fix: add numbered approval and clarify shortcuts (#956)

agent/auxiliary_client.py

@@ -1,4 +1,4 @@
-from agent.telemetry_logger import log_token_usage\n"""Shared auxiliary client router for side tasks.
+"""Shared auxiliary client router for side tasks.
 
 Provides a single resolution chain so every consumer (context compression,
 session search, web extraction, vision analysis, browser vision) picks up
@@ -34,6 +34,8 @@ Payment / credit exhaustion fallback:
   their OpenRouter balance but has Codex OAuth or another provider available.
 """
 
+from agent.telemetry_logger import log_token_usage
+
 import json
 import logging
 import os
@@ -396,7 +398,8 @@ class _CodexCompletionsAdapter:
                     prompt_tokens=getattr(resp_usage, "input_tokens", 0),
                     completion_tokens=getattr(resp_usage, "output_tokens", 0),
                     total_tokens=getattr(resp_usage, "total_tokens", 0),
-                )\n        log_token_usage(usage.prompt_tokens, usage.completion_tokens, model)
+                )
+                log_token_usage(usage.prompt_tokens, usage.completion_tokens, model)
         except Exception as exc:
             logger.debug("Codex auxiliary Responses API call failed: %s", exc)
             raise
@@ -529,7 +532,8 @@ class _AnthropicCompletionsAdapter:
                 prompt_tokens=prompt_tokens,
                 completion_tokens=completion_tokens,
                 total_tokens=total_tokens,
-            )\n    log_token_usage(usage.prompt_tokens, usage.completion_tokens, model)
+            )
+            log_token_usage(usage.prompt_tokens, usage.completion_tokens, model)
 
         choice = SimpleNamespace(
             index=0,

cli.py

@@ -7254,6 +7254,40 @@ class HermesCLI:
             "Use your best judgement to make the choice and proceed."
         )
 
+    def _handle_clarify_selection(self) -> None:
+        """Process the currently selected clarify choice."""
+        state = self._clarify_state
+        if not state or self._clarify_freetext:
+            return
+
+        selected = state.get("selected", 0)
+        choices = state.get("choices") or []
+        if selected < len(choices):
+            state["response_queue"].put(choices[selected])
+            self._clarify_state = None
+            self._clarify_freetext = False
+            self._invalidate()
+            return
+
+        if selected == len(choices):
+            self._clarify_freetext = True
+            self._invalidate()
+
+    def _handle_clarify_number_shortcut(self, number: int) -> bool:
+        """Select a clarify option by number key."""
+        state = self._clarify_state
+        if not state or self._clarify_freetext:
+            return False
+
+        choices = state.get("choices") or []
+        max_option = len(choices) + 1
+        if number < 1 or number > max_option:
+            return False
+
+        state["selected"] = number - 1
+        self._handle_clarify_selection()
+        return True
+
     def _sudo_password_callback(self) -> str:
         """
         Prompt for sudo password through the prompt_toolkit UI.
@@ -7362,6 +7396,20 @@ class HermesCLI:
             choices.append("view")
         return choices
 
+    def _handle_approval_number_shortcut(self, number: int) -> bool:
+        """Select an approval option by number key."""
+        state = self._approval_state
+        if not state:
+            return False
+
+        choices = state.get("choices") or []
+        if number < 1 or number > len(choices):
+            return False
+
+        state["selected"] = number - 1
+        self._handle_approval_selection()
+        return True
+
     def _handle_approval_selection(self) -> None:
         """Process the currently selected dangerous-command approval choice."""
         state = self._approval_state
@@ -7437,8 +7485,9 @@ class HermesCLI:
         preview_lines.extend(_wrap_panel_text(cmd_display, 60))
         for i, choice in enumerate(choices):
             prefix = '❯ ' if i == selected else '  '
+            label = f"{i + 1}. {choice_labels.get(choice, choice)}"
             preview_lines.extend(_wrap_panel_text(
-                f"{prefix}{choice_labels.get(choice, choice)}",
+                f"{prefix}{label}",
                 60,
                 subsequent_indent="  ",
             ))
@@ -7456,7 +7505,7 @@ class HermesCLI:
             _append_panel_line(lines, 'class:approval-border', 'class:approval-cmd', wrapped, box_width)
         _append_blank_panel_line(lines, 'class:approval-border', box_width)
         for i, choice in enumerate(choices):
-            label = choice_labels.get(choice, choice)
+            label = f"{i + 1}. {choice_labels.get(choice, choice)}"
             style = 'class:approval-selected' if i == selected else 'class:approval-choice'
             prefix = '❯ ' if i == selected else '  '
             for wrapped in _wrap_panel_text(f"{prefix}{label}", inner_text_width, subsequent_indent="  "):
@@ -7465,6 +7514,97 @@ class HermesCLI:
         lines.append(('class:approval-border', '╰' + ('─' * box_width) + '╯\n'))
         return lines
 
+    def _get_clarify_display_fragments(self):
+        """Render the clarify panel for the prompt_toolkit UI."""
+        state = self._clarify_state
+        if not state:
+            return []
+
+        def _panel_box_width(title: str, content_lines: list[str], min_width: int = 46, max_width: int = 76) -> int:
+            term_cols = shutil.get_terminal_size((100, 20)).columns
+            longest = max([len(title)] + [len(line) for line in content_lines] + [min_width - 4])
+            inner = min(max(longest + 4, min_width - 2), max_width - 2, max(24, term_cols - 6))
+            return inner + 2
+
+        def _wrap_panel_text(text: str, width: int, subsequent_indent: str = "") -> list[str]:
+            wrapped = textwrap.wrap(
+                text,
+                width=max(8, width),
+                break_long_words=False,
+                break_on_hyphens=False,
+                subsequent_indent=subsequent_indent,
+            )
+            return wrapped or [""]
+
+        def _append_panel_line(lines, border_style: str, content_style: str, text: str, box_width: int) -> None:
+            inner_width = max(0, box_width - 2)
+            lines.append((border_style, "│ "))
+            lines.append((content_style, text.ljust(inner_width)))
+            lines.append((border_style, " │\n"))
+
+        def _append_blank_panel_line(lines, border_style: str, box_width: int) -> None:
+            lines.append((border_style, "│" + (" " * box_width) + "│\n"))
+
+        question = state["question"]
+        choices = state.get("choices") or []
+        selected = state.get("selected", 0)
+        preview_lines = _wrap_panel_text(question, 60)
+        for i, choice in enumerate(choices):
+            prefix = "❯ " if i == selected and not self._clarify_freetext else "  "
+            label = f"{i + 1}. {choice}"
+            preview_lines.extend(_wrap_panel_text(f"{prefix}{label}", 60, subsequent_indent="  "))
+        other_number = len(choices) + 1
+        other_label = (
+            f"❯ {other_number}. Other (type below)" if self._clarify_freetext
+            else f"❯ {other_number}. Other (type your answer)" if selected == len(choices)
+            else f"  {other_number}. Other (type your answer)"
+        )
+        preview_lines.extend(_wrap_panel_text(other_label, 60, subsequent_indent="  "))
+        box_width = _panel_box_width("Hermes needs your input", preview_lines)
+        inner_text_width = max(8, box_width - 2)
+
+        lines = []
+        lines.append(('class:clarify-border', '╭─ '))
+        lines.append(('class:clarify-title', 'Hermes needs your input'))
+        lines.append(('class:clarify-border', ' ' + ('─' * max(0, box_width - len("Hermes needs your input") - 3)) + '╮\n'))
+        _append_blank_panel_line(lines, 'class:clarify-border', box_width)
+
+        for wrapped in _wrap_panel_text(question, inner_text_width):
+            _append_panel_line(lines, 'class:clarify-border', 'class:clarify-question', wrapped, box_width)
+        _append_blank_panel_line(lines, 'class:clarify-border', box_width)
+
+        if self._clarify_freetext and not choices:
+            guidance = "Type your answer in the prompt below, then press Enter."
+            for wrapped in _wrap_panel_text(guidance, inner_text_width):
+                _append_panel_line(lines, 'class:clarify-border', 'class:clarify-choice', wrapped, box_width)
+            _append_blank_panel_line(lines, 'class:clarify-border', box_width)
+
+        if choices:
+            for i, choice in enumerate(choices):
+                style = 'class:clarify-selected' if i == selected and not self._clarify_freetext else 'class:clarify-choice'
+                prefix = '❯ ' if i == selected and not self._clarify_freetext else '  '
+                label = f"{i + 1}. {choice}"
+                wrapped_lines = _wrap_panel_text(f"{prefix}{label}", inner_text_width, subsequent_indent="  ")
+                for wrapped in wrapped_lines:
+                    _append_panel_line(lines, 'class:clarify-border', style, wrapped, box_width)
+
+            other_idx = len(choices)
+            if selected == other_idx and not self._clarify_freetext:
+                other_style = 'class:clarify-selected'
+                other_label = f'❯ {other_number}. Other (type your answer)'
+            elif self._clarify_freetext:
+                other_style = 'class:clarify-active-other'
+                other_label = f'❯ {other_number}. Other (type below)'
+            else:
+                other_style = 'class:clarify-choice'
+                other_label = f'  {other_number}. Other (type your answer)'
+            for wrapped in _wrap_panel_text(other_label, inner_text_width, subsequent_indent="  "):
+                _append_panel_line(lines, 'class:clarify-border', other_style, wrapped, box_width)
+
+        _append_blank_panel_line(lines, 'class:clarify-border', box_width)
+        lines.append(('class:clarify-border', '╰' + ('─' * box_width) + '╯\n'))
+        return lines
+
     def _secret_capture_callback(self, var_name: str, prompt: str, metadata=None) -> dict:
         return prompt_for_secret(self, var_name, prompt, metadata)
 
@@ -8371,17 +8511,8 @@ class HermesCLI:
 
             # --- Clarify choice mode: confirm the highlighted selection ---
             if self._clarify_state and not self._clarify_freetext:
-                state = self._clarify_state
-                selected = state["selected"]
-                choices = state.get("choices") or []
-                if selected < len(choices):
-                    state["response_queue"].put(choices[selected])
-                    self._clarify_state = None
-                    event.app.invalidate()
-                else:
-                    # "Other" selected → switch to freetext
-                    self._clarify_freetext = True
-                    event.app.invalidate()
+                self._handle_clarify_selection()
+                event.app.invalidate()
                 return
 
             # --- Normal input routing ---
@@ -8501,6 +8632,19 @@ class HermesCLI:
                 self._approval_state["selected"] = min(max_idx, self._approval_state["selected"] + 1)
                 event.app.invalidate()
 
+        # --- Numbered shortcuts for clarify / approval modal prompts ---
+        for _digit in '123456789':
+            @kb.add(_digit, filter=Condition(lambda: bool(self._approval_state) or (bool(self._clarify_state) and not self._clarify_freetext)))
+            def _handle_modal_number(event, digit=_digit):
+                number = int(digit)
+                handled = False
+                if self._approval_state:
+                    handled = self._handle_approval_number_shortcut(number)
+                elif self._clarify_state and not self._clarify_freetext:
+                    handled = self._handle_clarify_number_shortcut(number)
+                if handled:
+                    event.app.invalidate()
+
         # --- /model picker: arrow-key navigation ---
         @kb.add('up', filter=Condition(lambda: bool(self._model_picker_state)))
         def model_picker_up(event):
@@ -8995,7 +9139,7 @@ class HermesCLI:
             if cli_ref._approval_state:
                 remaining = max(0, int(cli_ref._approval_deadline - _time.monotonic()))
                 return [
-                    ('class:hint', '  ↑/↓ to select, Enter to confirm'),
+                    ('class:hint', '  1-9 or ↑/↓ to select, Enter to confirm'),
                     ('class:clarify-countdown', f'  ({remaining}s)'),
                 ]
 
@@ -9008,7 +9152,7 @@ class HermesCLI:
                         ('class:clarify-countdown', countdown),
                     ]
                 return [
-                    ('class:hint', '  ↑/↓ to select, Enter to confirm'),
+                    ('class:hint', '  1-9 or ↑/↓ to select, Enter to confirm'),
                     ('class:clarify-countdown', countdown),
                 ]
 
@@ -9086,71 +9230,7 @@ class HermesCLI:
             lines.append((border_style, "│" + (" " * box_width) + "│\n"))
 
         def _get_clarify_display():
-            """Build styled text for the clarify question/choices panel."""
-            state = cli_ref._clarify_state
-            if not state:
-                return []
-
-            question = state["question"]
-            choices = state.get("choices") or []
-            selected = state.get("selected", 0)
-            preview_lines = _wrap_panel_text(question, 60)
-            for i, choice in enumerate(choices):
-                prefix = "❯ " if i == selected and not cli_ref._clarify_freetext else "  "
-                preview_lines.extend(_wrap_panel_text(f"{prefix}{choice}", 60, subsequent_indent="  "))
-            other_label = (
-                "❯ Other (type below)" if cli_ref._clarify_freetext
-                else "❯ Other (type your answer)" if selected == len(choices)
-                else "  Other (type your answer)"
-            )
-            preview_lines.extend(_wrap_panel_text(other_label, 60, subsequent_indent="  "))
-            box_width = _panel_box_width("Hermes needs your input", preview_lines)
-            inner_text_width = max(8, box_width - 2)
-
-            lines = []
-            # Box top border
-            lines.append(('class:clarify-border', '╭─ '))
-            lines.append(('class:clarify-title', 'Hermes needs your input'))
-            lines.append(('class:clarify-border', ' ' + ('─' * max(0, box_width - len("Hermes needs your input") - 3)) + '╮\n'))
-            _append_blank_panel_line(lines, 'class:clarify-border', box_width)
-
-            # Question text
-            for wrapped in _wrap_panel_text(question, inner_text_width):
-                _append_panel_line(lines, 'class:clarify-border', 'class:clarify-question', wrapped, box_width)
-            _append_blank_panel_line(lines, 'class:clarify-border', box_width)
-
-            if cli_ref._clarify_freetext and not choices:
-                guidance = "Type your answer in the prompt below, then press Enter."
-                for wrapped in _wrap_panel_text(guidance, inner_text_width):
-                    _append_panel_line(lines, 'class:clarify-border', 'class:clarify-choice', wrapped, box_width)
-                _append_blank_panel_line(lines, 'class:clarify-border', box_width)
-
-            if choices:
-                # Multiple-choice mode: show selectable options
-                for i, choice in enumerate(choices):
-                    style = 'class:clarify-selected' if i == selected and not cli_ref._clarify_freetext else 'class:clarify-choice'
-                    prefix = '❯ ' if i == selected and not cli_ref._clarify_freetext else '  '
-                    wrapped_lines = _wrap_panel_text(f"{prefix}{choice}", inner_text_width, subsequent_indent="  ")
-                    for wrapped in wrapped_lines:
-                        _append_panel_line(lines, 'class:clarify-border', style, wrapped, box_width)
-
-                # "Other" option (5th line, only shown when choices exist)
-                other_idx = len(choices)
-                if selected == other_idx and not cli_ref._clarify_freetext:
-                    other_style = 'class:clarify-selected'
-                    other_label = '❯ Other (type your answer)'
-                elif cli_ref._clarify_freetext:
-                    other_style = 'class:clarify-active-other'
-                    other_label = '❯ Other (type below)'
-                else:
-                    other_style = 'class:clarify-choice'
-                    other_label = '  Other (type your answer)'
-                for wrapped in _wrap_panel_text(other_label, inner_text_width, subsequent_indent="  "):
-                    _append_panel_line(lines, 'class:clarify-border', other_style, wrapped, box_width)
-
-            _append_blank_panel_line(lines, 'class:clarify-border', box_width)
-            lines.append(('class:clarify-border', '╰' + ('─' * box_width) + '╯\n'))
-            return lines
+            return cli_ref._get_clarify_display_fragments()
 
         clarify_widget = ConditionalContainer(
             Window(

hermes_cli/config.py

@@ -523,7 +523,7 @@ DEFAULT_CONFIG = {
     
     # Text-to-speech configuration
     "tts": {
-        "provider": "edge",  # "edge" (free) | "elevenlabs" (premium) | "openai" | "minimax" | "mistral" | "neutts" (local) | "kittentts" (local)
+        "provider": "edge",  # "edge" (free) | "elevenlabs" (premium) | "openai" | "minimax" | "mistral" | "neutts" (local)
         "edge": {
             "voice": "en-US-AriaNeural",
             # Popular: AriaNeural, JennyNeural, AndrewNeural, BrianNeural, SoniaNeural
@@ -547,12 +547,6 @@ DEFAULT_CONFIG = {
             "model": "neuphonic/neutts-air-q4-gguf",  # HuggingFace model repo
             "device": "cpu",  # cpu, cuda, or mps
         },
-        "kittentts": {
-            "model": "KittenML/kitten-tts-nano-0.8-int8",  # 25MB int8 default
-            "voice": "Jasper",  # Jasper, Bella, Luna, Bruno, Rosie, Hugo, Kiki, Leo
-            "speed": 1.0,
-            "clean_text": True,
-        },
     },
     
     "stt": {

hermes_cli/setup.py

@@ -443,16 +443,6 @@ def _print_setup_summary(config: dict, hermes_home):
             tool_status.append(("Text-to-Speech (NeuTTS local)", True, None))
         else:
             tool_status.append(("Text-to-Speech (NeuTTS — not installed)", False, "run 'hermes setup tts'"))
-    elif tts_provider == "kittentts":
-        try:
-            import importlib.util
-            kittentts_ok = importlib.util.find_spec("kittentts") is not None
-        except Exception:
-            kittentts_ok = False
-        if kittentts_ok:
-            tool_status.append(("Text-to-Speech (KittenTTS local)", True, None))
-        else:
-            tool_status.append(("Text-to-Speech (KittenTTS — not installed)", False, "run 'hermes setup tts'"))
     else:
         tool_status.append(("Text-to-Speech (Edge TTS)", True, None))
 
@@ -901,7 +891,6 @@ def _install_neutts_deps() -> bool:
                 return False
         else:
             print_warning("espeak-ng is required for NeuTTS. Install it manually before using NeuTTS.")
-            return False
 
     # Install neutts Python package
     print()
@@ -921,34 +910,8 @@ def _install_neutts_deps() -> bool:
         return False
 
 
-def _install_kittentts_deps() -> bool:
-    """Install KittenTTS dependencies with user approval. Returns True on success."""
-    import subprocess
-    import sys
-
-    wheel_url = (
-        "https://github.com/KittenML/KittenTTS/releases/download/"
-        "0.8.1/kittentts-0.8.1-py3-none-any.whl"
-    )
-    print()
-    print_info("Installing kittentts Python package (~25-80MB model downloaded on first use)...")
-    print()
-    try:
-        subprocess.run(
-            [sys.executable, "-m", "pip", "install", "-U", wheel_url, "soundfile", "--quiet"],
-            check=True, timeout=300,
-        )
-        print_success("kittentts installed successfully")
-        return True
-    except (subprocess.CalledProcessError, subprocess.TimeoutExpired) as e:
-        print_error(f"Failed to install kittentts: {e}")
-        print_info(f"Try manually: python -m pip install -U '{wheel_url}' soundfile")
-        return False
-
-
 def _setup_tts_provider(config: dict):
-    """Interactive TTS provider selection with install flow for local providers."""
-
+    """Interactive TTS provider selection with install flow for NeuTTS."""
     tts_config = config.get("tts", {})
     current_provider = tts_config.get("provider", "edge")
     subscription_features = get_nous_subscription_features(config)
@@ -960,7 +923,6 @@ def _setup_tts_provider(config: dict):
         "minimax": "MiniMax TTS",
         "mistral": "Mistral Voxtral TTS",
         "neutts": "NeuTTS",
-        "kittentts": "KittenTTS",
     }
     current_label = provider_labels.get(current_provider, current_provider)
 
@@ -982,10 +944,9 @@ def _setup_tts_provider(config: dict):
             "MiniMax TTS (high quality with voice cloning, needs API key)",
             "Mistral Voxtral TTS (multilingual, native Opus, needs API key)",
             "NeuTTS (local on-device, free, ~300MB model download)",
-            "KittenTTS (local on-device, free, lightweight ~25-80MB ONNX)",
         ]
     )
-    providers.extend(["edge", "elevenlabs", "openai", "minimax", "mistral", "neutts", "kittentts"])
+    providers.extend(["edge", "elevenlabs", "openai", "minimax", "mistral", "neutts"])
     choices.append(f"Keep current ({current_label})")
     keep_current_idx = len(choices) - 1
     idx = prompt_choice("Select TTS provider:", choices, keep_current_idx)
@@ -1027,28 +988,6 @@ def _setup_tts_provider(config: dict):
                 print_info("Skipping install. Set tts.provider to 'neutts' after installing manually.")
                 selected = "edge"
 
-    elif selected == "kittentts":
-        try:
-            import importlib.util
-            already_installed = importlib.util.find_spec("kittentts") is not None
-        except Exception:
-            already_installed = False
-
-        if already_installed:
-            print_success("KittenTTS is already installed")
-        else:
-            print()
-            print_info("KittenTTS is lightweight (~25-80MB, CPU-only, no API key required).")
-            print_info("Voices: Jasper, Bella, Luna, Bruno, Rosie, Hugo, Kiki, Leo")
-            print()
-            if prompt_yes_no("Install KittenTTS now?", True):
-                if not _install_kittentts_deps():
-                    print_warning("KittenTTS installation incomplete. Falling back to Edge TTS.")
-                    selected = "edge"
-            else:
-                print_info("Skipping install. Set tts.provider to 'kittentts' after installing manually.")
-                selected = "edge"
-
     elif selected == "elevenlabs":
         existing = get_env_value("ELEVENLABS_API_KEY")
         if not existing:

hermes_cli/tools_config.py

@@ -164,14 +164,6 @@ TOOL_CATEGORIES = {
                 ],
                 "tts_provider": "mistral",
             },
-            {
-                "name": "KittenTTS",
-                "badge": "local · free",
-                "tag": "Lightweight local ONNX TTS (~25MB), no API key",
-                "env_vars": [],
-                "tts_provider": "kittentts",
-                "post_setup": "kittentts",
-            },
         ],
     },
     "web": {
@@ -411,36 +403,6 @@ def _run_post_setup(post_setup_key: str):
             _print_warning("    Node.js not found. Install Camofox via Docker:")
             _print_info("      docker run -p 9377:9377 -e CAMOFOX_PORT=9377 jo-inc/camofox-browser")
 
-    elif post_setup_key == "kittentts":
-        try:
-            __import__("kittentts")
-            _print_success("    kittentts is already installed")
-            return
-        except ImportError:
-            pass
-        import subprocess
-        _print_info("    Installing kittentts (~25-80MB model, CPU-only)...")
-        wheel_url = (
-            "https://github.com/KittenML/KittenTTS/releases/download/"
-            "0.8.1/kittentts-0.8.1-py3-none-any.whl"
-        )
-        try:
-            result = subprocess.run(
-                [sys.executable, "-m", "pip", "install", "-U", wheel_url, "soundfile", "--quiet"],
-                capture_output=True, text=True, timeout=300,
-            )
-            if result.returncode == 0:
-                _print_success("    kittentts installed")
-                _print_info("    Voices: Jasper, Bella, Luna, Bruno, Rosie, Hugo, Kiki, Leo")
-                _print_info("    Models: KittenML/kitten-tts-nano-0.8-int8 (25MB), micro (41MB), mini (80MB)")
-            else:
-                _print_warning("    kittentts install failed:")
-                _print_info(f"      {result.stderr.strip()[:300]}")
-                _print_info(f"    Run manually: python -m pip install -U '{wheel_url}' soundfile")
-        except subprocess.TimeoutExpired:
-            _print_warning("    kittentts install timed out (>5min)")
-            _print_info(f"    Run manually: python -m pip install -U '{wheel_url}' soundfile")
-
     elif post_setup_key == "rl_training":
         try:
             __import__("tinker_atropos")

tests/cli/test_cli_numbered_prompt_shortcuts.py

@@ -0,0 +1,172 @@
+import queue
+import threading
+from types import SimpleNamespace
+from unittest.mock import MagicMock
+
+from cli import HermesCLI
+
+
+class _FakeBuffer:
+    def __init__(self, text="", cursor_position=None):
+        self.text = text
+        self.cursor_position = len(text) if cursor_position is None else cursor_position
+
+    def reset(self, append_to_history=False):
+        self.text = ""
+        self.cursor_position = 0
+
+
+def _make_cli_stub():
+    cli = HermesCLI.__new__(HermesCLI)
+    cli._approval_state = None
+    cli._approval_deadline = 0
+    cli._approval_lock = threading.Lock()
+    cli._clarify_state = None
+    cli._clarify_freetext = False
+    cli._clarify_deadline = 0
+    cli._sudo_state = None
+    cli._sudo_deadline = 0
+    cli._secret_state = None
+    cli._secret_deadline = 0
+    cli._modal_input_snapshot = None
+    cli._invalidate = MagicMock()
+    cli._app = SimpleNamespace(invalidate=MagicMock(), current_buffer=_FakeBuffer())
+    return cli
+
+
+def test_approval_display_numbers_choices():
+    cli = _make_cli_stub()
+    cli._approval_state = {
+        "command": "sudo rm -rf /tmp/example",
+        "description": "dangerous command",
+        "choices": ["once", "session", "always", "deny"],
+        "selected": 0,
+        "response_queue": queue.Queue(),
+    }
+
+    rendered = "".join(text for _style, text in cli._get_approval_display_fragments())
+
+    assert "❯ 1. Allow once" in rendered
+    assert "2. Allow for this session" in rendered
+    assert "3. Add to permanent allowlist" in rendered
+    assert "4. Deny" in rendered
+
+
+def test_approval_number_shortcut_submits_choice():
+    cli = _make_cli_stub()
+    response_queue = queue.Queue()
+    cli._approval_state = {
+        "command": "sudo rm -rf /tmp/example",
+        "description": "dangerous command",
+        "choices": ["once", "session", "always", "deny"],
+        "selected": 0,
+        "response_queue": response_queue,
+    }
+
+    assert cli._handle_approval_number_shortcut(2) is True
+    assert response_queue.get_nowait() == "session"
+    assert cli._approval_state is None
+
+
+def test_approval_selection_still_submits_selected_choice():
+    cli = _make_cli_stub()
+    response_queue = queue.Queue()
+    cli._approval_state = {
+        "command": "sudo rm -rf /tmp/example",
+        "description": "dangerous command",
+        "choices": ["once", "session", "always", "deny"],
+        "selected": 1,
+        "response_queue": response_queue,
+    }
+
+    cli._handle_approval_selection()
+
+    assert response_queue.get_nowait() == "session"
+    assert cli._approval_state is None
+
+
+def test_approval_number_shortcut_handles_view_in_place():
+    cli = _make_cli_stub()
+    response_queue = queue.Queue()
+    cli._approval_state = {
+        "command": "sudo dd if=/tmp/in of=/usr/share/keyrings/githubcli-archive-keyring.gpg bs=4M status=progress",
+        "description": "disk copy",
+        "choices": ["once", "session", "always", "deny", "view"],
+        "selected": 0,
+        "response_queue": response_queue,
+    }
+
+    assert cli._handle_approval_number_shortcut(5) is True
+    assert cli._approval_state is not None
+    assert cli._approval_state["show_full"] is True
+    assert "view" not in cli._approval_state["choices"]
+    assert cli._approval_state["selected"] == 3
+    assert response_queue.empty()
+
+
+def test_clarify_display_numbers_choices_and_other():
+    cli = _make_cli_stub()
+    cli._clarify_state = {
+        "question": "Pick the best option",
+        "choices": ["Alpha", "Beta", "Gamma", "Delta"],
+        "selected": 1,
+        "response_queue": queue.Queue(),
+    }
+
+    rendered = "".join(text for _style, text in cli._get_clarify_display_fragments())
+
+    assert "1. Alpha" in rendered
+    assert "❯ 2. Beta" in rendered
+    assert "3. Gamma" in rendered
+    assert "4. Delta" in rendered
+    assert "5. Other (type your answer)" in rendered
+
+
+def test_clarify_number_shortcut_submits_choice():
+    cli = _make_cli_stub()
+    response_queue = queue.Queue()
+    cli._clarify_state = {
+        "question": "Pick the best option",
+        "choices": ["Alpha", "Beta", "Gamma"],
+        "selected": 0,
+        "response_queue": response_queue,
+    }
+
+    assert cli._handle_clarify_number_shortcut(3) is True
+    assert response_queue.get_nowait() == "Gamma"
+    assert cli._clarify_state is None
+    assert cli._clarify_freetext is False
+
+
+def test_clarify_selection_still_submits_selected_choice():
+    cli = _make_cli_stub()
+    response_queue = queue.Queue()
+    cli._clarify_state = {
+        "question": "Pick the best option",
+        "choices": ["Alpha", "Beta", "Gamma"],
+        "selected": 1,
+        "response_queue": response_queue,
+    }
+
+    cli._handle_clarify_selection()
+
+    assert response_queue.get_nowait() == "Beta"
+    assert cli._clarify_state is None
+    assert cli._clarify_freetext is False
+
+
+def test_clarify_number_shortcut_activates_other_freetext():
+    cli = _make_cli_stub()
+    response_queue = queue.Queue()
+    cli._clarify_state = {
+        "question": "Pick the best option",
+        "choices": ["Alpha", "Beta", "Gamma"],
+        "selected": 0,
+        "response_queue": response_queue,
+    }
+
+    assert cli._handle_clarify_number_shortcut(4) is True
+    assert cli._clarify_state is not None
+    assert cli._clarify_state["selected"] == 3
+    assert cli._clarify_freetext is True
+    assert response_queue.empty()

tests/tools/test_tts_kittentts.py

@@ -1,236 +0,0 @@
-"""Tests for the KittenTTS local provider in tools/tts_tool.py."""
-
-import json
-from unittest.mock import MagicMock, patch
-
-import numpy as np
-import pytest
-
-
-@pytest.fixture(autouse=True)
-def clean_env(monkeypatch):
-    for key in ("HERMES_SESSION_PLATFORM",):
-        monkeypatch.delenv(key, raising=False)
-
-
-@pytest.fixture(autouse=True)
-def clear_kittentts_cache():
-    """Reset the module-level model cache between tests."""
-    from tools import tts_tool as _tt
-    _tt._kittentts_model_cache.clear()
-    yield
-    _tt._kittentts_model_cache.clear()
-
-
-@pytest.fixture
-def mock_kittentts_module():
-    """Inject a fake kittentts + soundfile module that return stub objects."""
-    fake_model = MagicMock()
-    # 24kHz float32 PCM at ~2s of silence
-    fake_model.generate.return_value = np.zeros(48000, dtype=np.float32)
-    fake_cls = MagicMock(return_value=fake_model)
-    fake_kittentts = MagicMock()
-    fake_kittentts.KittenTTS = fake_cls
-
-    # Stub soundfile — the real package isn't installed in CI venv, and
-    # _generate_kittentts does `import soundfile as sf` at runtime.
-    fake_sf = MagicMock()
-
-    def _fake_write(path, audio, samplerate):
-        # Emulate writing a real file so downstream path checks succeed.
-        import pathlib
-
-        pathlib.Path(path).write_bytes(b"RIFF\x00\x00\x00\x00WAVEfmt fake")
-
-    fake_sf.write = _fake_write
-
-    with patch.dict(
-        "sys.modules",
-        {"kittentts": fake_kittentts, "soundfile": fake_sf},
-    ):
-        yield fake_model, fake_cls
-
-
-class TestGenerateKittenTts:
-    def test_successful_wav_generation(self, tmp_path, mock_kittentts_module):
-        from tools.tts_tool import _generate_kittentts
-
-        fake_model, fake_cls = mock_kittentts_module
-        output_path = str(tmp_path / "test.wav")
-        result = _generate_kittentts("Hello world", output_path, {})
-
-        assert result == output_path
-        assert (tmp_path / "test.wav").exists()
-        fake_cls.assert_called_once()
-        fake_model.generate.assert_called_once()
-
-    def test_config_passes_voice_speed_cleantext(self, tmp_path, mock_kittentts_module):
-        from tools.tts_tool import _generate_kittentts
-
-        fake_model, _ = mock_kittentts_module
-        config = {
-            "kittentts": {
-                "model": "KittenML/kitten-tts-mini-0.8",
-                "voice": "Luna",
-                "speed": 1.25,
-                "clean_text": False,
-            }
-        }
-        _generate_kittentts("Hi there", str(tmp_path / "out.wav"), config)
-
-        call_kwargs = fake_model.generate.call_args.kwargs
-        assert call_kwargs["voice"] == "Luna"
-        assert call_kwargs["speed"] == 1.25
-        assert call_kwargs["clean_text"] is False
-
-    def test_default_model_and_voice(self, tmp_path, mock_kittentts_module):
-        from tools.tts_tool import (
-            DEFAULT_KITTENTTS_MODEL,
-            DEFAULT_KITTENTTS_VOICE,
-            _generate_kittentts,
-        )
-
-        fake_model, fake_cls = mock_kittentts_module
-        _generate_kittentts("Hi", str(tmp_path / "out.wav"), {})
-
-        fake_cls.assert_called_once_with(DEFAULT_KITTENTTS_MODEL)
-        assert fake_model.generate.call_args.kwargs["voice"] == DEFAULT_KITTENTTS_VOICE
-
-    def test_model_is_cached_across_calls(self, tmp_path, mock_kittentts_module):
-        from tools.tts_tool import _generate_kittentts
-
-        _, fake_cls = mock_kittentts_module
-        _generate_kittentts("One", str(tmp_path / "a.wav"), {})
-        _generate_kittentts("Two", str(tmp_path / "b.wav"), {})
-
-        # Same model name → class instantiated exactly once
-        assert fake_cls.call_count == 1
-
-    def test_different_models_are_cached_separately(self, tmp_path, mock_kittentts_module):
-        from tools.tts_tool import _generate_kittentts
-
-        _, fake_cls = mock_kittentts_module
-        _generate_kittentts(
-            "A",
-            str(tmp_path / "a.wav"),
-            {"kittentts": {"model": "KittenML/kitten-tts-nano-0.8-int8"}},
-        )
-        _generate_kittentts(
-            "B",
-            str(tmp_path / "b.wav"),
-            {"kittentts": {"model": "KittenML/kitten-tts-mini-0.8"}},
-        )
-
-        assert fake_cls.call_count == 2
-
-    def test_non_wav_extension_triggers_ffmpeg_conversion(
-        self, tmp_path, mock_kittentts_module, monkeypatch
-    ):
-        """Non-.wav output path causes WAV → target ffmpeg conversion."""
-        from tools import tts_tool as _tt
-
-        calls = []
-
-        def fake_shutil_which(cmd):
-            return "/usr/bin/ffmpeg" if cmd == "ffmpeg" else None
-
-        def fake_run(cmd, check=False, timeout=None, **kw):
-            calls.append(cmd)
-            # Emulate ffmpeg writing the output file
-            import pathlib
-
-            out_path = cmd[-1]
-            pathlib.Path(out_path).write_bytes(b"fake-mp3-data")
-            return MagicMock(returncode=0)
-
-        monkeypatch.setattr(_tt.shutil, "which", fake_shutil_which)
-        monkeypatch.setattr(_tt.subprocess, "run", fake_run)
-
-        output_path = str(tmp_path / "test.mp3")
-        result = _tt._generate_kittentts("Hi", output_path, {})
-
-        assert result == output_path
-        assert len(calls) == 1
-        assert calls[0][0] == "/usr/bin/ffmpeg"
-
-    def test_missing_kittentts_raises_import_error(self, tmp_path, monkeypatch):
-        """When kittentts package is not installed, _import_kittentts raises."""
-        import sys
-
-        monkeypatch.setitem(sys.modules, "kittentts", None)
-        from tools.tts_tool import _generate_kittentts
-
-        with pytest.raises((ImportError, TypeError)):
-            _generate_kittentts("Hi", str(tmp_path / "out.wav"), {})
-
-
-class TestCheckKittenttsAvailable:
-    def test_reports_available_when_package_present(self, monkeypatch):
-        import importlib.util
-        from tools.tts_tool import _check_kittentts_available
-
-        fake_spec = MagicMock()
-        monkeypatch.setattr(
-            importlib.util,
-            "find_spec",
-            lambda name: fake_spec if name == "kittentts" else None,
-        )
-        assert _check_kittentts_available() is True
-
-    def test_reports_unavailable_when_package_missing(self, monkeypatch):
-        import importlib.util
-        from tools.tts_tool import _check_kittentts_available
-
-        monkeypatch.setattr(importlib.util, "find_spec", lambda name: None)
-        assert _check_kittentts_available() is False
-
-
-class TestDispatcherBranch:
-    def test_kittentts_not_installed_returns_helpful_error(self, monkeypatch, tmp_path):
-        """When provider=kittentts but package missing, return JSON error with setup hint."""
-        import sys
-
-        monkeypatch.setitem(sys.modules, "kittentts", None)
-        monkeypatch.setenv("HERMES_HOME", str(tmp_path))
-
-        from tools.tts_tool import text_to_speech_tool
-
-        # Write a config telling it to use kittentts
-        import yaml
-
-        (tmp_path / "config.yaml").write_text(
-            yaml.safe_dump({"tts": {"provider": "kittentts"}})
-        )
-
-        result = json.loads(text_to_speech_tool(text="Hello"))
-        assert result["success"] is False
-        assert "kittentts" in result["error"].lower()
-        assert "hermes setup tts" in result["error"].lower()
-
-    def test_non_telegram_explicit_wav_path_is_preserved(
-        self, monkeypatch, tmp_path, mock_kittentts_module
-    ):
-        """Explicit WAV outputs should stay WAV outside Telegram sessions."""
-        import yaml
-        from tools import tts_tool as _tt
-
-        monkeypatch.setenv("HERMES_HOME", str(tmp_path))
-        (tmp_path / "config.yaml").write_text(
-            yaml.safe_dump({"tts": {"provider": "kittentts"}})
-        )
-
-        def fail_convert(_path):
-            raise AssertionError("_convert_to_opus should not run outside Telegram")
-
-        monkeypatch.setattr(_tt, "_convert_to_opus", fail_convert)
-
-        result = json.loads(
-            _tt.text_to_speech_tool(
-                text="Hello from KittenTTS",
-                output_path=str(tmp_path / "out.wav"),
-            )
-        )
-
-        assert result["success"] is True
-        assert result["file_path"] == str(tmp_path / "out.wav")
-        assert (tmp_path / "out.wav").exists()

tools/tts_tool.py

@@ -2,14 +2,13 @@
 """
 Text-to-Speech Tool Module
 
-Supports seven TTS providers:
+Supports six TTS providers:
 - Edge TTS (default, free, no API key): Microsoft Edge neural voices
 - ElevenLabs (premium): High-quality voices, needs ELEVENLABS_API_KEY
 - OpenAI TTS: Good quality, needs OPENAI_API_KEY
 - MiniMax TTS: High-quality with voice cloning, needs MINIMAX_API_KEY
 - Mistral (Voxtral TTS): Multilingual, native Opus, needs MISTRAL_API_KEY
 - NeuTTS (local, free, no API key): On-device TTS via neutts_cli, needs neutts installed
-- KittenTTS (local, free, no API key): Lightweight on-device ONNX TTS via kittentts
 
 Output formats:
 - Opus (.ogg) for Telegram voice bubbles (requires ffmpeg for Edge TTS)
@@ -78,12 +77,6 @@ def _import_sounddevice():
     return sd
 
 
-def _import_kittentts():
-    """Lazy import KittenTTS. Returns the class or raises ImportError."""
-    from kittentts import KittenTTS
-    return KittenTTS
-
-
 # ===========================================================================
 # Defaults
 # ===========================================================================
@@ -93,8 +86,6 @@ DEFAULT_ELEVENLABS_VOICE_ID = "pNInz6obpgDQGcFmaJgB"  # Adam
 DEFAULT_ELEVENLABS_MODEL_ID = "eleven_multilingual_v2"
 DEFAULT_ELEVENLABS_STREAMING_MODEL_ID = "eleven_flash_v2_5"
 DEFAULT_OPENAI_MODEL = "gpt-4o-mini-tts"
-DEFAULT_KITTENTTS_MODEL = "KittenML/kitten-tts-nano-0.8-int8"  # 25MB
-DEFAULT_KITTENTTS_VOICE = "Jasper"
 DEFAULT_OPENAI_VOICE = "alloy"
 DEFAULT_OPENAI_BASE_URL = "https://api.openai.com/v1"
 DEFAULT_MINIMAX_MODEL = "speech-2.8-hd"
@@ -457,15 +448,6 @@ def _check_neutts_available() -> bool:
         return False
 
 
-def _check_kittentts_available() -> bool:
-    """Check if the kittentts engine is importable (installed locally)."""
-    try:
-        import importlib.util
-        return importlib.util.find_spec("kittentts") is not None
-    except Exception:
-        return False
-
-
 def _default_neutts_ref_audio() -> str:
     """Return path to the bundled default voice reference audio."""
     return str(Path(__file__).parent / "neutts_samples" / "jo.wav")
@@ -529,51 +511,6 @@ def _generate_neutts(text: str, output_path: str, tts_config: Dict[str, Any]) ->
     return output_path
 
 
-# ===========================================================================
-# Provider: KittenTTS (local, lightweight)
-# ===========================================================================
-
-# Module-level cache for KittenTTS model instances
-_kittentts_model_cache: Dict[str, Any] = {}
-
-
-def _generate_kittentts(text: str, output_path: str, tts_config: Dict[str, Any]) -> str:
-    """Generate speech using the local KittenTTS ONNX model."""
-    KittenTTS = _import_kittentts()
-    kt_config = tts_config.get("kittentts", {})
-    model_name = kt_config.get("model", DEFAULT_KITTENTTS_MODEL)
-    voice = kt_config.get("voice", DEFAULT_KITTENTTS_VOICE)
-    speed = kt_config.get("speed", 1.0)
-    clean_text = kt_config.get("clean_text", True)
-
-    global _kittentts_model_cache
-    if model_name not in _kittentts_model_cache:
-        logger.info("[KittenTTS] Loading model: %s", model_name)
-        _kittentts_model_cache[model_name] = KittenTTS(model_name)
-
-    model = _kittentts_model_cache[model_name]
-    audio = model.generate(text, voice=voice, speed=speed, clean_text=clean_text)
-
-    import soundfile as sf
-
-    wav_path = output_path
-    if not output_path.endswith(".wav"):
-        wav_path = output_path.rsplit(".", 1)[0] + ".wav"
-
-    sf.write(wav_path, audio, 24000)
-
-    if wav_path != output_path:
-        ffmpeg = shutil.which("ffmpeg")
-        if ffmpeg:
-            conv_cmd = [ffmpeg, "-i", wav_path, "-y", "-loglevel", "error", output_path]
-            subprocess.run(conv_cmd, check=True, timeout=30)
-            os.remove(wav_path)
-        else:
-            os.rename(wav_path, output_path)
-
-    return output_path
-
-
 # ===========================================================================
 # Main tool function
 # ===========================================================================
@@ -685,19 +622,6 @@ def text_to_speech_tool(
             logger.info("Generating speech with NeuTTS (local)...")
             _generate_neutts(text, file_str, tts_config)
 
-        elif provider == "kittentts":
-            try:
-                _import_kittentts()
-            except ImportError:
-                return json.dumps({
-                    "success": False,
-                    "error": "KittenTTS provider selected but 'kittentts' package not installed. "
-                             "Run 'hermes setup tts' and choose KittenTTS, or install manually: "
-                             "pip install https://github.com/KittenML/KittenTTS/releases/download/0.8.1/kittentts-0.8.1-py3-none-any.whl"
-                }, ensure_ascii=False)
-            logger.info("Generating speech with KittenTTS (local, lightweight)...")
-            _generate_kittentts(text, file_str, tts_config)
-
         else:
             # Default: Edge TTS (free), with NeuTTS as local fallback
             edge_available = True
@@ -734,10 +658,10 @@ def text_to_speech_tool(
                 "error": f"TTS generation produced no output (provider: {provider})"
             }, ensure_ascii=False)
 
-        # Try Opus conversion for Telegram compatibility only.
-        # Outside Telegram, preserve the caller's explicit output format.
+        # Try Opus conversion for Telegram compatibility
+        # Edge TTS outputs MP3, NeuTTS outputs WAV — both need ffmpeg conversion
         voice_compatible = False
-        if want_opus and provider in ("edge", "neutts", "minimax", "kittentts") and not file_str.endswith(".ogg"):
+        if provider in ("edge", "neutts", "minimax") and not file_str.endswith(".ogg"):
             opus_path = _convert_to_opus(file_str)
             if opus_path:
                 file_str = opus_path
@@ -818,8 +742,6 @@ def check_tts_requirements() -> bool:
         pass
     if _check_neutts_available():
         return True
-    if _check_kittentts_available():
-        return True
     return False
 
 

website/docs/user-guide/features/tts.md

@@ -10,7 +10,7 @@ Hermes Agent supports both text-to-speech output and voice message transcription
 
 ## Text-to-Speech
 
-Convert text to speech with seven providers:
+Convert text to speech with six providers:
 
 | Provider | Quality | Cost | API Key |
 |----------|---------|------|---------|
@@ -20,7 +20,6 @@ Convert text to speech with seven providers:
 | **MiniMax TTS** | Excellent | Paid | `MINIMAX_API_KEY` |
 | **Mistral (Voxtral TTS)** | Excellent | Paid | `MISTRAL_API_KEY` |
 | **NeuTTS** | Good | Free | None needed |
-| **KittenTTS** | Good | Free (local) | None needed |
 
 ### Platform Delivery
 
@@ -36,7 +35,7 @@ Convert text to speech with seven providers:
 ```yaml
 # In ~/.hermes/config.yaml
 tts:
-  provider: "edge"              # "edge" | "elevenlabs" | "openai" | "minimax" | "mistral" | "neutts" | "kittentts"
+  provider: "edge"              # "edge" | "elevenlabs" | "openai" | "minimax" | "mistral" | "neutts"
   speed: 1.0                    # Global speed multiplier (provider-specific settings override this)
   edge:
     voice: "en-US-AriaNeural"   # 322 voices, 74 languages
@@ -63,11 +62,6 @@ tts:
     ref_text: ''
     model: neuphonic/neutts-air-q4-gguf
     device: cpu
-  kittentts:
-    model: KittenML/kitten-tts-nano-0.8-int8   # 25MB int8 default; also micro and mini variants
-    voice: Jasper                               # Jasper, Bella, Luna, Bruno, Rosie, Hugo, Kiki, Leo
-    speed: 1.0
-    clean_text: true
 ```
 
 **Speed control**: The global `tts.speed` value applies to all providers by default. Each provider can override it with its own `speed` setting (e.g., `tts.openai.speed: 1.5`). Provider-specific speed takes precedence over the global value. Default is `1.0` (normal speed).
@@ -80,7 +74,6 @@ Telegram voice bubbles require Opus/OGG audio format:
 - **Edge TTS** (default) outputs MP3 and needs **ffmpeg** to convert:
 - **MiniMax TTS** outputs MP3 and needs **ffmpeg** to convert for Telegram voice bubbles
 - **NeuTTS** outputs WAV and also needs **ffmpeg** to convert for Telegram voice bubbles
-- **KittenTTS** outputs WAV and also needs **ffmpeg** to convert for Telegram voice bubbles
 
 ```bash
 # Ubuntu/Debian
@@ -93,7 +86,7 @@ brew install ffmpeg
 sudo dnf install ffmpeg
 ```
 
-Without ffmpeg, Edge TTS, MiniMax TTS, NeuTTS, and KittenTTS audio are sent as regular audio files (playable, but shown as a rectangular player instead of a voice bubble).
+Without ffmpeg, Edge TTS, MiniMax TTS, and NeuTTS audio are sent as regular audio files (playable, but shown as a rectangular player instead of a voice bubble).
 
 :::tip
 If you want voice bubbles without installing ffmpeg, switch to the OpenAI, ElevenLabs, or Mistral provider.