feat: scroll aware sticky prompt

hermes_cli/auth.py

@@ -224,7 +224,7 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
     ),
     "ai-gateway": ProviderConfig(
         id="ai-gateway",
-        name="AI Gateway",
+        name="Vercel AI Gateway",
         auth_type="api_key",
         inference_base_url="https://ai-gateway.vercel.sh/v1",
         api_key_env_vars=("AI_GATEWAY_API_KEY",),

hermes_cli/commands.py

@@ -12,6 +12,9 @@ from __future__ import annotations
 
 import os
 import re
+import shutil
+import subprocess
+import time
 from collections.abc import Callable, Mapping
 from dataclasses import dataclass
 from typing import Any
@@ -614,6 +617,10 @@ class SlashCommandCompleter(Completer):
     ) -> None:
         self._skill_commands_provider = skill_commands_provider
         self._command_filter = command_filter
+        # Cached project file list for fuzzy @ completions
+        self._file_cache: list[str] = []
+        self._file_cache_time: float = 0.0
+        self._file_cache_cwd: str = ""
 
     def _command_allowed(self, slash_command: str) -> bool:
         if self._command_filter is None:
@@ -798,46 +805,138 @@ class SlashCommandCompleter(Completer):
                     count += 1
                 return
 
-        # Bare @ or @partial — show matching files/folders from cwd
+        # Bare @ or @partial — fuzzy project-wide file search
         query = word[1:]  # strip the @
-        if not query:
-            search_dir, match_prefix = ".", ""
-        else:
-            expanded = os.path.expanduser(query)
-            if expanded.endswith("/"):
-                search_dir, match_prefix = expanded, ""
-            else:
-                search_dir = os.path.dirname(expanded) or "."
-                match_prefix = os.path.basename(expanded)
+        yield from self._fuzzy_file_completions(word, query, limit)
 
-        try:
-            entries = os.listdir(search_dir)
-        except OSError:
+    def _get_project_files(self) -> list[str]:
+        """Return cached list of project files (refreshed every 5s)."""
+        cwd = os.getcwd()
+        now = time.monotonic()
+        if (
+            self._file_cache
+            and self._file_cache_cwd == cwd
+            and now - self._file_cache_time < 5.0
+        ):
+            return self._file_cache
+
+        files: list[str] = []
+        # Try rg first (fast, respects .gitignore), then fd, then find.
+        for cmd in [
+            ["rg", "--files", "--sortr=modified", cwd],
+            ["rg", "--files", cwd],
+            ["fd", "--type", "f", "--base-directory", cwd],
+        ]:
+            tool = cmd[0]
+            if not shutil.which(tool):
+                continue
+            try:
+                proc = subprocess.run(
+                    cmd, capture_output=True, text=True, timeout=2,
+                    cwd=cwd,
+                )
+                if proc.returncode == 0 and proc.stdout.strip():
+                    raw = proc.stdout.strip().split("\n")
+                    # Store relative paths
+                    for p in raw[:5000]:
+                        rel = os.path.relpath(p, cwd) if os.path.isabs(p) else p
+                        files.append(rel)
+                    break
+            except (subprocess.TimeoutExpired, OSError):
+                continue
+
+        self._file_cache = files
+        self._file_cache_time = now
+        self._file_cache_cwd = cwd
+        return files
+
+    @staticmethod
+    def _score_path(filepath: str, query: str) -> int:
+        """Score a file path against a fuzzy query. Higher = better match."""
+        if not query:
+            return 1  # show everything when query is empty
+
+        filename = os.path.basename(filepath)
+        lower_file = filename.lower()
+        lower_path = filepath.lower()
+        lower_q = query.lower()
+
+        # Exact filename match
+        if lower_file == lower_q:
+            return 100
+        # Filename starts with query
+        if lower_file.startswith(lower_q):
+            return 80
+        # Filename contains query as substring
+        if lower_q in lower_file:
+            return 60
+        # Full path contains query
+        if lower_q in lower_path:
+            return 40
+        # Initials / abbreviation match: e.g. "fo" matches "file_operations"
+        # Check if query chars appear in order in filename
+        qi = 0
+        for c in lower_file:
+            if qi < len(lower_q) and c == lower_q[qi]:
+                qi += 1
+        if qi == len(lower_q):
+            # Bonus if matches land on word boundaries (after _, -, /, .)
+            boundary_hits = 0
+            qi = 0
+            prev = "_"  # treat start as boundary
+            for c in lower_file:
+                if qi < len(lower_q) and c == lower_q[qi]:
+                    if prev in "_-./":
+                        boundary_hits += 1
+                    qi += 1
+                prev = c
+            if boundary_hits >= len(lower_q) * 0.5:
+                return 35
+            return 25
+        return 0
+
+    def _fuzzy_file_completions(self, word: str, query: str, limit: int = 20):
+        """Yield fuzzy file completions for bare @query."""
+        files = self._get_project_files()
+
+        if not query:
+            # No query — show recently modified files (already sorted by mtime)
+            for fp in files[:limit]:
+                is_dir = fp.endswith("/")
+                filename = os.path.basename(fp)
+                kind = "folder" if is_dir else "file"
+                meta = "dir" if is_dir else _file_size_label(
+                    os.path.join(os.getcwd(), fp)
+                )
+                yield Completion(
+                    f"@{kind}:{fp}",
+                    start_position=-len(word),
+                    display=filename,
+                    display_meta=meta,
+                )
             return
 
-        count = 0
-        prefix_lower = match_prefix.lower()
-        for entry in sorted(entries):
-            if match_prefix and not entry.lower().startswith(prefix_lower):
-                continue
-            if entry.startswith("."):
-                continue  # skip hidden files in bare @ mode
-            if count >= limit:
-                break
-            full_path = os.path.join(search_dir, entry)
-            is_dir = os.path.isdir(full_path)
-            display_path = os.path.relpath(full_path)
-            suffix = "/" if is_dir else ""
+        # Score and rank
+        scored = []
+        for fp in files:
+            s = self._score_path(fp, query)
+            if s > 0:
+                scored.append((s, fp))
+        scored.sort(key=lambda x: (-x[0], x[1]))
+
+        for _, fp in scored[:limit]:
+            is_dir = fp.endswith("/")
+            filename = os.path.basename(fp)
             kind = "folder" if is_dir else "file"
-            meta = "dir" if is_dir else _file_size_label(full_path)
-            completion = f"@{kind}:{display_path}{suffix}"
-            yield Completion(
-                completion,
-                start_position=-len(word),
-                display=entry + suffix,
-                display_meta=meta,
+            meta = "dir" if is_dir else _file_size_label(
+                os.path.join(os.getcwd(), fp)
+            )
+            yield Completion(
+                f"@{kind}:{fp}",
+                start_position=-len(word),
+                display=filename,
+                display_meta=f"{fp}  {meta}" if meta else fp,
             )
-            count += 1
 
     @staticmethod
     def _skin_completions(sub_text: str, sub_lower: str):

hermes_cli/config.py

@@ -45,6 +45,9 @@ _EXTRA_ENV_KEYS = frozenset({
     "WEIXIN_HOME_CHANNEL", "WEIXIN_HOME_CHANNEL_NAME", "WEIXIN_DM_POLICY", "WEIXIN_GROUP_POLICY",
     "WEIXIN_ALLOWED_USERS", "WEIXIN_GROUP_ALLOWED_USERS", "WEIXIN_ALLOW_ALL_USERS",
     "BLUEBUBBLES_SERVER_URL", "BLUEBUBBLES_PASSWORD",
+    "QQ_APP_ID", "QQ_CLIENT_SECRET", "QQ_HOME_CHANNEL", "QQ_HOME_CHANNEL_NAME",
+    "QQ_ALLOWED_USERS", "QQ_GROUP_ALLOWED_USERS", "QQ_ALLOW_ALL_USERS", "QQ_MARKDOWN_SUPPORT",
+    "QQ_STT_API_KEY", "QQ_STT_BASE_URL", "QQ_STT_MODEL",
     "TERMINAL_ENV", "TERMINAL_SSH_KEY", "TERMINAL_SSH_PORT",
     "WHATSAPP_MODE", "WHATSAPP_ENABLED",
     "MATTERMOST_HOME_CHANNEL", "MATTERMOST_REPLY_MODE",
@@ -1331,6 +1334,53 @@ OPTIONAL_ENV_VARS = {
         "password": False,
         "category": "messaging",
     },
+    "BLUEBUBBLES_ALLOW_ALL_USERS": {
+        "description": "Allow all BlueBubbles users without allowlist",
+        "prompt": "Allow All BlueBubbles Users",
+        "category": "messaging",
+    },
+    "QQ_APP_ID": {
+        "description": "QQ Bot App ID from QQ Open Platform (q.qq.com)",
+        "prompt": "QQ App ID",
+        "url": "https://q.qq.com",
+        "category": "messaging",
+    },
+    "QQ_CLIENT_SECRET": {
+        "description": "QQ Bot Client Secret from QQ Open Platform",
+        "prompt": "QQ Client Secret",
+        "password": True,
+        "category": "messaging",
+    },
+    "QQ_ALLOWED_USERS": {
+        "description": "Comma-separated QQ user IDs allowed to use the bot",
+        "prompt": "QQ Allowed Users",
+        "category": "messaging",
+    },
+    "QQ_GROUP_ALLOWED_USERS": {
+        "description": "Comma-separated QQ group IDs allowed to interact with the bot",
+        "prompt": "QQ Group Allowed Users",
+        "category": "messaging",
+    },
+    "QQ_ALLOW_ALL_USERS": {
+        "description": "Allow all QQ users without an allowlist (true/false)",
+        "prompt": "Allow All QQ Users",
+        "category": "messaging",
+    },
+    "QQ_HOME_CHANNEL": {
+        "description": "Default QQ channel/group for cron delivery and notifications",
+        "prompt": "QQ Home Channel",
+        "category": "messaging",
+    },
+    "QQ_HOME_CHANNEL_NAME": {
+        "description": "Display name for the QQ home channel",
+        "prompt": "QQ Home Channel Name",
+        "category": "messaging",
+    },
+    "QQ_SANDBOX": {
+        "description": "Enable QQ sandbox mode for development testing (true/false)",
+        "prompt": "QQ Sandbox Mode",
+        "category": "messaging",
+    },
     "GATEWAY_ALLOW_ALL_USERS": {
         "description": "Allow all users to interact with messaging bots (true/false). Default: false.",
         "prompt": "Allow all users (true/false)",

hermes_cli/doctor.py

@@ -729,7 +729,7 @@ def run_doctor(args):
         # MiniMax: the /anthropic endpoint doesn't support /models, but the /v1 endpoint does.
         ("MiniMax",          ("MINIMAX_API_KEY",),                            "https://api.minimax.io/v1/models",    "MINIMAX_BASE_URL", True),
         ("MiniMax (China)",  ("MINIMAX_CN_API_KEY",),                         "https://api.minimaxi.com/v1/models",  "MINIMAX_CN_BASE_URL", True),
-        ("AI Gateway",       ("AI_GATEWAY_API_KEY",),                          "https://ai-gateway.vercel.sh/v1/models", "AI_GATEWAY_BASE_URL", True),
+        ("Vercel AI Gateway",       ("AI_GATEWAY_API_KEY",),                          "https://ai-gateway.vercel.sh/v1/models", "AI_GATEWAY_BASE_URL", True),
         ("Kilo Code",        ("KILOCODE_API_KEY",),                            "https://api.kilo.ai/api/gateway/models",  "KILOCODE_BASE_URL", True),
         ("OpenCode Zen",     ("OPENCODE_ZEN_API_KEY",),                        "https://opencode.ai/zen/v1/models",  "OPENCODE_ZEN_BASE_URL", True),
         ("OpenCode Go",      ("OPENCODE_GO_API_KEY",),                         "https://opencode.ai/zen/go/v1/models", "OPENCODE_GO_BASE_URL", True),

hermes_cli/dump.py

@@ -131,6 +131,7 @@ def _configured_platforms() -> list[str]:
         "wecom": "WECOM_BOT_ID",
         "wecom_callback": "WECOM_CALLBACK_CORP_ID",
         "weixin": "WEIXIN_ACCOUNT_ID",
+        "qqbot": "QQ_APP_ID",
     }
     return [name for name, env in checks.items() if os.getenv(env)]
 

hermes_cli/gateway.py

@@ -1913,6 +1913,29 @@ _PLATFORMS = [
              "help": "Phone number or Apple ID to deliver cron results and notifications to."},
         ],
     },
+    {
+        "key": "qqbot",
+        "label": "QQ Bot",
+        "emoji": "🐧",
+        "token_var": "QQ_APP_ID",
+        "setup_instructions": [
+            "1. Register a QQ Bot application at q.qq.com",
+            "2. Note your App ID and App Secret from the application page",
+            "3. Enable the required intents (C2C, Group, Guild messages)",
+            "4. Configure sandbox or publish the bot",
+        ],
+        "vars": [
+            {"name": "QQ_APP_ID", "prompt": "QQ Bot App ID", "password": False,
+             "help": "Your QQ Bot App ID from q.qq.com."},
+            {"name": "QQ_CLIENT_SECRET", "prompt": "QQ Bot App Secret", "password": True,
+             "help": "Your QQ Bot App Secret from q.qq.com."},
+            {"name": "QQ_ALLOWED_USERS", "prompt": "Allowed user OpenIDs (comma-separated, leave empty for open access)", "password": False,
+             "is_allowlist": True,
+             "help": "Optional — restrict DM access to specific user OpenIDs."},
+            {"name": "QQ_HOME_CHANNEL", "prompt": "Home channel (user/group OpenID for cron delivery, or empty)", "password": False,
+             "help": "OpenID to deliver cron results and notifications to."},
+        ],
+    },
 ]
 
 

hermes_cli/main.py

@@ -1839,6 +1839,10 @@ def _model_flow_custom(config):
             model_name = input("Model name (e.g. gpt-4, llama-3-70b): ").strip()
 
         context_length_str = input("Context length in tokens [leave blank for auto-detect]: ").strip()
+
+        # Prompt for a display name — shown in the provider menu on future runs
+        default_name = _auto_provider_name(effective_url)
+        display_name = input(f"Display name [{default_name}]: ").strip() or default_name
     except (KeyboardInterrupt, EOFError):
         print("\nCancelled.")
         return
@@ -1894,15 +1898,37 @@ def _model_flow_custom(config):
         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 "", context_length=context_length)
+    _save_custom_provider(effective_url, effective_key, model_name or "",
+                          context_length=context_length, name=display_name)
 
 
-def _save_custom_provider(base_url, api_key="", model="", context_length=None):
+def _auto_provider_name(base_url: str) -> str:
+    """Generate a display name from a custom endpoint URL.
+
+    Returns a human-friendly label like "Local (localhost:11434)" or
+    "RunPod (xyz.runpod.io)".  Used as the default when prompting the
+    user for a display name during custom endpoint setup.
+    """
+    import re
+    clean = base_url.replace("https://", "").replace("http://", "").rstrip("/")
+    clean = re.sub(r"/v1/?$", "", clean)
+    name = clean.split("/")[0]
+    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()
+    return name
+
+
+def _save_custom_provider(base_url, api_key="", model="", context_length=None,
+                          name=None):
     """Save a custom endpoint to custom_providers in config.yaml.
 
     Deduplicates by base_url — if the URL already exists, updates the
     model name and context_length but doesn't add a duplicate entry.
-    Auto-generates a display name from the URL hostname.
+    Uses *name* when provided, otherwise auto-generates from the URL.
     """
     from hermes_cli.config import load_config, save_config
 
@@ -1930,20 +1956,9 @@ def _save_custom_provider(base_url, api_key="", model="", context_length=None):
                 save_config(cfg)
             return  # already saved, updated 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()
+    # Use provided name or auto-generate from URL
+    if not name:
+        name = _auto_provider_name(base_url)
 
     entry = {"name": name, "base_url": base_url}
     if api_key:

hermes_cli/model_switch.py

@@ -705,6 +705,10 @@ def switch_model(
             error_message=msg,
         )
 
+    # Apply auto-correction if validation found a closer match
+    if validation.get("corrected_model"):
+        new_model = validation["corrected_model"]
+
     # --- OpenCode api_mode override ---
     if target_provider in {"opencode-zen", "opencode-go", "opencode", "opencode-go"}:
         api_mode = opencode_model_api_mode(target_provider, new_model)

hermes_cli/models.py

@@ -29,6 +29,7 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
     ("qwen/qwen3.6-plus",               ""),
     ("anthropic/claude-sonnet-4.5",     ""),
     ("anthropic/claude-haiku-4.5",      ""),
+    ("openrouter/elephant-alpha",       "free"),
     ("openai/gpt-5.4",                  ""),
     ("openai/gpt-5.4-mini",             ""),
     ("xiaomi/mimo-v2-pro",               ""),
@@ -97,6 +98,7 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "arcee-ai/trinity-large-thinking",
         "openai/gpt-5.4-pro",
         "openai/gpt-5.4-nano",
+        "openrouter/elephant-alpha",
     ],
     "openai-codex": _codex_curated_models(),
     "copilot-acp": [
@@ -512,6 +514,7 @@ CANONICAL_PROVIDERS: list[ProviderEntry] = [
     ProviderEntry("openrouter",     "OpenRouter",               "OpenRouter (100+ models, pay-per-use)"),
     ProviderEntry("anthropic",      "Anthropic",                "Anthropic (Claude models — API key or Claude Code)"),
     ProviderEntry("openai-codex",   "OpenAI Codex",             "OpenAI Codex"),
+    ProviderEntry("xiaomi",         "Xiaomi MiMo",              "Xiaomi MiMo (MiMo-V2 models — pro, omni, flash)"),
     ProviderEntry("qwen-oauth",     "Qwen OAuth (Portal)",      "Qwen OAuth (reuses local Qwen CLI login)"),
     ProviderEntry("copilot",        "GitHub Copilot",           "GitHub Copilot (uses GITHUB_TOKEN or gh auth token)"),
     ProviderEntry("copilot-acp",    "GitHub Copilot ACP",       "GitHub Copilot ACP (spawns `copilot --acp --stdio`)"),
@@ -525,12 +528,11 @@ CANONICAL_PROVIDERS: list[ProviderEntry] = [
     ProviderEntry("minimax",        "MiniMax",                  "MiniMax (global direct API)"),
     ProviderEntry("minimax-cn",     "MiniMax (China)",          "MiniMax China (domestic direct API)"),
     ProviderEntry("alibaba",        "Alibaba Cloud (DashScope)","Alibaba Cloud / DashScope Coding (Qwen + multi-provider)"),
-    ProviderEntry("xiaomi",         "Xiaomi MiMo",              "Xiaomi MiMo (MiMo-V2 models — pro, omni, flash)"),
     ProviderEntry("arcee",          "Arcee AI",                 "Arcee AI (Trinity models — direct API)"),
     ProviderEntry("kilocode",       "Kilo Code",                "Kilo Code (Kilo Gateway API)"),
     ProviderEntry("opencode-zen",   "OpenCode Zen",             "OpenCode Zen (35+ curated models, pay-as-you-go)"),
     ProviderEntry("opencode-go",    "OpenCode Go",              "OpenCode Go (open models, $10/month subscription)"),
-    ProviderEntry("ai-gateway",     "AI Gateway",               "AI Gateway (Vercel — 200+ models, pay-per-use)"),
+    ProviderEntry("ai-gateway",     "Vercel AI Gateway",        "Vercel AI Gateway (200+ models, pay-per-use)"),
 ]
 
 # Derived dicts — used throughout the codebase
@@ -1818,6 +1820,17 @@ def validate_requested_model(
                     "message": None,
                 }
 
+            # Auto-correct if the top match is very similar (e.g. typo)
+            auto = get_close_matches(requested_for_lookup, api_models, n=1, cutoff=0.9)
+            if auto:
+                return {
+                    "accepted": True,
+                    "persist": True,
+                    "recognized": True,
+                    "corrected_model": auto[0],
+                    "message": f"Auto-corrected `{requested}` → `{auto[0]}`",
+                }
+
             suggestions = get_close_matches(requested, api_models, n=3, cutoff=0.5)
             suggestion_text = ""
             if suggestions:
@@ -1869,6 +1882,16 @@ def validate_requested_model(
                     "recognized": True,
                     "message": None,
                 }
+            # Auto-correct if the top match is very similar (e.g. typo)
+            auto = get_close_matches(requested_for_lookup, codex_models, n=1, cutoff=0.9)
+            if auto:
+                return {
+                    "accepted": True,
+                    "persist": True,
+                    "recognized": True,
+                    "corrected_model": auto[0],
+                    "message": f"Auto-corrected `{requested}` → `{auto[0]}`",
+                }
             suggestions = get_close_matches(requested_for_lookup, codex_models, n=3, cutoff=0.5)
             suggestion_text = ""
             if suggestions:
@@ -1895,10 +1918,27 @@ def validate_requested_model(
                 "recognized": True,
                 "message": None,
             }
-        suggestions = get_close_matches(requested, api_models, n=3, cutoff=0.5)
-        suggestion_text = ""
-        if suggestions:
-            suggestion_text = "\n  Similar models: " + ", ".join(f"`{s}`" for s in suggestions)
+        else:
+            # API responded but model is not listed.  Accept anyway —
+            # the user may have access to models not shown in the public
+            # listing (e.g. Z.AI Pro/Max plans can use glm-5 on coding
+            # endpoints even though it's not in /models).  Warn but allow.
+
+            # Auto-correct if the top match is very similar (e.g. typo)
+            auto = get_close_matches(requested_for_lookup, api_models, n=1, cutoff=0.9)
+            if auto:
+                return {
+                    "accepted": True,
+                    "persist": True,
+                    "recognized": True,
+                    "corrected_model": auto[0],
+                    "message": f"Auto-corrected `{requested}` → `{auto[0]}`",
+                }
+
+            suggestions = get_close_matches(requested, api_models, n=3, cutoff=0.5)
+            suggestion_text = ""
+            if suggestions:
+                suggestion_text = "\n  Similar models: " + ", ".join(f"`{s}`" for s in suggestions)
 
         return {
             "accepted": False,

hermes_cli/platforms.py

@@ -35,6 +35,7 @@ PLATFORMS: OrderedDict[str, PlatformInfo] = OrderedDict([
     ("wecom",          PlatformInfo(label="💬 WeCom",           default_toolset="hermes-wecom")),
     ("wecom_callback", PlatformInfo(label="💬 WeCom Callback",  default_toolset="hermes-wecom-callback")),
     ("weixin",         PlatformInfo(label="💬 Weixin",          default_toolset="hermes-weixin")),
+    ("qqbot",          PlatformInfo(label="💬 QQBot",           default_toolset="hermes-qqbot")),
     ("webhook",        PlatformInfo(label="🔗 Webhook",         default_toolset="hermes-webhook")),
     ("api_server",     PlatformInfo(label="🌐 API Server",      default_toolset="hermes-api-server")),
 ])

hermes_cli/plugins.py

@@ -584,6 +584,45 @@ def invoke_hook(hook_name: str, **kwargs: Any) -> List[Any]:
 
 
 
+def get_pre_tool_call_block_message(
+    tool_name: str,
+    args: Optional[Dict[str, Any]],
+    task_id: str = "",
+    session_id: str = "",
+    tool_call_id: str = "",
+) -> Optional[str]:
+    """Check ``pre_tool_call`` hooks for a blocking directive.
+
+    Plugins that need to enforce policy (rate limiting, security
+    restrictions, approval workflows) can return::
+
+        {"action": "block", "message": "Reason the tool was blocked"}
+
+    from their ``pre_tool_call`` callback.  The first valid block
+    directive wins.  Invalid or irrelevant hook return values are
+    silently ignored so existing observer-only hooks are unaffected.
+    """
+    hook_results = invoke_hook(
+        "pre_tool_call",
+        tool_name=tool_name,
+        args=args if isinstance(args, dict) else {},
+        task_id=task_id,
+        session_id=session_id,
+        tool_call_id=tool_call_id,
+    )
+
+    for result in hook_results:
+        if not isinstance(result, dict):
+            continue
+        if result.get("action") != "block":
+            continue
+        message = result.get("message")
+        if isinstance(message, str) and message:
+            return message
+
+    return None
+
+
 def get_plugin_context_engine():
     """Return the plugin-registered context engine, or None."""
     return get_plugin_manager()._context_engine
@@ -608,7 +647,7 @@ def get_plugin_toolsets() -> List[tuple]:
     toolset_tools: Dict[str, List[str]] = {}
     toolset_plugin: Dict[str, LoadedPlugin] = {}
     for tool_name in manager._plugin_tool_names:
-        entry = registry._tools.get(tool_name)
+        entry = registry.get_entry(tool_name)
         if not entry:
             continue
         ts = entry.toolset
@@ -617,7 +656,7 @@ def get_plugin_toolsets() -> List[tuple]:
     # Map toolsets back to the plugin that registered them
     for _name, loaded in manager._plugins.items():
         for tool_name in loaded.tools_registered:
-            entry = registry._tools.get(tool_name)
+            entry = registry.get_entry(tool_name)
             if entry and entry.toolset in toolset_tools:
                 toolset_plugin.setdefault(entry.toolset, loaded)
 

hermes_cli/runtime_provider.py

@@ -287,6 +287,9 @@ def _get_named_custom_provider(requested_provider: str) -> Optional[Dict[str, An
             # Resolve the API key from the env var name stored in key_env
             key_env = str(entry.get("key_env", "") or "").strip()
             resolved_api_key = os.getenv(key_env, "").strip() if key_env else ""
+            # Fall back to inline api_key when key_env is absent or unresolvable
+            if not resolved_api_key:
+                resolved_api_key = str(entry.get("api_key", "") or "").strip()
 
             if requested_norm in {ep_name, name_norm, f"custom:{name_norm}"}:
                 # Found match by provider key

hermes_cli/setup.py

@@ -776,7 +776,7 @@ def setup_model_provider(config: dict, *, quick: bool = False):
             "minimax": "MiniMax",
             "minimax-cn": "MiniMax CN",
             "anthropic": "Anthropic",
-            "ai-gateway": "AI Gateway",
+            "ai-gateway": "Vercel AI Gateway",
             "custom": "your custom endpoint",
         }
         _prov_display = _prov_names.get(selected_provider, selected_provider or "your provider")
@@ -1969,6 +1969,54 @@ def _setup_wecom_callback():
     _gw_setup()
 
 
+def _setup_qqbot():
+    """Configure QQ Bot gateway."""
+    print_header("QQ Bot")
+    existing = get_env_value("QQ_APP_ID")
+    if existing:
+        print_info("QQ Bot: already configured")
+        if not prompt_yes_no("Reconfigure QQ Bot?", False):
+            return
+
+    print_info("Connects Hermes to QQ via the Official QQ Bot API (v2).")
+    print_info("   Requires a QQ Bot application at q.qq.com")
+    print_info("   Reference: https://bot.q.qq.com/wiki/develop/api-v2/")
+    print()
+
+    app_id = prompt("QQ Bot App ID")
+    if not app_id:
+        print_warning("App ID is required — skipping QQ Bot setup")
+        return
+    save_env_value("QQ_APP_ID", app_id.strip())
+
+    client_secret = prompt("QQ Bot App Secret", password=True)
+    if not client_secret:
+        print_warning("App Secret is required — skipping QQ Bot setup")
+        return
+    save_env_value("QQ_CLIENT_SECRET", client_secret)
+    print_success("QQ Bot credentials saved")
+
+    print()
+    print_info("🔒 Security: Restrict who can DM your bot")
+    print_info("   Use QQ user OpenIDs (found in event payloads)")
+    print()
+    allowed_users = prompt("Allowed user OpenIDs (comma-separated, leave empty for open access)")
+    if allowed_users:
+        save_env_value("QQ_ALLOWED_USERS", allowed_users.replace(" ", ""))
+        print_success("QQ Bot allowlist configured")
+    else:
+        print_info("⚠️  No allowlist set — anyone can DM the bot!")
+
+    print()
+    print_info("📬 Home Channel: OpenID for cron job delivery and notifications.")
+    home_channel = prompt("Home channel OpenID (leave empty to set later)")
+    if home_channel:
+        save_env_value("QQ_HOME_CHANNEL", home_channel)
+
+    print()
+    print_success("QQ Bot configured!")
+
+
 def _setup_bluebubbles():
     """Configure BlueBubbles iMessage gateway."""
     print_header("BlueBubbles (iMessage)")
@@ -2034,6 +2082,15 @@ def _setup_bluebubbles():
     print_info("   Install: https://docs.bluebubbles.app/helper-bundle/installation")
 
 
+def _setup_qqbot():
+    """Configure QQ Bot (Official API v2) via standard platform setup."""
+    from hermes_cli.gateway import _PLATFORMS
+    qq_platform = next((p for p in _PLATFORMS if p["key"] == "qqbot"), None)
+    if qq_platform:
+        from hermes_cli.gateway import _setup_standard_platform
+        _setup_standard_platform(qq_platform)
+
+
 def _setup_webhooks():
     """Configure webhook integration."""
     print_header("Webhooks")
@@ -2097,6 +2154,7 @@ _GATEWAY_PLATFORMS = [
     ("WeCom Callback (Self-Built App)", "WECOM_CALLBACK_CORP_ID", _setup_wecom_callback),
     ("Weixin (WeChat)", "WEIXIN_ACCOUNT_ID", _setup_weixin),
     ("BlueBubbles (iMessage)", "BLUEBUBBLES_SERVER_URL", _setup_bluebubbles),
+    ("QQ Bot", "QQ_APP_ID", _setup_qqbot),
     ("Webhooks (GitHub, GitLab, etc.)", "WEBHOOK_ENABLED", _setup_webhooks),
 ]
 
@@ -2148,6 +2206,7 @@ def setup_gateway(config: dict):
         or get_env_value("WECOM_BOT_ID")
         or get_env_value("WEIXIN_ACCOUNT_ID")
         or get_env_value("BLUEBUBBLES_SERVER_URL")
+        or get_env_value("QQ_APP_ID")
         or get_env_value("WEBHOOK_ENABLED")
     )
     if any_messaging:
@@ -2169,6 +2228,8 @@ def setup_gateway(config: dict):
             missing_home.append("Slack")
         if get_env_value("BLUEBUBBLES_SERVER_URL") and not get_env_value("BLUEBUBBLES_HOME_CHANNEL"):
             missing_home.append("BlueBubbles")
+        if get_env_value("QQ_APP_ID") and not get_env_value("QQ_HOME_CHANNEL"):
+            missing_home.append("QQBot")
 
         if missing_home:
             print()

hermes_cli/skin_engine.py

@@ -32,6 +32,12 @@ All fields are optional. Missing values inherit from the ``default`` skin.
       response_border: "#FFD700"         # Response box border (ANSI)
       session_label: "#DAA520"           # Session label color
       session_border: "#8B8682"          # Session ID dim color
+      status_bar_bg: "#1a1a2e"          # TUI status/usage bar background
+      voice_status_bg: "#1a1a2e"        # TUI voice status background
+      completion_menu_bg: "#1a1a2e"      # Completion menu background
+      completion_menu_current_bg: "#333355"  # Active completion row background
+      completion_menu_meta_bg: "#1a1a2e"     # Completion meta column background
+      completion_menu_meta_current_bg: "#333355"  # Active completion meta background
 
     # Spinner: customize the animated spinner during API calls
     spinner:
@@ -87,6 +93,8 @@ BUILT-IN SKINS
 - ``ares``    — Crimson/bronze war-god theme with custom spinner wings
 - ``mono``    — Clean grayscale monochrome
 - ``slate``   — Cool blue developer-focused theme
+- ``daylight`` — Light background theme with dark text and blue accents
+- ``warm-lightmode`` — Warm brown/gold text for light terminal backgrounds
 
 USER SKINS
 ==========
@@ -304,6 +312,80 @@ _BUILTIN_SKINS: Dict[str, Dict[str, Any]] = {
         },
         "tool_prefix": "┊",
     },
+    "daylight": {
+        "name": "daylight",
+        "description": "Light theme for bright terminals with dark text and cool blue accents",
+        "colors": {
+            "banner_border": "#2563EB",
+            "banner_title": "#0F172A",
+            "banner_accent": "#1D4ED8",
+            "banner_dim": "#475569",
+            "banner_text": "#111827",
+            "ui_accent": "#2563EB",
+            "ui_label": "#0F766E",
+            "ui_ok": "#15803D",
+            "ui_error": "#B91C1C",
+            "ui_warn": "#B45309",
+            "prompt": "#111827",
+            "input_rule": "#93C5FD",
+            "response_border": "#2563EB",
+            "session_label": "#1D4ED8",
+            "session_border": "#64748B",
+            "status_bar_bg": "#E5EDF8",
+            "voice_status_bg": "#E5EDF8",
+            "completion_menu_bg": "#F8FAFC",
+            "completion_menu_current_bg": "#DBEAFE",
+            "completion_menu_meta_bg": "#EEF2FF",
+            "completion_menu_meta_current_bg": "#BFDBFE",
+        },
+        "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": "│",
+    },
+    "warm-lightmode": {
+        "name": "warm-lightmode",
+        "description": "Warm light mode — dark brown/gold text for light terminal backgrounds",
+        "colors": {
+            "banner_border": "#8B6914",
+            "banner_title": "#5C3D11",
+            "banner_accent": "#8B4513",
+            "banner_dim": "#8B7355",
+            "banner_text": "#2C1810",
+            "ui_accent": "#8B4513",
+            "ui_label": "#5C3D11",
+            "ui_ok": "#2E7D32",
+            "ui_error": "#C62828",
+            "ui_warn": "#E65100",
+            "prompt": "#2C1810",
+            "input_rule": "#8B6914",
+            "response_border": "#8B6914",
+            "session_label": "#5C3D11",
+            "session_border": "#A0845C",
+            "status_bar_bg": "#F5F0E8",
+            "voice_status_bg": "#F5F0E8",
+            "completion_menu_bg": "#F5EFE0",
+            "completion_menu_current_bg": "#E8DCC8",
+            "completion_menu_meta_bg": "#F0E8D8",
+            "completion_menu_meta_current_bg": "#DFCFB0",
+        },
+        "spinner": {},
+        "branding": {
+            "agent_name": "Hermes Agent",
+            "welcome": "Welcome to Hermes Agent! Type your message or /help for commands.",
+            "goodbye": "Goodbye! \u2695",
+            "response_label": " \u2695 Hermes ",
+            "prompt_symbol": "\u276f ",
+            "help_header": "(^_^)? Available Commands",
+        },
+        "tool_prefix": "\u250a",
+    },
     "poseidon": {
         "name": "poseidon",
         "description": "Ocean-god theme — deep blue and seafoam",
@@ -685,6 +767,12 @@ def get_prompt_toolkit_style_overrides() -> Dict[str, str]:
     label = skin.get_color("ui_label", title)
     warn = skin.get_color("ui_warn", "#FF8C00")
     error = skin.get_color("ui_error", "#FF6B6B")
+    status_bg = skin.get_color("status_bar_bg", "#1a1a2e")
+    voice_bg = skin.get_color("voice_status_bg", status_bg)
+    menu_bg = skin.get_color("completion_menu_bg", "#1a1a2e")
+    menu_current_bg = skin.get_color("completion_menu_current_bg", "#333355")
+    menu_meta_bg = skin.get_color("completion_menu_meta_bg", menu_bg)
+    menu_meta_current_bg = skin.get_color("completion_menu_meta_current_bg", menu_current_bg)
 
     return {
         "input-area": prompt,
@@ -692,13 +780,20 @@ def get_prompt_toolkit_style_overrides() -> Dict[str, str]:
         "prompt": prompt,
         "prompt-working": f"{dim} italic",
         "hint": f"{dim} italic",
+        "status-bar": f"bg:{status_bg} {text}",
+        "status-bar-strong": f"bg:{status_bg} {title} bold",
+        "status-bar-dim": f"bg:{status_bg} {dim}",
+        "status-bar-good": f"bg:{status_bg} {skin.get_color('ui_ok', '#8FBC8F')} bold",
+        "status-bar-warn": f"bg:{status_bg} {warn} bold",
+        "status-bar-bad": f"bg:{status_bg} {skin.get_color('banner_accent', warn)} bold",
+        "status-bar-critical": f"bg:{status_bg} {error} bold",
         "input-rule": input_rule,
         "image-badge": f"{label} bold",
-        "completion-menu": f"bg:#1a1a2e {text}",
-        "completion-menu.completion": f"bg:#1a1a2e {text}",
-        "completion-menu.completion.current": f"bg:#333355 {title}",
-        "completion-menu.meta.completion": f"bg:#1a1a2e {dim}",
-        "completion-menu.meta.completion.current": f"bg:#333355 {label}",
+        "completion-menu": f"bg:{menu_bg} {text}",
+        "completion-menu.completion": f"bg:{menu_bg} {text}",
+        "completion-menu.completion.current": f"bg:{menu_current_bg} {title}",
+        "completion-menu.meta.completion": f"bg:{menu_meta_bg} {dim}",
+        "completion-menu.meta.completion.current": f"bg:{menu_meta_current_bg} {label}",
         "clarify-border": input_rule,
         "clarify-title": f"{title} bold",
         "clarify-question": f"{text} bold",
@@ -716,4 +811,6 @@ def get_prompt_toolkit_style_overrides() -> Dict[str, str]:
         "approval-cmd": f"{dim} italic",
         "approval-choice": dim,
         "approval-selected": f"{title} bold",
+        "voice-status": f"bg:{voice_bg} {label}",
+        "voice-status-recording": f"bg:{voice_bg} {error} bold",
     }

hermes_cli/status.py

@@ -305,6 +305,7 @@ def show_status(args):
         "WeCom Callback": ("WECOM_CALLBACK_CORP_ID", None),
         "Weixin": ("WEIXIN_ACCOUNT_ID", "WEIXIN_HOME_CHANNEL"),
         "BlueBubbles": ("BLUEBUBBLES_SERVER_URL", "BLUEBUBBLES_HOME_CHANNEL"),
+        "QQBot": ("QQ_APP_ID", "QQ_HOME_CHANNEL"),
     }
     
     for name, (token_var, home_var) in platforms.items():

hermes_cli/tools_config.py

@@ -426,6 +426,8 @@ def _get_enabled_platforms() -> List[str]:
         enabled.append("slack")
     if get_env_value("WHATSAPP_ENABLED"):
         enabled.append("whatsapp")
+    if get_env_value("QQ_APP_ID"):
+        enabled.append("qqbot")
     return enabled
 
 

hermes_cli/web_server.py

@@ -96,6 +96,11 @@ _SCHEMA_OVERRIDES: Dict[str, Dict[str, Any]] = {
         "description": "Default model (e.g. anthropic/claude-sonnet-4.6)",
         "category": "general",
     },
+    "model_context_length": {
+        "type": "number",
+        "description": "Context window override (0 = auto-detect from model metadata)",
+        "category": "general",
+    },
     "terminal.backend": {
         "type": "select",
         "description": "Terminal execution backend",
@@ -246,6 +251,17 @@ def _build_schema_from_config(
 
 CONFIG_SCHEMA = _build_schema_from_config(DEFAULT_CONFIG)
 
+# Inject virtual fields that don't live in DEFAULT_CONFIG but are surfaced
+# by the normalize/denormalize cycle.  Insert model_context_length right after
+# the "model" key so it renders adjacent in the frontend.
+_mcl_entry = _SCHEMA_OVERRIDES["model_context_length"]
+_ordered_schema: Dict[str, Dict[str, Any]] = {}
+for _k, _v in CONFIG_SCHEMA.items():
+    _ordered_schema[_k] = _v
+    if _k == "model":
+        _ordered_schema["model_context_length"] = _mcl_entry
+CONFIG_SCHEMA = _ordered_schema
+
 
 class ConfigUpdate(BaseModel):
     config: dict
@@ -408,11 +424,19 @@ def _normalize_config_for_web(config: Dict[str, Any]) -> Dict[str, Any]:
     or a dict (``{default: ..., provider: ..., base_url: ...}``).  The schema is built
     from DEFAULT_CONFIG where ``model`` is a string, but user configs often have the
     dict form.  Normalize to the string form so the frontend schema matches.
+
+    Also surfaces ``model_context_length`` as a top-level field so the web UI can
+    display and edit it.  A value of 0 means "auto-detect".
     """
     config = dict(config)  # shallow copy
     model_val = config.get("model")
     if isinstance(model_val, dict):
+        # Extract context_length before flattening the dict
+        ctx_len = model_val.get("context_length", 0)
         config["model"] = model_val.get("default", model_val.get("name", ""))
+        config["model_context_length"] = ctx_len if isinstance(ctx_len, int) else 0
+    else:
+        config["model_context_length"] = 0
     return config
 
 
@@ -433,6 +457,93 @@ async def get_schema():
     return {"fields": CONFIG_SCHEMA, "category_order": _CATEGORY_ORDER}
 
 
+_EMPTY_MODEL_INFO: dict = {
+    "model": "",
+    "provider": "",
+    "auto_context_length": 0,
+    "config_context_length": 0,
+    "effective_context_length": 0,
+    "capabilities": {},
+}
+
+
+@app.get("/api/model/info")
+def get_model_info():
+    """Return resolved model metadata for the currently configured model.
+
+    Calls the same context-length resolution chain the agent uses, so the
+    frontend can display "Auto-detected: 200K" alongside the override field.
+    Also returns model capabilities (vision, reasoning, tools) when available.
+    """
+    try:
+        cfg = load_config()
+        model_cfg = cfg.get("model", "")
+
+        # Extract model name and provider from the config
+        if isinstance(model_cfg, dict):
+            model_name = model_cfg.get("default", model_cfg.get("name", ""))
+            provider = model_cfg.get("provider", "")
+            base_url = model_cfg.get("base_url", "")
+            config_ctx = model_cfg.get("context_length")
+        else:
+            model_name = str(model_cfg) if model_cfg else ""
+            provider = ""
+            base_url = ""
+            config_ctx = None
+
+        if not model_name:
+            return dict(_EMPTY_MODEL_INFO, provider=provider)
+
+        # Resolve auto-detected context length (pass config_ctx=None to get
+        # purely auto-detected value, then separately report the override)
+        try:
+            from agent.model_metadata import get_model_context_length
+            auto_ctx = get_model_context_length(
+                model=model_name,
+                base_url=base_url,
+                provider=provider,
+                config_context_length=None,  # ignore override — we want auto value
+            )
+        except Exception:
+            auto_ctx = 0
+
+        config_ctx_int = 0
+        if isinstance(config_ctx, int) and config_ctx > 0:
+            config_ctx_int = config_ctx
+
+        # Effective is what the agent actually uses
+        effective_ctx = config_ctx_int if config_ctx_int > 0 else auto_ctx
+
+        # Try to get model capabilities from models.dev
+        caps = {}
+        try:
+            from agent.models_dev import get_model_capabilities
+            mc = get_model_capabilities(provider=provider, model=model_name)
+            if mc is not None:
+                caps = {
+                    "supports_tools": mc.supports_tools,
+                    "supports_vision": mc.supports_vision,
+                    "supports_reasoning": mc.supports_reasoning,
+                    "context_window": mc.context_window,
+                    "max_output_tokens": mc.max_output_tokens,
+                    "model_family": mc.model_family,
+                }
+        except Exception:
+            pass
+
+        return {
+            "model": model_name,
+            "provider": provider,
+            "auto_context_length": auto_ctx,
+            "config_context_length": config_ctx_int,
+            "effective_context_length": effective_ctx,
+            "capabilities": caps,
+        }
+    except Exception:
+        _log.exception("GET /api/model/info failed")
+        return dict(_EMPTY_MODEL_INFO)
+
+
 def _denormalize_config_from_web(config: Dict[str, Any]) -> Dict[str, Any]:
     """Reverse _normalize_config_for_web before saving.
 
@@ -440,12 +551,24 @@ def _denormalize_config_from_web(config: Dict[str, Any]) -> Dict[str, Any]:
     to recover model subkeys (provider, base_url, api_mode, etc.) that were
     stripped from the GET response.  The frontend only sees model as a flat
     string; the rest is preserved transparently.
+
+    Also handles ``model_context_length`` — writes it back into the model dict
+    as ``context_length``.  A value of 0 or absent means "auto-detect" (omitted
+    from the dict so get_model_context_length() uses its normal resolution).
     """
     config = dict(config)
     # Remove any _model_meta that might have leaked in (shouldn't happen
     # with the stripped GET response, but be defensive)
     config.pop("_model_meta", None)
 
+    # Extract and remove model_context_length before processing model
+    ctx_override = config.pop("model_context_length", 0)
+    if not isinstance(ctx_override, int):
+        try:
+            ctx_override = int(ctx_override)
+        except (TypeError, ValueError):
+            ctx_override = 0
+
     model_val = config.get("model")
     if isinstance(model_val, str) and model_val:
         # Read the current disk config to recover model subkeys
@@ -455,7 +578,20 @@ def _denormalize_config_from_web(config: Dict[str, Any]) -> Dict[str, Any]:
             if isinstance(disk_model, dict):
                 # Preserve all subkeys, update default with the new value
                 disk_model["default"] = model_val
+                # Write context_length into the model dict (0 = remove/auto)
+                if ctx_override > 0:
+                    disk_model["context_length"] = ctx_override
+                else:
+                    disk_model.pop("context_length", None)
                 config["model"] = disk_model
+            else:
+                # Model was previously a bare string — upgrade to dict if
+                # user is setting a context_length override
+                if ctx_override > 0:
+                    config["model"] = {
+                        "default": model_val,
+                        "context_length": ctx_override,
+                    }
         except Exception:
             pass  # can't read disk config — just use the string form
     return config