Removing old patches

.env.example

@@ -231,21 +231,6 @@ VOICE_TOOLS_OPENAI_KEY=
 # Slack allowed users (comma-separated Slack user IDs)
 # SLACK_ALLOWED_USERS=
 
-# =============================================================================
-# TELEGRAM INTEGRATION
-# =============================================================================
-# Telegram Bot Token - From @BotFather (https://t.me/BotFather)
-# TELEGRAM_BOT_TOKEN=
-# TELEGRAM_ALLOWED_USERS=                  # Comma-separated user IDs
-# TELEGRAM_HOME_CHANNEL=                   # Default chat for cron delivery
-# TELEGRAM_HOME_CHANNEL_NAME=              # Display name for home channel
-
-# Webhook mode (optional — for cloud deployments like Fly.io/Railway)
-# Default is long polling. Setting TELEGRAM_WEBHOOK_URL switches to webhook mode.
-# TELEGRAM_WEBHOOK_URL=https://my-app.fly.dev/telegram
-# TELEGRAM_WEBHOOK_PORT=8443
-# TELEGRAM_WEBHOOK_SECRET=                 # Recommended for production
-
 # WhatsApp (built-in Baileys bridge — run `hermes whatsapp` to pair)
 # WHATSAPP_ENABLED=false
 # WHATSAPP_ALLOWED_USERS=15551234567

agent/anthropic_adapter.py

@@ -162,21 +162,6 @@ def _is_oauth_token(key: str) -> bool:
     return True
 
 
-def _requires_bearer_auth(base_url: str | None) -> bool:
-    """Return True for Anthropic-compatible providers that require Bearer auth.
-
-    Some third-party /anthropic endpoints implement Anthropic's Messages API but
-    require Authorization: Bearer instead of Anthropic's native x-api-key header.
-    MiniMax's global and China Anthropic-compatible endpoints follow this pattern.
-    """
-    if not base_url:
-        return False
-    normalized = base_url.rstrip("/").lower()
-    return normalized.startswith("https://api.minimax.io/anthropic") or normalized.startswith(
-        "https://api.minimaxi.com/anthropic"
-    )
-
-
 def build_anthropic_client(api_key: str, base_url: str = None):
     """Create an Anthropic client, auto-detecting setup-tokens vs API keys.
 
@@ -195,17 +180,7 @@ def build_anthropic_client(api_key: str, base_url: str = None):
     if base_url:
         kwargs["base_url"] = base_url
 
-    if _requires_bearer_auth(base_url):
-        # Some Anthropic-compatible providers (e.g. MiniMax) expect the API key in
-        # Authorization: Bearer even for regular API keys. Route those endpoints
-        # through auth_token so the SDK sends Bearer auth instead of x-api-key.
-        # Check this before OAuth token shape detection because MiniMax secrets do
-        # not use Anthropic's sk-ant-api prefix and would otherwise be misread as
-        # Anthropic OAuth/setup tokens.
-        kwargs["auth_token"] = api_key
-        if _COMMON_BETAS:
-            kwargs["default_headers"] = {"anthropic-beta": ",".join(_COMMON_BETAS)}
-    elif _is_oauth_token(api_key):
+    if _is_oauth_token(api_key):
         # OAuth access token / setup-token → Bearer auth + Claude Code identity.
         # Anthropic routes OAuth requests based on user-agent and headers;
         # without Claude Code's fingerprint, requests get intermittent 500s.

cli.py

@@ -2837,28 +2837,6 @@ class HermesCLI:
         print("  Example: python cli.py --toolsets web,terminal")
         print()
     
-    def _handle_profile_command(self):
-        """Display active profile name and home directory."""
-        from hermes_constants import get_hermes_home, display_hermes_home
-
-        home = get_hermes_home()
-        display = display_hermes_home()
-
-        profiles_parent = Path.home() / ".hermes" / "profiles"
-        try:
-            rel = home.relative_to(profiles_parent)
-            profile_name = str(rel).split("/")[0]
-        except ValueError:
-            profile_name = None
-
-        print()
-        if profile_name:
-            print(f"  Profile: {profile_name}")
-        else:
-            print("  Profile: default")
-        print(f"  Home:    {display}")
-        print()
-
     def show_config(self):
         """Display current configuration with kawaii ASCII art."""
         # Get terminal config from environment (which was set from cli-config.yaml)
@@ -3701,8 +3679,6 @@ class HermesCLI:
             return False
         elif canonical == "help":
             self.show_help()
-        elif canonical == "profile":
-            self._handle_profile_command()
         elif canonical == "tools":
             self._handle_tools_command(cmd_original)
         elif canonical == "toolsets":
@@ -3860,8 +3836,6 @@ class HermesCLI:
             self.console.print(f"  Status bar {state}")
         elif canonical == "verbose":
             self._toggle_verbose()
-        elif canonical == "yolo":
-            self._toggle_yolo()
         elif canonical == "reasoning":
             self._handle_reasoning_command(cmd_original)
         elif canonical == "compress":
@@ -4460,17 +4434,6 @@ class HermesCLI:
         }
         _cprint(labels.get(self.tool_progress_mode, ""))
 
-    def _toggle_yolo(self):
-        """Toggle YOLO mode — skip all dangerous command approval prompts."""
-        import os
-        current = bool(os.environ.get("HERMES_YOLO_MODE"))
-        if current:
-            os.environ.pop("HERMES_YOLO_MODE", None)
-            self.console.print("  ⚠ YOLO mode [bold red]OFF[/] — dangerous commands will require approval.")
-        else:
-            os.environ["HERMES_YOLO_MODE"] = "1"
-            self.console.print("  ⚡ YOLO mode [bold green]ON[/] — all commands auto-approved. Use with caution.")
-
     def _handle_reasoning_command(self, cmd: str):
         """Handle /reasoning — manage effort level and display toggle.
 
@@ -5597,8 +5560,6 @@ class HermesCLI:
             self.agent = None
 
         # Initialize agent if needed
-        if self.agent is None:
-            _cprint(f"{_DIM}Initializing agent...{_RST}")
         if not self._init_agent(
             model_override=turn_route["model"],
             runtime_override=turn_route["runtime"],

environments/__init__.py

@@ -13,6 +13,7 @@ Core layers:
 Concrete environments:
     - terminal_test_env/: Simple file-creation tasks for testing the stack
     - hermes_swe_env/: SWE-bench style tasks with Modal sandboxes
+    - endless_terminals/: Terminal tasks from HuggingFace dataset with Apptainer containers
 
 Benchmarks (eval-only):
     - benchmarks/terminalbench_2/: Terminal-Bench 2.0 evaluation

environments/endless_terminals/__init__.py

@@ -0,0 +1,5 @@
+"""Endless Terminals Environment - Terminal task training from HuggingFace dataset."""
+
+from .endless_terminals_env import EndlessTerminalsEnv, EndlessTerminalsEnvConfig
+
+__all__ = ["EndlessTerminalsEnv", "EndlessTerminalsEnvConfig"]

environments/endless_terminals/tinker_qwen.yaml

@@ -0,0 +1,91 @@
+# Endless Terminals - Qwen3-4B-Instruct-2507
+# Single config for both trainer (launch_training.py) and env (endless_terminals_env.py serve)
+#
+# Usage:
+#   Terminal 1: run-api
+#   Terminal 2: cd tinker-atropos && python launch_training.py --config ../environments/endless_terminals/tinker_qwen.yaml
+#   Terminal 3: python environments/endless_terminals/endless_terminals_env.py serve --config environments/endless_terminals/tinker_qwen.yaml
+
+env:
+  # Toolsets
+  enabled_toolsets: ["terminal", "file"]
+
+  # Model / tokenizer
+  tokenizer_name: "Qwen/Qwen3-4B-Instruct-2507"
+
+  # Agent configuration
+  max_agent_turns: 16
+  max_token_length: 2048
+  agent_temperature: 0.6
+  extra_body:
+    chat_template_kwargs:
+      enable_thinking: false
+  tool_call_parser: "hermes"
+
+  # Terminal backend
+  terminal_backend: "docker"
+
+  # Dataset settings
+  use_dataset: true
+  dataset_name: "obiwan96/endless-terminals"
+  dataset_split: "train"
+  dataset_cache_dir: "~/.cache/huggingface/datasets"
+  tasks_base_dir: "/Users/samherring/Desktop/Projects/Hermes-Agent/endless-terminals"
+
+  # Test execution
+  test_timeout_s: 180
+  default_docker_image: "ubuntu:22.04"
+  max_concurrent_containers: 16
+
+  # Training configuration
+  group_size: 16
+  batch_size: 64          # 4 groups × 16 rollouts per step
+  total_steps: 500
+  steps_per_eval: 5
+  min_items_sent_before_logging: 1
+  ensure_scores_are_not_same: true
+  max_num_workers: 2048
+  worker_timeout: 3600
+  inference_weight: 1.0
+  eval_limit_ratio: 0.1
+  rollout_server_url: "http://localhost:8000"
+
+  # Evaluation configuration
+  num_eval_tasks: 20
+  eval_split_ratio: 0.1
+
+  # Logging
+  use_wandb: true
+  wandb_name: "endless-terminals-qwen3-4b"
+
+  # System prompt
+  system_prompt: >
+    You are a skilled Linux system administrator and programmer.
+    You have access to a terminal and file tools to complete system administration
+    and programming tasks. Use the tools effectively to solve the given task,
+    and verify your solution works correctly before finishing.
+    Keep each command short and focused — break complex tasks into multiple steps
+    rather than writing long one-liners.
+
+tinker:
+  lora_rank: 32
+  learning_rate: 0.0000005
+  max_token_trainer_length: 32768
+  checkpoint_dir: "./temp/"
+  save_checkpoint_interval: 50
+  wandb_project: "endless-terminals"
+  wandb_group: null
+  wandb_run_name: "qwen3-4b"
+  tool_call_parser: "hermes"
+
+openai:
+  - model_name: "Qwen/Qwen3-4B-Instruct-2507"
+    base_url: "http://localhost:8001/v1"
+    api_key: "x"
+    weight: 1.0
+    num_requests_for_eval: 64
+    timeout: 600
+    server_type: "sglang"
+
+slurm: false
+testing: false

environments/hermes_base_env.py

@@ -298,7 +298,6 @@ class HermesAgentBaseEnv(BaseEnv):
             return False
 
         server = self.server.servers[0]
-        # If the server is an OpenAI server (not VLLM/SGLang), use direct mode
         from atroposlib.envs.server_handling.openai_server import OpenAIServer
         return not isinstance(server, OpenAIServer)
 

environments/tool_call_parsers/hermes_parser.py

@@ -48,7 +48,13 @@ class HermesToolCallParser(ToolCallParser):
                 if not raw_json.strip():
                     continue
 
-                tc_data = json.loads(raw_json)
+                try:
+                    tc_data = json.loads(raw_json)
+                except json.JSONDecodeError:
+                    # Fix invalid backslash escapes from shell commands in JSON strings
+                    # e.g. \s \w \d \n (unescaped) → \\s \\w \\d \\n
+                    fixed = re.sub(r'\\([^"\\/bfnrtu0-9\n])', r'\\\\\1', raw_json)
+                    tc_data = json.loads(fixed)
                 tool_calls.append(
                     ChatCompletionMessageToolCall(
                         id=f"call_{uuid.uuid4().hex[:8]}",

gateway/config.py

@@ -27,16 +27,9 @@ def _coerce_bool(value: Any, default: bool = True) -> bool:
         return default
     if isinstance(value, bool):
         return value
-    if isinstance(value, int):
-        return value != 0
     if isinstance(value, str):
-        lowered = value.strip().lower()
-        if lowered in ("true", "1", "yes", "on"):
-            return True
-        if lowered in ("false", "0", "no", "off"):
-            return False
-        return default
-    return default
+        return value.strip().lower() in ("true", "1", "yes", "on")
+    return bool(value)
 
 
 def _normalize_unauthorized_dm_behavior(value: Any, default: str = "pair") -> str:

gateway/platforms/matrix.py

@@ -49,14 +49,6 @@ _STORE_DIR = _get_hermes_dir("platforms/matrix/store", "matrix/store")
 # Grace period: ignore messages older than this many seconds before startup.
 _STARTUP_GRACE_SECONDS = 5
 
-# E2EE key export file for persistence across restarts.
-_KEY_EXPORT_FILE = _STORE_DIR / "exported_keys.txt"
-_KEY_EXPORT_PASSPHRASE = "hermes-matrix-e2ee-keys"
-
-# Pending undecrypted events: cap and TTL for retry buffer.
-_MAX_PENDING_EVENTS = 100
-_PENDING_EVENT_TTL = 300  # seconds — stop retrying after 5 min
-
 
 def check_matrix_requirements() -> bool:
     """Return True if the Matrix adapter can be used."""
@@ -119,10 +111,6 @@ class MatrixAdapter(BasePlatformAdapter):
         self._processed_events: deque = deque(maxlen=1000)
         self._processed_events_set: set = set()
 
-        # Buffer for undecrypted events pending key receipt.
-        # Each entry: (room, event, timestamp)
-        self._pending_megolm: list = []
-
     def _is_duplicate_event(self, event_id) -> bool:
         """Return True if this event was already processed. Tracks the ID otherwise."""
         if not event_id:
@@ -244,16 +232,6 @@ class MatrixAdapter(BasePlatformAdapter):
                 logger.info("Matrix: E2EE crypto initialized")
             except Exception as exc:
                 logger.warning("Matrix: crypto init issue: %s", exc)
-
-            # Import previously exported Megolm keys (survives restarts).
-            if _KEY_EXPORT_FILE.exists():
-                try:
-                    await client.import_keys(
-                        str(_KEY_EXPORT_FILE), _KEY_EXPORT_PASSPHRASE,
-                    )
-                    logger.info("Matrix: imported Megolm keys from backup")
-                except Exception as exc:
-                    logger.debug("Matrix: could not import keys: %s", exc)
         elif self._encryption:
             logger.warning(
                 "Matrix: E2EE requested but crypto store is not loaded; "
@@ -308,18 +286,6 @@ class MatrixAdapter(BasePlatformAdapter):
             except (asyncio.CancelledError, Exception):
                 pass
 
-        # Export Megolm keys before closing so the next restart can decrypt
-        # events that used sessions from this run.
-        if self._client and self._encryption and getattr(self._client, "olm", None):
-            try:
-                _STORE_DIR.mkdir(parents=True, exist_ok=True)
-                await self._client.export_keys(
-                    str(_KEY_EXPORT_FILE), _KEY_EXPORT_PASSPHRASE,
-                )
-                logger.info("Matrix: exported Megolm keys for next restart")
-            except Exception as exc:
-                logger.debug("Matrix: could not export keys on disconnect: %s", exc)
-
         if self._client:
             await self._client.close()
             self._client = None
@@ -699,22 +665,17 @@ class MatrixAdapter(BasePlatformAdapter):
         Hermes uses a custom sync loop instead of matrix-nio's sync_forever(),
         so we need to explicitly drive the key management work that sync_forever()
         normally handles for encrypted rooms.
-
-        Also auto-trusts all devices (so senders share session keys with us)
-        and retries decryption for any buffered MegolmEvents.
         """
         client = self._client
         if not client or not self._encryption or not getattr(client, "olm", None):
             return
 
-        did_query_keys = client.should_query_keys
-
         tasks = [asyncio.create_task(client.send_to_device_messages())]
 
         if client.should_upload_keys:
             tasks.append(asyncio.create_task(client.keys_upload()))
 
-        if did_query_keys:
+        if client.should_query_keys:
             tasks.append(asyncio.create_task(client.keys_query()))
 
         if client.should_claim_keys:
@@ -730,111 +691,6 @@ class MatrixAdapter(BasePlatformAdapter):
             except Exception as exc:
                 logger.warning("Matrix: E2EE maintenance task failed: %s", exc)
 
-        # After key queries, auto-trust all devices so senders share keys with
-        # us.  For a bot this is the right default — we want to decrypt
-        # everything, not enforce manual verification.
-        if did_query_keys:
-            self._auto_trust_devices()
-
-        # Retry any buffered undecrypted events now that new keys may have
-        # arrived (from key requests, key queries, or to-device forwarding).
-        if self._pending_megolm:
-            await self._retry_pending_decryptions()
-
-    def _auto_trust_devices(self) -> None:
-        """Trust/verify all unverified devices we know about.
-
-        When other clients see our device as verified, they proactively share
-        Megolm session keys with us.  Without this, many clients will refuse
-        to include an unverified device in key distributions.
-        """
-        client = self._client
-        if not client:
-            return
-
-        device_store = getattr(client, "device_store", None)
-        if not device_store:
-            return
-
-        own_device = getattr(client, "device_id", None)
-        trusted_count = 0
-
-        try:
-            # DeviceStore.__iter__ yields OlmDevice objects directly.
-            for device in device_store:
-                if getattr(device, "device_id", None) == own_device:
-                    continue
-                if not getattr(device, "verified", False):
-                    client.verify_device(device)
-                    trusted_count += 1
-        except Exception as exc:
-            logger.debug("Matrix: auto-trust error: %s", exc)
-
-        if trusted_count:
-            logger.info("Matrix: auto-trusted %d new device(s)", trusted_count)
-
-    async def _retry_pending_decryptions(self) -> None:
-        """Retry decrypting buffered MegolmEvents after new keys arrive."""
-        import nio
-
-        client = self._client
-        if not client or not self._pending_megolm:
-            return
-
-        now = time.time()
-        still_pending: list = []
-
-        for room, event, ts in self._pending_megolm:
-            # Drop events that have aged past the TTL.
-            if now - ts > _PENDING_EVENT_TTL:
-                logger.debug(
-                    "Matrix: dropping expired pending event %s (age %.0fs)",
-                    getattr(event, "event_id", "?"), now - ts,
-                )
-                continue
-
-            try:
-                decrypted = client.decrypt_event(event)
-            except Exception:
-                # Still missing the key — keep in buffer.
-                still_pending.append((room, event, ts))
-                continue
-
-            if isinstance(decrypted, nio.MegolmEvent):
-                # decrypt_event returned the same undecryptable event.
-                still_pending.append((room, event, ts))
-                continue
-
-            logger.info(
-                "Matrix: decrypted buffered event %s (%s)",
-                getattr(event, "event_id", "?"),
-                type(decrypted).__name__,
-            )
-
-            # Route to the appropriate handler based on decrypted type.
-            try:
-                if isinstance(decrypted, nio.RoomMessageText):
-                    await self._on_room_message(room, decrypted)
-                elif isinstance(
-                    decrypted,
-                    (nio.RoomMessageImage, nio.RoomMessageAudio,
-                     nio.RoomMessageVideo, nio.RoomMessageFile),
-                ):
-                    await self._on_room_message_media(room, decrypted)
-                else:
-                    logger.debug(
-                        "Matrix: decrypted event %s has unhandled type %s",
-                        getattr(event, "event_id", "?"),
-                        type(decrypted).__name__,
-                    )
-            except Exception as exc:
-                logger.warning(
-                    "Matrix: error processing decrypted event %s: %s",
-                    getattr(event, "event_id", "?"), exc,
-                )
-
-        self._pending_megolm = still_pending
-
     # ------------------------------------------------------------------
     # Event callbacks
     # ------------------------------------------------------------------
@@ -856,29 +712,13 @@ class MatrixAdapter(BasePlatformAdapter):
         if event_ts and event_ts < self._startup_ts - _STARTUP_GRACE_SECONDS:
             return
 
-        # Handle undecryptable MegolmEvents: request the missing session key
-        # and buffer the event for retry once the key arrives.
+        # Handle decrypted MegolmEvents — extract the inner event.
         if isinstance(event, nio.MegolmEvent):
+            # Failed to decrypt.
             logger.warning(
-                "Matrix: could not decrypt event %s in %s — requesting key",
+                "Matrix: could not decrypt event %s in %s",
                 event.event_id, room.room_id,
             )
-
-            # Ask other devices in the room to forward the session key.
-            try:
-                resp = await self._client.request_room_key(event)
-                if hasattr(resp, "event_id") or not isinstance(resp, Exception):
-                    logger.debug(
-                        "Matrix: room key request sent for session %s",
-                        getattr(event, "session_id", "?"),
-                    )
-            except Exception as exc:
-                logger.debug("Matrix: room key request failed: %s", exc)
-
-            # Buffer for retry on next maintenance cycle.
-            self._pending_megolm.append((room, event, time.time()))
-            if len(self._pending_megolm) > _MAX_PENDING_EVENTS:
-                self._pending_megolm = self._pending_megolm[-_MAX_PENDING_EVENTS:]
             return
 
         # Skip edits (m.replace relation).

gateway/platforms/telegram.py

@@ -622,19 +622,10 @@ class TelegramAdapter(BasePlatformAdapter):
             # gateway command there automatically adds it to the Telegram menu.
             try:
                 from telegram import BotCommand
-                from hermes_cli.commands import telegram_menu_commands
-                # Telegram allows up to 100 commands but has an undocumented
-                # payload size limit.  Skill descriptions are truncated to 40
-                # chars in telegram_menu_commands() to fit 100 commands safely.
-                menu_commands, hidden_count = telegram_menu_commands(max_commands=100)
+                from hermes_cli.commands import telegram_bot_commands
                 await self._bot.set_my_commands([
-                    BotCommand(name, desc) for name, desc in menu_commands
+                    BotCommand(name, desc) for name, desc in telegram_bot_commands()
                 ])
-                if hidden_count:
-                    logger.info(
-                        "[%s] Telegram menu: %d commands registered, %d hidden (over 100 limit). Use /commands for full list.",
-                        self.name, len(menu_commands), hidden_count,
-                    )
             except Exception as e:
                 logger.warning(
                     "[%s] Could not register Telegram command menu: %s",

gateway/run.py

@@ -301,50 +301,6 @@ def _resolve_runtime_agent_kwargs() -> dict:
     }
 
 
-def _check_unavailable_skill(command_name: str) -> str | None:
-    """Check if a command matches a known-but-inactive skill.
-
-    Returns a helpful message if the skill exists but is disabled or only
-    available as an optional install. Returns None if no match found.
-    """
-    # Normalize: command uses hyphens, skill names may use hyphens or underscores
-    normalized = command_name.lower().replace("_", "-")
-    try:
-        from tools.skills_tool import SKILLS_DIR, _get_disabled_skill_names
-        disabled = _get_disabled_skill_names()
-
-        # Check disabled built-in skills
-        for skill_md in SKILLS_DIR.rglob("SKILL.md"):
-            if any(part in ('.git', '.github', '.hub') for part in skill_md.parts):
-                continue
-            name = skill_md.parent.name.lower().replace("_", "-")
-            if name == normalized and name in disabled:
-                return (
-                    f"The **{command_name}** skill is installed but disabled.\n"
-                    f"Enable it with: `hermes skills config`"
-                )
-
-        # Check optional skills (shipped with repo but not installed)
-        from hermes_constants import get_hermes_home
-        repo_root = Path(__file__).resolve().parent.parent
-        optional_dir = repo_root / "optional-skills"
-        if optional_dir.exists():
-            for skill_md in optional_dir.rglob("SKILL.md"):
-                name = skill_md.parent.name.lower().replace("_", "-")
-                if name == normalized:
-                    # Build install path: official/<category>/<name>
-                    rel = skill_md.parent.relative_to(optional_dir)
-                    parts = list(rel.parts)
-                    install_path = f"official/{'/'.join(parts)}"
-                    return (
-                        f"The **{command_name}** skill is available but not installed.\n"
-                        f"Install it with: `hermes skills install {install_path}`"
-                    )
-    except Exception:
-        pass
-    return None
-
-
 def _platform_config_key(platform: "Platform") -> str:
     """Map a Platform enum to its config.yaml key (LOCAL→"cli", rest→enum value)."""
     return "cli" if platform == Platform.LOCAL else platform.value
@@ -476,13 +432,6 @@ class GatewayRunner:
         self._honcho_managers: Dict[str, Any] = {}
         self._honcho_configs: Dict[str, Any] = {}
 
-        # Rate-limit compression warning messages sent to users.
-        # Keyed by chat_id — value is the timestamp of the last warning sent.
-        # Prevents the warning from firing on every message when a session
-        # remains above the threshold after compression.
-        self._compression_warn_sent: Dict[str, float] = {}
-        self._compression_warn_cooldown: int = 3600  # seconds (1 hour)
-
         # Ensure tirith security scanner is available (downloads if needed)
         try:
             from tools.tirith_security import ensure_installed
@@ -1702,11 +1651,6 @@ class GatewayRunner:
             # In DMs: offer pairing code. In groups: silently ignore.
             if source.chat_type == "dm" and self._get_unauthorized_dm_behavior(source.platform) == "pair":
                 platform_name = source.platform.value if source.platform else "unknown"
-                # Rate-limit ALL pairing responses (code or rejection) to
-                # prevent spamming the user with repeated messages when
-                # multiple DMs arrive in quick succession.
-                if self.pairing_store._is_rate_limited(platform_name, source.user_id):
-                    return None
                 code = self.pairing_store.generate_code(
                     platform_name, source.user_id, source.user_name or ""
                 )
@@ -1728,8 +1672,6 @@ class GatewayRunner:
                             "Too many pairing requests right now~ "
                             "Please try again later!"
                         )
-                    # Record rate limit so subsequent messages are silently ignored
-                    self.pairing_store._record_rate_limit(platform_name, source.user_id)
             return None
         
         # PRIORITY handling when an agent is already running for this session.
@@ -1875,13 +1817,7 @@ class GatewayRunner:
         
         if canonical == "help":
             return await self._handle_help_command(event)
-
-        if canonical == "commands":
-            return await self._handle_commands_command(event)
         
-        if canonical == "profile":
-            return await self._handle_profile_command(event)
-
         if canonical == "status":
             return await self._handle_status_command(event)
         
@@ -1894,9 +1830,6 @@ class GatewayRunner:
         if canonical == "verbose":
             return await self._handle_verbose_command(event)
 
-        if canonical == "yolo":
-            return await self._handle_yolo_command(event)
-
         if canonical == "provider":
             return await self._handle_provider_command(event)
         
@@ -2041,12 +1974,6 @@ class GatewayRunner:
                     if msg:
                         event.text = msg
                         # Fall through to normal message processing with skill content
-                else:
-                    # Not an active skill — check if it's a known-but-disabled or
-                    # uninstalled skill and give actionable guidance.
-                    _unavail_msg = _check_unavailable_skill(command)
-                    if _unavail_msg:
-                        return _unavail_msg
             except Exception as e:
                 logger.debug("Skill command check failed (non-fatal): %s", e)
         
@@ -2284,29 +2211,6 @@ class GatewayRunner:
                         _hyg_api_key = _hyg_runtime.get("api_key")
                     except Exception:
                         pass
-
-                # Check custom_providers per-model context_length
-                # (same fallback as run_agent.py lines 1171-1189).
-                # Must run after runtime resolution so _hyg_base_url is set.
-                if _hyg_config_context_length is None and _hyg_base_url:
-                    try:
-                        _hyg_custom_providers = _hyg_data.get("custom_providers")
-                        if isinstance(_hyg_custom_providers, list):
-                            for _cp in _hyg_custom_providers:
-                                if not isinstance(_cp, dict):
-                                    continue
-                                _cp_url = (_cp.get("base_url") or "").rstrip("/")
-                                if _cp_url and _cp_url == _hyg_base_url.rstrip("/"):
-                                    _cp_models = _cp.get("models", {})
-                                    if isinstance(_cp_models, dict):
-                                        _cp_model_cfg = _cp_models.get(_hyg_model, {})
-                                        if isinstance(_cp_model_cfg, dict):
-                                            _cp_ctx = _cp_model_cfg.get("context_length")
-                                            if _cp_ctx is not None:
-                                                _hyg_config_context_length = int(_cp_ctx)
-                                    break
-                    except (TypeError, ValueError):
-                        pass
             except Exception:
                 pass
 
@@ -2440,18 +2344,13 @@ class GatewayRunner:
                                         pass
 
                                 # Still too large after compression — warn user
-                                # Rate-limited to once per cooldown period per
-                                # chat to avoid spamming on every message.
                                 if _new_tokens >= _warn_token_threshold:
                                     logger.warning(
                                         "Session hygiene: still ~%s tokens after "
                                         "compression — suggesting /reset",
                                         f"{_new_tokens:,}",
                                     )
-                                    _now = time.time()
-                                    _last_warn = self._compression_warn_sent.get(source.chat_id, 0)
-                                    if _hyg_adapter and _now - _last_warn >= self._compression_warn_cooldown:
-                                        self._compression_warn_sent[source.chat_id] = _now
+                                    if _hyg_adapter:
                                         try:
                                             await _hyg_adapter.send(
                                                 source.chat_id,
@@ -2473,10 +2372,7 @@ class GatewayRunner:
                         if _approx_tokens >= _warn_token_threshold:
                             _hyg_adapter = self.adapters.get(source.platform)
                             _hyg_meta = {"thread_id": source.thread_id} if source.thread_id else None
-                            _now = time.time()
-                            _last_warn = self._compression_warn_sent.get(source.chat_id, 0)
-                            if _hyg_adapter and _now - _last_warn >= self._compression_warn_cooldown:
-                                self._compression_warn_sent[source.chat_id] = _now
+                            if _hyg_adapter:
                                 try:
                                     await _hyg_adapter.send(
                                         source.chat_id,
@@ -3103,36 +2999,6 @@ class GatewayRunner:
             return f"{header}\n\n{session_info}"
         return header
     
-    async def _handle_profile_command(self, event: MessageEvent) -> str:
-        """Handle /profile — show active profile name and home directory."""
-        from hermes_constants import get_hermes_home, display_hermes_home
-        from pathlib import Path
-
-        home = get_hermes_home()
-        display = display_hermes_home()
-
-        # Detect profile name from HERMES_HOME path
-        # Profile paths look like: ~/.hermes/profiles/<name>
-        profiles_parent = Path.home() / ".hermes" / "profiles"
-        try:
-            rel = home.relative_to(profiles_parent)
-            profile_name = str(rel).split("/")[0]
-        except ValueError:
-            profile_name = None
-
-        if profile_name:
-            lines = [
-                f"👤 **Profile:** `{profile_name}`",
-                f"📂 **Home:** `{display}`",
-            ]
-        else:
-            lines = [
-                "👤 **Profile:** default",
-                f"📂 **Home:** `{display}`",
-            ]
-
-        return "\n".join(lines)
-
     async def _handle_status_command(self, event: MessageEvent) -> str:
         """Handle /status command."""
         source = event.source
@@ -3199,68 +3065,11 @@ class GatewayRunner:
             from agent.skill_commands import get_skill_commands
             skill_cmds = get_skill_commands()
             if skill_cmds:
-                lines.append(f"\n⚡ **Skill Commands** ({len(skill_cmds)} active):")
-                # Show first 10, then point to /commands for the rest
-                sorted_cmds = sorted(skill_cmds)
-                for cmd in sorted_cmds[:10]:
-                    lines.append(f"`{cmd}` — {skill_cmds[cmd]['description']}")
-                if len(sorted_cmds) > 10:
-                    lines.append(f"\n... and {len(sorted_cmds) - 10} more. Use `/commands` for the full paginated list.")
-        except Exception:
-            pass
-        return "\n".join(lines)
-
-    async def _handle_commands_command(self, event: MessageEvent) -> str:
-        """Handle /commands [page] - paginated list of all commands and skills."""
-        from hermes_cli.commands import gateway_help_lines
-
-        raw_args = event.get_command_args().strip()
-        if raw_args:
-            try:
-                requested_page = int(raw_args)
-            except ValueError:
-                return "Usage: `/commands [page]`"
-        else:
-            requested_page = 1
-
-        # Build combined entry list: built-in commands + skill commands
-        entries = list(gateway_help_lines())
-        try:
-            from agent.skill_commands import get_skill_commands
-            skill_cmds = get_skill_commands()
-            if skill_cmds:
-                entries.append("")
-                entries.append("⚡ **Skill Commands**:")
+                lines.append(f"\n⚡ **Skill Commands** ({len(skill_cmds)} installed):")
                 for cmd in sorted(skill_cmds):
-                    desc = skill_cmds[cmd].get("description", "").strip() or "Skill command"
-                    entries.append(f"`{cmd}` — {desc}")
+                    lines.append(f"`{cmd}` — {skill_cmds[cmd]['description']}")
         except Exception:
             pass
-
-        if not entries:
-            return "No commands available."
-
-        from gateway.config import Platform
-        page_size = 15 if event.source.platform == Platform.TELEGRAM else 20
-        total_pages = max(1, (len(entries) + page_size - 1) // page_size)
-        page = max(1, min(requested_page, total_pages))
-        start = (page - 1) * page_size
-        page_entries = entries[start:start + page_size]
-
-        lines = [
-            f"📚 **Commands** ({len(entries)} total, page {page}/{total_pages})",
-            "",
-            *page_entries,
-        ]
-        if total_pages > 1:
-            nav_parts = []
-            if page > 1:
-                nav_parts.append(f"`/commands {page - 1}` ← prev")
-            if page < total_pages:
-                nav_parts.append(f"next → `/commands {page + 1}`")
-            lines.extend(["", " | ".join(nav_parts)])
-        if page != requested_page:
-            lines.append(f"_(Requested page {requested_page} was out of range, showing page {page}.)_")
         return "\n".join(lines)
     
     async def _handle_provider_command(self, event: MessageEvent) -> str:
@@ -4190,16 +3999,6 @@ class GatewayRunner:
         else:
             return f"🧠 ✓ Reasoning effort set to `{effort}` (this session only)"
 
-    async def _handle_yolo_command(self, event: MessageEvent) -> str:
-        """Handle /yolo — toggle dangerous command approval bypass."""
-        current = bool(os.environ.get("HERMES_YOLO_MODE"))
-        if current:
-            os.environ.pop("HERMES_YOLO_MODE", None)
-            return "⚠️ YOLO mode **OFF** — dangerous commands will require approval."
-        else:
-            os.environ["HERMES_YOLO_MODE"] = "1"
-            return "⚡ YOLO mode **ON** — all commands auto-approved. Use with caution."
-
     async def _handle_verbose_command(self, event: MessageEvent) -> str:
         """Handle /verbose command — cycle tool progress display mode.
 

hermes_cli/colors.py

@@ -1,24 +1,8 @@
 """Shared ANSI color utilities for Hermes CLI modules."""
 
-import os
 import sys
 
 
-def should_use_color() -> bool:
-    """Return True when colored output is appropriate.
-
-    Respects the NO_COLOR environment variable (https://no-color.org/)
-    and TERM=dumb, in addition to the existing TTY check.
-    """
-    if os.environ.get("NO_COLOR") is not None:
-        return False
-    if os.environ.get("TERM") == "dumb":
-        return False
-    if not sys.stdout.isatty():
-        return False
-    return True
-
-
 class Colors:
     RESET = "\033[0m"
     BOLD = "\033[1m"
@@ -32,7 +16,7 @@ class Colors:
 
 
 def color(text: str, *codes) -> str:
-    """Apply color codes to text (only when color output is appropriate)."""
-    if not should_use_color():
+    """Apply color codes to text (only when output is a TTY)."""
+    if not sys.stdout.isatty():
         return text
     return "".join(codes) + text + Colors.RESET

hermes_cli/commands.py

@@ -71,7 +71,6 @@ COMMAND_REGISTRY: list[CommandDef] = [
                aliases=("q",), args_hint="<prompt>"),
     CommandDef("status", "Show session info", "Session",
                gateway_only=True),
-    CommandDef("profile", "Show active profile name and home directory", "Info"),
     CommandDef("sethome", "Set this chat as the home channel", "Session",
                gateway_only=True, aliases=("set-home",)),
     CommandDef("resume", "Resume a previously-named session", "Session",
@@ -91,8 +90,6 @@ COMMAND_REGISTRY: list[CommandDef] = [
     CommandDef("verbose", "Cycle tool progress display: off -> new -> all -> verbose",
                "Configuration", cli_only=True,
                gateway_config_gate="display.tool_progress_command"),
-    CommandDef("yolo", "Toggle YOLO mode (skip all dangerous command approvals)",
-               "Configuration"),
     CommandDef("reasoning", "Manage reasoning effort and display", "Configuration",
                args_hint="[level|show|hide]",
                subcommands=("none", "low", "minimal", "medium", "high", "xhigh", "show", "hide", "on", "off")),
@@ -121,8 +118,6 @@ COMMAND_REGISTRY: list[CommandDef] = [
                "Tools & Skills", cli_only=True),
 
     # Info
-    CommandDef("commands", "Browse all commands and skills (paginated)", "Info",
-               gateway_only=True, args_hint="[page]"),
     CommandDef("help", "Show available commands", "Info"),
     CommandDef("usage", "Show token usage for the current session", "Info"),
     CommandDef("insights", "Show usage insights and analytics", "Info",
@@ -366,69 +361,6 @@ def telegram_bot_commands() -> list[tuple[str, str]]:
     return result
 
 
-def telegram_menu_commands(max_commands: int = 100) -> tuple[list[tuple[str, str]], int]:
-    """Return Telegram menu commands capped to the Bot API limit.
-
-    Priority order (higher priority = never bumped by overflow):
-      1. Core CommandDef commands (always included)
-      2. Plugin slash commands (take precedence over skills)
-      3. Built-in skill commands (fill remaining slots, alphabetical)
-
-    Skills are the only tier that gets trimmed when the cap is hit.
-    User-installed hub skills are excluded — accessible via /skills.
-
-    Returns:
-        (menu_commands, hidden_count) where hidden_count is the number of
-        skill commands omitted due to the cap.
-    """
-    all_commands = list(telegram_bot_commands())
-
-    # Plugin slash commands get priority over skills
-    try:
-        from hermes_cli.plugins import get_plugin_manager
-        pm = get_plugin_manager()
-        plugin_cmds = getattr(pm, "_plugin_commands", {})
-        for cmd_name in sorted(plugin_cmds):
-            tg_name = cmd_name.replace("-", "_")
-            desc = "Plugin command"
-            if len(desc) > 40:
-                desc = desc[:37] + "..."
-            all_commands.append((tg_name, desc))
-    except Exception:
-        pass
-
-    # Remaining slots go to built-in skill commands (not hub-installed).
-    skill_entries: list[tuple[str, str]] = []
-    try:
-        from agent.skill_commands import get_skill_commands
-        from tools.skills_tool import SKILLS_DIR
-        _skills_dir = str(SKILLS_DIR.resolve())
-        _hub_dir = str((SKILLS_DIR / ".hub").resolve())
-        skill_cmds = get_skill_commands()
-        for cmd_key in sorted(skill_cmds):
-            info = skill_cmds[cmd_key]
-            skill_path = info.get("skill_md_path", "")
-            if not skill_path.startswith(_skills_dir):
-                continue
-            if skill_path.startswith(_hub_dir):
-                continue
-            name = cmd_key.lstrip("/").replace("-", "_")
-            desc = info.get("description", "")
-            # Keep descriptions short — setMyCommands has an undocumented
-            # total payload limit.  40 chars fits 100 commands safely.
-            if len(desc) > 40:
-                desc = desc[:37] + "..."
-            skill_entries.append((name, desc))
-    except Exception:
-        pass
-
-    # Skills fill remaining slots — they're the only tier that gets trimmed
-    remaining_slots = max(0, max_commands - len(all_commands))
-    hidden_count = max(0, len(skill_entries) - remaining_slots)
-    all_commands.extend(skill_entries[:remaining_slots])
-    return all_commands[:max_commands], hidden_count
-
-
 def slack_subcommand_map() -> dict[str, str]:
     """Return subcommand -> /command mapping for Slack /hermes handler.
 

hermes_cli/config.py

@@ -706,14 +706,6 @@ OPTIONAL_ENV_VARS = {
         "password": True,
         "category": "tool",
     },
-    "CAMOFOX_URL": {
-        "description": "Camofox browser server URL for local anti-detection browsing (e.g. http://localhost:9377)",
-        "prompt": "Camofox server URL",
-        "url": "https://github.com/jo-inc/camofox-browser",
-        "tools": ["browser_navigate", "browser_click"],
-        "password": False,
-        "category": "tool",
-    },
     "FAL_KEY": {
         "description": "FAL API key for image generation",
         "prompt": "FAL API key",

hermes_cli/doctor.py

@@ -406,11 +406,8 @@ def run_doctor(args):
     if terminal_env == "docker":
         if shutil.which("docker"):
             # Check if docker daemon is running
-            try:
-                result = subprocess.run(["docker", "info"], capture_output=True, timeout=10)
-            except subprocess.TimeoutExpired:
-                result = None
-            if result is not None and result.returncode == 0:
+            result = subprocess.run(["docker", "info"], capture_output=True)
+            if result.returncode == 0:
                 check_ok("docker", "(daemon running)")
             else:
                 check_fail("docker daemon not running")
@@ -429,16 +426,12 @@ def run_doctor(args):
         ssh_host = os.getenv("TERMINAL_SSH_HOST")
         if ssh_host:
             # Try to connect
-            try:
-                result = subprocess.run(
-                    ["ssh", "-o", "ConnectTimeout=5", "-o", "BatchMode=yes", ssh_host, "echo ok"],
-                    capture_output=True,
-                    text=True,
-                    timeout=15
-                )
-            except subprocess.TimeoutExpired:
-                result = None
-            if result is not None and result.returncode == 0:
+            result = subprocess.run(
+                ["ssh", "-o", "ConnectTimeout=5", "-o", "BatchMode=yes", ssh_host, "echo ok"],
+                capture_output=True,
+                text=True
+            )
+            if result.returncode == 0:
                 check_ok(f"SSH connection to {ssh_host}")
             else:
                 check_fail(f"SSH connection to {ssh_host}")

hermes_cli/setup.py

@@ -601,15 +601,13 @@ def _print_setup_summary(config: dict, hermes_home):
             Path(__file__).parent.parent / "node_modules" / ".bin" / "agent-browser"
         ).exists()
     )
-    if get_env_value("CAMOFOX_URL"):
-        tool_status.append(("Browser Automation (Camofox)", True, None))
-    elif get_env_value("BROWSERBASE_API_KEY"):
+    if get_env_value("BROWSERBASE_API_KEY"):
         tool_status.append(("Browser Automation (Browserbase)", True, None))
     elif _ab_found:
         tool_status.append(("Browser Automation (local)", True, None))
     else:
         tool_status.append(
-            ("Browser Automation", False, "npm install -g agent-browser or set CAMOFOX_URL")
+            ("Browser Automation", False, "npm install -g agent-browser")
         )
 
     # FAL (image generation)

hermes_cli/status.py

@@ -285,31 +285,23 @@ def show_status(args):
             _gw_svc = get_service_name()
         except Exception:
             _gw_svc = "hermes-gateway"
-        try:
-            result = subprocess.run(
-                ["systemctl", "--user", "is-active", _gw_svc],
-                capture_output=True,
-                text=True,
-                timeout=5
-            )
-            is_active = result.stdout.strip() == "active"
-        except subprocess.TimeoutExpired:
-            is_active = False
+        result = subprocess.run(
+            ["systemctl", "--user", "is-active", _gw_svc],
+            capture_output=True,
+            text=True
+        )
+        is_active = result.stdout.strip() == "active"
         print(f"  Status:       {check_mark(is_active)} {'running' if is_active else 'stopped'}")
         print("  Manager:      systemd (user)")
         
     elif sys.platform == 'darwin':
         from hermes_cli.gateway import get_launchd_label
-        try:
-            result = subprocess.run(
-                ["launchctl", "list", get_launchd_label()],
-                capture_output=True,
-                text=True,
-                timeout=5
-            )
-            is_loaded = result.returncode == 0
-        except subprocess.TimeoutExpired:
-            is_loaded = False
+        result = subprocess.run(
+            ["launchctl", "list", get_launchd_label()],
+            capture_output=True,
+            text=True
+        )
+        is_loaded = result.returncode == 0
         print(f"  Status:       {check_mark(is_loaded)} {'loaded' if is_loaded else 'not loaded'}")
         print("  Manager:      launchd")
     else:

hermes_cli/tools_config.py

@@ -273,16 +273,6 @@ TOOL_CATEGORIES = {
                 "browser_provider": "browser-use",
                 "post_setup": "browserbase",
             },
-            {
-                "name": "Camofox",
-                "tag": "Local anti-detection browser (Firefox/Camoufox)",
-                "env_vars": [
-                    {"key": "CAMOFOX_URL", "prompt": "Camofox server URL", "default": "http://localhost:9377",
-                     "url": "https://github.com/jo-inc/camofox-browser"},
-                ],
-                "browser_provider": "camofox",
-                "post_setup": "camofox",
-            },
         ],
     },
     "homeassistant": {
@@ -347,28 +337,6 @@ def _run_post_setup(post_setup_key: str):
         elif not node_modules.exists():
             _print_warning("    Node.js not found - browser tools require: npm install (in hermes-agent directory)")
 
-    elif post_setup_key == "camofox":
-        camofox_dir = PROJECT_ROOT / "node_modules" / "@askjo" / "camoufox-browser"
-        if not camofox_dir.exists() and shutil.which("npm"):
-            _print_info("    Installing Camofox browser server...")
-            import subprocess
-            result = subprocess.run(
-                ["npm", "install", "--silent"],
-                capture_output=True, text=True, cwd=str(PROJECT_ROOT)
-            )
-            if result.returncode == 0:
-                _print_success("    Camofox installed")
-            else:
-                _print_warning("    npm install failed - run manually: npm install")
-        if camofox_dir.exists():
-            _print_info("    Start the Camofox server:")
-            _print_info("      npx @askjo/camoufox-browser")
-            _print_info("    First run downloads the Camoufox engine (~300MB)")
-            _print_info("    Or use Docker: docker run -p 9377:9377 jo-inc/camofox-browser")
-        elif not shutil.which("npm"):
-            _print_warning("    Node.js not found. Install Camofox via Docker:")
-            _print_info("      docker run -p 9377:9377 jo-inc/camofox-browser")
-
     elif post_setup_key == "rl_training":
         try:
             __import__("tinker_atropos")
@@ -597,9 +565,7 @@ def _toolset_has_keys(ts_key: str) -> bool:
     if cat:
         for provider in cat.get("providers", []):
             env_vars = provider.get("env_vars", [])
-            if not env_vars:
-                return True  # No-key provider (e.g. Local Browser, Edge TTS)
-            if all(get_env_value(e["key"]) for e in env_vars):
+            if env_vars and all(get_env_value(e["key"]) for e in env_vars):
                 return True
         return False
 

honcho_integration/cli.py

@@ -10,27 +10,16 @@ import os
 import sys
 from pathlib import Path
 
-from hermes_constants import get_hermes_home
 from honcho_integration.client import resolve_config_path, GLOBAL_CONFIG_PATH
 
 HOST = "hermes"
 
 
 def _config_path() -> Path:
-    """Return the active Honcho config path for reading (instance-local or global)."""
+    """Return the active Honcho config path (instance-local or global)."""
     return resolve_config_path()
 
 
-def _local_config_path() -> Path:
-    """Return the instance-local Honcho config path for writing.
-
-    Always returns $HERMES_HOME/honcho.json so each profile/instance gets
-    its own config file.  The global ~/.honcho/config.json is only used as
-    a read fallback (via resolve_config_path) for cross-app interop.
-    """
-    return get_hermes_home() / "honcho.json"
-
-
 def _read_config() -> dict:
     path = _config_path()
     if path.exists():
@@ -42,7 +31,7 @@ def _read_config() -> dict:
 
 
 def _write_config(cfg: dict, path: Path | None = None) -> None:
-    path = path or _local_config_path()
+    path = path or _config_path()
     path.parent.mkdir(parents=True, exist_ok=True)
     path.write_text(
         json.dumps(cfg, indent=2, ensure_ascii=False) + "\n",
@@ -106,13 +95,13 @@ def cmd_setup(args) -> None:
     """Interactive Honcho setup wizard."""
     cfg = _read_config()
 
-    write_path = _local_config_path()
-    read_path = _config_path()
+    active_path = _config_path()
     print("\nHoncho memory setup\n" + "─" * 40)
     print("  Honcho gives Hermes persistent cross-session memory.")
-    print(f"  Config: {write_path}")
-    if read_path != write_path and read_path.exists():
-        print(f"  (seeding from existing config at {read_path})")
+    if active_path != GLOBAL_CONFIG_PATH:
+        print(f"  Instance config: {active_path}")
+    else:
+        print("  Config is shared with other hosts at ~/.honcho/config.json")
     print()
 
     if not _ensure_sdk_installed():
@@ -200,7 +189,7 @@ def cmd_setup(args) -> None:
     hermes_host.setdefault("saveMessages", True)
 
     _write_config(cfg)
-    print(f"\n  Config written to {write_path}")
+    print(f"\n  Config written to {active_path}")
 
     # Test connection
     print("  Testing connection... ", end="", flush=True)
@@ -248,7 +237,6 @@ def cmd_status(args) -> None:
     cfg = _read_config()
 
     active_path = _config_path()
-    write_path = _local_config_path()
 
     if not cfg:
         print(f"  No Honcho config found at {active_path}")
@@ -271,8 +259,6 @@ def cmd_status(args) -> None:
     print(f"  Workspace:      {hcfg.workspace_id}")
     print(f"  Host:           {hcfg.host}")
     print(f"  Config path:    {active_path}")
-    if write_path != active_path:
-        print(f"  Write path:     {write_path}  (instance-local)")
     print(f"  AI peer:        {hcfg.ai_peer}")
     print(f"  User peer:      {hcfg.peer_name or 'not set'}")
     print(f"  Session key:    {hcfg.resolve_session_name()}")

package.json

@@ -16,8 +16,7 @@
   },
   "homepage": "https://github.com/NousResearch/Hermes-Agent#readme",
   "dependencies": {
-    "agent-browser": "^0.13.0",
-    "@askjo/camoufox-browser": "^1.0.0"
+    "agent-browser": "^0.13.0"
   },
   "engines": {
     "node": ">=18.0.0"

run_agent.py

@@ -5221,8 +5221,11 @@ class AIAgent:
             except Exception as e:
                 logger.warning("Session DB compression split failed — new session will NOT be indexed: %s", e)
 
-        # Update token estimate after compaction so pressure calculations
-        # use the post-compression count, not the stale pre-compression one.
+        # Reset context pressure warning and token estimate — usage drops
+        # after compaction.  Without this, the stale last_prompt_tokens from
+        # the previous API call causes the pressure calculation to stay at
+        # >1000% and spam warnings / re-trigger compression in a loop.
+        self._context_pressure_warned = False
         _compressed_est = (
             estimate_tokens_rough(new_system_prompt)
             + estimate_messages_tokens_rough(compressed)
@@ -5230,16 +5233,6 @@ class AIAgent:
         self.context_compressor.last_prompt_tokens = _compressed_est
         self.context_compressor.last_completion_tokens = 0
 
-        # Only reset the pressure warning if compression actually brought
-        # us below the warning level (85% of threshold).  When compression
-        # can't reduce enough (e.g. threshold is very low, or system prompt
-        # alone exceeds the warning level), keep the flag set to prevent
-        # spamming the user with repeated warnings every loop iteration.
-        if self.context_compressor.threshold_tokens > 0:
-            _post_progress = _compressed_est / self.context_compressor.threshold_tokens
-            if _post_progress < 0.85:
-                self._context_pressure_warned = False
-
         return compressed, new_system_prompt
 
     def _execute_tool_calls(self, assistant_message, messages: list, effective_task_id: str, api_call_count: int = 0) -> None:

scripts/install.sh

@@ -94,7 +94,7 @@ print_banner() {
     echo ""
     echo -e "${MAGENTA}${BOLD}"
     echo "┌─────────────────────────────────────────────────────────┐"
-    echo "│             ⚕ Hermes Agent Installer                    │"
+    echo "│             ⚕ Hermes Agent Installer                   │"
     echo "├─────────────────────────────────────────────────────────┤"
     echo "│  An open source AI agent by Nous Research.              │"
     echo "└─────────────────────────────────────────────────────────┘"
@@ -699,19 +699,14 @@ install_deps() {
 
     # Install the main package in editable mode with all extras.
     # Try [all] first, fall back to base install if extras have issues.
-    ALL_INSTALL_LOG=$(mktemp)
-    if ! $UV_CMD pip install -e ".[all]" 2>"$ALL_INSTALL_LOG"; then
+    if ! $UV_CMD pip install -e ".[all]" 2>/dev/null; then
         log_warn "Full install (.[all]) failed, trying base install..."
-        log_info "Reason: $(tail -5 "$ALL_INSTALL_LOG" | head -3)"
-        rm -f "$ALL_INSTALL_LOG"
         if ! $UV_CMD pip install -e "."; then
             log_error "Package installation failed."
             log_info "Check that build tools are installed: sudo apt install build-essential python3-dev"
             log_info "Then re-run: cd $INSTALL_DIR && uv pip install -e '.[all]'"
             exit 1
         fi
-    else
-        rm -f "$ALL_INSTALL_LOG"
     fi
 
     log_success "Main package installed"
@@ -1075,14 +1070,7 @@ print_success() {
     echo ""
     echo -e "${YELLOW}⚡ Reload your shell to use 'hermes' command:${NC}"
     echo ""
-    LOGIN_SHELL="$(basename "${SHELL:-/bin/bash}")"
-    if [ "$LOGIN_SHELL" = "zsh" ]; then
-        echo "   source ~/.zshrc"
-    elif [ "$LOGIN_SHELL" = "bash" ]; then
-        echo "   source ~/.bashrc"
-    else
-        echo "   source ~/.bashrc   # or ~/.zshrc"
-    fi
+    echo "   source ~/.bashrc   # or ~/.zshrc"
     echo ""
 
     # Show Node.js warning if auto-install failed

skills/creative/ascii-video/references/composition.md

@@ -744,149 +744,3 @@ class PixelBlendStack:
             result = blend_canvas(result, canvas, mode, opacity)
         return result
 ```
-
-## Text Backdrop (Readability Mask)
-
-When placing readable text over busy multi-grid ASCII backgrounds, the text will blend into the background and become illegible. **Always apply a dark backdrop behind text regions.**
-
-The technique: compute the bounding box of all text glyphs, create a gaussian-blurred dark mask covering that area with padding, and multiply the background by `(1 - mask * darkness)` before rendering text on top.
-
-```python
-from scipy.ndimage import gaussian_filter
-
-def apply_text_backdrop(canvas, glyphs, padding=80, darkness=0.75):
-    """Darken the background behind text for readability.
-    
-    Call AFTER rendering background, BEFORE rendering text.
-    
-    Args:
-        canvas: (VH, VW, 3) uint8 background
-        glyphs: list of {"x": float, "y": float, ...} glyph positions
-        padding: pixel padding around text bounding box
-        darkness: 0.0 = no darkening, 1.0 = fully black
-    Returns:
-        darkened canvas (uint8)
-    """
-    if not glyphs:
-        return canvas
-    xs = [g['x'] for g in glyphs]
-    ys = [g['y'] for g in glyphs]
-    x0 = max(0, int(min(xs)) - padding)
-    y0 = max(0, int(min(ys)) - padding)
-    x1 = min(VW, int(max(xs)) + padding + 50)   # extra for char width
-    y1 = min(VH, int(max(ys)) + padding + 60)   # extra for char height
-    
-    # Soft dark mask with gaussian blur for feathered edges
-    mask = np.zeros((VH, VW), dtype=np.float32)
-    mask[y0:y1, x0:x1] = 1.0
-    mask = gaussian_filter(mask, sigma=padding * 0.6)
-    
-    factor = 1.0 - mask * darkness
-    return (canvas.astype(np.float32) * factor[:, :, np.newaxis]).astype(np.uint8)
-```
-
-### Usage in render pipeline
-
-Insert between background rendering and text rendering:
-
-```python
-# 1. Render background (multi-grid ASCII effects)
-bg = render_background(cfg, t)
-
-# 2. Darken behind text region
-bg = apply_text_backdrop(bg, frame_glyphs, padding=80, darkness=0.75)
-
-# 3. Render text on top (now readable against dark backdrop)
-bg = text_renderer.render(bg, frame_glyphs, color=(255, 255, 255))
-```
-
-Combine with **reverse vignette** (see shaders.md) for scenes where text is always centered — the reverse vignette provides a persistent center-dark zone, while the backdrop handles per-frame glyph positions.
-
-## External Layout Oracle Pattern
-
-For text-heavy videos where text needs to dynamically reflow around obstacles (shapes, icons, other text), use an external layout engine to pre-compute glyph positions and feed them into the Python renderer via JSON.
-
-### Architecture
-
-```
-Layout Engine (browser/Node.js)  →  layouts.json  →  Python ASCII Renderer
-         ↑                                                    ↑
-   Computes per-frame                               Reads glyph positions,
-   glyph (x,y) positions                            renders as ASCII chars
-   with obstacle-aware reflow                        with full effect pipeline
-```
-
-### JSON interchange format
-
-```json
-{
-  "meta": {
-    "canvas_width": 1080, "canvas_height": 1080,
-    "fps": 24, "total_frames": 1248,
-    "fonts": {
-      "body": {"charW": 12.04, "charH": 24, "fontSize": 20},
-      "hero": {"charW": 24.08, "charH": 48, "fontSize": 40}
-    }
-  },
-  "scenes": [
-    {
-      "id": "scene_name",
-      "start_frame": 0, "end_frame": 96,
-      "frames": {
-        "0": {
-          "glyphs": [
-            {"char": "H", "x": 287.1, "y": 400.0, "alpha": 1.0},
-            {"char": "e", "x": 311.2, "y": 400.0, "alpha": 1.0}
-          ],
-          "obstacles": [
-            {"type": "circle", "cx": 540, "cy": 540, "r": 80},
-            {"type": "rect", "x": 300, "y": 500, "w": 120, "h": 80}
-          ]
-        }
-      }
-    }
-  ]
-}
-```
-
-### When to use
-
-- Text that dynamically reflows around moving objects
-- Per-glyph animation (reveal, scatter, physics)
-- Variable typography that needs precise measurement
-- Any case where Python's Pillow text layout is insufficient
-
-### When NOT to use
-
-- Static centered text (just use PIL `draw.text()` directly)
-- Text that only fades in/out without spatial animation
-- Simple typewriter effects (handle in Python with a character counter)
-
-### Running the oracle
-
-Use Playwright to run the layout engine in a headless browser:
-
-```javascript
-// extract.mjs
-import { chromium } from 'playwright';
-const browser = await chromium.launch({ headless: true });
-const page = await browser.newPage();
-await page.goto(`file://${oraclePath}`);
-await page.waitForFunction(() => window.__ORACLE_DONE__ === true, null, { timeout: 60000 });
-const result = await page.evaluate(() => window.__ORACLE_RESULT__);
-writeFileSync('layouts.json', JSON.stringify(result));
-await browser.close();
-```
-
-### Consuming in Python
-
-```python
-# In the renderer, map pixel positions to the canvas:
-for glyph in frame_data['glyphs']:
-    char, px, py = glyph['char'], glyph['x'], glyph['y']
-    alpha = glyph.get('alpha', 1.0)
-    # Render using PIL draw.text() at exact pixel position
-    draw.text((px, py), char, fill=(int(255*alpha),)*3, font=font)
-```
-
-Obstacles from the JSON can also be rendered as glowing ASCII shapes (circles, rectangles) to visualize the reflow zones.

skills/creative/ascii-video/references/shaders.md

@@ -834,39 +834,6 @@ def sh_vignette(c, s=0.22):
     return np.clip(c * _vig_cache[k][:,:,None], 0, 255).astype(np.uint8)
 ```
 
-#### Reverse Vignette
-
-Inverted vignette: darkens the **center** and leaves edges bright. Useful when text is centered over busy backgrounds — creates a natural dark zone for readability without a hard-edged box.
-
-Combine with `apply_text_backdrop()` (see composition.md) for per-frame glyph-aware darkening.
-
-```python
-_rvignette_cache = {}
-
-def sh_reverse_vignette(c, strength=0.5):
-    """Center darkening, edge brightening. Cached."""
-    k = ('rv', c.shape[0], c.shape[1], round(strength, 2))
-    if k not in _rvignette_cache:
-        h, w = c.shape[:2]
-        Y = np.linspace(-1, 1, h)[:, None]
-        X = np.linspace(-1, 1, w)[None, :]
-        d = np.sqrt(X**2 + Y**2)
-        # Invert: bright at edges, dark at center
-        mask = np.clip(1.0 - (1.0 - d * 0.7) * strength, 0.2, 1.0)
-        _rvignette_cache[k] = mask[:, :, np.newaxis].astype(np.float32)
-    return np.clip(c.astype(np.float32) * _rvignette_cache[k], 0, 255).astype(np.uint8)
-```
-
-| Param | Default | Effect |
-|-------|---------|--------|
-| `strength` | 0.5 | 0 = no effect, 1.0 = center nearly black |
-
-Add to ShaderChain dispatch:
-```python
-elif name == "reverse_vignette":
-    return sh_reverse_vignette(canvas, kwargs.get("strength", 0.5))
-```
-
 #### Contrast
 ```python
 def sh_contrast(c, factor=1.3):

skills/creative/ascii-video/references/troubleshooting.md

@@ -14,8 +14,6 @@
 | Random dark holes in output | Font missing Unicode glyphs | Validate palettes at init |
 | Audio-visual desync | Frame timing accumulation | Use integer frame counter, compute t fresh each frame |
 | Single-color flat output | Hue field shape mismatch | Ensure h,s,v arrays all (rows,cols) before hsv2rgb |
-| Text unreadable over busy bg | No contrast between text and background | Use `apply_text_backdrop()` (composition.md) + `reverse_vignette` shader (shaders.md) |
-| Text garbled/mirrored | Kaleidoscope or mirror shader applied to text scene | **Never apply kaleidoscope, mirror_h/v/quad/diag to scenes with readable text** — radial folding destroys legibility. Apply these only to background layers or text-free scenes |
 
 Common bugs, gotchas, and platform-specific issues encountered during ASCII video development.
 

tests/gateway/test_matrix.py

@@ -643,353 +643,3 @@ class TestMatrixEncryptedSendFallback:
         assert fake_client.room_send.await_count == 2
         second_call = fake_client.room_send.await_args_list[1]
         assert second_call.kwargs.get("ignore_unverified_devices") is True
-
-
-# ---------------------------------------------------------------------------
-# E2EE: Auto-trust devices
-# ---------------------------------------------------------------------------
-
-class TestMatrixAutoTrustDevices:
-    def test_auto_trust_verifies_unverified_devices(self):
-        adapter = _make_adapter()
-
-        # DeviceStore.__iter__ yields OlmDevice objects directly.
-        device_a = MagicMock()
-        device_a.device_id = "DEVICE_A"
-        device_a.verified = False
-        device_b = MagicMock()
-        device_b.device_id = "DEVICE_B"
-        device_b.verified = True  # already trusted
-        device_c = MagicMock()
-        device_c.device_id = "DEVICE_C"
-        device_c.verified = False
-
-        fake_client = MagicMock()
-        fake_client.device_id = "OWN_DEVICE"
-        fake_client.verify_device = MagicMock()
-
-        # Simulate DeviceStore iteration (yields OlmDevice objects)
-        fake_client.device_store = MagicMock()
-        fake_client.device_store.__iter__ = MagicMock(
-            return_value=iter([device_a, device_b, device_c])
-        )
-
-        adapter._client = fake_client
-        adapter._auto_trust_devices()
-
-        # Should have verified device_a and device_c (not device_b, already verified)
-        assert fake_client.verify_device.call_count == 2
-        verified_devices = [call.args[0] for call in fake_client.verify_device.call_args_list]
-        assert device_a in verified_devices
-        assert device_c in verified_devices
-        assert device_b not in verified_devices
-
-    def test_auto_trust_skips_own_device(self):
-        adapter = _make_adapter()
-
-        own_device = MagicMock()
-        own_device.device_id = "MY_DEVICE"
-        own_device.verified = False
-
-        fake_client = MagicMock()
-        fake_client.device_id = "MY_DEVICE"
-        fake_client.verify_device = MagicMock()
-
-        fake_client.device_store = MagicMock()
-        fake_client.device_store.__iter__ = MagicMock(
-            return_value=iter([own_device])
-        )
-
-        adapter._client = fake_client
-        adapter._auto_trust_devices()
-
-        fake_client.verify_device.assert_not_called()
-
-    def test_auto_trust_handles_missing_device_store(self):
-        adapter = _make_adapter()
-        fake_client = MagicMock(spec=[])  # empty spec — no attributes
-        adapter._client = fake_client
-        # Should not raise
-        adapter._auto_trust_devices()
-
-
-# ---------------------------------------------------------------------------
-# E2EE: MegolmEvent key request + buffering
-# ---------------------------------------------------------------------------
-
-class TestMatrixMegolmEventHandling:
-    @pytest.mark.asyncio
-    async def test_megolm_event_requests_room_key_and_buffers(self):
-        adapter = _make_adapter()
-        adapter._user_id = "@bot:example.org"
-        adapter._startup_ts = 0.0
-        adapter._dm_rooms = {}
-
-        fake_megolm = MagicMock()
-        fake_megolm.sender = "@alice:example.org"
-        fake_megolm.event_id = "$encrypted_event"
-        fake_megolm.server_timestamp = 9999999999000  # future
-        fake_megolm.session_id = "SESSION123"
-
-        fake_room = MagicMock()
-        fake_room.room_id = "!room:example.org"
-
-        fake_client = MagicMock()
-        fake_client.request_room_key = AsyncMock(return_value=MagicMock())
-        adapter._client = fake_client
-
-        # Create a MegolmEvent class for isinstance check
-        fake_nio = MagicMock()
-        FakeMegolmEvent = type("MegolmEvent", (), {})
-        fake_megolm.__class__ = FakeMegolmEvent
-        fake_nio.MegolmEvent = FakeMegolmEvent
-
-        with patch.dict("sys.modules", {"nio": fake_nio}):
-            await adapter._on_room_message(fake_room, fake_megolm)
-
-        # Should have requested the room key
-        fake_client.request_room_key.assert_awaited_once_with(fake_megolm)
-
-        # Should have buffered the event
-        assert len(adapter._pending_megolm) == 1
-        room, event, ts = adapter._pending_megolm[0]
-        assert room is fake_room
-        assert event is fake_megolm
-
-    @pytest.mark.asyncio
-    async def test_megolm_buffer_capped(self):
-        adapter = _make_adapter()
-        adapter._user_id = "@bot:example.org"
-        adapter._startup_ts = 0.0
-        adapter._dm_rooms = {}
-
-        fake_client = MagicMock()
-        fake_client.request_room_key = AsyncMock(return_value=MagicMock())
-        adapter._client = fake_client
-
-        FakeMegolmEvent = type("MegolmEvent", (), {})
-        fake_nio = MagicMock()
-        fake_nio.MegolmEvent = FakeMegolmEvent
-
-        # Fill the buffer past max
-        from gateway.platforms.matrix import _MAX_PENDING_EVENTS
-        with patch.dict("sys.modules", {"nio": fake_nio}):
-            for i in range(_MAX_PENDING_EVENTS + 10):
-                evt = MagicMock()
-                evt.__class__ = FakeMegolmEvent
-                evt.sender = "@alice:example.org"
-                evt.event_id = f"$event_{i}"
-                evt.server_timestamp = 9999999999000
-                evt.session_id = f"SESSION_{i}"
-                room = MagicMock()
-                room.room_id = "!room:example.org"
-                await adapter._on_room_message(room, evt)
-
-        assert len(adapter._pending_megolm) == _MAX_PENDING_EVENTS
-
-
-# ---------------------------------------------------------------------------
-# E2EE: Retry pending decryptions
-# ---------------------------------------------------------------------------
-
-class TestMatrixRetryPendingDecryptions:
-    @pytest.mark.asyncio
-    async def test_successful_decryption_routes_to_text_handler(self):
-        import time as _time
-
-        adapter = _make_adapter()
-        adapter._user_id = "@bot:example.org"
-        adapter._startup_ts = 0.0
-        adapter._dm_rooms = {}
-
-        # Create types
-        FakeMegolmEvent = type("MegolmEvent", (), {})
-        FakeRoomMessageText = type("RoomMessageText", (), {})
-
-        decrypted_event = MagicMock()
-        decrypted_event.__class__ = FakeRoomMessageText
-
-        fake_megolm = MagicMock()
-        fake_megolm.__class__ = FakeMegolmEvent
-        fake_megolm.event_id = "$encrypted"
-
-        fake_room = MagicMock()
-        now = _time.time()
-
-        adapter._pending_megolm = [(fake_room, fake_megolm, now)]
-
-        fake_client = MagicMock()
-        fake_client.decrypt_event = MagicMock(return_value=decrypted_event)
-        adapter._client = fake_client
-
-        fake_nio = MagicMock()
-        fake_nio.MegolmEvent = FakeMegolmEvent
-        fake_nio.RoomMessageText = FakeRoomMessageText
-        fake_nio.RoomMessageImage = type("RoomMessageImage", (), {})
-        fake_nio.RoomMessageAudio = type("RoomMessageAudio", (), {})
-        fake_nio.RoomMessageVideo = type("RoomMessageVideo", (), {})
-        fake_nio.RoomMessageFile = type("RoomMessageFile", (), {})
-
-        with patch.dict("sys.modules", {"nio": fake_nio}):
-            with patch.object(adapter, "_on_room_message", AsyncMock()) as mock_handler:
-                await adapter._retry_pending_decryptions()
-                mock_handler.assert_awaited_once_with(fake_room, decrypted_event)
-
-        # Buffer should be empty now
-        assert len(adapter._pending_megolm) == 0
-
-    @pytest.mark.asyncio
-    async def test_still_undecryptable_stays_in_buffer(self):
-        import time as _time
-
-        adapter = _make_adapter()
-
-        FakeMegolmEvent = type("MegolmEvent", (), {})
-
-        fake_megolm = MagicMock()
-        fake_megolm.__class__ = FakeMegolmEvent
-        fake_megolm.event_id = "$still_encrypted"
-
-        now = _time.time()
-        adapter._pending_megolm = [(MagicMock(), fake_megolm, now)]
-
-        fake_client = MagicMock()
-        # decrypt_event raises when key is still missing
-        fake_client.decrypt_event = MagicMock(side_effect=Exception("missing key"))
-        adapter._client = fake_client
-
-        fake_nio = MagicMock()
-        fake_nio.MegolmEvent = FakeMegolmEvent
-
-        with patch.dict("sys.modules", {"nio": fake_nio}):
-            await adapter._retry_pending_decryptions()
-
-        assert len(adapter._pending_megolm) == 1
-
-    @pytest.mark.asyncio
-    async def test_expired_events_dropped(self):
-        import time as _time
-
-        adapter = _make_adapter()
-
-        from gateway.platforms.matrix import _PENDING_EVENT_TTL
-
-        fake_megolm = MagicMock()
-        fake_megolm.event_id = "$old_event"
-        fake_megolm.__class__ = type("MegolmEvent", (), {})
-
-        # Timestamp well past TTL
-        old_ts = _time.time() - _PENDING_EVENT_TTL - 60
-        adapter._pending_megolm = [(MagicMock(), fake_megolm, old_ts)]
-
-        fake_client = MagicMock()
-        adapter._client = fake_client
-
-        fake_nio = MagicMock()
-        fake_nio.MegolmEvent = type("MegolmEvent", (), {})
-
-        with patch.dict("sys.modules", {"nio": fake_nio}):
-            await adapter._retry_pending_decryptions()
-
-        # Should have been dropped
-        assert len(adapter._pending_megolm) == 0
-        # Should NOT have tried to decrypt
-        fake_client.decrypt_event.assert_not_called()
-
-    @pytest.mark.asyncio
-    async def test_media_event_routes_to_media_handler(self):
-        import time as _time
-
-        adapter = _make_adapter()
-        adapter._user_id = "@bot:example.org"
-        adapter._startup_ts = 0.0
-
-        FakeMegolmEvent = type("MegolmEvent", (), {})
-        FakeRoomMessageImage = type("RoomMessageImage", (), {})
-
-        decrypted_image = MagicMock()
-        decrypted_image.__class__ = FakeRoomMessageImage
-
-        fake_megolm = MagicMock()
-        fake_megolm.__class__ = FakeMegolmEvent
-        fake_megolm.event_id = "$encrypted_image"
-
-        fake_room = MagicMock()
-        now = _time.time()
-        adapter._pending_megolm = [(fake_room, fake_megolm, now)]
-
-        fake_client = MagicMock()
-        fake_client.decrypt_event = MagicMock(return_value=decrypted_image)
-        adapter._client = fake_client
-
-        fake_nio = MagicMock()
-        fake_nio.MegolmEvent = FakeMegolmEvent
-        fake_nio.RoomMessageText = type("RoomMessageText", (), {})
-        fake_nio.RoomMessageImage = FakeRoomMessageImage
-        fake_nio.RoomMessageAudio = type("RoomMessageAudio", (), {})
-        fake_nio.RoomMessageVideo = type("RoomMessageVideo", (), {})
-        fake_nio.RoomMessageFile = type("RoomMessageFile", (), {})
-
-        with patch.dict("sys.modules", {"nio": fake_nio}):
-            with patch.object(adapter, "_on_room_message_media", AsyncMock()) as mock_media:
-                await adapter._retry_pending_decryptions()
-                mock_media.assert_awaited_once_with(fake_room, decrypted_image)
-
-        assert len(adapter._pending_megolm) == 0
-
-
-# ---------------------------------------------------------------------------
-# E2EE: Key export / import
-# ---------------------------------------------------------------------------
-
-class TestMatrixKeyExportImport:
-    @pytest.mark.asyncio
-    async def test_disconnect_exports_keys(self):
-        adapter = _make_adapter()
-        adapter._encryption = True
-        adapter._sync_task = None
-
-        fake_client = MagicMock()
-        fake_client.olm = object()
-        fake_client.export_keys = AsyncMock()
-        fake_client.close = AsyncMock()
-        adapter._client = fake_client
-
-        from gateway.platforms.matrix import _KEY_EXPORT_FILE, _KEY_EXPORT_PASSPHRASE
-
-        await adapter.disconnect()
-
-        fake_client.export_keys.assert_awaited_once_with(
-            str(_KEY_EXPORT_FILE), _KEY_EXPORT_PASSPHRASE,
-        )
-
-    @pytest.mark.asyncio
-    async def test_disconnect_handles_export_failure(self):
-        adapter = _make_adapter()
-        adapter._encryption = True
-        adapter._sync_task = None
-
-        fake_client = MagicMock()
-        fake_client.olm = object()
-        fake_client.export_keys = AsyncMock(side_effect=Exception("export failed"))
-        fake_client.close = AsyncMock()
-        adapter._client = fake_client
-
-        # Should not raise
-        await adapter.disconnect()
-        assert adapter._client is None  # still cleaned up
-
-    @pytest.mark.asyncio
-    async def test_disconnect_skips_export_when_no_encryption(self):
-        adapter = _make_adapter()
-        adapter._encryption = False
-        adapter._sync_task = None
-
-        fake_client = MagicMock()
-        fake_client.close = AsyncMock()
-        adapter._client = fake_client
-
-        await adapter.disconnect()
-        # Should not have tried to export
-        assert not hasattr(fake_client, "export_keys") or \
-               not fake_client.export_keys.called

tests/gateway/test_session_hygiene.py

@@ -212,49 +212,6 @@ class TestSessionHygieneWarnThreshold:
         assert post_compress_tokens < warn_threshold
 
 
-class TestCompressionWarnRateLimit:
-    """Compression warning messages must be rate-limited per chat_id."""
-
-    def _make_runner(self):
-        from unittest.mock import MagicMock, patch
-        with patch("gateway.run.load_gateway_config"), \
-             patch("gateway.run.SessionStore"), \
-             patch("gateway.run.DeliveryRouter"):
-            from gateway.run import GatewayRunner
-            runner = GatewayRunner.__new__(GatewayRunner)
-            runner._compression_warn_sent = {}
-            runner._compression_warn_cooldown = 3600
-            return runner
-
-    def test_first_warn_is_sent(self):
-        runner = self._make_runner()
-        now = 1_000_000.0
-        last = runner._compression_warn_sent.get("chat:1", 0)
-        assert now - last >= runner._compression_warn_cooldown
-
-    def test_second_warn_suppressed_within_cooldown(self):
-        runner = self._make_runner()
-        now = 1_000_000.0
-        runner._compression_warn_sent["chat:1"] = now - 60  # 1 minute ago
-        last = runner._compression_warn_sent.get("chat:1", 0)
-        assert now - last < runner._compression_warn_cooldown
-
-    def test_warn_allowed_after_cooldown(self):
-        runner = self._make_runner()
-        now = 1_000_000.0
-        runner._compression_warn_sent["chat:1"] = now - 3601  # just past cooldown
-        last = runner._compression_warn_sent.get("chat:1", 0)
-        assert now - last >= runner._compression_warn_cooldown
-
-    def test_rate_limit_is_per_chat(self):
-        """Rate-limiting one chat must not suppress warnings for another."""
-        runner = self._make_runner()
-        now = 1_000_000.0
-        runner._compression_warn_sent["chat:1"] = now - 60  # suppressed
-        last_other = runner._compression_warn_sent.get("chat:2", 0)
-        assert now - last_other >= runner._compression_warn_cooldown
-
-
 class TestEstimatedTokenThreshold:
     """Verify that hygiene thresholds are always below the model's context
     limit — for both actual and estimated token counts.

tests/gateway/test_unauthorized_dm_behavior.py

@@ -60,7 +60,6 @@ def _make_runner(platform: Platform, config: GatewayConfig):
     runner.adapters = {platform: adapter}
     runner.pairing_store = MagicMock()
     runner.pairing_store.is_approved.return_value = False
-    runner.pairing_store._is_rate_limited.return_value = False
     return runner, adapter
 
 
@@ -143,56 +142,6 @@ async def test_unauthorized_whatsapp_dm_can_be_ignored(monkeypatch):
     adapter.send.assert_not_awaited()
 
 
-@pytest.mark.asyncio
-async def test_rate_limited_user_gets_no_response(monkeypatch):
-    """When a user is already rate-limited, pairing messages are silently ignored."""
-    _clear_auth_env(monkeypatch)
-    config = GatewayConfig(
-        platforms={Platform.WHATSAPP: PlatformConfig(enabled=True)},
-    )
-    runner, adapter = _make_runner(Platform.WHATSAPP, config)
-    runner.pairing_store._is_rate_limited.return_value = True
-
-    result = await runner._handle_message(
-        _make_event(
-            Platform.WHATSAPP,
-            "15551234567@s.whatsapp.net",
-            "15551234567@s.whatsapp.net",
-        )
-    )
-
-    assert result is None
-    runner.pairing_store.generate_code.assert_not_called()
-    adapter.send.assert_not_awaited()
-
-
-@pytest.mark.asyncio
-async def test_rejection_message_records_rate_limit(monkeypatch):
-    """After sending a 'too many requests' rejection, rate limit is recorded
-    so subsequent messages are silently ignored."""
-    _clear_auth_env(monkeypatch)
-    config = GatewayConfig(
-        platforms={Platform.WHATSAPP: PlatformConfig(enabled=True)},
-    )
-    runner, adapter = _make_runner(Platform.WHATSAPP, config)
-    runner.pairing_store.generate_code.return_value = None  # triggers rejection
-
-    result = await runner._handle_message(
-        _make_event(
-            Platform.WHATSAPP,
-            "15551234567@s.whatsapp.net",
-            "15551234567@s.whatsapp.net",
-        )
-    )
-
-    assert result is None
-    adapter.send.assert_awaited_once()
-    assert "Too many" in adapter.send.await_args.args[1]
-    runner.pairing_store._record_rate_limit.assert_called_once_with(
-        "whatsapp", "15551234567@s.whatsapp.net"
-    )
-
-
 @pytest.mark.asyncio
 async def test_global_ignore_suppresses_pairing_reply(monkeypatch):
     _clear_auth_env(monkeypatch)