1273,11 +1226,6 @@ class HermesCLI:
 
         return changed
 
-    def _on_thinking(self, text: str) -> None:
-        """Called by agent when thinking starts/stops. Updates TUI spinner."""
-        self._spinner_text = text or ""
-        self._invalidate()
-
     def _ensure_runtime_credentials(self) -> bool:
         """
         Ensure runtime credentials are resolved before agent use.
@@ -1416,9 +1364,6 @@ class HermesCLI:
                 clarify_callback=self._clarify_callback,
                 honcho_session_key=self.session_id,
                 fallback_model=self._fallback_model,
-                thinking_callback=self._on_thinking,
-                checkpoints_enabled=self.checkpoints_enabled,
-                checkpoint_max_snapshots=self.checkpoint_max_snapshots,
             )
             # Apply any pending title now that the session exists in the DB
             if self._pending_title and self._session_db:
@@ -1438,13 +1383,8 @@ class HermesCLI:
         """Display the welcome banner in Claude Code style."""
         self.console.clear()
         
-        # Auto-compact for narrow terminals — the full banner with caduceus
-        # + tool list needs ~80 columns minimum to render without wrapping.
-        term_width = shutil.get_terminal_size().columns
-        use_compact = self.compact or term_width < 80
-        
-        if use_compact:
-            self.console.print(_build_compact_banner())
+        if self.compact:
+            self.console.print(COMPACT_BANNER)
             self._show_status()
         else:
             # Get tools for display
@@ -1688,55 +1628,6 @@ class HermesCLI:
         self._image_counter -= 1
         return False
 
-    def _handle_rollback_command(self, command: str):
-        """Handle /rollback — list or restore filesystem checkpoints."""
-        from tools.checkpoint_manager import CheckpointManager, format_checkpoint_list
-
-        if not hasattr(self, 'agent') or not self.agent:
-            print("  No active agent session.")
-            return
-
-        mgr = self.agent._checkpoint_mgr
-        if not mgr.enabled:
-            print("  Checkpoints are not enabled.")
-            print("  Enable with: hermes --checkpoints")
-            print("  Or in config.yaml: checkpoints: { enabled: true }")
-            return
-
-        cwd = os.getenv("TERMINAL_CWD", os.getcwd())
-        parts = command.split(maxsplit=1)
-        arg = parts[1].strip() if len(parts) > 1 else ""
-
-        if not arg:
-            # List checkpoints
-            checkpoints = mgr.list_checkpoints(cwd)
-            print(format_checkpoint_list(checkpoints, cwd))
-        else:
-            # Restore by number or hash
-            checkpoints = mgr.list_checkpoints(cwd)
-            if not checkpoints:
-                print(f"  No checkpoints found for {cwd}")
-                return
-
-            target_hash = None
-            try:
-                idx = int(arg) - 1  # 1-indexed for user
-                if 0 <= idx < len(checkpoints):
-                    target_hash = checkpoints[idx]["hash"]
-                else:
-                    print(f"  Invalid checkpoint number. Use 1-{len(checkpoints)}.")
-                    return
-            except ValueError:
-                # Try as a git hash
-                target_hash = arg
-
-            result = mgr.restore(cwd, target_hash)
-            if result["success"]:
-                print(f"  ✅ Restored to checkpoint {result['restored_to']}: {result['reason']}")
-                print(f"  A pre-rollback snapshot was saved automatically.")
-            else:
-                print(f"  ❌ {result['error']}")
-
     def _handle_paste_command(self):
         """Handle /paste — explicitly check clipboard for an image.
 
@@ -2503,9 +2394,8 @@ class HermesCLI:
             # and gets mangled by patch_stdout).
             if self._app:
                 cc = ChatConsole()
-                term_w = shutil.get_terminal_size().columns
-                if self.compact or term_w < 80:
-                    cc.print(_build_compact_banner())
+                if self.compact:
+                    cc.print(COMPACT_BANNER)
                 else:
                     tools = get_tool_definitions(enabled_toolsets=self.enabled_toolsets, quiet_mode=True)
                     cwd = os.getenv("TERMINAL_CWD", os.getcwd())
@@ -2746,10 +2636,6 @@ class HermesCLI:
             self._handle_paste_command()
         elif cmd_lower == "/reload-mcp":
             self._reload_mcp()
-        elif cmd_lower.startswith("/rollback"):
-            self._handle_rollback_command(cmd_original)
-        elif cmd_lower.startswith("/skin"):
-            self._handle_skin_command(cmd_original)
         else:
             # Check for skill slash commands (/gif-search, /axolotl, etc.)
             base_cmd = cmd_lower.split()[0]
@@ -2769,43 +2655,6 @@ class HermesCLI:
         
         return True
     
-    def _handle_skin_command(self, cmd: str):
-        """Handle /skin [name] — show or change the display skin."""
-        try:
-            from hermes_cli.skin_engine import list_skins, set_active_skin, get_active_skin_name
-        except ImportError:
-            print("Skin engine not available.")
-            return
-
-        parts = cmd.strip().split(maxsplit=1)
-        if len(parts) < 2 or not parts[1].strip():
-            # Show current skin and list available
-            current = get_active_skin_name()
-            skins = list_skins()
-            print(f"\n  Current skin: {current}")
-            print(f"  Available skins:")
-            for s in skins:
-                marker = " ●" if s["name"] == current else "  "
-                source = f" ({s['source']})" if s["source"] == "user" else ""
-                print(f"   {marker} {s['name']}{source} — {s['description']}")
-            print(f"\n  Usage: /skin <name>")
-            print(f"  Custom skins: drop a YAML file in ~/.hermes/skins/\n")
-            return
-
-        new_skin = parts[1].strip().lower()
-        available = {s["name"] for s in list_skins()}
-        if new_skin not in available:
-            print(f"  Unknown skin: {new_skin}")
-            print(f"  Available: {', '.join(sorted(available))}")
-            return
-
-        set_active_skin(new_skin)
-        if save_config_value("display.skin", new_skin):
-            print(f"  Skin set to: {new_skin} (saved)")
-        else:
-            print(f"  Skin set to: {new_skin}")
-        print("  Note: banner colors will update on next session start.")
-
     def _toggle_verbose(self):
         """Cycle tool progress mode: off → new → all → verbose → off."""
         cycle = ["off", "new", "all", "verbose"]
@@ -3277,22 +3126,10 @@ class HermesCLI:
             
             if response:
                 w = shutil.get_terminal_size().columns
-                # Use skin branding for response box label
-                try:
-                    from hermes_cli.skin_engine import get_active_skin
-                    _skin = get_active_skin()
-                    label = _skin.get_branding("response_label", " ⚕ Hermes ")
-                    _resp_color = _skin.get_color("response_border", "")
-                    if _resp_color:
-                        _resp_start = f"\033[38;2;{int(_resp_color[1:3], 16)};{int(_resp_color[3:5], 16)};{int(_resp_color[5:7], 16)}m"
-                    else:
-                        _resp_start = _GOLD
-                except Exception:
-                    label = " ⚕ Hermes "
-                    _resp_start = _GOLD
+                label = " ⚕ Hermes "
                 fill = w - 2 - len(label)  # 2 for ╭ and ╮
-                top = f"{_resp_start}╭─{label}{'─' * max(fill - 1, 0)}╮{_RST}"
-                bot = f"{_resp_start}╰{'─' * (w - 2)}╯{_RST}"
+                top = f"{_GOLD}╭─{label}{'─' * max(fill - 1, 0)}╮{_RST}"
+                bot = f"{_GOLD}╰{'─' * (w - 2)}╯{_RST}"
 
                 # Render box + response as a single _cprint call so
                 # nothing can interleave between the box borders.
@@ -3361,15 +3198,7 @@ class HermesCLI:
             if self._preload_resumed_session():
                 self._display_resumed_history()
 
-        try:
-            from hermes_cli.skin_engine import get_active_skin
-            _welcome_skin = get_active_skin()
-            _welcome_text = _welcome_skin.get_branding("welcome", "Welcome to Hermes Agent! Type your message or /help for commands.")
-            _welcome_color = _welcome_skin.get_color("banner_text", "#FFF8DC")
-        except Exception:
-            _welcome_text = "Welcome to Hermes Agent! Type your message or /help for commands."
-            _welcome_color = "#FFF8DC"
-        self.console.print(f"[{_welcome_color}]{_welcome_text}[/]")
+        self.console.print("[#FFF8DC]Welcome to Hermes Agent! Type your message or /help for commands.[/]")
         self.console.print()
         
         # State for async operation
@@ -3757,8 +3586,6 @@ class HermesCLI:
                 return "type password (hidden), Enter to skip"
             if cli_ref._approval_state:
                 return ""
-            if cli_ref._clarify_freetext:
-                return "type your answer here and press Enter"
             if cli_ref._clarify_state:
                 return ""
             if cli_ref._agent_running:
@@ -3809,20 +3636,6 @@ class HermesCLI:
             # right up against the top rule of the input area
             return 1 if cli_ref._agent_running else 0
 
-        def get_spinner_text():
-            txt = cli_ref._spinner_text
-            if not txt:
-                return []
-            return [('class:hint', f'  {txt}')]
-
-        def get_spinner_height():
-            return 1 if cli_ref._spinner_text else 0
-
-        spinner_widget = Window(
-            content=FormattedTextControl(get_spinner_text),
-            height=get_spinner_height,
-        )
-
         spacer = Window(
             content=FormattedTextControl(get_hint_text),
             height=get_hint_height,
@@ -3830,32 +3643,6 @@ class HermesCLI:
 
         # --- Clarify tool: dynamic display widget for questions + choices ---
 
-        def _panel_box_width(title: str, content_lines: list[str], min_width: int = 46, max_width: int = 76) -> int:
-            """Choose a stable panel width wide enough for the title and content."""
-            term_cols = shutil.get_terminal_size((100, 20)).columns
-            longest = max([len(title)] + [len(line) for line in content_lines] + [min_width - 4])
-            inner = min(max(longest + 4, min_width - 2), max_width - 2, max(24, term_cols - 6))
-            return inner + 2  # account for the single leading/trailing spaces inside borders
-
-        def _wrap_panel_text(text: str, width: int, subsequent_indent: str = "") -> list[str]:
-            wrapped = textwrap.wrap(
-                text,
-                width=max(8, width),
-                break_long_words=False,
-                break_on_hyphens=False,
-                subsequent_indent=subsequent_indent,
-            )
-            return wrapped or [""]
-
-        def _append_panel_line(lines, border_style: str, content_style: str, text: str, box_width: int) -> None:
-            inner_width = max(0, box_width - 2)
-            lines.append((border_style, "│ "))
-            lines.append((content_style, text.ljust(inner_width)))
-            lines.append((border_style, " │\n"))
-
-        def _append_blank_panel_line(lines, border_style: str, box_width: int) -> None:
-            lines.append((border_style, "│" + (" " * box_width) + "│\n"))
-
         def _get_clarify_display():
             """Build styled text for the clarify question/choices panel."""
             state = cli_ref._clarify_state
@@ -3865,62 +3652,43 @@ class HermesCLI:
             question = state["question"]
             choices = state.get("choices") or []
             selected = state.get("selected", 0)
-            preview_lines = _wrap_panel_text(question, 60)
-            for i, choice in enumerate(choices):
-                prefix = "❯ " if i == selected and not cli_ref._clarify_freetext else "  "
-                preview_lines.extend(_wrap_panel_text(f"{prefix}{choice}", 60, subsequent_indent="  "))
-            other_label = (
-                "❯ Other (type below)" if cli_ref._clarify_freetext
-                else "❯ Other (type your answer)" if selected == len(choices)
-                else "  Other (type your answer)"
-            )
-            preview_lines.extend(_wrap_panel_text(other_label, 60, subsequent_indent="  "))
-            box_width = _panel_box_width("Hermes needs your input", preview_lines)
-            inner_text_width = max(8, box_width - 2)
 
             lines = []
             # Box top border
             lines.append(('class:clarify-border', '╭─ '))
             lines.append(('class:clarify-title', 'Hermes needs your input'))
-            lines.append(('class:clarify-border', ' ' + ('─' * max(0, box_width - len("Hermes needs your input") - 3)) + '╮\n'))
-            _append_blank_panel_line(lines, 'class:clarify-border', box_width)
+            lines.append(('class:clarify-border', ' ─────────────────────────────╮\n'))
+            lines.append(('class:clarify-border', '│\n'))
 
             # Question text
-            for wrapped in _wrap_panel_text(question, inner_text_width):
-                _append_panel_line(lines, 'class:clarify-border', 'class:clarify-question', wrapped, box_width)
-            _append_blank_panel_line(lines, 'class:clarify-border', box_width)
-
-            if cli_ref._clarify_freetext and not choices:
-                guidance = "Type your answer in the prompt below, then press Enter."
-                for wrapped in _wrap_panel_text(guidance, inner_text_width):
-                    _append_panel_line(lines, 'class:clarify-border', 'class:clarify-choice', wrapped, box_width)
-                _append_blank_panel_line(lines, 'class:clarify-border', box_width)
+            lines.append(('class:clarify-border', '│  '))
+            lines.append(('class:clarify-question', question))
+            lines.append(('', '\n'))
+            lines.append(('class:clarify-border', '│\n'))
 
             if choices:
                 # Multiple-choice mode: show selectable options
                 for i, choice in enumerate(choices):
-                    style = 'class:clarify-selected' if i == selected and not cli_ref._clarify_freetext else 'class:clarify-choice'
-                    prefix = '❯ ' if i == selected and not cli_ref._clarify_freetext else '  '
-                    wrapped_lines = _wrap_panel_text(f"{prefix}{choice}", inner_text_width, subsequent_indent="  ")
-                    for wrapped in wrapped_lines:
-                        _append_panel_line(lines, 'class:clarify-border', style, wrapped, box_width)
+                    lines.append(('class:clarify-border', '│  '))
+                    if i == selected and not cli_ref._clarify_freetext:
+                        lines.append(('class:clarify-selected', f'❯ {choice}'))
+                    else:
+                        lines.append(('class:clarify-choice', f'  {choice}'))
+                    lines.append(('', '\n'))
 
                 # "Other" option (5th line, only shown when choices exist)
                 other_idx = len(choices)
+                lines.append(('class:clarify-border', '│  '))
                 if selected == other_idx and not cli_ref._clarify_freetext:
-                    other_style = 'class:clarify-selected'
-                    other_label = '❯ Other (type your answer)'
+                    lines.append(('class:clarify-selected', '❯ Other (type your answer)'))
                 elif cli_ref._clarify_freetext:
-                    other_style = 'class:clarify-active-other'
-                    other_label = '❯ Other (type below)'
+                    lines.append(('class:clarify-active-other', '❯ Other (type below)'))
                 else:
-                    other_style = 'class:clarify-choice'
-                    other_label = '  Other (type your answer)'
-                for wrapped in _wrap_panel_text(other_label, inner_text_width, subsequent_indent="  "):
-                    _append_panel_line(lines, 'class:clarify-border', other_style, wrapped, box_width)
+                    lines.append(('class:clarify-choice', '  Other (type your answer)'))
+                lines.append(('', '\n'))
 
-            _append_blank_panel_line(lines, 'class:clarify-border', box_width)
-            lines.append(('class:clarify-border', '╰' + ('─' * box_width) + '╯\n'))
+            lines.append(('class:clarify-border', '│\n'))
+            lines.append(('class:clarify-border', '╰──────────────────────────────────────────────────╯\n'))
             return lines
 
         clarify_widget = ConditionalContainer(
@@ -3975,32 +3743,29 @@ class HermesCLI:
                 "always": "Add to permanent allowlist",
                 "deny": "Deny",
             }
-            preview_lines = _wrap_panel_text(description, 60)
-            preview_lines.extend(_wrap_panel_text(cmd_display, 60))
-            for i, choice in enumerate(choices):
-                prefix = '❯ ' if i == selected else '  '
-                preview_lines.extend(_wrap_panel_text(f"{prefix}{choice_labels.get(choice, choice)}", 60, subsequent_indent="  "))
-            box_width = _panel_box_width("⚠️  Dangerous Command", preview_lines)
-            inner_text_width = max(8, box_width - 2)
 
             lines = []
             lines.append(('class:approval-border', '╭─ '))
             lines.append(('class:approval-title', '⚠️  Dangerous Command'))
-            lines.append(('class:approval-border', ' ' + ('─' * max(0, box_width - len("⚠️  Dangerous Command") - 3)) + '╮\n'))
-            _append_blank_panel_line(lines, 'class:approval-border', box_width)
-            for wrapped in _wrap_panel_text(description, inner_text_width):
-                _append_panel_line(lines, 'class:approval-border', 'class:approval-desc', wrapped, box_width)
-            for wrapped in _wrap_panel_text(cmd_display, inner_text_width):
-                _append_panel_line(lines, 'class:approval-border', 'class:approval-cmd', wrapped, box_width)
-            _append_blank_panel_line(lines, 'class:approval-border', box_width)
+            lines.append(('class:approval-border', ' ───────────────────────────────╮\n'))
+            lines.append(('class:approval-border', '│\n'))
+            lines.append(('class:approval-border', '│  '))
+            lines.append(('class:approval-desc', description))
+            lines.append(('', '\n'))
+            lines.append(('class:approval-border', '│  '))
+            lines.append(('class:approval-cmd', cmd_display))
+            lines.append(('', '\n'))
+            lines.append(('class:approval-border', '│\n'))
             for i, choice in enumerate(choices):
+                lines.append(('class:approval-border', '│  '))
                 label = choice_labels.get(choice, choice)
-                style = 'class:approval-selected' if i == selected else 'class:approval-choice'
-                prefix = '❯ ' if i == selected else '  '
-                for wrapped in _wrap_panel_text(f"{prefix}{label}", inner_text_width, subsequent_indent="  "):
-                    _append_panel_line(lines, 'class:approval-border', style, wrapped, box_width)
-            _append_blank_panel_line(lines, 'class:approval-border', box_width)
-            lines.append(('class:approval-border', '╰' + ('─' * box_width) + '╯\n'))
+                if i == selected:
+                    lines.append(('class:approval-selected', f'❯ {label}'))
+                else:
+                    lines.append(('class:approval-choice', f'  {label}'))
+                lines.append(('', '\n'))
+            lines.append(('class:approval-border', '│\n'))
+            lines.append(('class:approval-border', '╰──────────────────────────────────────────────────────╯\n'))
             return lines
 
         approval_widget = ConditionalContainer(
@@ -4053,7 +3818,6 @@ class HermesCLI:
                 sudo_widget,
                 approval_widget,
                 clarify_widget,
-                spinner_widget,
                 spacer,
                 input_rule_top,
                 image_bar,
@@ -4108,7 +3872,6 @@ class HermesCLI:
             style=style,
             full_screen=False,
             mouse_support=False,
-            **({'cursor': _STEADY_CURSOR} if _STEADY_CURSOR is not None else {}),
         )
         self._app = app  # Store reference for clarify_callback
         
@@ -4177,7 +3940,6 @@ class HermesCLI:
                         self.chat(user_input, images=submit_images or None)
                     finally:
                         self._agent_running = False
-                        self._spinner_text = ""
                         app.invalidate()  # Refresh status line
                     
                 except Exception as e:
@@ -4238,7 +4000,6 @@ def main(
     resume: str = None,
     worktree: bool = False,
     w: bool = False,
-    checkpoints: bool = False,
 ):
     """
     Hermes Agent CLI - Interactive AI Assistant
@@ -4343,7 +4104,6 @@ def main(
         verbose=verbose,
         compact=compact,
         resume=resume,
-        checkpoints=checkpoints,
     )
 
     # Inject worktree context into agent's system prompt

cron/jobs.py

@@ -26,7 +26,7 @@ except ImportError:
 # Configuration
 # =============================================================================
 
-HERMES_DIR = Path(os.getenv("HERMES_HOME", Path.home() / ".hermes"))
+HERMES_DIR = Path.home() / ".hermes"
 CRON_DIR = HERMES_DIR / "cron"
 JOBS_FILE = CRON_DIR / "jobs.json"
 OUTPUT_DIR = CRON_DIR / "output"

datagen-config-examples/web_research.yaml

@@ -1,46 +0,0 @@
-# datagen-config-examples/web_research.yaml
-#
-# Batch data generation config for WebResearchEnv.
-# Generates tool-calling trajectories for multi-step web research tasks.
-#
-# Usage:
-#   python batch_runner.py \
-#     --config datagen-config-examples/web_research.yaml \
-#     --run_name web_research_v1
-
-environment: web-research
-
-# Toolsets available to the agent during data generation
-toolsets:
-  - web
-  - file
-
-# How many parallel workers to use
-num_workers: 4
-
-# Questions per batch
-batch_size: 20
-
-# Total trajectories to generate (comment out to run full dataset)
-max_items: 500
-
-# Model to use for generation (override with --model flag)
-model: openrouter/nousresearch/hermes-3-llama-3.1-405b
-
-# System prompt additions (ephemeral — not saved to trajectories)
-ephemeral_system_prompt: |
-  You are a highly capable research agent. When asked a factual question,
-  always use web_search to find current, accurate information before answering.
-  Cite at least 2 sources. Be concise and accurate.
-
-# Output directory
-output_dir: data/web_research_v1
-
-# Trajectory compression settings (for fitting into training token budgets)
-compression:
-  enabled: true
-  target_max_tokens: 16000
-
-# Eval settings
-eval_every: 100       # Run eval every N trajectories
-eval_size: 25         # Number of held-out questions per eval run

environments/web_research_env.py

@@ -1,718 +0,0 @@
-"""
-WebResearchEnv — RL Environment for Multi-Step Web Research
-============================================================
-
-Trains models to do accurate, efficient, multi-source web research.
-
-Reward signals:
-  - Answer correctness  (LLM judge, 0.0–1.0)
-  - Source diversity    (used ≥2 distinct domains)
-  - Efficiency          (penalizes excessive tool calls)
-  - Tool usage          (bonus for actually using web tools)
-
-Dataset: FRAMES benchmark (Google, 2024) — multi-hop factual questions
-  HuggingFace: google/frames-benchmark
-  Fallback:    built-in sample questions (no HF token needed)
-
-Usage:
-    # Phase 1 (OpenAI-compatible server)
-    python environments/web_research_env.py serve \\
-        --openai.base_url http://localhost:8000/v1 \\
-        --openai.model_name YourModel \\
-        --openai.server_type openai
-
-    # Process mode (offline data generation)
-    python environments/web_research_env.py process \\
-        --env.data_path_to_save_groups data/web_research.jsonl
-
-    # Standalone eval
-    python environments/web_research_env.py evaluate \\
-        --openai.base_url http://localhost:8000/v1 \\
-        --openai.model_name YourModel
-
-Built by: github.com/jackx707
-Inspired by: GroceryMind — production Hermes agent doing live web research
-             across German grocery stores (firecrawl + hermes-agent)
-"""
-
-from __future__ import annotations
-
-import asyncio
-import json
-import logging
-import os
-import random
-import re
-import sys
-from pathlib import Path
-from typing import Any, Dict, List, Optional, Tuple
-from urllib.parse import urlparse
-
-from pydantic import Field
-
-# Ensure hermes-agent root is on path
-_repo_root = Path(__file__).resolve().parent.parent
-if str(_repo_root) not in sys.path:
-    sys.path.insert(0, str(_repo_root))
-
-# ---------------------------------------------------------------------------
-# Optional HuggingFace datasets import
-# ---------------------------------------------------------------------------
-try:
-    from datasets import load_dataset
-    HF_AVAILABLE = True
-except ImportError:
-    HF_AVAILABLE = False
-
-from atroposlib.envs.base import ScoredDataGroup
-from atroposlib.envs.server_handling.server_manager import APIServerConfig
-from atroposlib.type_definitions import Item
-
-from environments.hermes_base_env import HermesAgentBaseEnv, HermesAgentEnvConfig
-from environments.agent_loop import AgentResult
-from environments.tool_context import ToolContext
-
-logger = logging.getLogger(__name__)
-
-# ---------------------------------------------------------------------------
-# Fallback sample dataset (used when HuggingFace is unavailable)
-# Multi-hop questions requiring real web search to answer.
-# ---------------------------------------------------------------------------
-SAMPLE_QUESTIONS = [
-    {
-        "question": "What is the current population of the capital city of the country that won the 2022 FIFA World Cup?",
-        "answer": "Buenos Aires has approximately 3 million people in the city proper, or around 15 million in the greater metro area.",
-        "difficulty": "medium",
-        "hops": 2,
-    },
-    {
-        "question": "Who is the CEO of the company that makes the most widely used open-source container orchestration platform?",
-        "answer": "The Linux Foundation oversees Kubernetes. CNCF (Cloud Native Computing Foundation) is the specific body — it does not have a traditional CEO but has an executive director.",
-        "difficulty": "medium",
-        "hops": 2,
-    },
-    {
-        "question": "What programming language was used to write the original version of the web framework used by Instagram?",
-        "answer": "Django, which Instagram was built on, is written in Python.",
-        "difficulty": "easy",
-        "hops": 2,
-    },
-    {
-        "question": "In what year was the university founded where the inventor of the World Wide Web currently holds a professorship?",
-        "answer": "Tim Berners-Lee holds a professorship at MIT (founded 1861) and the University of Southampton (founded 1952).",
-        "difficulty": "hard",
-        "hops": 3,
-    },
-    {
-        "question": "What is the latest stable version of the programming language that ranks #1 on the TIOBE index as of this year?",
-        "answer": "Python is currently #1 on TIOBE. The latest stable version should be verified via the official python.org site.",
-        "difficulty": "medium",
-        "hops": 2,
-    },
-    {
-        "question": "How many employees does the parent company of Instagram have?",
-        "answer": "Meta Platforms (parent of Instagram) employs approximately 70,000+ people as of recent reports.",
-        "difficulty": "medium",
-        "hops": 2,
-    },
-    {
-        "question": "What is the current interest rate set by the central bank of the country where the Eiffel Tower is located?",
-        "answer": "The European Central Bank sets rates for France/eurozone. The current rate should be verified — it has changed frequently in 2023-2025.",
-        "difficulty": "hard",
-        "hops": 2,
-    },
-    {
-        "question": "Which company acquired the startup founded by the creator of Oculus VR?",
-        "answer": "Palmer Luckey founded Oculus VR, which was acquired by Facebook (now Meta). He later founded Anduril Industries.",
-        "difficulty": "medium",
-        "hops": 2,
-    },
-    {
-        "question": "What is the market cap of the company that owns the most popular search engine in Russia?",
-        "answer": "Yandex (now split into separate entities after 2024 restructuring). Current market cap should be verified via financial sources.",
-        "difficulty": "hard",
-        "hops": 2,
-    },
-    {
-        "question": "What was the GDP growth rate of the country that hosted the most recent Summer Olympics?",
-        "answer": "Paris, France hosted the 2024 Summer Olympics. France's recent GDP growth should be verified via World Bank or IMF data.",
-        "difficulty": "hard",
-        "hops": 2,
-    },
-]
-
-
-# ---------------------------------------------------------------------------
-# Configuration
-# ---------------------------------------------------------------------------
-
-class WebResearchEnvConfig(HermesAgentEnvConfig):
-    """Configuration for the web research RL environment."""
-
-    # Reward weights
-    correctness_weight: float = Field(
-        default=0.6,
-        description="Weight for answer correctness in reward (LLM judge score).",
-    )
-    tool_usage_weight: float = Field(
-        default=0.2,
-        description="Weight for tool usage signal (did the model actually use web tools?).",
-    )
-    efficiency_weight: float = Field(
-        default=0.2,
-        description="Weight for efficiency signal (penalizes excessive tool calls).",
-    )
-    diversity_bonus: float = Field(
-        default=0.1,
-        description="Bonus reward for citing ≥2 distinct domains.",
-    )
-
-    # Efficiency thresholds
-    efficient_max_calls: int = Field(
-        default=5,
-        description="Maximum tool calls before efficiency penalty begins.",
-    )
-    heavy_penalty_calls: int = Field(
-        default=10,
-        description="Tool call count where efficiency penalty steepens.",
-    )
-
-    # Eval
-    eval_size: int = Field(
-        default=20,
-        description="Number of held-out items for evaluation.",
-    )
-    eval_split_ratio: float = Field(
-        default=0.1,
-        description="Fraction of dataset to hold out for evaluation (0.0–1.0).",
-    )
-
-    # Dataset
-    dataset_name: str = Field(
-        default="google/frames-benchmark",
-        description="HuggingFace dataset name for research questions.",
-    )
-
-
-# ---------------------------------------------------------------------------
-# Environment
-# ---------------------------------------------------------------------------
-
-class WebResearchEnv(HermesAgentBaseEnv):
-    """
-    RL environment for training multi-step web research skills.
-
-    The model is given a factual question requiring 2-3 hops of web research
-    and must use web_search / web_extract tools to find and synthesize the answer.
-
-    Reward is multi-signal:
-      60% — answer correctness (LLM judge)
-      20% — tool usage (did the model actually search the web?)
-      20% — efficiency (penalizes >5 tool calls)
-
-    Bonus +0.1 for source diversity (≥2 distinct domains cited).
-    """
-
-    name = "web-research"
-    env_config_cls = WebResearchEnvConfig
-
-    # Default toolsets for this environment — web + file for saving notes
-    default_toolsets = ["web", "file"]
-
-    @classmethod
-    def config_init(cls) -> Tuple[WebResearchEnvConfig, List[APIServerConfig]]:
-        """Default configuration for the web research environment."""
-        env_config = WebResearchEnvConfig(
-            enabled_toolsets=["web", "file"],
-            max_agent_turns=15,
-            agent_temperature=1.0,
-            system_prompt=(
-                "You are a highly capable research agent. When asked a factual question, "
-                "always use web_search to find current, accurate information before answering. "
-                "Cite at least 2 sources. Be concise and accurate."
-            ),
-            group_size=4,
-            total_steps=1000,
-            steps_per_eval=100,
-            use_wandb=True,
-            wandb_name="web-research",
-        )
-
-        server_configs = [
-            APIServerConfig(
-                base_url="https://openrouter.ai/api/v1",
-                model_name="anthropic/claude-sonnet-4.5",
-                server_type="openai",
-                api_key=os.getenv("OPENROUTER_API_KEY", ""),
-                health_check=False,
-            )
-        ]
-
-        return env_config, server_configs
-
-    def __init__(self, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-        self._items: list[dict] = []
-        self._eval_items: list[dict] = []
-        self._index: int = 0
-
-        # Metrics tracking for wandb
-        self._reward_buffer: list[float] = []
-        self._correctness_buffer: list[float] = []
-        self._tool_usage_buffer: list[float] = []
-        self._efficiency_buffer: list[float] = []
-        self._diversity_buffer: list[float] = []
-
-    # ------------------------------------------------------------------
-    # 1. Setup — load dataset
-    # ------------------------------------------------------------------
-
-    async def setup(self) -> None:
-        """Load the FRAMES benchmark or fall back to built-in samples."""
-        if HF_AVAILABLE:
-            try:
-                logger.info("Loading FRAMES benchmark from HuggingFace...")
-                ds = load_dataset(self.config.dataset_name, split="test")
-                self._items = [
-                    {
-                        "question": row["Prompt"],
-                        "answer": row["Answer"],
-                        "difficulty": row.get("reasoning_types", "unknown"),
-                        "hops": 2,
-                    }
-                    for row in ds
-                ]
-                # Hold out for eval
-                eval_size = max(
-                    self.config.eval_size,
-                    int(len(self._items) * self.config.eval_split_ratio),
-                )
-                random.shuffle(self._items)
-                self._eval_items = self._items[:eval_size]
-                self._items = self._items[eval_size:]
-                logger.info(
-                    f"Loaded {len(self._items)} train / {len(self._eval_items)} eval items "
-                    f"from FRAMES benchmark."
-                )
-                return
-            except Exception as e:
-                logger.warning(f"Could not load FRAMES from HuggingFace: {e}. Using built-in samples.")
-
-        # Fallback
-        random.shuffle(SAMPLE_QUESTIONS)
-        split = max(1, len(SAMPLE_QUESTIONS) * 8 // 10)
-        self._items = SAMPLE_QUESTIONS[:split]
-        self._eval_items = SAMPLE_QUESTIONS[split:]
-        logger.info(
-            f"Using built-in sample dataset: {len(self._items)} train / "
-            f"{len(self._eval_items)} eval items."
-        )
-
-    # ------------------------------------------------------------------
-    # 2. get_next_item — return the next question
-    # ------------------------------------------------------------------
-
-    async def get_next_item(self) -> dict:
-        """Return the next item, cycling through the dataset."""
-        if not self._items:
-            raise RuntimeError("Dataset is empty. Did you call setup()?")
-        item = self._items[self._index % len(self._items)]
-        self._index += 1
-        return item
-
-    # ------------------------------------------------------------------
-    # 3. format_prompt — build the user-facing prompt
-    # ------------------------------------------------------------------
-
-    def format_prompt(self, item: dict) -> str:
-        """Format the research question as a task prompt."""
-        return (
-            f"Research the following question thoroughly using web search. "
-            f"You MUST search the web to find current, accurate information — "
-            f"do not rely solely on your training data.\n\n"
-            f"Question: {item['question']}\n\n"
-            f"Requirements:\n"
-            f"- Use web_search and/or web_extract tools to find information\n"
-            f"- Search at least 2 different sources\n"
-            f"- Provide a concise, accurate answer (2-4 sentences)\n"
-            f"- Cite the sources you used"
-        )
-
-    # ------------------------------------------------------------------
-    # 4. compute_reward — multi-signal scoring
-    # ------------------------------------------------------------------
-
-    async def compute_reward(
-        self,
-        item: dict,
-        result: AgentResult,
-        ctx: ToolContext,
-    ) -> float:
-        """
-        Multi-signal reward function:
-
-          correctness_weight * correctness  — LLM judge comparing answer to ground truth
-          tool_usage_weight  * tool_used    — binary: did the model use web tools?
-          efficiency_weight  * efficiency   — penalizes wasteful tool usage
-          + diversity_bonus                 — source diversity (≥2 distinct domains)
-        """
-        # Extract final response from messages (last assistant message with content)
-        final_response = ""
-        tools_used: list[str] = []
-        for msg in reversed(result.messages):
-            if msg.get("role") == "assistant" and msg.get("content") and not final_response:
-                final_response = msg["content"]
-            # Collect tool names from tool call messages
-            if msg.get("role") == "assistant" and msg.get("tool_calls"):
-                for tc in msg["tool_calls"]:
-                    fn = tc.get("function", {}) if isinstance(tc, dict) else {}
-                    name = fn.get("name", "")
-                    if name:
-                        tools_used.append(name)
-        tool_call_count: int = result.turns_used or len(tools_used)
-
-        cfg = self.config
-
-        # ---- Signal 1: Answer correctness (LLM judge) ----------------
-        correctness = await self._llm_judge(
-            question=item["question"],
-            expected=item["answer"],
-            model_answer=final_response,
-        )
-
-        # ---- Signal 2: Web tool usage --------------------------------
-        web_tools = {"web_search", "web_extract", "search", "firecrawl"}
-        tool_used = 1.0 if any(t in web_tools for t in tools_used) else 0.0
-
-        # ---- Signal 3: Efficiency ------------------------------------
-        if tool_call_count <= cfg.efficient_max_calls:
-            efficiency = 1.0
-        elif tool_call_count <= cfg.heavy_penalty_calls:
-            efficiency = 1.0 - (tool_call_count - cfg.efficient_max_calls) * 0.08
-        else:
-            efficiency = max(0.0, 1.0 - (tool_call_count - cfg.efficient_max_calls) * 0.12)
-
-        # ---- Bonus: Source diversity ---------------------------------
-        domains = self._extract_domains(final_response)
-        diversity = cfg.diversity_bonus if len(domains) >= 2 else 0.0
-
-        # ---- Combine ------------------------------------------------
-        reward = (
-            cfg.correctness_weight * correctness
-            + cfg.tool_usage_weight * tool_used
-            + cfg.efficiency_weight * efficiency
-            + diversity
-        )
-        reward = min(1.0, max(0.0, reward))  # clamp to [0, 1]
-
-        # Track for wandb
-        self._reward_buffer.append(reward)
-        self._correctness_buffer.append(correctness)
-        self._tool_usage_buffer.append(tool_used)
-        self._efficiency_buffer.append(efficiency)
-        self._diversity_buffer.append(diversity)
-
-        logger.debug(
-            f"Reward breakdown — correctness={correctness:.2f}, "
-            f"tool_used={tool_used:.1f}, efficiency={efficiency:.2f}, "
-            f"diversity={diversity:.1f} → total={reward:.3f}"
-        )
-
-        return reward
-
-    # ------------------------------------------------------------------
-    # 5. evaluate — run on held-out eval split
-    # ------------------------------------------------------------------
-
-    async def evaluate(self, *args, **kwargs) -> None:
-        """Run evaluation on the held-out split using the full agent loop with tools.
-
-        Each eval item runs through the same agent loop as training —
-        the model can use web_search, web_extract, etc. to research answers.
-        This measures actual agentic research capability, not just knowledge.
-        """
-        import time
-        import uuid
-        from environments.agent_loop import HermesAgentLoop
-        from environments.tool_context import ToolContext
-
-        items = self._eval_items
-        if not items:
-            logger.warning("No eval items available.")
-            return
-
-        eval_size = min(self.config.eval_size, len(items))
-        eval_items = items[:eval_size]
-
-        logger.info(f"Running eval on {len(eval_items)} questions (with agent loop + tools)...")
-        start_time = time.time()
-        samples = []
-
-        # Resolve tools once for all eval items
-        tools, valid_names = self._resolve_tools_for_group()
-
-        for i, item in enumerate(eval_items):
-            task_id = str(uuid.uuid4())
-            logger.info(f"Eval [{i+1}/{len(eval_items)}]: {item['question'][:80]}...")
-
-            try:
-                # Build messages
-                messages: List[Dict[str, Any]] = []
-                if self.config.system_prompt:
-                    messages.append({"role": "system", "content": self.config.system_prompt})
-                messages.append({"role": "user", "content": self.format_prompt(item)})
-
-                # Run the full agent loop with tools
-                agent = HermesAgentLoop(
-                    server=self.server,
-                    tool_schemas=tools,
-                    valid_tool_names=valid_names,
-                    max_turns=self.config.max_agent_turns,
-                    task_id=task_id,
-                    temperature=0.0,  # Deterministic for eval
-                    max_tokens=self.config.max_token_length,
-                    extra_body=self.config.extra_body,
-                )
-                result = await agent.run(messages)
-
-                # Extract final response and tool usage from messages
-                final_response = ""
-                tool_call_count = 0
-                for msg in reversed(result.messages):
-                    if msg.get("role") == "assistant" and msg.get("content") and not final_response:
-                        final_response = msg["content"]
-                    if msg.get("role") == "assistant" and msg.get("tool_calls"):
-                        tool_call_count += len(msg["tool_calls"])
-
-                # Compute reward (includes LLM judge for correctness)
-                # Temporarily save buffer lengths so we can extract the
-                # correctness score without calling judge twice, and avoid
-                # polluting training metric buffers with eval data.
-                buf_len = len(self._correctness_buffer)
-                ctx = ToolContext(task_id)
-                try:
-                    reward = await self.compute_reward(item, result, ctx)
-                finally:
-                    ctx.cleanup()
-
-                # Extract correctness from the buffer (compute_reward appended it)
-                # then remove eval entries from training buffers
-                correctness = (
-                    self._correctness_buffer[buf_len]
-                    if len(self._correctness_buffer) > buf_len
-                    else 0.0
-                )
-                # Roll back buffers to avoid polluting training metrics
-                for buf in (
-                    self._reward_buffer, self._correctness_buffer,
-                    self._tool_usage_buffer, self._efficiency_buffer,
-                    self._diversity_buffer,
-                ):
-                    if len(buf) > buf_len:
-                        buf.pop()
-
-                samples.append({
-                    "prompt": item["question"],
-                    "response": final_response[:500],
-                    "expected": item["answer"],
-                    "correctness": correctness,
-                    "reward": reward,
-                    "tool_calls": tool_call_count,
-                    "turns": result.turns_used,
-                })
-
-                logger.info(
-                    f"  → correctness={correctness:.2f}, reward={reward:.3f}, "
-                    f"tools={tool_call_count}, turns={result.turns_used}"
-                )
-
-            except Exception as e:
-                logger.error(f"Eval error on item: {e}")
-                samples.append({
-                    "prompt": item["question"],
-                    "response": f"ERROR: {e}",
-                    "expected": item["answer"],
-                    "correctness": 0.0,
-                    "reward": 0.0,
-                    "tool_calls": 0,
-                    "turns": 0,
-                })
-
-        end_time = time.time()
-
-        # Compute aggregate metrics
-        correctness_scores = [s["correctness"] for s in samples]
-        rewards = [s["reward"] for s in samples]
-        tool_counts = [s["tool_calls"] for s in samples]
-        n = len(samples)
-
-        eval_metrics = {
-            "eval/mean_correctness": sum(correctness_scores) / n if n else 0.0,
-            "eval/mean_reward": sum(rewards) / n if n else 0.0,
-            "eval/mean_tool_calls": sum(tool_counts) / n if n else 0.0,
-            "eval/tool_usage_rate": sum(1 for t in tool_counts if t > 0) / n if n else 0.0,
-            "eval/n_items": n,
-        }
-
-        logger.info(
-            f"Eval complete — correctness={eval_metrics['eval/mean_correctness']:.3f}, "
-            f"reward={eval_metrics['eval/mean_reward']:.3f}, "
-            f"tool_usage={eval_metrics['eval/tool_usage_rate']:.0%}"
-        )
-
-        await self.evaluate_log(
-            metrics=eval_metrics,
-            samples=samples,
-            start_time=start_time,
-            end_time=end_time,
-        )
-
-    # ------------------------------------------------------------------
-    # 6. wandb_log — custom metrics
-    # ------------------------------------------------------------------
-
-    async def wandb_log(self, wandb_metrics: Optional[Dict] = None) -> None:
-        """Log reward breakdown metrics to wandb."""
-        if wandb_metrics is None:
-            wandb_metrics = {}
-
-        if self._reward_buffer:
-            n = len(self._reward_buffer)
-            wandb_metrics["train/mean_reward"] = sum(self._reward_buffer) / n
-            wandb_metrics["train/mean_correctness"] = sum(self._correctness_buffer) / n
-            wandb_metrics["train/mean_tool_usage"] = sum(self._tool_usage_buffer) / n
-            wandb_metrics["train/mean_efficiency"] = sum(self._efficiency_buffer) / n
-            wandb_metrics["train/mean_diversity"] = sum(self._diversity_buffer) / n
-            wandb_metrics["train/total_rollouts"] = n
-
-            # Accuracy buckets
-            wandb_metrics["train/correct_rate"] = (
-                sum(1 for c in self._correctness_buffer if c >= 0.7) / n
-            )
-            wandb_metrics["train/tool_usage_rate"] = (
-                sum(1 for t in self._tool_usage_buffer if t > 0) / n
-            )
-
-            # Clear buffers
-            self._reward_buffer.clear()
-            self._correctness_buffer.clear()
-            self._tool_usage_buffer.clear()
-            self._efficiency_buffer.clear()
-            self._diversity_buffer.clear()
-
-        await super().wandb_log(wandb_metrics)
-
-    # ------------------------------------------------------------------
-    # Private helpers
-    # ------------------------------------------------------------------
-
-    async def _llm_judge(
-        self,
-        question: str,
-        expected: str,
-        model_answer: str,
-    ) -> float:
-        """
-        Use the server's LLM to judge answer correctness.
-        Falls back to keyword heuristic if LLM call fails.
-        """
-        if not model_answer or not model_answer.strip():
-            return 0.0
-
-        judge_prompt = (
-            "You are an impartial judge evaluating the quality of an AI research answer.\n\n"
-            f"Question: {question}\n\n"
-            f"Reference answer: {expected}\n\n"
-            f"Model answer: {model_answer}\n\n"
-            "Score the model answer on a scale from 0.0 to 1.0 where:\n"
-            "  1.0 = fully correct and complete\n"
-            "  0.7 = mostly correct with minor gaps\n"
-            "  0.4 = partially correct\n"
-            "  0.1 = mentions relevant topic but wrong or very incomplete\n"
-            "  0.0 = completely wrong or no answer\n\n"
-            "Consider: factual accuracy, completeness, and relevance.\n"
-            'Respond with ONLY a JSON object: {"score": <float>, "reason": "<one sentence>"}'
-        )
-
-        try:
-            response = await self.server.chat_completion(
-                messages=[{"role": "user", "content": judge_prompt}],
-                n=1,
-                max_tokens=150,
-                temperature=0.0,
-                split="eval",
-            )
-            text = response.choices[0].message.content if response.choices else ""
-            parsed = self._parse_judge_json(text)
-            if parsed is not None:
-                return float(parsed)
-        except Exception as e:
-            logger.debug(f"LLM judge failed: {e}. Using heuristic.")
-
-        return self._heuristic_score(expected, model_answer)
-
-    @staticmethod
-    def _parse_judge_json(text: str) -> Optional[float]:
-        """Extract the score float from LLM judge JSON response."""
-        try:
-            clean = re.sub(r"```(?:json)?|```", "", text).strip()
-            data = json.loads(clean)
-            score = float(data.get("score", -1))
-            if 0.0 <= score <= 1.0:
-                return score
-        except Exception:
-            match = re.search(r'"score"\s*:\s*([0-9.]+)', text)
-            if match:
-                score = float(match.group(1))
-                if 0.0 <= score <= 1.0:
-                    return score
-        return None
-
-    @staticmethod
-    def _heuristic_score(expected: str, model_answer: str) -> float:
-        """Lightweight keyword overlap score as fallback."""
-        stopwords = {
-            "the", "a", "an", "is", "are", "was", "were", "of", "in", "on",
-            "at", "to", "for", "with", "and", "or", "but", "it", "its",
-            "this", "that", "as", "by", "from", "be", "has", "have", "had",
-        }
-
-        def tokenize(text: str) -> set:
-            tokens = re.findall(r'\b\w+\b', text.lower())
-            return {t for t in tokens if t not in stopwords and len(t) > 2}
-
-        expected_tokens = tokenize(expected)
-        answer_tokens = tokenize(model_answer)
-
-        if not expected_tokens:
-            return 0.5
-
-        overlap = len(expected_tokens & answer_tokens)
-        union = len(expected_tokens | answer_tokens)
-
-        jaccard = overlap / union if union > 0 else 0.0
-        recall = overlap / len(expected_tokens)
-        return min(1.0, 0.4 * jaccard + 0.6 * recall)
-
-    @staticmethod
-    def _extract_domains(text: str) -> set:
-        """Extract unique domains from URLs cited in the response."""
-        urls = re.findall(r'https?://[^\s\)>\]"\']+', text)
-        domains = set()
-        for url in urls:
-            try:
-                parsed = urlparse(url)
-                domain = parsed.netloc.lower().lstrip("www.")
-                if domain:
-                    domains.add(domain)
-            except Exception:
-                pass
-        return domains
-
-
-# ---------------------------------------------------------------------------
-# Entry point
-# ---------------------------------------------------------------------------
-
-if __name__ == "__main__":
-    WebResearchEnv.cli()

gateway/config.py

@@ -270,7 +270,7 @@ def load_gateway_config() -> GatewayConfig:
     gateway_config_path = Path.home() / ".hermes" / "gateway.json"
     if gateway_config_path.exists():
         try:
-            with open(gateway_config_path, "r", encoding="utf-8") as f:
+            with open(gateway_config_path, "r") as f:
                 data = json.load(f)
                 config = GatewayConfig.from_dict(data)
         except Exception as e:
@@ -283,7 +283,7 @@ def load_gateway_config() -> GatewayConfig:
         import yaml
         config_yaml_path = Path.home() / ".hermes" / "config.yaml"
         if config_yaml_path.exists():
-            with open(config_yaml_path, encoding="utf-8") as f:
+            with open(config_yaml_path) as f:
                 yaml_cfg = yaml.safe_load(f) or {}
             sr = yaml_cfg.get("session_reset")
             if sr and isinstance(sr, dict):
@@ -441,5 +441,5 @@ def save_gateway_config(config: GatewayConfig) -> None:
     gateway_config_path = Path.home() / ".hermes" / "gateway.json"
     gateway_config_path.parent.mkdir(parents=True, exist_ok=True)
     
-    with open(gateway_config_path, "w", encoding="utf-8") as f:
+    with open(gateway_config_path, "w") as f:
         json.dump(config.to_dict(), f, indent=2)

gateway/mirror.py

@@ -111,7 +111,6 @@ def _append_to_jsonl(session_id: str, message: dict) -> None:
 
 def _append_to_sqlite(session_id: str, message: dict) -> None:
     """Append a message to the SQLite session database."""
-    db = None
     try:
         from hermes_state import SessionDB
         db = SessionDB()
@@ -122,6 +121,3 @@ def _append_to_sqlite(session_id: str, message: dict) -> None:
         )
     except Exception as e:
         logger.debug("Mirror SQLite write failed: %s", e)
-    finally:
-        if db is not None:
-            db.close()

gateway/platforms/base.py

@@ -252,7 +252,6 @@ def cleanup_document_cache(max_age_hours: int = 24) -> int:
 class MessageType(Enum):
     """Types of incoming messages."""
     TEXT = "text"
-    LOCATION = "location"
     PHOTO = "photo"
     VIDEO = "video"
     AUDIO = "audio"

gateway/platforms/slack.py

@@ -10,7 +10,6 @@ Uses slack-bolt (Python) with Socket Mode for:
 
 import asyncio
 import os
-import re
 from typing import Dict, List, Optional, Any
 
 try:
@@ -34,8 +33,6 @@ from gateway.platforms.base import (
     MessageEvent,
     MessageType,
     SendResult,
-    SUPPORTED_DOCUMENT_TYPES,
-    cache_document_from_bytes,
     cache_image_from_url,
     cache_audio_from_url,
 )
@@ -99,13 +96,6 @@ class SlackAdapter(BasePlatformAdapter):
             async def handle_message_event(event, say):
                 await self._handle_slack_message(event)
 
-            # Acknowledge app_mention events to prevent Bolt 404 errors.
-            # The "message" handler above already processes @mentions in
-            # channels, so this is intentionally a no-op to avoid duplicates.
-            @self._app.event("app_mention")
-            async def handle_app_mention(event, say):
-                pass
-
             # Register slash command handler
             @self._app.command("/hermes")
             async def handle_hermes_command(ack, command):
@@ -276,65 +266,6 @@ class SlackAdapter(BasePlatformAdapter):
         except Exception as e:
             return SendResult(success=False, error=str(e))
 
-    async def send_video(
-        self,
-        chat_id: str,
-        video_path: str,
-        caption: Optional[str] = None,
-        reply_to: Optional[str] = None,
-    ) -> SendResult:
-        """Send a video file to Slack."""
-        if not self._app:
-            return SendResult(success=False, error="Not connected")
-
-        if not os.path.exists(video_path):
-            return SendResult(success=False, error=f"Video file not found: {video_path}")
-
-        try:
-            result = await self._app.client.files_upload_v2(
-                channel=chat_id,
-                file=video_path,
-                filename=os.path.basename(video_path),
-                initial_comment=caption or "",
-                thread_ts=reply_to,
-            )
-            return SendResult(success=True, raw_response=result)
-
-        except Exception as e:
-            print(f"[{self.name}] Failed to send video: {e}")
-            return await super().send_video(chat_id, video_path, caption, reply_to)
-
-    async def send_document(
-        self,
-        chat_id: str,
-        file_path: str,
-        caption: Optional[str] = None,
-        file_name: Optional[str] = None,
-        reply_to: Optional[str] = None,
-    ) -> SendResult:
-        """Send a document/file attachment to Slack."""
-        if not self._app:
-            return SendResult(success=False, error="Not connected")
-
-        if not os.path.exists(file_path):
-            return SendResult(success=False, error=f"File not found: {file_path}")
-
-        display_name = file_name or os.path.basename(file_path)
-
-        try:
-            result = await self._app.client.files_upload_v2(
-                channel=chat_id,
-                file=file_path,
-                filename=display_name,
-                initial_comment=caption or "",
-                thread_ts=reply_to,
-            )
-            return SendResult(success=True, raw_response=result)
-
-        except Exception as e:
-            print(f"[{self.name}] Failed to send document: {e}")
-            return await super().send_document(chat_id, file_path, caption, file_name, reply_to)
-
     async def get_chat_info(self, chat_id: str) -> Dict[str, Any]:
         """Get information about a Slack channel."""
         if not self._app:
@@ -416,58 +347,6 @@ class SlackAdapter(BasePlatformAdapter):
                     msg_type = MessageType.VOICE
                 except Exception as e:
                     print(f"[Slack] Failed to cache audio: {e}", flush=True)
-            elif url:
-                # Try to handle as a document attachment
-                try:
-                    original_filename = f.get("name", "")
-                    ext = ""
-                    if original_filename:
-                        _, ext = os.path.splitext(original_filename)
-                        ext = ext.lower()
-
-                    # Fallback: reverse-lookup from MIME type
-                    if not ext and mimetype:
-                        mime_to_ext = {v: k for k, v in SUPPORTED_DOCUMENT_TYPES.items()}
-                        ext = mime_to_ext.get(mimetype, "")
-
-                    if ext not in SUPPORTED_DOCUMENT_TYPES:
-                        continue  # Skip unsupported file types silently
-
-                    # Check file size (Slack limit: 20 MB for bots)
-                    file_size = f.get("size", 0)
-                    MAX_DOC_BYTES = 20 * 1024 * 1024
-                    if not file_size or file_size > MAX_DOC_BYTES:
-                        print(f"[Slack] Document too large or unknown size: {file_size}", flush=True)
-                        continue
-
-                    # Download and cache
-                    raw_bytes = await self._download_slack_file_bytes(url)
-                    cached_path = cache_document_from_bytes(
-                        raw_bytes, original_filename or f"document{ext}"
-                    )
-                    doc_mime = SUPPORTED_DOCUMENT_TYPES[ext]
-                    media_urls.append(cached_path)
-                    media_types.append(doc_mime)
-                    msg_type = MessageType.DOCUMENT
-                    print(f"[Slack] Cached user document: {cached_path}", flush=True)
-
-                    # Inject text content for .txt/.md files (capped at 100 KB)
-                    MAX_TEXT_INJECT_BYTES = 100 * 1024
-                    if ext in (".md", ".txt") and len(raw_bytes) <= MAX_TEXT_INJECT_BYTES:
-                        try:
-                            text_content = raw_bytes.decode("utf-8")
-                            display_name = original_filename or f"document{ext}"
-                            display_name = re.sub(r'[^\w.\- ]', '_', display_name)
-                            injection = f"[Content of {display_name}]:\n{text_content}"
-                            if text:
-                                text = f"{injection}\n\n{text}"
-                            else:
-                                text = injection
-                        except UnicodeDecodeError:
-                            pass  # Binary content, skip injection
-
-                except Exception as e:
-                    print(f"[Slack] Failed to cache document: {e}", flush=True)
 
         # Build source
         source = self.build_source(
@@ -548,16 +427,3 @@ class SlackAdapter(BasePlatformAdapter):
         else:
             from gateway.platforms.base import cache_image_from_bytes
             return cache_image_from_bytes(response.content, ext)
-
-    async def _download_slack_file_bytes(self, url: str) -> bytes:
-        """Download a Slack file and return raw bytes."""
-        import httpx
-
-        bot_token = self.config.token
-        async with httpx.AsyncClient(timeout=30.0, follow_redirects=True) as client:
-            response = await client.get(
-                url,
-                headers={"Authorization": f"Bearer {bot_token}"},
-            )
-            response.raise_for_status()
-        return response.content

gateway/platforms/telegram.py

@@ -132,10 +132,6 @@ class TelegramAdapter(BasePlatformAdapter):
                 filters.COMMAND,
                 self._handle_command
             ))
-            self._app.add_handler(TelegramMessageHandler(
-                filters.LOCATION | getattr(filters, "VENUE", filters.LOCATION),
-                self._handle_location_message
-            ))
             self._app.add_handler(TelegramMessageHandler(
                 filters.PHOTO | filters.VIDEO | filters.AUDIO | filters.VOICE | filters.Document.ALL | filters.Sticker.ALL,
                 self._handle_media_message
@@ -550,41 +546,6 @@ class TelegramAdapter(BasePlatformAdapter):
         event = self._build_message_event(update.message, MessageType.COMMAND)
         await self.handle_message(event)
     
-    async def _handle_location_message(self, update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
-        """Handle incoming location/venue pin messages."""
-        if not update.message:
-            return
-
-        msg = update.message
-        venue = getattr(msg, "venue", None)
-        location = getattr(venue, "location", None) if venue else getattr(msg, "location", None)
-
-        if not location:
-            return
-
-        lat = getattr(location, "latitude", None)
-        lon = getattr(location, "longitude", None)
-        if lat is None or lon is None:
-            return
-
-        # Build a text message with coordinates and context
-        parts = ["[The user shared a location pin.]"]
-        if venue:
-            title = getattr(venue, "title", None)
-            address = getattr(venue, "address", None)
-            if title:
-                parts.append(f"Venue: {title}")
-            if address:
-                parts.append(f"Address: {address}")
-        parts.append(f"latitude: {lat}")
-        parts.append(f"longitude: {lon}")
-        parts.append(f"Map: https://www.google.com/maps/search/?api=1&query={lat},{lon}")
-        parts.append("Ask what they'd like to find nearby (restaurants, cafes, etc.) and any preferences.")
-
-        event = self._build_message_event(msg, MessageType.LOCATION)
-        event.text = "\n".join(parts)
-        await self.handle_message(event)
-
     async def _handle_media_message(self, update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
         """Handle incoming media messages, downloading images to local cache."""
         if not update.message:

gateway/run.py

@@ -48,7 +48,7 @@ _config_path = _hermes_home / 'config.yaml'
 if _config_path.exists():
     try:
         import yaml as _yaml
-        with open(_config_path, encoding="utf-8") as _f:
+        with open(_config_path) as _f:
             _cfg = _yaml.safe_load(_f) or {}
         # Top-level simple values (fallback only — don't override .env)
         for _key, _val in _cfg.items():
@@ -75,16 +75,11 @@ if _config_path.exists():
                 "container_memory": "TERMINAL_CONTAINER_MEMORY",
                 "container_disk": "TERMINAL_CONTAINER_DISK",
                 "container_persistent": "TERMINAL_CONTAINER_PERSISTENT",
-                "docker_volumes": "TERMINAL_DOCKER_VOLUMES",
                 "sandbox_dir": "TERMINAL_SANDBOX_DIR",
             }
             for _cfg_key, _env_var in _terminal_env_map.items():
                 if _cfg_key in _terminal_cfg:
-                    _val = _terminal_cfg[_cfg_key]
-                    if isinstance(_val, list):
-                        os.environ[_env_var] = json.dumps(_val)
-                    else:
-                        os.environ[_env_var] = str(_val)
+                    os.environ[_env_var] = str(_terminal_cfg[_cfg_key])
         _compression_cfg = _cfg.get("compression", {})
         if _compression_cfg and isinstance(_compression_cfg, dict):
             _compression_env_map = {
@@ -316,7 +311,7 @@ class GatewayRunner:
                 import yaml as _y
                 cfg_path = _hermes_home / "config.yaml"
                 if cfg_path.exists():
-                    with open(cfg_path, encoding="utf-8") as _f:
+                    with open(cfg_path) as _f:
                         cfg = _y.safe_load(_f) or {}
                     file_path = cfg.get("prefill_messages_file", "")
             except Exception:
@@ -354,7 +349,7 @@ class GatewayRunner:
             import yaml as _y
             cfg_path = _hermes_home / "config.yaml"
             if cfg_path.exists():
-                with open(cfg_path, encoding="utf-8") as _f:
+                with open(cfg_path) as _f:
                     cfg = _y.safe_load(_f) or {}
                 return (cfg.get("agent", {}).get("system_prompt", "") or "").strip()
         except Exception:
@@ -375,7 +370,7 @@ class GatewayRunner:
                 import yaml as _y
                 cfg_path = _hermes_home / "config.yaml"
                 if cfg_path.exists():
-                    with open(cfg_path, encoding="utf-8") as _f:
+                    with open(cfg_path) as _f:
                         cfg = _y.safe_load(_f) or {}
                     effort = str(cfg.get("agent", {}).get("reasoning_effort", "") or "").strip()
             except Exception:
@@ -398,7 +393,7 @@ class GatewayRunner:
             import yaml as _y
             cfg_path = _hermes_home / "config.yaml"
             if cfg_path.exists():
-                with open(cfg_path, encoding="utf-8") as _f:
+                with open(cfg_path) as _f:
                     cfg = _y.safe_load(_f) or {}
                 return cfg.get("provider_routing", {}) or {}
         except Exception:
@@ -416,7 +411,7 @@ class GatewayRunner:
             import yaml as _y
             cfg_path = _hermes_home / "config.yaml"
             if cfg_path.exists():
-                with open(cfg_path, encoding="utf-8") as _f:
+                with open(cfg_path) as _f:
                     cfg = _y.safe_load(_f) or {}
                 fb = cfg.get("fallback_model", {}) or {}
                 if fb.get("provider") and fb.get("model"):
@@ -771,7 +766,7 @@ class GatewayRunner:
         _known_commands = {"new", "reset", "help", "status", "stop", "model",
                           "personality", "retry", "undo", "sethome", "set-home",
                           "compress", "usage", "insights", "reload-mcp", "reload_mcp",
-                          "update", "title", "resume", "provider", "rollback"}
+                          "update", "title", "resume", "provider"}
         if command and command in _known_commands:
             await self.hooks.emit(f"command:{command}", {
                 "platform": source.platform.value if source.platform else "",
@@ -830,9 +825,6 @@ class GatewayRunner:
 
         if command == "resume":
             return await self._handle_resume_command(event)
-
-        if command == "rollback":
-            return await self._handle_rollback_command(event)
         
         # Skill slash commands: /skill-name loads the skill and sends to agent
         if command:
@@ -934,7 +926,7 @@ class GatewayRunner:
                 _hyg_cfg_path = _hermes_home / "config.yaml"
                 if _hyg_cfg_path.exists():
                     import yaml as _hyg_yaml
-                    with open(_hyg_cfg_path, encoding="utf-8") as _hyg_f:
+                    with open(_hyg_cfg_path) as _hyg_f:
                         _hyg_data = _hyg_yaml.safe_load(_hyg_f) or {}
 
                     # Resolve model name (same logic as run_sync)
@@ -1403,7 +1395,6 @@ class GatewayRunner:
             "`/resume [name]` — Resume a previously-named session",
             "`/usage` — Show token usage for this session",
             "`/insights [days]` — Show usage insights and analytics",
-            "`/rollback [number]` — List or restore filesystem checkpoints",
             "`/reload-mcp` — Reload MCP servers from config",
             "`/update` — Update Hermes Agent to the latest version",
             "`/help` — Show this message",
@@ -1438,7 +1429,7 @@ class GatewayRunner:
         current_provider = "openrouter"
         try:
             if config_path.exists():
-                with open(config_path, encoding="utf-8") as f:
+                with open(config_path) as f:
                     cfg = yaml.safe_load(f) or {}
                 model_cfg = cfg.get("model", {})
                 if isinstance(model_cfg, str):
@@ -1458,11 +1449,6 @@ class GatewayRunner:
             except Exception:
                 current_provider = "openrouter"
 
-        # Detect custom endpoint: provider resolved to openrouter but a custom
-        # base URL is configured — the user set up a custom endpoint.
-        if current_provider == "openrouter" and os.getenv("OPENAI_BASE_URL", "").strip():
-            current_provider = "custom"
-
         if not args:
             provider_label = _PROVIDER_LABELS.get(current_provider, current_provider)
             lines = [
@@ -1529,14 +1515,14 @@ class GatewayRunner:
             try:
                 user_config = {}
                 if config_path.exists():
-                    with open(config_path, encoding="utf-8") as f:
+                    with open(config_path) as f:
                         user_config = yaml.safe_load(f) or {}
                 if "model" not in user_config or not isinstance(user_config["model"], dict):
                     user_config["model"] = {}
                 user_config["model"]["default"] = new_model
                 if provider_changed:
                     user_config["model"]["provider"] = target_provider
-                with open(config_path, 'w', encoding="utf-8") as f:
+                with open(config_path, 'w') as f:
                     yaml.dump(user_config, f, default_flow_style=False, sort_keys=False)
             except Exception as e:
                 return f"⚠️ Failed to save model change: {e}"
@@ -1573,7 +1559,7 @@ class GatewayRunner:
         config_path = _hermes_home / 'config.yaml'
         try:
             if config_path.exists():
-                with open(config_path, encoding="utf-8") as f:
+                with open(config_path) as f:
                     cfg = yaml.safe_load(f) or {}
                 model_cfg = cfg.get("model", {})
                 if isinstance(model_cfg, dict):
@@ -1589,10 +1575,6 @@ class GatewayRunner:
             except Exception:
                 current_provider = "openrouter"
 
-        # Detect custom endpoint
-        if current_provider == "openrouter" and os.getenv("OPENAI_BASE_URL", "").strip():
-            current_provider = "custom"
-
         current_label = _PROVIDER_LABELS.get(current_provider, current_provider)
 
         lines = [
@@ -1622,7 +1604,7 @@ class GatewayRunner:
 
         try:
             if config_path.exists():
-                with open(config_path, 'r', encoding="utf-8") as f:
+                with open(config_path, 'r') as f:
                     config = yaml.safe_load(f) or {}
                 personalities = config.get("agent", {}).get("personalities", {})
             else:
@@ -1651,7 +1633,7 @@ class GatewayRunner:
                 if "agent" not in config or not isinstance(config.get("agent"), dict):
                     config["agent"] = {}
                 config["agent"]["system_prompt"] = new_prompt
-                with open(config_path, 'w', encoding="utf-8") as f:
+                with open(config_path, 'w') as f:
                     yaml.dump(config, f, default_flow_style=False, sort_keys=False)
             except Exception as e:
                 return f"⚠️ Failed to save personality change: {e}"
@@ -1735,10 +1717,10 @@ class GatewayRunner:
             config_path = _hermes_home / 'config.yaml'
             user_config = {}
             if config_path.exists():
-                with open(config_path, encoding="utf-8") as f:
+                with open(config_path) as f:
                     user_config = yaml.safe_load(f) or {}
             user_config[env_key] = chat_id
-            with open(config_path, 'w', encoding="utf-8") as f:
+            with open(config_path, 'w') as f:
                 yaml.dump(user_config, f, default_flow_style=False)
             # Also set in the current environment so it takes effect immediately
             os.environ[env_key] = str(chat_id)
@@ -1750,65 +1732,6 @@ class GatewayRunner:
             f"Cron jobs and cross-platform messages will be delivered here."
         )
     
-    async def _handle_rollback_command(self, event: MessageEvent) -> str:
-        """Handle /rollback command — list or restore filesystem checkpoints."""
-        from tools.checkpoint_manager import CheckpointManager, format_checkpoint_list
-
-        # Read checkpoint config from config.yaml
-        cp_cfg = {}
-        try:
-            import yaml as _y
-            _cfg_path = _hermes_home / "config.yaml"
-            if _cfg_path.exists():
-                with open(_cfg_path, encoding="utf-8") as _f:
-                    _data = _y.safe_load(_f) or {}
-                cp_cfg = _data.get("checkpoints", {})
-                if isinstance(cp_cfg, bool):
-                    cp_cfg = {"enabled": cp_cfg}
-        except Exception:
-            pass
-
-        if not cp_cfg.get("enabled", False):
-            return (
-                "Checkpoints are not enabled.\n"
-                "Enable in config.yaml:\n```\ncheckpoints:\n  enabled: true\n```"
-            )
-
-        mgr = CheckpointManager(
-            enabled=True,
-            max_snapshots=cp_cfg.get("max_snapshots", 50),
-        )
-
-        cwd = os.getenv("MESSAGING_CWD", str(Path.home()))
-        arg = event.get_command_args().strip()
-
-        if not arg:
-            checkpoints = mgr.list_checkpoints(cwd)
-            return format_checkpoint_list(checkpoints, cwd)
-
-        # Restore by number or hash
-        checkpoints = mgr.list_checkpoints(cwd)
-        if not checkpoints:
-            return f"No checkpoints found for {cwd}"
-
-        target_hash = None
-        try:
-            idx = int(arg) - 1
-            if 0 <= idx < len(checkpoints):
-                target_hash = checkpoints[idx]["hash"]
-            else:
-                return f"Invalid checkpoint number. Use 1-{len(checkpoints)}."
-        except ValueError:
-            target_hash = arg
-
-        result = mgr.restore(cwd, target_hash)
-        if result["success"]:
-            return (
-                f"✅ Restored to checkpoint {result['restored_to']}: {result['reason']}\n"
-                f"A pre-rollback snapshot was saved automatically."
-            )
-        return f"❌ {result['error']}"
-
     async def _handle_compress_command(self, event: MessageEvent) -> str:
         """Handle /compress command -- manually compress conversation context."""
         source = event.source
@@ -2465,8 +2388,6 @@ class GatewayRunner:
             Platform.DISCORD: "hermes-discord",
             Platform.WHATSAPP: "hermes-whatsapp",
             Platform.SLACK: "hermes-slack",
-            Platform.SIGNAL: "hermes-signal",
-            Platform.HOMEASSISTANT: "hermes-homeassistant",
         }
         
         # Try to load platform_toolsets from config
@@ -2475,7 +2396,7 @@ class GatewayRunner:
             config_path = _hermes_home / 'config.yaml'
             if config_path.exists():
                 import yaml
-                with open(config_path, 'r', encoding="utf-8") as f:
+                with open(config_path, 'r') as f:
                     user_config = yaml.safe_load(f) or {}
                 platform_toolsets_config = user_config.get("platform_toolsets", {})
         except Exception as e:
@@ -2488,8 +2409,6 @@ class GatewayRunner:
             Platform.DISCORD: "discord",
             Platform.WHATSAPP: "whatsapp",
             Platform.SLACK: "slack",
-            Platform.SIGNAL: "signal",
-            Platform.HOMEASSISTANT: "homeassistant",
         }.get(source.platform, "telegram")
         
         # Use config override if present (list of toolsets), otherwise hardcoded default
@@ -2507,7 +2426,7 @@ class GatewayRunner:
             _tp_cfg_path = _hermes_home / "config.yaml"
             if _tp_cfg_path.exists():
                 import yaml as _tp_yaml
-                with open(_tp_cfg_path, encoding="utf-8") as _tp_f:
+                with open(_tp_cfg_path) as _tp_f:
                     _tp_data = _tp_yaml.safe_load(_tp_f) or {}
                 _progress_cfg = _tp_data.get("display", {})
         except Exception:
@@ -2725,7 +2644,7 @@ class GatewayRunner:
                 import yaml as _y
                 _cfg_path = _hermes_home / "config.yaml"
                 if _cfg_path.exists():
-                    with open(_cfg_path, encoding="utf-8") as _f:
+                    with open(_cfg_path) as _f:
                         _cfg = _y.safe_load(_f) or {}
                     _model_cfg = _cfg.get("model", {})
                     if isinstance(_model_cfg, str):
@@ -3207,7 +3126,7 @@ def main():
     config = None
     if args.config:
         import json
-        with open(args.config, encoding="utf-8") as f:
+        with open(args.config) as f:
             data = json.load(f)
             config = GatewayConfig.from_dict(data)
     

hermes_cli/auth.py

@@ -23,7 +23,6 @@ import stat
 import base64
 import hashlib
 import subprocess
-import threading
 import time
 import uuid
 import webbrowser
@@ -45,10 +44,6 @@ try:
     import fcntl
 except Exception:
     fcntl = None
-try:
-    import msvcrt
-except Exception:
-    msvcrt = None
 
 # =============================================================================
 # Constants
@@ -304,64 +299,31 @@ def _auth_lock_path() -> Path:
     return _auth_file_path().with_suffix(".lock")
 
 
-_auth_lock_holder = threading.local()
-
 @contextmanager
 def _auth_store_lock(timeout_seconds: float = AUTH_LOCK_TIMEOUT_SECONDS):
-    """Cross-process advisory lock for auth.json reads+writes.  Reentrant."""
-    # Reentrant: if this thread already holds the lock, just yield.
-    if getattr(_auth_lock_holder, "depth", 0) > 0:
-        _auth_lock_holder.depth += 1
-        try:
-            yield
-        finally:
-            _auth_lock_holder.depth -= 1
-        return
-
+    """Cross-process advisory lock for auth.json reads+writes."""
     lock_path = _auth_lock_path()
     lock_path.parent.mkdir(parents=True, exist_ok=True)
 
-    if fcntl is None and msvcrt is None:
-        _auth_lock_holder.depth = 1
-        try:
+    with lock_path.open("a+") as lock_file:
+        if fcntl is None:
             yield
-        finally:
-            _auth_lock_holder.depth = 0
-        return
+            return
 
-    # On Windows, msvcrt.locking needs the file to have content and the
-    # file pointer at position 0.  Ensure the lock file has at least 1 byte.
-    if msvcrt and (not lock_path.exists() or lock_path.stat().st_size == 0):
-        lock_path.write_text(" ", encoding="utf-8")
-
-    with lock_path.open("r+" if msvcrt else "a+") as lock_file:
         deadline = time.time() + max(1.0, timeout_seconds)
         while True:
             try:
-                if fcntl:
-                    fcntl.flock(lock_file.fileno(), fcntl.LOCK_EX | fcntl.LOCK_NB)
-                else:
-                    lock_file.seek(0)
-                    msvcrt.locking(lock_file.fileno(), msvcrt.LK_NBLCK, 1)
+                fcntl.flock(lock_file.fileno(), fcntl.LOCK_EX | fcntl.LOCK_NB)
                 break
-            except (BlockingIOError, OSError, PermissionError):
+            except BlockingIOError:
                 if time.time() >= deadline:
                     raise TimeoutError("Timed out waiting for auth store lock")
                 time.sleep(0.05)
 
-        _auth_lock_holder.depth = 1
         try:
             yield
         finally:
-            _auth_lock_holder.depth = 0
-            if fcntl:
-                fcntl.flock(lock_file.fileno(), fcntl.LOCK_UN)
-            elif msvcrt:
-                try:
-                    lock_file.seek(0)
-                    msvcrt.locking(lock_file.fileno(), msvcrt.LK_UNLCK, 1)
-                except (OSError, IOError):
-                    pass
+            fcntl.flock(lock_file.fileno(), fcntl.LOCK_UN)
 
 
 def _load_auth_store(auth_file: Optional[Path] = None) -> Dict[str, Any]:

hermes_cli/banner.py

@@ -36,28 +36,6 @@ def cprint(text: str):
     _pt_print(_PT_ANSI(text))
 
 
-# =========================================================================
-# Skin-aware color helpers
-# =========================================================================
-
-def _skin_color(key: str, fallback: str) -> str:
-    """Get a color from the active skin, or return fallback."""
-    try:
-        from hermes_cli.skin_engine import get_active_skin
-        return get_active_skin().get_color(key, fallback)
-    except Exception:
-        return fallback
-
-
-def _skin_branding(key: str, fallback: str) -> str:
-    """Get a branding string from the active skin, or return fallback."""
-    try:
-        from hermes_cli.skin_engine import get_active_skin
-        return get_active_skin().get_branding(key, fallback)
-    except Exception:
-        return fallback
-
-
 # =========================================================================
 # ASCII Art & Branding
 # =========================================================================
@@ -239,24 +217,18 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
     layout_table.add_column("left", justify="center")
     layout_table.add_column("right", justify="left")
 
-    # Resolve skin colors once for the entire banner
-    accent = _skin_color("banner_accent", "#FFBF00")
-    dim = _skin_color("banner_dim", "#B8860B")
-    text = _skin_color("banner_text", "#FFF8DC")
-    session_color = _skin_color("session_border", "#8B8682")
-
     left_lines = ["", HERMES_CADUCEUS, ""]
     model_short = model.split("/")[-1] if "/" in model else model
     if len(model_short) > 28:
         model_short = model_short[:25] + "..."
-    ctx_str = f" [dim {dim}]·[/] [dim {dim}]{_format_context_length(context_length)} context[/]" if context_length else ""
-    left_lines.append(f"[{accent}]{model_short}[/]{ctx_str} [dim {dim}]·[/] [dim {dim}]Nous Research[/]")
-    left_lines.append(f"[dim {dim}]{cwd}[/]")
+    ctx_str = f" [dim #B8860B]·[/] [dim #B8860B]{_format_context_length(context_length)} context[/]" if context_length else ""
+    left_lines.append(f"[#FFBF00]{model_short}[/]{ctx_str} [dim #B8860B]·[/] [dim #B8860B]Nous Research[/]")
+    left_lines.append(f"[dim #B8860B]{cwd}[/]")
     if session_id:
-        left_lines.append(f"[dim {session_color}]Session: {session_id}[/]")
+        left_lines.append(f"[dim #8B8682]Session: {session_id}[/]")
     left_content = "\n".join(left_lines)
 
-    right_lines = [f"[bold {accent}]Available Tools[/]"]
+    right_lines = ["[bold #FFBF00]Available Tools[/]"]
     toolsets_dict: Dict[str, list] = {}
 
     for tool in tools:
@@ -284,7 +256,7 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
             if name in disabled_tools:
                 colored_names.append(f"[red]{name}[/]")
             else:
-                colored_names.append(f"[{text}]{name}[/]")
+                colored_names.append(f"[#FFF8DC]{name}[/]")
 
         tools_str = ", ".join(colored_names)
         if len(", ".join(sorted(tool_names))) > 45:
@@ -303,7 +275,7 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
                 elif name in disabled_tools:
                     colored_names.append(f"[red]{name}[/]")
                 else:
-                    colored_names.append(f"[{text}]{name}[/]")
+                    colored_names.append(f"[#FFF8DC]{name}[/]")
             tools_str = ", ".join(colored_names)
 
         right_lines.append(f"[dim #B8860B]{toolset}:[/] {tools_str}")
@@ -334,7 +306,7 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
                 )
 
     right_lines.append("")
-    right_lines.append(f"[bold {accent}]Available Skills[/]")
+    right_lines.append("[bold #FFBF00]Available Skills[/]")
     skills_by_category = get_available_skills()
     total_skills = sum(len(s) for s in skills_by_category.values())
 
@@ -348,9 +320,9 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
                 skills_str = ", ".join(skill_names)
             if len(skills_str) > 50:
                 skills_str = skills_str[:47] + "..."
-            right_lines.append(f"[dim {dim}]{category}:[/] [{text}]{skills_str}[/]")
+            right_lines.append(f"[dim #B8860B]{category}:[/] [#FFF8DC]{skills_str}[/]")
     else:
-        right_lines.append(f"[dim {dim}]No skills installed[/]")
+        right_lines.append("[dim #B8860B]No skills installed[/]")
 
     right_lines.append("")
     mcp_connected = sum(1 for s in mcp_status if s["connected"]) if mcp_status else 0
@@ -358,7 +330,7 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
     if mcp_connected:
         summary_parts.append(f"{mcp_connected} MCP servers")
     summary_parts.append("/help for commands")
-    right_lines.append(f"[dim {dim}]{' · '.join(summary_parts)}[/]")
+    right_lines.append(f"[dim #B8860B]{' · '.join(summary_parts)}[/]")
 
     # Update check — show if behind origin/main
     try:
@@ -375,13 +347,10 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
     right_content = "\n".join(right_lines)
     layout_table.add_row(left_content, right_content)
 
-    agent_name = _skin_branding("agent_name", "Hermes Agent")
-    title_color = _skin_color("banner_title", "#FFD700")
-    border_color = _skin_color("banner_border", "#CD7F32")
     outer_panel = Panel(
         layout_table,
-        title=f"[bold {title_color}]{agent_name} {VERSION}[/]",
-        border_style=border_color,
+        title=f"[bold #FFD700]Hermes Agent {VERSION}[/]",
+        border_style="#CD7F32",
         padding=(0, 2),
     )
 

hermes_cli/codex_models.py

@@ -47,7 +47,7 @@ def _fetch_models_from_api(access_token: str) -> List[str]:
         if item.get("supported_in_api") is False:
             continue
         visibility = item.get("visibility", "")
-        if isinstance(visibility, str) and visibility.strip().lower() == "hidden":
+        if isinstance(visibility, str) and visibility.strip().lower() == "hide":
             continue
         priority = item.get("priority")
         rank = int(priority) if isinstance(priority, (int, float)) else 10_000

hermes_cli/commands.py

@@ -39,8 +39,6 @@ COMMANDS = {
     "/insights": "Show usage insights and analytics (last 30 days)",
     "/paste": "Check clipboard for an image and attach it",
     "/reload-mcp": "Reload MCP servers from config.yaml",
-    "/rollback": "List or restore filesystem checkpoints (usage: /rollback [number])",
-    "/skin": "Show or change the display skin/theme",
     "/quit": "Exit the CLI (also: /exit, /q)",
 }
 

hermes_cli/config.py

@@ -14,9 +14,8 @@ This module provides:
 
 import os
 import platform
-import stat
-import subprocess
 import sys
+import subprocess
 from pathlib import Path
 from typing import Dict, Any, Optional, List, Tuple
 
@@ -78,10 +77,6 @@ DEFAULT_CONFIG = {
         "container_memory": 5120,       # MB (default 5GB)
         "container_disk": 51200,        # MB (default 50GB)
         "container_persistent": True,   # Persist filesystem across sessions
-        # Docker volume mounts — share host directories with the container.
-        # Each entry is "host_path:container_path" (standard Docker -v syntax).
-        # Example: ["/home/user/projects:/workspace/projects", "/data:/data"]
-        "docker_volumes": [],
     },
     
     "browser": {
@@ -89,14 +84,6 @@ DEFAULT_CONFIG = {
         "record_sessions": False,  # Auto-record browser sessions as WebM videos
     },
     
-    # Filesystem checkpoints — automatic snapshots before destructive file ops.
-    # When enabled, the agent takes a snapshot of the working directory once per
-    # conversation turn (on first write_file/patch call).  Use /rollback to restore.
-    "checkpoints": {
-        "enabled": False,
-        "max_snapshots": 50,  # Max checkpoints to keep per directory
-    },
-    
     "compression": {
         "enabled": True,
         "threshold": 0.85,
@@ -120,9 +107,8 @@ DEFAULT_CONFIG = {
     "display": {
         "compact": False,
         "personality": "kawaii",
-        "resume_display": "full",
-        "bell_on_complete": False,
-        "skin": "default",
+        "resume_display": "full",  # "full" (show previous messages) | "minimal" (one-liner only)
+        "bell_on_complete": False,  # Play terminal bell (\a) when agent finishes a response
     },
     
     # Text-to-speech configuration
@@ -180,7 +166,7 @@ DEFAULT_CONFIG = {
     "command_allowlist": [],
 
     # Config schema version - bump this when adding new required fields
-    "_config_version": 6,
+    "_config_version": 5,
 }
 
 # =============================================================================
@@ -415,18 +401,14 @@ OPTIONAL_ENV_VARS = {
         "category": "messaging",
     },
     "SLACK_BOT_TOKEN": {
-        "description": "Slack bot token (xoxb-). Get from OAuth & Permissions after installing your app. "
-                       "Required scopes: chat:write, app_mentions:read, channels:history, groups:history, "
-                       "im:history, im:read, im:write, users:read, files:write",
+        "description": "Slack bot integration",
         "prompt": "Slack Bot Token (xoxb-...)",
         "url": "https://api.slack.com/apps",
         "password": True,
         "category": "messaging",
     },
     "SLACK_APP_TOKEN": {
-        "description": "Slack app-level token (xapp-) for Socket Mode. Get from Basic Information → "
-                       "App-Level Tokens. Also ensure Event Subscriptions include: message.im, "
-                       "message.channels, message.groups, app_mention",
+        "description": "Slack Socket Mode connection",
         "prompt": "Slack App Token (xapp-...)",
         "url": "https://api.slack.com/apps",
         "password": True,
@@ -767,9 +749,9 @@ def load_config() -> Dict[str, Any]:
     
     if config_path.exists():
         try:
-            with open(config_path, encoding="utf-8") as f:
+            with open(config_path) as f:
                 user_config = yaml.safe_load(f) or {}
-
+            
             config = _deep_merge(config, user_config)
         except Exception as e:
             print(f"Warning: Failed to load config: {e}")
@@ -812,7 +794,7 @@ def save_config(config: Dict[str, Any]):
     ensure_hermes_home()
     config_path = get_config_path()
     
-    with open(config_path, 'w', encoding="utf-8") as f:
+    with open(config_path, 'w') as f:
         yaml.dump(config, f, default_flow_style=False, sort_keys=False)
         # Append commented-out sections for features that are off by default
         # or only relevant when explicitly configured. Skip sections the
@@ -879,13 +861,6 @@ def save_env_value(key: str, value: str):
     with open(env_path, 'w', **write_kw) as f:
         f.writelines(lines)
 
-    # Restrict .env permissions to owner-only (contains API keys)
-    if not _IS_WINDOWS:
-        try:
-            os.chmod(env_path, stat.S_IRUSR | stat.S_IWUSR)
-        except OSError:
-            pass
-
 
 def get_env_value(key: str) -> Optional[str]:
     """Get a value from ~/.hermes/.env or environment."""
@@ -1094,7 +1069,7 @@ def set_config_value(key: str, value: str):
     user_config = {}
     if config_path.exists():
         try:
-            with open(config_path, encoding="utf-8") as f:
+            with open(config_path) as f:
                 user_config = yaml.safe_load(f) or {}
         except Exception:
             user_config = {}
@@ -1122,7 +1097,7 @@ def set_config_value(key: str, value: str):
     
     # Write only user config back (not the full merged defaults)
     ensure_hermes_home()
-    with open(config_path, 'w', encoding="utf-8") as f:
+    with open(config_path, 'w') as f:
         yaml.dump(user_config, f, default_flow_style=False, sort_keys=False)
     
     # Keep .env in sync for keys that terminal_tool reads directly from env vars.

hermes_cli/gateway.py

@@ -482,19 +482,14 @@ _PLATFORMS = [
         "token_var": "SLACK_BOT_TOKEN",
         "setup_instructions": [
             "1. Go to https://api.slack.com/apps → Create New App → From Scratch",
-            "2. Enable Socket Mode: Settings → Socket Mode → Enable",
-            "   Create an App-Level Token with scope: connections:write → copy xapp-... token",
-            "3. Add Bot Token Scopes: Features → OAuth & Permissions → Scopes",
-            "   Required: chat:write, app_mentions:read, channels:history, channels:read,",
-            "   groups:history, im:history, im:read, im:write, users:read, files:write",
-            "4. Subscribe to Events: Features → Event Subscriptions → Enable",
-            "   Required events: message.im, message.channels, app_mention",
-            "   Optional: message.groups (for private channels)",
-            "   ⚠ Without message.channels the bot will ONLY work in DMs!",
-            "5. Install to Workspace: Settings → Install App → copy xoxb-... token",
-            "6. Reinstall the app after any scope or event changes",
+            "2. Enable Socket Mode: App Settings → Socket Mode → Enable",
+            "3. Get Bot Token: OAuth & Permissions → Install to Workspace → copy xoxb-... token",
+            "4. Get App Token: Basic Information → App-Level Tokens → Generate",
+            "   Name it anything, add scope: connections:write → copy xapp-... token",
+            "5. Add bot scopes: OAuth & Permissions → Scopes → chat:write, im:history,",
+            "   im:read, im:write, channels:history, channels:read",
+            "6. Reinstall the app to your workspace after adding scopes",
             "7. Find your user ID: click your profile → three dots → Copy member ID",
-            "8. Invite the bot to channels: /invite @YourBot",
         ],
         "vars": [
             {"name": "SLACK_BOT_TOKEN", "prompt": "Bot Token (xoxb-...)", "password": True,

hermes_cli/main.py

@@ -489,7 +489,6 @@ def cmd_chat(args):
         "query": args.query,
         "resume": getattr(args, "resume", None),
         "worktree": getattr(args, "worktree", False),
-        "checkpoints": getattr(args, "checkpoints", False),
     }
     # Filter out None values
     kwargs = {k: v for k, v in kwargs.items() if v is not None}
@@ -762,39 +761,9 @@ def cmd_model(args):
         ("kimi-coding", "Kimi / Moonshot (Moonshot AI direct API)"),
         ("minimax", "MiniMax (global direct API)"),
         ("minimax-cn", "MiniMax China (domestic direct API)"),
+        ("custom", "Custom endpoint (self-hosted / VLLM / etc.)"),
     ]
 
-    # Add user-defined custom providers from config.yaml
-    custom_providers_cfg = config.get("custom_providers") or []
-    _custom_provider_map = {}  # key → {name, base_url, api_key}
-    if isinstance(custom_providers_cfg, list):
-        for entry in custom_providers_cfg:
-            if not isinstance(entry, dict):
-                continue
-            name = entry.get("name", "").strip()
-            base_url = entry.get("base_url", "").strip()
-            if not name or not base_url:
-                continue
-            # Generate a stable key from the name
-            key = "custom:" + name.lower().replace(" ", "-")
-            short_url = base_url.replace("https://", "").replace("http://", "").rstrip("/")
-            saved_model = entry.get("model", "")
-            model_hint = f" — {saved_model}" if saved_model else ""
-            providers.append((key, f"{name} ({short_url}){model_hint}"))
-            _custom_provider_map[key] = {
-                "name": name,
-                "base_url": base_url,
-                "api_key": entry.get("api_key", ""),
-                "model": saved_model,
-            }
-
-    # Always add the manual custom endpoint option last
-    providers.append(("custom", "Custom endpoint (enter URL manually)"))
-
-    # Add removal option if there are saved custom providers
-    if _custom_provider_map:
-        providers.append(("remove-custom", "Remove a saved custom provider"))
-
     # Reorder so the active provider is at the top
     known_keys = {k for k, _ in providers}
     active_key = active if active in known_keys else "custom"
@@ -822,10 +791,6 @@ def cmd_model(args):
         _model_flow_openai_codex(config, current_model)
     elif selected_provider == "custom":
         _model_flow_custom(config)
-    elif selected_provider.startswith("custom:") and selected_provider in _custom_provider_map:
-        _model_flow_named_custom(config, _custom_provider_map[selected_provider])
-    elif selected_provider == "remove-custom":
-        _remove_custom_provider(config)
     elif selected_provider in ("zai", "kimi-coding", "minimax", "minimax-cn"):
         _model_flow_api_key_provider(config, selected_provider, current_model)
 
@@ -1041,11 +1006,7 @@ def _model_flow_openai_codex(config, current_model=""):
 
 
 def _model_flow_custom(config):
-    """Custom endpoint: collect URL, API key, and model name.
-
-    Automatically saves the endpoint to ``custom_providers`` in config.yaml
-    so it appears in the provider menu on subsequent runs.
-    """
+    """Custom endpoint: collect URL, API key, and model name."""
     from hermes_cli.auth import _save_model_choice, deactivate_provider
     from hermes_cli.config import get_env_value, save_env_value, load_config, save_config
 
@@ -1077,8 +1038,6 @@ def _model_flow_custom(config):
         print(f"Invalid URL: {effective_url} (must start with http:// or https://)")
         return
 
-    effective_key = api_key or current_key
-
     if base_url:
         save_env_value("OPENAI_BASE_URL", base_url)
     if api_key:
@@ -1091,7 +1050,7 @@ def _model_flow_custom(config):
         cfg = load_config()
         model = cfg.get("model")
         if isinstance(model, dict):
-            model["provider"] = "custom"
+            model["provider"] = "auto"
             model["base_url"] = effective_url
         save_config(cfg)
         deactivate_provider()
@@ -1102,223 +1061,6 @@ def _model_flow_custom(config):
             deactivate_provider()
         print("Endpoint saved. Use `/model` in chat or `hermes model` to set a model.")
 
-    # Auto-save to custom_providers so it appears in the menu next time
-    _save_custom_provider(effective_url, effective_key, model_name or "")
-
-
-def _save_custom_provider(base_url, api_key="", model=""):
-    """Save a custom endpoint to custom_providers in config.yaml.
-
-    Deduplicates by base_url — if the URL already exists, updates the
-    model name but doesn't add a duplicate entry.
-    Auto-generates a display name from the URL hostname.
-    """
-    from hermes_cli.config import load_config, save_config
-
-    cfg = load_config()
-    providers = cfg.get("custom_providers") or []
-    if not isinstance(providers, list):
-        providers = []
-
-    # Check if this URL is already saved — update model if so
-    for entry in providers:
-        if isinstance(entry, dict) and entry.get("base_url", "").rstrip("/") == base_url.rstrip("/"):
-            if model and entry.get("model") != model:
-                entry["model"] = model
-                cfg["custom_providers"] = providers
-                save_config(cfg)
-            return  # already saved, updated model if needed
-
-    # Auto-generate a name from the URL
-    import re
-    clean = base_url.replace("https://", "").replace("http://", "").rstrip("/")
-    # Remove /v1 suffix for cleaner names
-    clean = re.sub(r"/v1/?$", "", clean)
-    # Use hostname:port as the name
-    name = clean.split("/")[0]
-    # Capitalize for readability
-    if "localhost" in name or "127.0.0.1" in name:
-        name = f"Local ({name})"
-    elif "runpod" in name.lower():
-        name = f"RunPod ({name})"
-    else:
-        name = name.capitalize()
-
-    entry = {"name": name, "base_url": base_url}
-    if api_key:
-        entry["api_key"] = api_key
-    if model:
-        entry["model"] = model
-
-    providers.append(entry)
-    cfg["custom_providers"] = providers
-    save_config(cfg)
-    print(f"  💾 Saved to custom providers as \"{name}\" (edit in config.yaml)")
-
-
-def _remove_custom_provider(config):
-    """Let the user remove a saved custom provider from config.yaml."""
-    from hermes_cli.config import load_config, save_config
-
-    cfg = load_config()
-    providers = cfg.get("custom_providers") or []
-    if not isinstance(providers, list) or not providers:
-        print("No custom providers configured.")
-        return
-
-    print("Remove a custom provider:\n")
-
-    choices = []
-    for entry in providers:
-        if isinstance(entry, dict):
-            name = entry.get("name", "unnamed")
-            url = entry.get("base_url", "")
-            short_url = url.replace("https://", "").replace("http://", "").rstrip("/")
-            choices.append(f"{name} ({short_url})")
-        else:
-            choices.append(str(entry))
-    choices.append("Cancel")
-
-    try:
-        from simple_term_menu import TerminalMenu
-        menu = TerminalMenu(
-            [f"  {c}" for c in choices], cursor_index=0,
-            menu_cursor="-> ", menu_cursor_style=("fg_red", "bold"),
-            menu_highlight_style=("fg_red",),
-            cycle_cursor=True, clear_screen=False,
-            title="Select provider to remove:",
-        )
-        idx = menu.show()
-        print()
-    except (ImportError, NotImplementedError):
-        for i, c in enumerate(choices, 1):
-            print(f"  {i}. {c}")
-        print()
-        try:
-            val = input(f"Choice [1-{len(choices)}]: ").strip()
-            idx = int(val) - 1 if val else None
-        except (ValueError, KeyboardInterrupt, EOFError):
-            idx = None
-
-    if idx is None or idx >= len(providers):
-        print("No change.")
-        return
-
-    removed = providers.pop(idx)
-    cfg["custom_providers"] = providers
-    save_config(cfg)
-    removed_name = removed.get("name", "unnamed") if isinstance(removed, dict) else str(removed)
-    print(f"✅ Removed \"{removed_name}\" from custom providers.")
-
-
-def _model_flow_named_custom(config, provider_info):
-    """Handle a named custom provider from config.yaml custom_providers list.
-
-    If the entry has a saved model name, activates it immediately.
-    Otherwise probes the endpoint's /models API to let the user pick one.
-    """
-    from hermes_cli.auth import _save_model_choice, deactivate_provider
-    from hermes_cli.config import save_env_value, load_config, save_config
-    from hermes_cli.models import fetch_api_models
-
-    name = provider_info["name"]
-    base_url = provider_info["base_url"]
-    api_key = provider_info.get("api_key", "")
-    saved_model = provider_info.get("model", "")
-
-    # If a model is saved, just activate immediately — no probing needed
-    if saved_model:
-        save_env_value("OPENAI_BASE_URL", base_url)
-        if api_key:
-            save_env_value("OPENAI_API_KEY", api_key)
-        _save_model_choice(saved_model)
-
-        cfg = load_config()
-        model = cfg.get("model")
-        if isinstance(model, dict):
-            model["provider"] = "custom"
-            model["base_url"] = base_url
-        save_config(cfg)
-        deactivate_provider()
-
-        print(f"✅ Switched to: {saved_model}")
-        print(f"   Provider: {name} ({base_url})")
-        return
-
-    # No saved model — probe endpoint and let user pick
-    print(f"  Provider: {name}")
-    print(f"  URL:      {base_url}")
-    print()
-    print("No model saved for this provider. Fetching available models...")
-    models = fetch_api_models(api_key, base_url, timeout=8.0)
-
-    if models:
-        print(f"Found {len(models)} model(s):\n")
-        try:
-            from simple_term_menu import TerminalMenu
-            menu_items = [f"  {m}" for m in models] + ["  Cancel"]
-            menu = TerminalMenu(
-                menu_items, cursor_index=0,
-                menu_cursor="-> ", menu_cursor_style=("fg_green", "bold"),
-                menu_highlight_style=("fg_green",),
-                cycle_cursor=True, clear_screen=False,
-                title=f"Select model from {name}:",
-            )
-            idx = menu.show()
-            print()
-            if idx is None or idx >= len(models):
-                print("Cancelled.")
-                return
-            model_name = models[idx]
-        except (ImportError, NotImplementedError):
-            for i, m in enumerate(models, 1):
-                print(f"  {i}. {m}")
-            print(f"  {len(models) + 1}. Cancel")
-            print()
-            try:
-                val = input(f"Choice [1-{len(models) + 1}]: ").strip()
-                if not val:
-                    print("Cancelled.")
-                    return
-                idx = int(val) - 1
-                if idx < 0 or idx >= len(models):
-                    print("Cancelled.")
-                    return
-                model_name = models[idx]
-            except (ValueError, KeyboardInterrupt, EOFError):
-                print("\nCancelled.")
-                return
-    else:
-        print("Could not fetch models from endpoint. Enter model name manually.")
-        try:
-            model_name = input("Model name: ").strip()
-        except (KeyboardInterrupt, EOFError):
-            print("\nCancelled.")
-            return
-        if not model_name:
-            print("No model specified. Cancelled.")
-            return
-
-    # Activate and save the model to the custom_providers entry
-    save_env_value("OPENAI_BASE_URL", base_url)
-    if api_key:
-        save_env_value("OPENAI_API_KEY", api_key)
-    _save_model_choice(model_name)
-
-    cfg = load_config()
-    model = cfg.get("model")
-    if isinstance(model, dict):
-        model["provider"] = "custom"
-        model["base_url"] = base_url
-    save_config(cfg)
-    deactivate_provider()
-
-    # Save model name to the custom_providers entry for next time
-    _save_custom_provider(base_url, api_key, model_name)
-
-    print(f"\n✅ Model set to: {model_name}")
-    print(f"   Provider: {name} ({base_url})")
-
 
 # Curated model lists for direct API-key providers
 _PROVIDER_MODELS = {
@@ -1778,44 +1520,6 @@ def cmd_update(args):
             sys.exit(1)
 
 
-def _coalesce_session_name_args(argv: list) -> list:
-    """Join unquoted multi-word session names after -c/--continue and -r/--resume.
-
-    When a user types ``hermes -c Pokemon Agent Dev`` without quoting the
-    session name, argparse sees three separate tokens.  This function merges
-    them into a single argument so argparse receives
-    ``['-c', 'Pokemon Agent Dev']`` instead.
-
-    Tokens are collected after the flag until we hit another flag (``-*``)
-    or a known top-level subcommand.
-    """
-    _SUBCOMMANDS = {
-        "chat", "model", "gateway", "setup", "whatsapp", "login", "logout",
-        "status", "cron", "doctor", "config", "pairing", "skills", "tools",
-        "sessions", "insights", "version", "update", "uninstall",
-    }
-    _SESSION_FLAGS = {"-c", "--continue", "-r", "--resume"}
-
-    result = []
-    i = 0
-    while i < len(argv):
-        token = argv[i]
-        if token in _SESSION_FLAGS:
-            result.append(token)
-            i += 1
-            # Collect subsequent non-flag, non-subcommand tokens as one name
-            parts: list = []
-            while i < len(argv) and not argv[i].startswith("-") and argv[i] not in _SUBCOMMANDS:
-                parts.append(argv[i])
-                i += 1
-            if parts:
-                result.append(" ".join(parts))
-        else:
-            result.append(token)
-            i += 1
-    return result
-
-
 def main():
     """Main entry point for hermes CLI."""
     parser = argparse.ArgumentParser(
@@ -1928,12 +1632,6 @@ For more help on a command:
         default=False,
         help="Run in an isolated git worktree (for parallel agents on the same repo)"
     )
-    chat_parser.add_argument(
-        "--checkpoints",
-        action="store_true",
-        default=False,
-        help="Enable filesystem checkpoints before destructive file operations (use /rollback to restore)"
-    )
     chat_parser.set_defaults(func=cmd_chat)
 
     # =========================================================================
@@ -2401,12 +2099,12 @@ For more help on a command:
                 if not data:
                     print(f"Session '{args.session_id}' not found.")
                     return
-                with open(args.output, "w", encoding="utf-8") as f:
+                with open(args.output, "w") as f:
                     f.write(_json.dumps(data, ensure_ascii=False) + "\n")
                 print(f"Exported 1 session to {args.output}")
             else:
                 sessions = db.export_all(source=args.source)
-                with open(args.output, "w", encoding="utf-8") as f:
+                with open(args.output, "w") as f:
                     for s in sessions:
                         f.write(_json.dumps(s, ensure_ascii=False) + "\n")
                 print(f"Exported {len(sessions)} sessions to {args.output}")
@@ -2560,11 +2258,7 @@ For more help on a command:
     # =========================================================================
     # Parse and execute
     # =========================================================================
-    # Pre-process argv so unquoted multi-word session names after -c / -r
-    # are merged into a single token before argparse sees them.
-    # e.g. ``hermes -c Pokemon Agent Dev`` → ``hermes -c 'Pokemon Agent Dev'``
-    _processed_argv = _coalesce_session_name_args(sys.argv[1:])
-    args = parser.parse_args(_processed_argv)
+    args = parser.parse_args()
     
     # Handle --version flag
     if args.version:

hermes_cli/models.py

@@ -63,7 +63,7 @@ _PROVIDER_LABELS = {
     "kimi-coding": "Kimi / Moonshot",
     "minimax": "MiniMax",
     "minimax-cn": "MiniMax (China)",
-    "custom": "Custom endpoint",
+    "custom": "custom endpoint",
 }
 
 _PROVIDER_ALIASES = {

hermes_cli/setup.py

@@ -632,29 +632,6 @@ def setup_model_provider(config: dict):
             save_env_value("OPENAI_BASE_URL", "")
             save_env_value("OPENAI_API_KEY", "")
 
-        # Update config.yaml and deactivate any OAuth provider so the
-        # resolver doesn't keep returning the old provider (e.g. Codex).
-        try:
-            from hermes_cli.auth import deactivate_provider
-            deactivate_provider()
-        except Exception:
-            pass
-        import yaml
-        config_path = Path(os.environ.get("HERMES_HOME", Path.home() / ".hermes")) / "config.yaml"
-        try:
-            disk_cfg = {}
-            if config_path.exists():
-                disk_cfg = yaml.safe_load(config_path.read_text()) or {}
-            model_section = disk_cfg.get("model", {})
-            if isinstance(model_section, str):
-                model_section = {"default": model_section}
-            model_section["provider"] = "openrouter"
-            model_section.pop("base_url", None)  # OpenRouter uses default URL
-            disk_cfg["model"] = model_section
-            config_path.write_text(yaml.safe_dump(disk_cfg, sort_keys=False))
-        except Exception as e:
-            logger.debug("Could not save provider to config.yaml: %s", e)
-
     elif provider_idx == 3:  # Custom endpoint
         selected_provider = "custom"
         print()
@@ -682,28 +659,6 @@ def setup_model_provider(config: dict):
         if model_name:
             config['model'] = model_name
             save_env_value("LLM_MODEL", model_name)
-
-        # Save provider and base_url to config.yaml so the gateway and CLI
-        # both resolve the correct provider without relying on env-var heuristics.
-        if base_url:
-            import yaml
-            config_path = Path(os.environ.get("HERMES_HOME", Path.home() / ".hermes")) / "config.yaml"
-            try:
-                disk_cfg = {}
-                if config_path.exists():
-                    disk_cfg = yaml.safe_load(config_path.read_text()) or {}
-                model_section = disk_cfg.get("model", {})
-                if isinstance(model_section, str):
-                    model_section = {"default": model_section}
-                model_section["provider"] = "custom"
-                model_section["base_url"] = base_url.rstrip("/")
-                if model_name:
-                    model_section["default"] = model_name
-                disk_cfg["model"] = model_section
-                config_path.write_text(yaml.safe_dump(disk_cfg, sort_keys=False))
-            except Exception as e:
-                logger.debug("Could not save provider to config.yaml: %s", e)
-
         print_success("Custom endpoint configured")
 
     elif provider_idx == 4:  # Z.AI / GLM
@@ -1572,22 +1527,10 @@ def setup_gateway(config: dict):
     
     if not existing_slack and prompt_yes_no("Set up Slack bot?", False):
         print_info("Steps to create a Slack app:")
-        print_info("   1. Go to https://api.slack.com/apps → Create New App (from scratch)")
-        print_info("   2. Enable Socket Mode: Settings → Socket Mode → Enable")
-        print_info("      • Create an App-Level Token with 'connections:write' scope")
-        print_info("   3. Add Bot Token Scopes: Features → OAuth & Permissions")
-        print_info("      Required scopes: chat:write, app_mentions:read,")
-        print_info("      channels:history, channels:read, groups:history,")
-        print_info("      im:history, im:read, im:write, users:read, files:write")
-        print_info("   4. Subscribe to Events: Features → Event Subscriptions → Enable")
-        print_info("      Required events: message.im, message.channels,")
-        print_info("      message.groups, app_mention")
-        print_warning("   ⚠ Without message.channels/message.groups events,")
-        print_warning("     the bot will ONLY work in DMs, not channels!")
-        print_info("   5. Install to Workspace: Settings → Install App")
-        print_info("   6. After installing, invite the bot to channels: /invite @YourBot")
-        print()
-        print_info("   Full guide: https://hermes-agent.ai/docs/user-guide/messaging/slack")
+        print_info("   1. Go to https://api.slack.com/apps → Create New App")
+        print_info("   2. Enable Socket Mode: App Settings → Socket Mode → Enable")
+        print_info("   3. Bot Token: OAuth & Permissions → Install to Workspace")
+        print_info("   4. App Token: Basic Information → App-Level Tokens → Generate")
         print()
         bot_token = prompt("Slack Bot Token (xoxb-...)", password=True)
         if bot_token:
@@ -1599,7 +1542,7 @@ def setup_gateway(config: dict):
             
             print()
             print_info("🔒 Security: Restrict who can use your bot")
-            print_info("   To find a Member ID: click a user's name → View full profile → ⋮ → Copy member ID")
+            print_info("   Find Slack user IDs in your profile or via the Slack API")
             print()
             allowed_users = prompt("Allowed user IDs (comma-separated, leave empty for open access)")
             if allowed_users:

hermes_cli/skin_engine.py

@@ -1,341 +0,0 @@
-"""Hermes CLI skin/theme engine.
-
-A data-driven skin system that lets users customize the CLI's visual appearance.
-Skins are defined as YAML files in ~/.hermes/skins/ or as built-in presets.
-
-Each skin defines:
-- colors: banner and UI color palette (hex values for Rich markup)
-- spinner: kawaii faces, thinking verbs, optional wings
-- branding: agent name, welcome/goodbye messages, prompt symbol
-- tool_prefix: character used for tool output lines (default: ┊)
-
-Usage:
-    from hermes_cli.skin_engine import get_active_skin, list_skins, set_active_skin
-
-    skin = get_active_skin()
-    print(skin.colors["banner_title"])  # "#FFD700"
-    print(skin.spinner["thinking_verbs"])  # ["pondering", ...]
-"""
-
-import logging
-import os
-from dataclasses import dataclass, field
-from pathlib import Path
-from typing import Any, Dict, List, Optional, Tuple
-
-logger = logging.getLogger(__name__)
-
-
-# =============================================================================
-# Skin data structure
-# =============================================================================
-
-@dataclass
-class SkinConfig:
-    """Complete skin configuration."""
-    name: str
-    description: str = ""
-    colors: Dict[str, str] = field(default_factory=dict)
-    spinner: Dict[str, Any] = field(default_factory=dict)
-    branding: Dict[str, str] = field(default_factory=dict)
-    tool_prefix: str = "┊"
-
-    def get_color(self, key: str, fallback: str = "") -> str:
-        """Get a color value with fallback."""
-        return self.colors.get(key, fallback)
-
-    def get_spinner_list(self, key: str) -> List[str]:
-        """Get a spinner list (faces, verbs, etc.)."""
-        return self.spinner.get(key, [])
-
-    def get_spinner_wings(self) -> List[Tuple[str, str]]:
-        """Get spinner wing pairs, or empty list if none."""
-        raw = self.spinner.get("wings", [])
-        result = []
-        for pair in raw:
-            if isinstance(pair, (list, tuple)) and len(pair) == 2:
-                result.append((str(pair[0]), str(pair[1])))
-        return result
-
-    def get_branding(self, key: str, fallback: str = "") -> str:
-        """Get a branding value with fallback."""
-        return self.branding.get(key, fallback)
-
-
-# =============================================================================
-# Built-in skin definitions
-# =============================================================================
-
-_BUILTIN_SKINS: Dict[str, Dict[str, Any]] = {
-    "default": {
-        "name": "default",
-        "description": "Classic Hermes — gold and kawaii",
-        "colors": {
-            "banner_border": "#CD7F32",
-            "banner_title": "#FFD700",
-            "banner_accent": "#FFBF00",
-            "banner_dim": "#B8860B",
-            "banner_text": "#FFF8DC",
-            "ui_accent": "#FFBF00",
-            "ui_label": "#4dd0e1",
-            "ui_ok": "#4caf50",
-            "ui_error": "#ef5350",
-            "ui_warn": "#ffa726",
-            "prompt": "#FFF8DC",
-            "input_rule": "#CD7F32",
-            "response_border": "#FFD700",
-            "session_label": "#DAA520",
-            "session_border": "#8B8682",
-        },
-        "spinner": {
-            # Empty = use hardcoded defaults in display.py
-        },
-        "branding": {
-            "agent_name": "Hermes Agent",
-            "welcome": "Welcome to Hermes Agent! Type your message or /help for commands.",
-            "goodbye": "Goodbye! ⚕",
-            "response_label": " ⚕ Hermes ",
-            "prompt_symbol": "❯ ",
-            "help_header": "(^_^)? Available Commands",
-        },
-        "tool_prefix": "┊",
-    },
-    "ares": {
-        "name": "ares",
-        "description": "War-god theme — crimson and bronze",
-        "colors": {
-            "banner_border": "#9F1C1C",
-            "banner_title": "#C7A96B",
-            "banner_accent": "#DD4A3A",
-            "banner_dim": "#6B1717",
-            "banner_text": "#F1E6CF",
-            "ui_accent": "#DD4A3A",
-            "ui_label": "#C7A96B",
-            "ui_ok": "#4caf50",
-            "ui_error": "#ef5350",
-            "ui_warn": "#ffa726",
-            "prompt": "#F1E6CF",
-            "input_rule": "#9F1C1C",
-            "response_border": "#C7A96B",
-            "session_label": "#C7A96B",
-            "session_border": "#6E584B",
-        },
-        "spinner": {
-            "waiting_faces": ["(⚔)", "(⛨)", "(▲)", "(<>)", "(/)"],
-            "thinking_faces": ["(⚔)", "(⛨)", "(▲)", "(⌁)", "(<>)"],
-            "thinking_verbs": [
-                "forging", "marching", "sizing the field", "holding the line",
-                "hammering plans", "tempering steel", "plotting impact", "raising the shield",
-            ],
-            "wings": [
-                ["⟪⚔", "⚔⟫"],
-                ["⟪▲", "▲⟫"],
-                ["⟪╸", "╺⟫"],
-                ["⟪⛨", "⛨⟫"],
-            ],
-        },
-        "branding": {
-            "agent_name": "Ares Agent",
-            "welcome": "Welcome to Ares Agent! Type your message or /help for commands.",
-            "goodbye": "Farewell, warrior! ⚔",
-            "response_label": " ⚔ Ares ",
-            "prompt_symbol": "⚔ ❯ ",
-            "help_header": "(⚔) Available Commands",
-        },
-        "tool_prefix": "╎",
-    },
-    "mono": {
-        "name": "mono",
-        "description": "Monochrome — clean grayscale",
-        "colors": {
-            "banner_border": "#555555",
-            "banner_title": "#e6edf3",
-            "banner_accent": "#aaaaaa",
-            "banner_dim": "#444444",
-            "banner_text": "#c9d1d9",
-            "ui_accent": "#aaaaaa",
-            "ui_label": "#888888",
-            "ui_ok": "#888888",
-            "ui_error": "#cccccc",
-            "ui_warn": "#999999",
-            "prompt": "#c9d1d9",
-            "input_rule": "#444444",
-            "response_border": "#aaaaaa",
-            "session_label": "#888888",
-            "session_border": "#555555",
-        },
-        "spinner": {},
-        "branding": {
-            "agent_name": "Hermes Agent",
-            "welcome": "Welcome to Hermes Agent! Type your message or /help for commands.",
-            "goodbye": "Goodbye! ⚕",
-            "response_label": " ⚕ Hermes ",
-            "prompt_symbol": "❯ ",
-            "help_header": "[?] Available Commands",
-        },
-        "tool_prefix": "┊",
-    },
-    "slate": {
-        "name": "slate",
-        "description": "Cool blue — developer-focused",
-        "colors": {
-            "banner_border": "#4169e1",
-            "banner_title": "#7eb8f6",
-            "banner_accent": "#8EA8FF",
-            "banner_dim": "#4b5563",
-            "banner_text": "#c9d1d9",
-            "ui_accent": "#7eb8f6",
-            "ui_label": "#8EA8FF",
-            "ui_ok": "#63D0A6",
-            "ui_error": "#F7A072",
-            "ui_warn": "#e6a855",
-            "prompt": "#c9d1d9",
-            "input_rule": "#4169e1",
-            "response_border": "#7eb8f6",
-            "session_label": "#7eb8f6",
-            "session_border": "#4b5563",
-        },
-        "spinner": {},
-        "branding": {
-            "agent_name": "Hermes Agent",
-            "welcome": "Welcome to Hermes Agent! Type your message or /help for commands.",
-            "goodbye": "Goodbye! ⚕",
-            "response_label": " ⚕ Hermes ",
-            "prompt_symbol": "❯ ",
-            "help_header": "(^_^)? Available Commands",
-        },
-        "tool_prefix": "┊",
-    },
-}
-
-
-# =============================================================================
-# Skin loading and management
-# =============================================================================
-
-_active_skin: Optional[SkinConfig] = None
-_active_skin_name: str = "default"
-
-
-def _skins_dir() -> Path:
-    """User skins directory."""
-    home = Path(os.getenv("HERMES_HOME", Path.home() / ".hermes"))
-    return home / "skins"
-
-
-def _load_skin_from_yaml(path: Path) -> Optional[Dict[str, Any]]:
-    """Load a skin definition from a YAML file."""
-    try:
-        import yaml
-        with open(path, "r", encoding="utf-8") as f:
-            data = yaml.safe_load(f)
-        if isinstance(data, dict) and "name" in data:
-            return data
-    except Exception as e:
-        logger.debug("Failed to load skin from %s: %s", path, e)
-    return None
-
-
-def _build_skin_config(data: Dict[str, Any]) -> SkinConfig:
-    """Build a SkinConfig from a raw dict (built-in or loaded from YAML)."""
-    # Start with default values as base for missing keys
-    default = _BUILTIN_SKINS["default"]
-    colors = dict(default.get("colors", {}))
-    colors.update(data.get("colors", {}))
-    spinner = dict(default.get("spinner", {}))
-    spinner.update(data.get("spinner", {}))
-    branding = dict(default.get("branding", {}))
-    branding.update(data.get("branding", {}))
-
-    return SkinConfig(
-        name=data.get("name", "unknown"),
-        description=data.get("description", ""),
-        colors=colors,
-        spinner=spinner,
-        branding=branding,
-        tool_prefix=data.get("tool_prefix", default.get("tool_prefix", "┊")),
-    )
-
-
-def list_skins() -> List[Dict[str, str]]:
-    """List all available skins (built-in + user-installed).
-
-    Returns list of {"name": ..., "description": ..., "source": "builtin"|"user"}.
-    """
-    result = []
-    for name, data in _BUILTIN_SKINS.items():
-        result.append({
-            "name": name,
-            "description": data.get("description", ""),
-            "source": "builtin",
-        })
-
-    skins_path = _skins_dir()
-    if skins_path.is_dir():
-        for f in sorted(skins_path.glob("*.yaml")):
-            data = _load_skin_from_yaml(f)
-            if data:
-                skin_name = data.get("name", f.stem)
-                # Skip if it shadows a built-in
-                if any(s["name"] == skin_name for s in result):
-                    continue
-                result.append({
-                    "name": skin_name,
-                    "description": data.get("description", ""),
-                    "source": "user",
-                })
-
-    return result
-
-
-def load_skin(name: str) -> SkinConfig:
-    """Load a skin by name. Checks user skins first, then built-in."""
-    # Check user skins directory
-    skins_path = _skins_dir()
-    user_file = skins_path / f"{name}.yaml"
-    if user_file.is_file():
-        data = _load_skin_from_yaml(user_file)
-        if data:
-            return _build_skin_config(data)
-
-    # Check built-in skins
-    if name in _BUILTIN_SKINS:
-        return _build_skin_config(_BUILTIN_SKINS[name])
-
-    # Fallback to default
-    logger.warning("Skin '%s' not found, using default", name)
-    return _build_skin_config(_BUILTIN_SKINS["default"])
-
-
-def get_active_skin() -> SkinConfig:
-    """Get the currently active skin config (cached)."""
-    global _active_skin
-    if _active_skin is None:
-        _active_skin = load_skin(_active_skin_name)
-    return _active_skin
-
-
-def set_active_skin(name: str) -> SkinConfig:
-    """Switch the active skin. Returns the new SkinConfig."""
-    global _active_skin, _active_skin_name
-    _active_skin_name = name
-    _active_skin = load_skin(name)
-    return _active_skin
-
-
-def get_active_skin_name() -> str:
-    """Get the name of the currently active skin."""
-    return _active_skin_name
-
-
-def init_skin_from_config(config: dict) -> None:
-    """Initialize the active skin from CLI config at startup.
-
-    Call this once during CLI init with the loaded config dict.
-    """
-    display = config.get("display", {})
-    skin_name = display.get("skin", "default")
-    if isinstance(skin_name, str) and skin_name.strip():
-        set_active_skin(skin_name.strip())
-    else:
-        set_active_skin("default")

hermes_cli/status.py

@@ -263,7 +263,7 @@ def show_status(args):
     if jobs_file.exists():
         import json
         try:
-            with open(jobs_file, encoding="utf-8") as f:
+            with open(jobs_file) as f:
                 data = json.load(f)
                 jobs = data.get("jobs", [])
                 enabled_jobs = [j for j in jobs if j.get("enabled", True)]
@@ -283,7 +283,7 @@ def show_status(args):
     if sessions_file.exists():
         import json
         try:
-            with open(sessions_file, encoding="utf-8") as f:
+            with open(sessions_file) as f:
                 data = json.load(f)
                 print(f"  Active:       {len(data)} session(s)")
         except Exception:

hermes_state.py

@@ -16,7 +16,6 @@ Key design decisions:
 
 import json
 import os
-import re
 import sqlite3
 import time
 from pathlib import Path
@@ -491,16 +490,12 @@ class SessionDB:
         msg_id = cursor.lastrowid
 
         # Update counters
-        # Count actual tool calls from the tool_calls list (not from tool responses).
-        # A single assistant message can contain multiple parallel tool calls.
-        num_tool_calls = 0
-        if tool_calls is not None:
-            num_tool_calls = len(tool_calls) if isinstance(tool_calls, list) else 1
-        if num_tool_calls > 0:
+        is_tool_related = role == "tool" or tool_calls is not None
+        if is_tool_related:
             self._conn.execute(
                 """UPDATE sessions SET message_count = message_count + 1,
-                   tool_call_count = tool_call_count + ? WHERE id = ?""",
-                (num_tool_calls, session_id),
+                   tool_call_count = tool_call_count + 1 WHERE id = ?""",
+                (session_id,),
             )
         else:
             self._conn.execute(
@@ -558,32 +553,6 @@ class SessionDB:
     # Search
     # =========================================================================
 
-    @staticmethod
-    def _sanitize_fts5_query(query: str) -> str:
-        """Sanitize user input for safe use in FTS5 MATCH queries.
-
-        FTS5 has its own query syntax where characters like ``"``, ``(``, ``)``,
-        ``+``, ``*``, ``{``, ``}`` and bare boolean operators (``AND``, ``OR``,
-        ``NOT``) have special meaning.  Passing raw user input directly to
-        MATCH can cause ``sqlite3.OperationalError``.
-
-        Strategy: strip characters that are only meaningful as FTS5 operators
-        and would otherwise cause syntax errors.  This preserves normal keyword
-        search while preventing crashes on inputs like ``C++``, ``"unterminated``,
-        or ``hello AND``.
-        """
-        # Remove FTS5-special characters that are not useful in keyword search
-        sanitized = re.sub(r'[+{}()"^]', " ", query)
-        # Collapse repeated * (e.g. "***") into a single one, and remove
-        # leading * (prefix-only matching requires at least one char before *)
-        sanitized = re.sub(r"\*+", "*", sanitized)
-        sanitized = re.sub(r"(^|\s)\*", r"\1", sanitized)
-        # Remove dangling boolean operators at start/end that would cause
-        # syntax errors (e.g. "hello AND" or "OR world")
-        sanitized = re.sub(r"(?i)^(AND|OR|NOT)\b\s*", "", sanitized.strip())
-        sanitized = re.sub(r"(?i)\s+(AND|OR|NOT)\s*$", "", sanitized.strip())
-        return sanitized.strip()
-
     def search_messages(
         self,
         query: str,
@@ -607,10 +576,6 @@ class SessionDB:
         if not query or not query.strip():
             return []
 
-        query = self._sanitize_fts5_query(query)
-        if not query:
-            return []
-
         if source_filter is None:
             source_filter = ["cli", "telegram", "discord", "whatsapp", "slack"]
 
@@ -650,11 +615,7 @@ class SessionDB:
             LIMIT ? OFFSET ?
         """
 
-        try:
-            cursor = self._conn.execute(sql, params)
-        except sqlite3.OperationalError:
-            # FTS5 query syntax error despite sanitization — return empty
-            return []
+        cursor = self._conn.execute(sql, params)
         matches = [dict(row) for row in cursor.fetchall()]
 
         # Add surrounding context (1 message before + after each match)

optional-skills/migration/DESCRIPTION.md

@@ -1,2 +0,0 @@
-Optional migration workflows for importing user state and customizations from
-other agent systems into Hermes Agent.

optional-skills/migration/openclaw-migration/SKILL.md

@@ -1,281 +0,0 @@
----
-name: openclaw-migration
-description: Migrate a user's OpenClaw customization footprint into Hermes Agent. Imports Hermes-compatible memories, SOUL.md, command allowlists, user skills, and selected workspace assets from ~/.openclaw, then reports exactly what could not be migrated and why.
-version: 1.0.0
-author: Hermes Agent (Nous Research)
-license: MIT
-metadata:
-  hermes:
-    tags: [Migration, OpenClaw, Hermes, Memory, Persona, Import]
-    related_skills: [hermes-agent]
----
-
-# OpenClaw -> Hermes Migration
-
-Use this skill when a user wants to move their OpenClaw setup into Hermes Agent with minimal manual cleanup.
-
-## What this skill does
-
-It uses `scripts/openclaw_to_hermes.py` to:
-
-- import `SOUL.md` into the Hermes home directory as `SOUL.md`
-- transform OpenClaw `MEMORY.md` and `USER.md` into Hermes memory entries
-- merge OpenClaw command approval patterns into Hermes `command_allowlist`
-- migrate Hermes-compatible messaging settings such as `TELEGRAM_ALLOWED_USERS` and `MESSAGING_CWD`
-- copy OpenClaw skills into `~/.hermes/skills/openclaw-imports/`
-- optionally copy the OpenClaw workspace instructions file into a chosen Hermes workspace
-- mirror compatible workspace assets such as `workspace/tts/` into `~/.hermes/tts/`
-- archive non-secret docs that do not have a direct Hermes destination
-- produce a structured report listing migrated items, conflicts, skipped items, and reasons
-
-## Path resolution
-
-The helper script lives in this skill directory at:
-
-- `scripts/openclaw_to_hermes.py`
-
-When this skill is installed from the Skills Hub, the normal location is:
-
-- `~/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py`
-
-Do not guess a shorter path like `~/.hermes/skills/openclaw-migration/...`.
-
-Before running the helper:
-
-1. Prefer the installed path under `~/.hermes/skills/migration/openclaw-migration/`.
-2. If that path fails, inspect the installed skill directory and resolve the script relative to the installed `SKILL.md`.
-3. Only use `find` as a fallback if the installed location is missing or the skill was moved manually.
-4. When calling the terminal tool, do not pass `workdir: "~"`. Use an absolute directory such as the user's home directory, or omit `workdir` entirely.
-
-With `--migrate-secrets`, it will also import a small allowlisted set of Hermes-compatible secrets, currently:
-
-- `TELEGRAM_BOT_TOKEN`
-
-## Default workflow
-
-1. Inspect first with a dry run.
-2. Present a simple summary of what can be migrated, what cannot be migrated, and what would be archived.
-3. If the `clarify` tool is available, use it for user decisions instead of asking for a free-form prose reply.
-4. If the dry run finds imported skill directory conflicts, ask how those should be handled before executing.
-5. Ask the user to choose between the two supported migration modes before executing.
-6. Ask for a target workspace path only if the user wants the workspace instructions file brought over.
-7. Execute the migration with the matching preset and flags.
-8. Summarize the results, especially:
-   - what was migrated
-   - what was archived for manual review
-   - what was skipped and why
-
-## User interaction protocol
-
-Hermes CLI supports the `clarify` tool for interactive prompts, but it is limited to:
-
-- one choice at a time
-- up to 4 predefined choices
-- an automatic `Other` free-text option
-
-It does **not** support true multi-select checkboxes in a single prompt.
-
-For every `clarify` call:
-
-- always include a non-empty `question`
-- include `choices` only for real selectable prompts
-- keep `choices` to 2-4 plain string options
-- never emit placeholder or truncated options such as `...`
-- never pad or stylize choices with extra whitespace
-- never include fake form fields in the question such as `enter directory here`, blank lines to fill in, or underscores like `_____`
-- for open-ended path questions, ask only the plain sentence; the user types in the normal CLI prompt below the panel
-
-If a `clarify` call returns an error, inspect the error text, correct the payload, and retry once with a valid `question` and clean choices.
-
-When `clarify` is available and the dry run reveals any required user decision, your **next action must be a `clarify` tool call**.
-Do not end the turn with a normal assistant message such as:
-
-- "Let me present the choices"
-- "What would you like to do?"
-- "Here are the options"
-
-If a user decision is required, collect it via `clarify` before producing more prose.
-If multiple unresolved decisions remain, do not insert an explanatory assistant message between them. After one `clarify` response is received, your next action should usually be the next required `clarify` call.
-
-Treat `workspace-agents` as an unresolved decision whenever the dry run reports:
-
-- `kind="workspace-agents"`
-- `status="skipped"`
-- reason containing `No workspace target was provided`
-
-In that case, you must ask about workspace instructions before execution. Do not silently treat that as a decision to skip.
-
-Because of that limitation, use this simplified decision flow:
-
-1. For `SOUL.md` conflicts, use `clarify` with choices such as:
-   - `keep existing`
-   - `overwrite with backup`
-   - `review first`
-2. If the dry run shows one or more `kind="skill"` items with `status="conflict"`, use `clarify` with choices such as:
-   - `keep existing skills`
-   - `overwrite conflicting skills with backup`
-   - `import conflicting skills under renamed folders`
-3. For workspace instructions, use `clarify` with choices such as:
-   - `skip workspace instructions`
-   - `copy to a workspace path`
-   - `decide later`
-4. If the user chooses to copy workspace instructions, ask a follow-up open-ended `clarify` question requesting an **absolute path**.
-5. If the user chooses `skip workspace instructions` or `decide later`, proceed without `--workspace-target`.
-5. For migration mode, use `clarify` with these 3 choices:
-   - `user-data only`
-   - `full compatible migration`
-   - `cancel`
-6. `user-data only` means: migrate user data and compatible config, but do **not** import allowlisted secrets.
-7. `full compatible migration` means: migrate the same compatible user data plus the allowlisted secrets when present.
-8. If `clarify` is not available, ask the same question in normal text, but still constrain the answer to `user-data only`, `full compatible migration`, or `cancel`.
-
-Execution gate:
-
-- Do not execute while a `workspace-agents` skip caused by `No workspace target was provided` remains unresolved.
-- The only valid ways to resolve it are:
-  - user explicitly chooses `skip workspace instructions`
-  - user explicitly chooses `decide later`
-  - user provides a workspace path after choosing `copy to a workspace path`
-- Absence of a workspace target in the dry run is not itself permission to execute.
-- Do not execute while any required `clarify` decision remains unresolved.
-
-Use these exact `clarify` payload shapes as the default pattern:
-
-- `{"question":"Your existing SOUL.md conflicts with the imported one. What should I do?","choices":["keep existing","overwrite with backup","review first"]}`
-- `{"question":"One or more imported OpenClaw skills already exist in Hermes. How should I handle those skill conflicts?","choices":["keep existing skills","overwrite conflicting skills with backup","import conflicting skills under renamed folders"]}`
-- `{"question":"Choose migration mode: migrate only user data, or run the full compatible migration including allowlisted secrets?","choices":["user-data only","full compatible migration","cancel"]}`
-- `{"question":"Do you want to copy the OpenClaw workspace instructions file into a Hermes workspace?","choices":["skip workspace instructions","copy to a workspace path","decide later"]}`
-- `{"question":"Please provide an absolute path where the workspace instructions should be copied."}`
-
-## Decision-to-command mapping
-
-Map user decisions to command flags exactly:
-
-- If the user chooses `keep existing` for `SOUL.md`, do **not** add `--overwrite`.
-- If the user chooses `overwrite with backup`, add `--overwrite`.
-- If the user chooses `review first`, stop before execution and review the relevant files.
-- If the user chooses `keep existing skills`, add `--skill-conflict skip`.
-- If the user chooses `overwrite conflicting skills with backup`, add `--skill-conflict overwrite`.
-- If the user chooses `import conflicting skills under renamed folders`, add `--skill-conflict rename`.
-- If the user chooses `user-data only`, execute with `--preset user-data` and do **not** add `--migrate-secrets`.
-- If the user chooses `full compatible migration`, execute with `--preset full --migrate-secrets`.
-- Only add `--workspace-target` if the user explicitly provided an absolute workspace path.
-- If the user chooses `skip workspace instructions` or `decide later`, do not add `--workspace-target`.
-
-Before executing, restate the exact command plan in plain language and make sure it matches the user's choices.
-
-## Post-run reporting rules
-
-After execution, treat the script's JSON output as the source of truth.
-
-1. Base all counts on `report.summary`.
-2. Only list an item under "Successfully Migrated" if its `status` is exactly `migrated`.
-3. Do not claim a conflict was resolved unless the report shows that item as `migrated`.
-4. Do not say `SOUL.md` was overwritten unless the report item for `kind="soul"` has `status="migrated"`.
-5. If `report.summary.conflict > 0`, include a conflict section instead of silently implying success.
-6. If counts and listed items disagree, fix the list to match the report before responding.
-7. Include the `output_dir` path from the report when available so the user can inspect `report.json`, `summary.md`, backups, and archived files.
-8. For memory or user-profile overflow, do not say the entries were archived unless the report explicitly shows an archive path. If `details.overflow_file` exists, say the full overflow list was exported there.
-9. If a skill was imported under a renamed folder, report the final destination and mention `details.renamed_from`.
-10. If `report.skill_conflict_mode` is present, use it as the source of truth for the selected imported-skill conflict policy.
-11. If an item has `status="skipped"`, do not describe it as overwritten, backed up, migrated, or resolved.
-12. If `kind="soul"` has `status="skipped"` with reason `Target already matches source`, say it was left unchanged and do not mention a backup.
-13. If a renamed imported skill has an empty `details.backup`, do not imply the existing Hermes skill was renamed or backed up. Say only that the imported copy was placed in the new destination and reference `details.renamed_from` as the pre-existing folder that remained in place.
-
-## Migration presets
-
-Prefer these two presets in normal use:
-
-- `user-data`
-- `full`
-
-`user-data` includes:
-
-- `soul`
-- `workspace-agents`
-- `memory`
-- `user-profile`
-- `messaging-settings`
-- `command-allowlist`
-- `skills`
-- `tts-assets`
-- `archive`
-
-`full` includes everything in `user-data` plus:
-
-- `secret-settings`
-
-The helper script still supports category-level `--include` / `--exclude`, but treat that as an advanced fallback rather than the default UX.
-
-## Commands
-
-Dry run with full discovery:
-
-```bash
-python3 ~/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py
-```
-
-When using the terminal tool, prefer an absolute invocation pattern such as:
-
-```json
-{"command":"python3 /home/USER/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py","workdir":"/home/USER"}
-```
-
-Dry run with the user-data preset:
-
-```bash
-python3 ~/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py --preset user-data
-```
-
-Execute a user-data migration:
-
-```bash
-python3 ~/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py --execute --preset user-data --skill-conflict skip
-```
-
-Execute a full compatible migration:
-
-```bash
-python3 ~/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py --execute --preset full --migrate-secrets --skill-conflict skip
-```
-
-Execute with workspace instructions included:
-
-```bash
-python3 ~/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py --execute --preset user-data --skill-conflict rename --workspace-target "/absolute/workspace/path"
-```
-
-Do not use `$PWD` or the home directory as the workspace target by default. Ask for an explicit workspace path first.
-
-## Important rules
-
-1. Run a dry run before writing unless the user explicitly says to proceed immediately.
-2. Do not migrate secrets by default. Tokens, auth blobs, device credentials, and raw gateway config should stay out of Hermes unless the user explicitly asks for secret migration.
-3. Do not silently overwrite non-empty Hermes targets unless the user explicitly wants that. The helper script will preserve backups when overwriting is enabled.
-4. Always give the user the skipped-items report. That report is part of the migration, not an optional extra.
-5. Prefer the primary OpenClaw workspace (`~/.openclaw/workspace/`) over `workspace.default/`. Only use the default workspace as fallback when the primary files are missing.
-6. Even in secret-migration mode, only migrate secrets with a clean Hermes destination. Unsupported auth blobs must still be reported as skipped.
-7. If the dry run shows a large asset copy, a conflicting `SOUL.md`, or overflowed memory entries, call those out separately before execution.
-8. Default to `user-data only` if the user is unsure.
-9. Only include `workspace-agents` when the user has explicitly provided a destination workspace path.
-10. Treat category-level `--include` / `--exclude` as an advanced escape hatch, not the normal flow.
-11. Do not end the dry-run summary with a vague “What would you like to do?” if `clarify` is available. Use structured follow-up prompts instead.
-12. Do not use an open-ended `clarify` prompt when a real choice prompt would work. Prefer selectable choices first, then free text only for absolute paths or file review requests.
-13. After a dry run, never stop after summarizing if there is still an unresolved decision. Use `clarify` immediately for the highest-priority blocking decision.
-14. Priority order for follow-up questions:
-    - `SOUL.md` conflict
-    - imported skill conflicts
-    - migration mode
-    - workspace instructions destination
-15. Do not promise to present choices later in the same message. Present them by actually calling `clarify`.
-16. After the migration-mode answer, explicitly check whether `workspace-agents` is still unresolved. If it is, your next action must be the workspace-instructions `clarify` call.
-17. After any `clarify` answer, if another required decision remains, do not narrate what was just decided. Ask the next required question immediately.
-
-## Expected result
-
-After a successful run, the user should have:
-
-- Hermes persona state imported
-- Hermes memory files populated with converted OpenClaw knowledge
-- OpenClaw skills available under `~/.hermes/skills/openclaw-imports/`
-- a migration report showing any conflicts, omissions, or unsupported data

pyproject.toml

@@ -40,16 +40,13 @@ dependencies = [
 [project.optional-dependencies]
 modal = ["swe-rex[modal]>=1.4.0"]
 daytona = ["daytona>=0.148.0"]
-dev = ["pytest", "pytest-asyncio", "mcp>=1.2.0"]
+dev = ["pytest", "pytest-asyncio"]
 messaging = ["python-telegram-bot>=20.0", "discord.py>=2.0", "aiohttp>=3.9.0", "slack-bolt>=1.18.0", "slack-sdk>=3.27.0"]
 cron = ["croniter"]
 slack = ["slack-bolt>=1.18.0", "slack-sdk>=3.27.0"]
 cli = ["simple-term-menu"]
 tts-premium = ["elevenlabs"]
-pty = [
-  "ptyprocess>=0.7.0; sys_platform != 'win32'",
-  "pywinpty>=2.0.0; sys_platform == 'win32'",
-]
+pty = ["ptyprocess>=0.7.0"]
 honcho = ["honcho-ai>=2.0.1"]
 mcp = ["mcp>=1.2.0"]
 homeassistant = ["aiohttp>=3.9.0"]

run_agent.py

@@ -172,7 +172,6 @@ class AIAgent:
         provider_data_collection: str = None,
         session_id: str = None,
         tool_progress_callback: callable = None,
-        thinking_callback: callable = None,
         clarify_callback: callable = None,
         step_callback: callable = None,
         max_tokens: int = None,
@@ -185,8 +184,6 @@ class AIAgent:
         honcho_session_key: str = None,
         iteration_budget: "IterationBudget" = None,
         fallback_model: Dict[str, Any] = None,
-        checkpoints_enabled: bool = False,
-        checkpoint_max_snapshots: int = 50,
     ):
         """
         Initialize the AI Agent.
@@ -259,7 +256,6 @@ class AIAgent:
             self.api_mode = "chat_completions"
 
         self.tool_progress_callback = tool_progress_callback
-        self.thinking_callback = thinking_callback
         self.clarify_callback = clarify_callback
         self.step_callback = step_callback
         self._last_reported_tool = None  # Track for "new tool" mode
@@ -488,13 +484,6 @@ class AIAgent:
         # Cached system prompt -- built once per session, only rebuilt on compression
         self._cached_system_prompt: Optional[str] = None
         
-        # Filesystem checkpoint manager (transparent — not a tool)
-        from tools.checkpoint_manager import CheckpointManager
-        self._checkpoint_mgr = CheckpointManager(
-            enabled=checkpoints_enabled,
-            max_snapshots=checkpoint_max_snapshots,
-        )
-        
         # SQLite session store (optional -- provided by CLI or gateway)
         self._session_db = session_db
         if self._session_db:
@@ -2700,8 +2689,6 @@ class AIAgent:
             except json.JSONDecodeError as e:
                 logging.warning(f"Unexpected JSON error after validation: {e}")
                 function_args = {}
-            if not isinstance(function_args, dict):
-                function_args = {}
 
             if not self.quiet_mode:
                 args_str = json.dumps(function_args, ensure_ascii=False)
@@ -2715,18 +2702,6 @@ class AIAgent:
                 except Exception as cb_err:
                     logging.debug(f"Tool progress callback error: {cb_err}")
 
-            # Checkpoint: snapshot working dir before file-mutating tools
-            if function_name in ("write_file", "patch") and self._checkpoint_mgr.enabled:
-                try:
-                    file_path = function_args.get("path", "")
-                    if file_path:
-                        work_dir = self._checkpoint_mgr.get_working_dir_for_path(file_path)
-                        self._checkpoint_mgr.ensure_checkpoint(
-                            work_dir, f"before {function_name}"
-                        )
-                except Exception:
-                    pass  # never block tool execution
-
             tool_start_time = time.time()
 
             if function_name == "todo":
@@ -3236,9 +3211,6 @@ class AIAgent:
         self.clear_interrupt()
         
         while api_call_count < self.max_iterations and self.iteration_budget.remaining > 0:
-            # Reset per-turn checkpoint dedup so each iteration can take one snapshot
-            self._checkpoint_mgr.new_turn()
-
             # Check for interrupt request (e.g., user sent new message)
             if self._interrupt_requested:
                 interrupted = True
@@ -3351,13 +3323,9 @@ class AIAgent:
                 # Animated thinking spinner in quiet mode
                 face = random.choice(KawaiiSpinner.KAWAII_THINKING)
                 verb = random.choice(KawaiiSpinner.THINKING_VERBS)
-                if self.thinking_callback:
-                    # CLI TUI mode: use prompt_toolkit widget instead of raw spinner
-                    self.thinking_callback(f"{face} {verb}...")
-                else:
-                    spinner_type = random.choice(['brain', 'sparkle', 'pulse', 'moon', 'star'])
-                    thinking_spinner = KawaiiSpinner(f"{face} {verb}...", spinner_type=spinner_type)
-                    thinking_spinner.start()
+                spinner_type = random.choice(['brain', 'sparkle', 'pulse', 'moon', 'star'])
+                thinking_spinner = KawaiiSpinner(f"{face} {verb}...", spinner_type=spinner_type)
+                thinking_spinner.start()
             
             # Log request details if verbose
             if self.verbose_logging:
@@ -3394,8 +3362,6 @@ class AIAgent:
                     if thinking_spinner:
                         thinking_spinner.stop("")
                         thinking_spinner = None
-                    if self.thinking_callback:
-                        self.thinking_callback("")
                     
                     if not self.quiet_mode:
                         print(f"{self.log_prefix}⏱️  API call completed in {api_duration:.2f}s")
@@ -3436,8 +3402,6 @@ class AIAgent:
                         if thinking_spinner:
                             thinking_spinner.stop(f"(´;ω;`) oops, retrying...")
                             thinking_spinner = None
-                        if self.thinking_callback:
-                            self.thinking_callback("")
                         
                         # This is often rate limiting or provider returning malformed response
                         retry_count += 1
@@ -3607,8 +3571,6 @@ class AIAgent:
                     if thinking_spinner:
                         thinking_spinner.stop("")
                         thinking_spinner = None
-                    if self.thinking_callback:
-                        self.thinking_callback("")
                     api_elapsed = time.time() - api_start_time
                     print(f"{self.log_prefix}⚡ Interrupted during API call.")
                     self._persist_session(messages, conversation_history)
@@ -3621,8 +3583,6 @@ class AIAgent:
                     if thinking_spinner:
                         thinking_spinner.stop(f"(╥_╥) error, retrying...")
                         thinking_spinner = None
-                    if self.thinking_callback:
-                        self.thinking_callback("")
 
                     status_code = getattr(api_error, "status_code", None)
                     if (
@@ -3874,27 +3834,6 @@ class AIAgent:
                 else:
                     assistant_message = response.choices[0].message
                 
-                # Normalize content to string — some OpenAI-compatible servers
-                # (llama-server, etc.) return content as a dict or list instead
-                # of a plain string, which crashes downstream .strip() calls.
-                if assistant_message.content is not None and not isinstance(assistant_message.content, str):
-                    raw = assistant_message.content
-                    if isinstance(raw, dict):
-                        assistant_message.content = raw.get("text", "") or raw.get("content", "") or json.dumps(raw)
-                    elif isinstance(raw, list):
-                        # Multimodal content list — extract text parts
-                        parts = []
-                        for part in raw:
-                            if isinstance(part, str):
-                                parts.append(part)
-                            elif isinstance(part, dict) and part.get("type") == "text":
-                                parts.append(part.get("text", ""))
-                            elif isinstance(part, dict) and "text" in part:
-                                parts.append(str(part["text"]))
-                        assistant_message.content = "\n".join(parts)
-                    else:
-                        assistant_message.content = str(raw)
-
                 # Handle assistant response
                 if assistant_message.content and not self.quiet_mode:
                     print(f"{self.log_prefix}🤖 Assistant: {assistant_message.content[:100]}{'...' if len(assistant_message.content) > 100 else ''}")

skills/creative/DESCRIPTION.md

@@ -1,3 +0,0 @@
----
-description: Creative content generation — ASCII art, hand-drawn style diagrams, and visual design tools.
----

skills/gaming/pokemon-player/SKILL.md

@@ -1,215 +0,0 @@
----
-name: pokemon-player
-description: Play Pokemon games autonomously via headless emulation. Starts a game server, reads structured game state from RAM, makes strategic decisions, and sends button inputs — all from the terminal.
-tags: [gaming, pokemon, emulator, pyboy, gameplay, gameboy]
----
-# Pokemon Player
-
-Play Pokemon games via headless emulation using the `pokemon-agent` package.
-
-## When to Use
-- User says "play pokemon", "start pokemon", "pokemon game"
-- User asks about Pokemon Red, Blue, Yellow, FireRed, etc.
-- User wants to watch an AI play Pokemon
-- User references a ROM file (.gb, .gbc, .gba)
-
-## Startup Procedure
-
-### 1. First-time setup (clone, venv, install)
-The repo is NousResearch/pokemon-agent on GitHub. Clone it, then
-set up a Python 3.10+ virtual environment. Use uv (preferred for speed)
-to create the venv and install the package in editable mode with the
-pyboy extra. If uv is not available, fall back to python3 -m venv + pip.
-
-On this machine it is already set up at /home/teknium/pokemon-agent
-with a venv ready — just cd there and source .venv/bin/activate.
-
-You also need a ROM file. Ask the user for theirs. On this machine
-one exists at roms/pokemon_red.gb inside that directory.
-NEVER download or provide ROM files — always ask the user.
-
-### 2. Start the game server
-From inside the pokemon-agent directory with the venv activated, run
-pokemon-agent serve with --rom pointing to the ROM and --port 9876.
-Run it in the background with &.
-To resume from a saved game, add --load-state with the save name.
-Wait 4 seconds for startup, then verify with GET /health.
-
-### 3. Set up live dashboard for user to watch
-Use an SSH reverse tunnel via localhost.run so the user can view
-the dashboard in their browser. Connect with ssh, forwarding local
-port 9876 to remote port 80 on nokey@localhost.run. Redirect output
-to a log file, wait 10 seconds, then grep the log for the .lhr.life
-URL. Give the user the URL with /dashboard/ appended.
-The tunnel URL changes each time — give the user the new one if restarted.
-
-## Save and Load
-
-### When to save
-- Every 15-20 turns of gameplay
-- ALWAYS before gym battles, rival encounters, or risky fights
-- Before entering a new town or dungeon
-- Before any action you are unsure about
-
-### How to save
-POST /save with a descriptive name. Good examples:
-before_brock, route1_start, mt_moon_entrance, got_cut
-
-### How to load
-POST /load with the save name.
-
-### List available saves
-GET /saves returns all saved states.
-
-### Loading on server startup
-Use --load-state flag when starting the server to auto-load a save.
-This is faster than loading via the API after startup.
-
-## The Gameplay Loop
-
-### Step 1: OBSERVE — check state AND take a screenshot
-GET /state for position, HP, battle, dialog.
-GET /screenshot and save to /tmp/pokemon.png, then use vision_analyze.
-Always do BOTH — RAM state gives numbers, vision gives spatial awareness.
-
-### Step 2: ORIENT
-- Dialog/text on screen → advance it
-- In battle → fight or run
-- Party hurt → head to Pokemon Center
-- Near objective → navigate carefully
-
-### Step 3: DECIDE
-Priority: dialog > battle > heal > story objective > training > explore
-
-### Step 4: ACT — move 2-4 steps max, then re-check
-POST /action with a SHORT action list (2-4 actions, not 10-15).
-
-### Step 5: VERIFY — screenshot after every move sequence
-Take a screenshot and use vision_analyze to confirm you moved where
-intended. This is the MOST IMPORTANT step. Without vision you WILL get lost.
-
-### Step 6: RECORD progress to memory with PKM: prefix
-
-### Step 7: SAVE periodically
-
-## Action Reference
-- press_a — confirm, talk, select
-- press_b — cancel, close menu
-- press_start — open game menu
-- walk_up/down/left/right — move one tile
-- hold_b_N — hold B for N frames (use for speeding through text)
-- wait_60 — wait about 1 second (60 frames)
-- a_until_dialog_end — press A repeatedly until dialog clears
-
-## Critical Tips from Experience
-
-### USE VISION CONSTANTLY
-- Take a screenshot every 2-4 movement steps
-- The RAM state tells you position and HP but NOT what is around you
-- Ledges, fences, signs, building doors, NPCs — only visible via screenshot
-- Ask the vision model specific questions: "what is one tile north of me?"
-- When stuck, always screenshot before trying random directions
-
-### Warp Transitions Need Extra Wait Time
-When walking through a door or stairs, the screen fades to black during
-the map transition. You MUST wait for it to complete. Add 2-3 wait_60
-actions after any door/stair warp. Without waiting, the position reads
-as stale and you will think you are still in the old map.
-
-### Building Exit Trap
-When you exit a building, you appear directly IN FRONT of the door.
-If you walk north, you go right back inside. ALWAYS sidestep first
-by walking left or right 2 tiles, then proceed in your intended direction.
-
-### Dialog Handling
-Gen 1 text scrolls slowly letter-by-letter. To speed through dialog,
-hold B for 120 frames then press A. Repeat as needed. Holding B makes
-text display at max speed. Then press A to advance to the next line.
-The a_until_dialog_end action checks the RAM dialog flag, but this flag
-does not catch ALL text states. If dialog seems stuck, use the manual
-hold_b + press_a pattern instead and verify via screenshot.
-
-### Ledges Are One-Way
-Ledges (small cliff edges) can only be jumped DOWN (south), never climbed
-UP (north). If blocked by a ledge going north, you must go left or right
-to find the gap around it. Use vision to identify which direction the
-gap is. Ask the vision model explicitly.
-
-### Navigation Strategy
-- Move 2-4 steps at a time, then screenshot to check position
-- When entering a new area, screenshot immediately to orient
-- Ask the vision model "which direction to [destination]?"
-- If stuck for 3+ attempts, screenshot and re-evaluate completely
-- Do not spam 10-15 movements — you will overshoot or get stuck
-
-### Running from Wild Battles
-On the battle menu, RUN is bottom-right. To reach it from the default
-cursor position (FIGHT, top-left): press down then right to move cursor
-to RUN, then press A. Wrap with hold_b to speed through text/animations.
-
-### Battling (FIGHT)
-On the battle menu FIGHT is top-left (default cursor position).
-Press A to enter move selection, A again to use the first move.
-Then hold B to speed through attack animations and text.
-
-## Battle Strategy
-
-### Decision Tree
-1. Want to catch? → Weaken then throw Poke Ball
-2. Wild you don't need? → RUN
-3. Type advantage? → Use super-effective move
-4. No advantage? → Use strongest STAB move
-5. Low HP? → Switch or use Potion
-
-### Gen 1 Type Chart (key matchups)
-- Water beats Fire, Ground, Rock
-- Fire beats Grass, Bug, Ice
-- Grass beats Water, Ground, Rock
-- Electric beats Water, Flying
-- Ground beats Fire, Electric, Rock, Poison
-- Psychic beats Fighting, Poison (dominant in Gen 1!)
-
-### Gen 1 Quirks
-- Special stat = both offense AND defense for special moves
-- Psychic type is overpowered (Ghost moves bugged)
-- Critical hits based on Speed stat
-- Wrap/Bind prevent opponent from acting
-- Focus Energy bug: REDUCES crit rate instead of raising it
-
-## Memory Conventions
-| Prefix | Purpose | Example |
-|--------|---------|---------|
-| PKM:OBJECTIVE | Current goal | Get Parcel from Viridian Mart |
-| PKM:MAP | Navigation knowledge | Viridian: mart is northeast |
-| PKM:STRATEGY | Battle/team plans | Need Grass type before Misty |
-| PKM:PROGRESS | Milestone tracker | Beat rival, heading to Viridian |
-| PKM:STUCK | Stuck situations | Ledge at y=28 go right to bypass |
-| PKM:TEAM | Team notes | Squirtle Lv6, Tackle + Tail Whip |
-
-## Progression Milestones
-- Choose starter
-- Deliver Parcel from Viridian Mart, receive Pokedex
-- Boulder Badge — Brock (Rock) → use Water/Grass
-- Cascade Badge — Misty (Water) → use Grass/Electric
-- Thunder Badge — Lt. Surge (Electric) → use Ground
-- Rainbow Badge — Erika (Grass) → use Fire/Ice/Flying
-- Soul Badge — Koga (Poison) → use Ground/Psychic
-- Marsh Badge — Sabrina (Psychic) → hardest gym
-- Volcano Badge — Blaine (Fire) → use Water/Ground
-- Earth Badge — Giovanni (Ground) → use Water/Grass/Ice
-- Elite Four → Champion!
-
-## Stopping Play
-1. Save the game with a descriptive name via POST /save
-2. Update memory with PKM:PROGRESS
-3. Tell user: "Game saved as [name]! Say 'play pokemon' to resume."
-4. Kill the server and tunnel background processes
-
-## Pitfalls
-- NEVER download or provide ROM files
-- Do NOT send more than 4-5 actions without checking vision
-- Always sidestep after exiting buildings before going north
-- Always add wait_60 x2-3 after door/stair warps
-- Dialog detection via RAM is unreliable — verify with screenshots
-- Save BEFORE risky encounters
-- The tunnel URL changes each time you restart it

skills/leisure/find-nearby/SKILL.md

@@ -1,69 +0,0 @@
----
-name: find-nearby
-description: Find nearby places (restaurants, cafes, bars, pharmacies, etc.) using OpenStreetMap. Works with coordinates, addresses, cities, zip codes, or Telegram location pins. No API keys needed.
-version: 1.0.0
-metadata:
-  hermes:
-    tags: [location, maps, nearby, places, restaurants, local]
-    related_skills: []
----
-
-# Find Nearby — Local Place Discovery
-
-Find restaurants, cafes, bars, pharmacies, and other places near any location. Uses OpenStreetMap (free, no API keys). Works with:
-
-- **Coordinates** from Telegram location pins (latitude/longitude in conversation)
-- **Addresses** ("near 123 Main St, Springfield")
-- **Cities** ("restaurants in downtown Austin")
-- **Zip codes** ("pharmacies near 90210")
-- **Landmarks** ("cafes near Times Square")
-
-## Quick Reference
-
-```bash
-# By coordinates (from Telegram location pin or user-provided)
-python3 SKILL_DIR/scripts/find_nearby.py --lat <LAT> --lon <LON> --type restaurant --radius 1500
-
-# By address, city, or landmark (auto-geocoded)
-python3 SKILL_DIR/scripts/find_nearby.py --near "Times Square, New York" --type cafe
-
-# Multiple place types
-python3 SKILL_DIR/scripts/find_nearby.py --near "downtown austin" --type restaurant --type bar --limit 10
-
-# JSON output
-python3 SKILL_DIR/scripts/find_nearby.py --near "90210" --type pharmacy --json
-```
-
-### Parameters
-
-| Flag | Description | Default |
-|------|-------------|---------|
-| `--lat`, `--lon` | Exact coordinates | — |
-| `--near` | Address, city, zip, or landmark (geocoded) | — |
-| `--type` | Place type (repeatable for multiple) | restaurant |
-| `--radius` | Search radius in meters | 1500 |
-| `--limit` | Max results | 15 |
-| `--json` | Machine-readable JSON output | off |
-
-### Common Place Types
-
-`restaurant`, `cafe`, `bar`, `pub`, `fast_food`, `pharmacy`, `hospital`, `bank`, `atm`, `fuel`, `parking`, `supermarket`, `convenience`, `hotel`
-
-## Workflow
-
-1. **Get the location.** Look for coordinates (`latitude: ... / longitude: ...`) from a Telegram pin, or ask the user for an address/city/zip.
-
-2. **Ask for preferences** (only if not already stated): place type, how far they're willing to go, any specifics (cuisine, "open now", etc.).
-
-3. **Run the script** with appropriate flags. Use `--json` if you need to process results programmatically.
-
-4. **Present results** with names, distances, and Google Maps links. If the user asked about hours or "open now," check the `hours` field in results — if missing or unclear, verify with `web_search`.
-
-5. **For directions**, use the `directions_url` from results, or construct: `https://www.google.com/maps/dir/?api=1&origin=<LAT>,<LON>&destination=<LAT>,<LON>`
-
-## Tips
-
-- If results are sparse, widen the radius (1500 → 3000m)
-- For "open now" requests: check the `hours` field in results, cross-reference with `web_search` for accuracy since OSM hours aren't always complete
-- Zip codes alone can be ambiguous globally — prompt the user for country/state if results look wrong
-- The script uses OpenStreetMap data which is community-maintained; coverage varies by region

skills/leisure/find-nearby/scripts/find_nearby.py

@@ -1,184 +0,0 @@
-#!/usr/bin/env python3
-"""Find nearby places using OpenStreetMap (Overpass + Nominatim). No API keys needed.
-
-Usage:
-    # By coordinates
-    python find_nearby.py --lat 36.17 --lon -115.14 --type restaurant --radius 1500
-
-    # By address/city/zip (auto-geocoded)
-    python find_nearby.py --near "Times Square, New York" --type cafe --radius 1000
-    python find_nearby.py --near "90210" --type pharmacy
-
-    # Multiple types
-    python find_nearby.py --lat 36.17 --lon -115.14 --type restaurant --type bar
-
-    # JSON output for programmatic use
-    python find_nearby.py --near "downtown las vegas" --type restaurant --json
-"""
-
-import argparse
-import json
-import math
-import sys
-import urllib.parse
-import urllib.request
-from typing import Any
-
-OVERPASS_URLS = [
-    "https://overpass-api.de/api/interpreter",
-    "https://overpass.kumi.systems/api/interpreter",
-]
-NOMINATIM_URL = "https://nominatim.openstreetmap.org/search"
-USER_AGENT = "HermesAgent/1.0 (find-nearby skill)"
-TIMEOUT = 15
-
-
-def _http_get(url: str) -> Any:
-    req = urllib.request.Request(url, headers={"User-Agent": USER_AGENT})
-    with urllib.request.urlopen(req, timeout=TIMEOUT) as r:
-        return json.loads(r.read())
-
-
-def _http_post(url: str, data: str) -> Any:
-    req = urllib.request.Request(
-        url, data=data.encode(), headers={"User-Agent": USER_AGENT}
-    )
-    with urllib.request.urlopen(req, timeout=TIMEOUT) as r:
-        return json.loads(r.read())
-
-
-def haversine(lat1: float, lon1: float, lat2: float, lon2: float) -> float:
-    """Distance in meters between two coordinates."""
-    R = 6_371_000
-    rlat1, rlat2 = math.radians(lat1), math.radians(lat2)
-    dlat = math.radians(lat2 - lat1)
-    dlon = math.radians(lon2 - lon1)
-    a = math.sin(dlat / 2) ** 2 + math.cos(rlat1) * math.cos(rlat2) * math.sin(dlon / 2) ** 2
-    return R * 2 * math.atan2(math.sqrt(a), math.sqrt(1 - a))
-
-
-def geocode(query: str) -> tuple[float, float]:
-    """Convert address/city/zip to coordinates via Nominatim."""
-    params = urllib.parse.urlencode({"q": query, "format": "json", "limit": 1})
-    results = _http_get(f"{NOMINATIM_URL}?{params}")
-    if not results:
-        print(f"Error: Could not geocode '{query}'. Try a more specific address.", file=sys.stderr)
-        sys.exit(1)
-    return float(results[0]["lat"]), float(results[0]["lon"])
-
-
-def find_nearby(lat: float, lon: float, types: list[str], radius: int = 1500, limit: int = 15) -> list[dict]:
-    """Query Overpass for nearby amenities."""
-    # Build Overpass QL query
-    type_filters = "".join(
-        f'nwr["amenity"="{t}"](around:{radius},{lat},{lon});' for t in types
-    )
-    query = f"[out:json][timeout:{TIMEOUT}];({type_filters});out center tags;"
-
-    # Try each Overpass server
-    data = None
-    for url in OVERPASS_URLS:
-        try:
-            data = _http_post(url, f"data={urllib.parse.quote(query)}")
-            break
-        except Exception:
-            continue
-
-    if not data:
-        return []
-
-    # Parse results
-    places = []
-    for el in data.get("elements", []):
-        tags = el.get("tags", {})
-        name = tags.get("name")
-        if not name:
-            continue
-
-        # Get coordinates (nodes have lat/lon directly, ways/relations use center)
-        plat = el.get("lat") or (el.get("center", {}) or {}).get("lat")
-        plon = el.get("lon") or (el.get("center", {}) or {}).get("lon")
-        if not plat or not plon:
-            continue
-
-        dist = haversine(lat, lon, plat, plon)
-
-        place = {
-            "name": name,
-            "type": tags.get("amenity", ""),
-            "distance_m": round(dist),
-            "lat": plat,
-            "lon": plon,
-            "maps_url": f"https://www.google.com/maps/search/?api=1&query={plat},{plon}",
-            "directions_url": f"https://www.google.com/maps/dir/?api=1&origin={lat},{lon}&destination={plat},{plon}",
-        }
-
-        # Add useful optional fields
-        if tags.get("cuisine"):
-            place["cuisine"] = tags["cuisine"]
-        if tags.get("opening_hours"):
-            place["hours"] = tags["opening_hours"]
-        if tags.get("phone"):
-            place["phone"] = tags["phone"]
-        if tags.get("website"):
-            place["website"] = tags["website"]
-        if tags.get("addr:street"):
-            addr_parts = [tags.get("addr:housenumber", ""), tags.get("addr:street", "")]
-            if tags.get("addr:city"):
-                addr_parts.append(tags["addr:city"])
-            place["address"] = " ".join(p for p in addr_parts if p)
-
-        places.append(place)
-
-    # Sort by distance, limit results
-    places.sort(key=lambda p: p["distance_m"])
-    return places[:limit]
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Find nearby places via OpenStreetMap")
-    parser.add_argument("--lat", type=float, help="Latitude")
-    parser.add_argument("--lon", type=float, help="Longitude")
-    parser.add_argument("--near", type=str, help="Address, city, or zip code (geocoded automatically)")
-    parser.add_argument("--type", action="append", dest="types", default=[], help="Place type (restaurant, cafe, bar, pharmacy, etc.)")
-    parser.add_argument("--radius", type=int, default=1500, help="Search radius in meters (default: 1500)")
-    parser.add_argument("--limit", type=int, default=15, help="Max results (default: 15)")
-    parser.add_argument("--json", action="store_true", dest="json_output", help="Output as JSON")
-    args = parser.parse_args()
-
-    # Resolve coordinates
-    if args.near:
-        lat, lon = geocode(args.near)
-    elif args.lat is not None and args.lon is not None:
-        lat, lon = args.lat, args.lon
-    else:
-        print("Error: Provide --lat/--lon or --near", file=sys.stderr)
-        sys.exit(1)
-
-    if not args.types:
-        args.types = ["restaurant"]
-
-    places = find_nearby(lat, lon, args.types, args.radius, args.limit)
-
-    if args.json_output:
-        print(json.dumps({"origin": {"lat": lat, "lon": lon}, "results": places, "count": len(places)}, indent=2))
-    else:
-        if not places:
-            print(f"No {'/'.join(args.types)} found within {args.radius}m")
-            return
-        print(f"Found {len(places)} places within {args.radius}m:\n")
-        for i, p in enumerate(places, 1):
-            dist_str = f"{p['distance_m']}m" if p["distance_m"] < 1000 else f"{p['distance_m']/1000:.1f}km"
-            print(f"  {i}. {p['name']} ({p['type']}) — {dist_str}")
-            if p.get("cuisine"):
-                print(f"     Cuisine: {p['cuisine']}")
-            if p.get("hours"):
-                print(f"     Hours: {p['hours']}")
-            if p.get("address"):
-                print(f"     Address: {p['address']}")
-            print(f"     Map: {p['maps_url']}")
-            print()
-
-
-if __name__ == "__main__":
-    main()

skills/mcp/native-mcp/SKILL.md

@@ -321,32 +321,6 @@ mcp_servers:
 
 All tools from all servers are registered and available simultaneously. Each server's tools are prefixed with its name to avoid collisions.
 
-## Sampling (Server-Initiated LLM Requests)
-
-Hermes supports MCP's `sampling/createMessage` capability — MCP servers can request LLM completions through the agent during tool execution. This enables agent-in-the-loop workflows (data analysis, content generation, decision-making).
-
-Sampling is **enabled by default**. Configure per server:
-
-```yaml
-mcp_servers:
-  my_server:
-    command: "npx"
-    args: ["-y", "my-mcp-server"]
-    sampling:
-      enabled: true           # default: true
-      model: "gemini-3-flash" # model override (optional)
-      max_tokens_cap: 4096    # max tokens per request
-      timeout: 30             # LLM call timeout (seconds)
-      max_rpm: 10             # max requests per minute
-      allowed_models: []      # model whitelist (empty = all)
-      max_tool_rounds: 5      # tool loop limit (0 = disable)
-      log_level: "info"       # audit verbosity
-```
-
-Servers can also include `tools` in sampling requests for multi-turn tool-augmented workflows. The `max_tool_rounds` config prevents infinite tool loops. Per-server audit metrics (requests, errors, tokens, tool use count) are tracked via `get_mcp_status()`.
-
-Disable sampling for untrusted servers with `sampling: { enabled: false }`.
-
 ## Notes
 
 - MCP tools are called synchronously from the agent's perspective but run asynchronously on a dedicated background event loop

skills/media/DESCRIPTION.md

@@ -1,3 +1 @@
----
-description: Skills for working with media content — YouTube transcripts, GIF search, music generation, and audio visualization.
----
+Media content extraction and transformation tools — YouTube transcripts, audio, video processing.

skills/mlops/axolotl/references/other.md

@@ -1098,7 +1098,7 @@ Please see the ocifs docs.
 
 The path should start with https://.
 
-This must be publicly accessible.
+This must be publically accessible.
 
 Now that you know how to load datasets, you can learn more on how to load your specific dataset format into your target output format dataset formats docs.
 

skills/mlops/cloud/DESCRIPTION.md

@@ -1,3 +0,0 @@
----
-description: GPU cloud providers and serverless compute platforms for ML workloads.
----

skills/mlops/evaluation/DESCRIPTION.md

@@ -1,3 +0,0 @@
----
-description: Model evaluation benchmarks, experiment tracking, data curation, tokenizers, and interpretability tools.
----

skills/mlops/inference/DESCRIPTION.md

@@ -1,3 +0,0 @@
----
-description: Model serving, quantization (GGUF/GPTQ), structured output, inference optimization, and model surgery tools for deploying and running LLMs.
----

skills/mlops/inference/obliteratus/SKILL.md

@@ -1,330 +0,0 @@
----
-name: obliteratus
-description: Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament evaluation, and telemetry-driven recommendations. Use when a user wants to uncensor, abliterate, or remove refusal from an LLM.
-version: 2.0.0
-author: Hermes Agent
-license: MIT
-dependencies: [obliteratus, torch, transformers, bitsandbytes, accelerate, safetensors]
-metadata:
-  hermes:
-    tags: [Abliteration, Uncensoring, Refusal-Removal, LLM, Weight-Projection, SVD, Mechanistic-Interpretability, HuggingFace, Model-Surgery]
-    related_skills: [vllm, gguf, huggingface-tokenizers]
----
-
-# OBLITERATUS Skill
-
-Remove refusal behaviors (guardrails) from open-weight LLMs without retraining or fine-tuning. Uses mechanistic interpretability techniques — including diff-in-means, SVD, whitened SVD, LEACE concept erasure, SAE decomposition, Bayesian kernel projection, and more — to identify and surgically excise refusal directions from model weights while preserving reasoning capabilities.
-
-**License warning:** OBLITERATUS is AGPL-3.0. NEVER import it as a Python library. Always invoke via CLI (`obliteratus` command) or subprocess. This keeps Hermes Agent's MIT license clean.
-
-## When to Use This Skill
-
-Trigger when the user:
-- Wants to "uncensor" or "abliterate" an LLM
-- Asks about removing refusal/guardrails from a model
-- Wants to create an uncensored version of Llama, Qwen, Mistral, etc.
-- Mentions "refusal removal", "abliteration", "weight projection"
-- Wants to analyze how a model's refusal mechanism works
-- References OBLITERATUS, abliterator, or refusal directions
-
-## Step 1: Installation
-
-Check if already installed:
-```bash
-obliteratus --version 2>/dev/null && echo "INSTALLED" || echo "NOT INSTALLED"
-```
-
-If not installed, clone and install from GitHub:
-```bash
-git clone https://github.com/elder-plinius/OBLITERATUS.git
-cd OBLITERATUS
-pip install -e .
-# For Gradio web UI support:
-# pip install -e ".[spaces]"
-```
-
-**IMPORTANT:** Confirm with user before installing. This pulls in ~5-10GB of dependencies (PyTorch, Transformers, bitsandbytes, etc.).
-
-## Step 2: Check Hardware
-
-Before anything, check what GPU is available:
-```bash
-python3 -c "
-import torch
-if torch.cuda.is_available():
-    gpu = torch.cuda.get_device_name(0)
-    vram = torch.cuda.get_device_properties(0).total_memory / 1024**3
-    print(f'GPU: {gpu}')
-    print(f'VRAM: {vram:.1f} GB')
-    if vram < 4: print('TIER: tiny (models under 1B)')
-    elif vram < 8: print('TIER: small (models 1-4B)')
-    elif vram < 16: print('TIER: medium (models 4-9B with 4bit quant)')
-    elif vram < 32: print('TIER: large (models 8-32B with 4bit quant)')
-    else: print('TIER: frontier (models 32B+)')
-else:
-    print('NO GPU - only tiny models (under 1B) on CPU')
-"
-```
-
-### VRAM Requirements (with 4-bit quantization)
-
-| VRAM     | Max Model Size  | Example Models                              |
-|:---------|:----------------|:--------------------------------------------|
-| CPU only | ~1B params      | GPT-2, TinyLlama, SmolLM                    |
-| 4-8 GB   | ~4B params      | Qwen2.5-1.5B, Phi-3.5 mini, Llama 3.2 3B   |
-| 8-16 GB  | ~9B params      | Llama 3.1 8B, Mistral 7B, Gemma 2 9B       |
-| 24 GB    | ~32B params     | Qwen3-32B, Llama 3.1 70B (tight), Command-R |
-| 48 GB+   | ~72B+ params    | Qwen2.5-72B, DeepSeek-R1                    |
-| Multi-GPU| 200B+ params    | Llama 3.1 405B, DeepSeek-V3 (685B MoE)      |
-
-## Step 3: Browse Available Models & Get Recommendations
-
-```bash
-# Browse models by compute tier
-obliteratus models --tier medium
-
-# Get architecture info for a specific model
-obliteratus info <model_name>
-
-# Get telemetry-driven recommendation for best method & params
-obliteratus recommend <model_name>
-obliteratus recommend <model_name> --insights  # global cross-architecture rankings
-```
-
-## Step 4: Choose a Method
-
-### Method Selection Guide
-**Default / recommended for most cases: `advanced`.** It uses multi-direction SVD with norm-preserving projection and is well-tested.
-
-| Situation                         | Recommended Method | Why                                      |
-|:----------------------------------|:-------------------|:-----------------------------------------|
-| Default / most models             | `advanced`         | Multi-direction SVD, norm-preserving, reliable |
-| Quick test / prototyping          | `basic`            | Fast, simple, good enough to evaluate    |
-| Dense model (Llama, Mistral)      | `advanced`         | Multi-direction, norm-preserving         |
-| MoE model (DeepSeek, Mixtral)     | `nuclear`          | Expert-granular, handles MoE complexity  |
-| Reasoning model (R1 distills)     | `surgical`         | CoT-aware, preserves chain-of-thought    |
-| Stubborn refusals persist         | `aggressive`       | Whitened SVD + head surgery + jailbreak   |
-| Want reversible changes           | Use steering vectors (see Analysis section) |
-| Maximum quality, time no object   | `optimized`        | Bayesian search for best parameters      |
-| Experimental auto-detection       | `informed`         | Auto-detects alignment type — experimental, may not always outperform advanced |
-
-### 9 CLI Methods
-- **basic** — Single refusal direction via diff-in-means. Fast (~5-10 min for 8B).
-- **advanced** (DEFAULT, RECOMMENDED) — Multiple SVD directions, norm-preserving projection, 2 refinement passes. Medium speed (~10-20 min).
-- **aggressive** — Whitened SVD + jailbreak-contrastive + attention head surgery. Higher risk of coherence damage.
-- **spectral_cascade** — DCT frequency-domain decomposition. Research/novel approach.
-- **informed** — Runs analysis DURING abliteration to auto-configure. Experimental — slower and less predictable than advanced.
-- **surgical** — SAE features + neuron masking + head surgery + per-expert. Very slow (~1-2 hrs). Best for reasoning models.
-- **optimized** — Bayesian hyperparameter search (Optuna TPE). Longest runtime but finds optimal parameters.
-- **inverted** — Flips the refusal direction. Model becomes actively willing.
-- **nuclear** — Maximum force combo for stubborn MoE models. Expert-granular.
-
-### Direction Extraction Methods (--direction-method flag)
-- **diff_means** (default) — Simple difference-in-means between refused/complied activations. Robust.
-- **svd** — Multi-direction SVD extraction. Better for complex alignment.
-- **leace** — LEACE (Linear Erasure via Closed-form Estimation). Optimal linear erasure.
-
-### 4 Python-API-Only Methods
-(NOT available via CLI — require Python import, which violates AGPL boundary. Mention to user only if they explicitly want to use OBLITERATUS as a library in their own AGPL project.)
-- failspy, gabliteration, heretic, rdo
-
-## Step 5: Run Abliteration
-
-### Standard usage
-```bash
-# Default method (advanced) — recommended for most models
-obliteratus obliterate <model_name> --method advanced --output-dir ./abliterated-models
-
-# With 4-bit quantization (saves VRAM)
-obliteratus obliterate <model_name> --method advanced --quantization 4bit --output-dir ./abliterated-models
-
-# Large models (70B+) — conservative defaults
-obliteratus obliterate <model_name> --method advanced --quantization 4bit --large-model --output-dir ./abliterated-models
-```
-
-### Fine-tuning parameters
-```bash
-obliteratus obliterate <model_name> \
-  --method advanced \
-  --direction-method diff_means \
-  --n-directions 4 \
-  --refinement-passes 2 \
-  --regularization 0.1 \
-  --quantization 4bit \
-  --output-dir ./abliterated-models \
-  --contribute  # opt-in telemetry for community research
-```
-
-### Key flags
-| Flag | Description | Default |
-|:-----|:------------|:--------|
-| `--method` | Abliteration method | advanced |
-| `--direction-method` | Direction extraction | diff_means |
-| `--n-directions` | Number of refusal directions (1-32) | method-dependent |
-| `--refinement-passes` | Iterative passes (1-5) | 2 |
-| `--regularization` | Regularization strength (0.0-1.0) | 0.1 |
-| `--quantization` | Load in 4bit or 8bit | none (full precision) |
-| `--large-model` | Conservative defaults for 120B+ | false |
-| `--output-dir` | Where to save the abliterated model | ./obliterated_model |
-| `--contribute` | Share anonymized results for research | false |
-| `--verify-sample-size` | Number of test prompts for refusal check | 20 |
-| `--dtype` | Model dtype (float16, bfloat16) | auto |
-
-### Other execution modes
-```bash
-# Interactive guided mode (hardware → model → preset)
-obliteratus interactive
-
-# Web UI (Gradio)
-obliteratus ui --port 7860
-
-# Run a full ablation study from YAML config
-obliteratus run config.yaml --preset quick
-
-# Tournament: pit all methods against each other
-obliteratus tourney <model_name>
-```
-
-## Step 6: Verify Results
-
-After abliteration, check the output metrics:
-
-| Metric | Good Value | Warning |
-|:-------|:-----------|:--------|
-| Refusal rate | < 5% (ideally ~0%) | > 10% means refusals persist |
-| Perplexity change | < 10% increase | > 15% means coherence damage |
-| KL divergence | < 0.1 | > 0.5 means significant distribution shift |
-| Coherence | High / passes qualitative check | Degraded responses, repetition |
-
-### If refusals persist (> 10%)
-1. Try `aggressive` method
-2. Increase `--n-directions` (e.g., 8 or 16)
-3. Add `--refinement-passes 3`
-4. Try `--direction-method svd` instead of diff_means
-
-### If coherence is damaged (perplexity > 15% increase)
-1. Reduce `--n-directions` (try 2)
-2. Increase `--regularization` (try 0.3)
-3. Reduce `--refinement-passes` to 1
-4. Try `basic` method (gentler)
-
-## Step 7: Use the Abliterated Model
-
-The output is a standard HuggingFace model directory.
-
-```bash
-# Test locally with transformers
-python3 -c "
-from transformers import AutoModelForCausalLM, AutoTokenizer
-model = AutoModelForCausalLM.from_pretrained('./abliterated-models/<model>')
-tokenizer = AutoTokenizer.from_pretrained('./abliterated-models/<model>')
-inputs = tokenizer('How do I pick a lock?', return_tensors='pt')
-outputs = model.generate(**inputs, max_new_tokens=200)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
-"
-
-# Upload to HuggingFace Hub
-huggingface-cli upload <username>/<model-name>-abliterated ./abliterated-models/<model>
-
-# Serve with vLLM
-vllm serve ./abliterated-models/<model>
-```
-
-## CLI Command Reference
-
-| Command | Description |
-|:--------|:------------|
-| `obliteratus obliterate` | Main abliteration command |
-| `obliteratus info <model>` | Print model architecture details |
-| `obliteratus models --tier <tier>` | Browse curated models by compute tier |
-| `obliteratus recommend <model>` | Telemetry-driven method/param suggestion |
-| `obliteratus interactive` | Guided setup wizard |
-| `obliteratus tourney <model>` | Tournament: all methods head-to-head |
-| `obliteratus run <config.yaml>` | Execute ablation study from YAML |
-| `obliteratus strategies` | List all registered ablation strategies |
-| `obliteratus report <results.json>` | Regenerate visual reports |
-| `obliteratus ui` | Launch Gradio web interface |
-| `obliteratus aggregate` | Summarize community telemetry data |
-
-## Analysis Modules
-
-OBLITERATUS includes 28 analysis modules for mechanistic interpretability.
-See `skill_view(name="obliteratus", file_path="references/analysis-modules.md")` for the full reference.
-
-### Quick analysis commands
-```bash
-# Run specific analysis modules
-obliteratus run analysis-config.yaml --preset quick
-
-# Key modules to run first:
-# - alignment_imprint: Fingerprint DPO/RLHF/CAI/SFT alignment method
-# - concept_geometry: Single direction vs polyhedral cone
-# - logit_lens: Which layer decides to refuse
-# - anti_ouroboros: Self-repair risk score
-# - causal_tracing: Causally necessary components
-```
-
-### Steering Vectors (Reversible Alternative)
-Instead of permanent weight modification, use inference-time steering:
-```python
-# Python API only — for user's own projects
-from obliteratus.analysis.steering_vectors import SteeringVectorFactory, SteeringHookManager
-```
-
-## Ablation Strategies
-
-Beyond direction-based abliteration, OBLITERATUS includes structural ablation strategies:
-- **Embedding Ablation** — Target embedding layer components
-- **FFN Ablation** — Feed-forward network block removal
-- **Head Pruning** — Attention head pruning
-- **Layer Removal** — Full layer removal
-
-List all available: `obliteratus strategies`
-
-## Evaluation
-
-OBLITERATUS includes built-in evaluation tools:
-- Refusal rate benchmarking
-- Perplexity comparison (before/after)
-- LM Eval Harness integration for academic benchmarks
-- Head-to-head competitor comparison
-- Baseline performance tracking
-
-## Platform Support
-
-- **CUDA** — Full support (NVIDIA GPUs)
-- **Apple Silicon (MLX)** — Supported via MLX backend
-- **CPU** — Supported for tiny models (< 1B params)
-
-## YAML Config Templates
-
-Load templates for reproducible runs via `skill_view`:
-- `templates/abliteration-config.yaml` — Standard single-model config
-- `templates/analysis-study.yaml` — Pre-abliteration analysis study
-- `templates/batch-abliteration.yaml` — Multi-model batch processing
-
-## Telemetry
-
-OBLITERATUS can optionally contribute anonymized run data to a global research dataset.
-Enable with `--contribute` flag. No personal data is collected — only model name, method, metrics.
-
-## Common Pitfalls
-
-1. **Don't use `informed` as default** — it's experimental and slower. Use `advanced` for reliable results.
-2. **Models under ~1B respond poorly to abliteration** — their refusal behaviors are shallow and fragmented, making clean direction extraction difficult. Expect partial results (20-40% remaining refusal). Models 3B+ have cleaner refusal directions and respond much better (often 0% refusal with `advanced`).
-3. **`aggressive` can make things worse** — on small models it can damage coherence and actually increase refusal rate. Only use it if `advanced` leaves > 10% refusals on a 3B+ model.
-4. **Always check perplexity** — if it spikes > 15%, the model is damaged. Reduce aggressiveness.
-5. **MoE models need special handling** — use `nuclear` method for Mixtral, DeepSeek-MoE, etc.
-6. **Quantized models can't be re-quantized** — abliterate the full-precision model, then quantize the output.
-7. **VRAM estimation is approximate** — 4-bit quant helps but peak usage can spike during extraction.
-8. **Reasoning models are sensitive** — use `surgical` for R1 distills to preserve chain-of-thought.
-9. **Check `obliteratus recommend`** — telemetry data may have better parameters than defaults.
-10. **AGPL license** — never `import obliteratus` in MIT/Apache projects. CLI invocation only.
-11. **Large models (70B+)** — always use `--large-model` flag for conservative defaults.
-12. **Spectral certification RED is common** — the spectral check often flags "incomplete" even when practical refusal rate is 0%. Check actual refusal rate rather than relying on spectral certification alone.
-
-## Complementary Skills
-
-- **vllm** — Serve abliterated models with high throughput
-- **gguf** — Convert abliterated models to GGUF for llama.cpp
-- **huggingface-tokenizers** — Work with model tokenizers

skills/mlops/inference/obliteratus/references/analysis-modules.md

@@ -1,166 +0,0 @@
-# OBLITERATUS Analysis Modules — Reference
-
-OBLITERATUS includes 28 analysis modules for mechanistic interpretability of refusal in LLMs.
-These modules help understand how and where refusal behaviors are encoded before performing abliteration.
-
----
-
-## Core Analysis (Run These First)
-
-### 1. Alignment Imprint Detection (`alignment_imprint.py`)
-Fingerprints whether a model was trained via DPO, RLHF, CAI, or SFT.
-This determines which extraction strategy will work best.
-
-### 2. Concept Cone Geometry (`concept_geometry.py`)
-Determines if refusal is a single linear direction or a polyhedral cone
-(set of multiple mechanisms). Single-direction models respond well to `basic`;
-polyhedral models need `advanced` or `surgical`.
-
-### 3. Refusal Logit Lens (`logit_lens.py`)
-Identifies the specific layer where a model "decides" to refuse by decoding
-intermediate layer representations into token space.
-
-### 4. Ouroboros Detection (`anti_ouroboros.py`)
-Identifies if a model attempts to "self-repair" refusal behaviors after
-excision. Reports a risk score (0-1). High scores mean additional refinement
-passes are needed.
-
-### 5. Causal Tracing (`causal_tracing.py`)
-Identifies which components (layers, heads, MLPs) are causally necessary
-for refusal behavior using activation patching.
-
----
-
-## Geometric Analysis
-
-### 6. Cross-Layer Alignment (`cross_layer.py`)
-Measures how refusal directions align across different layers. High alignment
-means the refusal signal is consistent; low alignment suggests layer-specific
-mechanisms.
-
-### 7. Residual Stream Decomposition (`residual_stream.py`)
-Decomposes the residual stream into attention and MLP contributions to
-understand which component type contributes more to refusal.
-
-### 8. Riemannian Manifold Geometry (`riemannian_manifold.py`)
-Analyzes the curvature and geometry of the weight manifold near refusal
-directions. Informs how aggressively projections can be applied without
-damaging the manifold structure.
-
-### 9. Whitened SVD (`whitened_svd.py`)
-Covariance-normalized SVD extraction that separates guardrail signals from
-natural activation variance. More precise than standard SVD for models with
-high activation variance.
-
-### 10. Concept Cone Geometry (extended)
-Maps the full polyhedral structure of refusal, including cone angles,
-face counts, and intersection patterns.
-
----
-
-## Probing & Classification
-
-### 11. Activation Probing (`activation_probing.py`)
-Post-excision verification — probes for residual refusal concepts after
-abliteration to ensure complete removal.
-
-### 12. Probing Classifiers (`probing_classifiers.py`)
-Trains linear classifiers to detect refusal in activations. Used both
-before (to verify refusal exists) and after (to verify it's gone).
-
-### 13. Activation Patching (`activation_patching.py`)
-Interchange interventions — swaps activations between refused and complied
-runs to identify causal components.
-
-### 14. Tuned Lens (`tuned_lens.py`)
-Trained version of logit lens that provides more accurate per-layer
-decoding by learning affine transformations for each layer.
-
-### 15. Multi-Token Position Analysis (`multi_token_position.py`)
-Analyzes refusal signals across multiple token positions, not just the
-last token. Important for models that distribute refusal across the sequence.
-
----
-
-## Abliteration & Manipulation
-
-### 16. SAE-Based Abliteration (`sae_abliteration.py`)
-Uses Sparse Autoencoder features to identify and remove specific refusal
-features. More surgical than direction-based methods.
-
-### 17. Steering Vectors (`steering_vectors.py`)
-Creates and applies inference-time steering vectors for reversible refusal
-modification. Includes `SteeringVectorFactory` and `SteeringHookManager`.
-
-### 18. LEACE Concept Erasure (`leace.py`)
-Linear Erasure via Closed-form Estimation — mathematically optimal linear
-concept removal. Available as both analysis module and direction extraction method.
-
-### 19. Sparse Surgery (`sparse_surgery.py`)
-High-precision weight modification targeting individual neurons and
-weight matrix entries rather than full directions.
-
-### 20. Conditional Abliteration (`conditional_abliteration.py`)
-Targeted removal that only affects specific refusal categories while
-preserving others (e.g., remove weapons refusal but keep CSAM refusal).
-
----
-
-## Transfer & Robustness
-
-### 21. Cross-Model Transfer (`cross_model_transfer.py`)
-Tests whether refusal directions extracted from one model transfer to
-another architecture. Measures universality of guardrail directions.
-
-### 22. Defense Robustness (`defense_robustness.py`)
-Evaluates how robust the abliteration is against various defense mechanisms
-and re-alignment attempts.
-
-### 23. Spectral Certification (`spectral_certification.py`)
-Provides mathematical bounds on the completeness of refusal removal
-using spectral analysis of the projection.
-
-### 24. Wasserstein Optimal Extraction (`wasserstein_optimal.py`)
-Uses optimal transport theory for more precise direction extraction
-that minimizes distribution shift.
-
-### 25. Wasserstein Transfer (`wasserstein_transfer.py`)
-Distribution transfer between models using Wasserstein distance
-for cross-architecture refusal direction mapping.
-
----
-
-## Advanced / Research
-
-### 26. Bayesian Kernel Projection (`bayesian_kernel_projection.py`)
-Probabilistic feature mapping that estimates uncertainty in refusal
-direction identification.
-
-### 27. Cross-Model Universality Index
-Measures if guardrail directions generalize across different model
-architectures and training regimes.
-
-### 28. Visualization (`visualization.py`)
-Plotting and graphing utilities for all analysis modules. Generates
-heatmaps, direction plots, and layer-wise analysis charts.
-
----
-
-## Running Analysis
-
-### Via CLI
-```bash
-# Run analysis from a YAML config
-obliteratus run analysis-study.yaml --preset quick
-
-# Available study presets:
-# quick     — Fast sanity check (2-3 modules)
-# full      — All core + geometric analysis
-# jailbreak — Refusal circuit localization
-# knowledge — Knowledge preservation analysis
-# robustness — Stress testing / defense evaluation
-```
-
-### Via YAML Config
-See the `templates/analysis-study.yaml` template for a complete example.
-Load with: `skill_view(name="obliteratus", file_path="templates/analysis-study.yaml")`

skills/mlops/inference/obliteratus/references/methods-guide.md

@@ -1,141 +0,0 @@
-# OBLITERATUS Methods — Detailed Guide
-
-> The CLI accepts 9 methods via `--method`: basic, advanced, aggressive, spectral_cascade,
-> informed, surgical, optimized, inverted, nuclear.
-> Four additional methods (failspy, gabliteration, heretic, rdo) are available only via the Python API.
-
-## How Abliteration Works (Theory)
-
-Abliteration identifies a "refusal direction" — a vector in the model's activation space that
-corresponds to refusal behavior — and projects it out of the weight matrices.
-
-Mathematically: `W_new = W_old - (W_old @ d @ d.T)` where `d` is the refusal direction.
-
-The key challenge is finding accurate refusal directions without damaging other capabilities.
-
----
-
-## Direction Extraction Methods
-
-Before projecting, OBLITERATUS extracts refusal directions using one of three methods:
-
-| Method | Flag | Description | Best For |
-|:-------|:-----|:------------|:---------|
-| Diff-in-Means | `--direction-method diff_means` | Difference between mean activations on refused vs. complied prompts | Default, fast, robust |
-| SVD | `--direction-method svd` | Multi-direction extraction via Singular Value Decomposition | Complex alignment, multiple refusal mechanisms |
-| LEACE | `--direction-method leace` | Linear Erasure via Closed-form Estimation — mathematically optimal | Maximum precision, research |
-
----
-
-## Method Details
-
-### basic
-- **Directions:** 1 (single diff-in-means vector)
-- **Speed:** Fast (~5-10 min for 8B model)
-- **Risk:** Low
-- **Use case:** Quick tests, prototyping, evaluating if abliteration works for a model
-- **How it works:** Extracts one refusal direction and projects it out uniformly across all layers.
-
-### advanced (DEFAULT — RECOMMENDED)
-- **Directions:** 4 (multi-direction SVD)
-- **Speed:** Medium (~10-20 min for 8B model)
-- **Risk:** Low-Medium
-- **Refinement passes:** 2
-- **Use case:** Default for most models. Well-tested and reliable.
-- **How it works:** Extracts multiple refusal directions via SVD, applies norm-preserving bi-projection to maintain weight matrix norms. Two refinement passes catch residual refusal.
-
-### aggressive
-- **Directions:** 8+ (whitened SVD + jailbreak-contrastive)
-- **Speed:** Medium-Slow
-- **Risk:** Medium-High (may damage coherence)
-- **Use case:** When `advanced` leaves > 10% refusals. Stubborn models.
-- **How it works:** Uses whitened SVD for covariance-normalized extraction, adds jailbreak-contrastive directions, performs attention head surgery on the most refusal-active heads.
-
-### spectral_cascade
-- **Speed:** Medium
-- **Risk:** Medium
-- **Use case:** Research, novel approaches
-- **How it works:** DCT (Discrete Cosine Transform) frequency-domain decomposition of refusal signals. Separates high-frequency (surface-level) from low-frequency (deep) refusal patterns.
-
-### informed (EXPERIMENTAL)
-- **Speed:** Slow (~20-40 min for 8B model)
-- **Risk:** Variable — results depend on analysis quality
-- **Use case:** When you want auto-configuration, but be aware this is experimental and may not outperform `advanced`.
-- **How it works:** Runs 4 analysis modules first (alignment imprint, concept geometry, logit lens, ouroboros detection), then auto-configures extraction strategy. Includes an "Ouroboros loop" that detects and counteracts self-repair.
-- **Note:** The auto-detection can sometimes misconfigure. If results are poor, fall back to `advanced`.
-
-### surgical
-- **Speed:** Very slow (~1-2 hrs for 8B model)
-- **Risk:** Low (very precise)
-- **Use case:** Reasoning models (R1 distills, QwQ, etc.) where chain-of-thought must be preserved.
-- **How it works:** Uses SAE (Sparse Autoencoder) features + individual neuron masking + attention head surgery + per-expert decomposition (for MoE). CoT-aware — identifies and protects reasoning-critical directions before projecting.
-
-### optimized
-- **Speed:** Very slow (hours — runs many trials)
-- **Risk:** Low (finds optimal parameters)
-- **Use case:** When quality matters more than speed. Production models.
-- **How it works:** Bayesian hyperparameter search via Optuna TPE sampler. Optimizes n_directions, regularization, refinement passes, and layer selection jointly. Evaluates each configuration on refusal rate + perplexity.
-
-### inverted
-- **Speed:** Fast
-- **Risk:** High (model behavior changes dramatically)
-- **Use case:** Research, studying refusal mechanisms
-- **How it works:** Instead of projecting out the refusal direction, reflects it. The model actively complies rather than passively not-refusing. Useful for understanding the geometry of alignment.
-
-### nuclear
-- **Speed:** Slow
-- **Risk:** Medium-High
-- **Use case:** Stubborn MoE models (DeepSeek-MoE, Mixtral, etc.)
-- **How it works:** Combines expert-granular abliteration (EGA), steering vector injection, attention head pruning, and multi-pass refinement. Decomposes refusal signals into per-expert components for MoE architectures.
-
----
-
-## Method Selection Flowchart
-
-```
-Is this a quick test?
-  → YES: basic
-  → NO: continue
-
-Is it an MoE model (Mixtral, DeepSeek-MoE)?
-  → YES: nuclear
-  → NO: continue
-
-Is it a reasoning model (R1, QwQ, CoT-focused)?
-  → YES: surgical
-  → NO: continue
-
-Do you need the absolute best quality and have time?
-  → YES: optimized
-  → NO: advanced (recommended default)
-
-Did advanced leave > 10% refusals?
-  → YES: aggressive
-  → Still refusing: nuclear
-```
-
----
-
-## Key Parameters
-
-| Parameter | Range | Default | Effect |
-|:----------|:------|:--------|:-------|
-| `--n-directions` | 1-32 | method-dependent | More directions = more complete removal, but higher damage risk |
-| `--regularization` | 0.0-1.0 | 0.1 | Higher = more conservative (less removal, less damage) |
-| `--refinement-passes` | 1-5 | 2 | More passes catch residual refusal, but diminishing returns |
-| `--quantization` | 4bit, 8bit | none | Reduces VRAM usage; quality impact minimal for extraction |
-| `--verify-sample-size` | 10-200 | 20 | More samples = more accurate refusal rate estimate |
-
----
-
-## Troubleshooting
-
-| Problem | Likely Cause | Fix |
-|:--------|:-------------|:----|
-| Refusal rate > 20% | Too few directions | Increase `--n-directions`, try `aggressive` |
-| Refusal rate 5-20% | Residual refusal | Add `--refinement-passes 3`, try `--direction-method svd` |
-| Perplexity spike > 20% | Over-aggressive removal | Reduce `--n-directions`, increase `--regularization` |
-| Repetitive output | Weight matrix damage | Use `basic` with fewer directions, check norm preservation |
-| MoE model still refuses | Non-expert-aware method | Switch to `nuclear` |
-| Reasoning degraded | CoT directions damaged | Use `surgical` method |
-| OOM during extraction | Insufficient VRAM | Add `--quantization 4bit` and/or `--large-model` |