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

agent/anthropic_adapter.py

@@ -1396,8 +1396,6 @@ def normalize_anthropic_response(
         "tool_use": "tool_calls",
         "max_tokens": "length",
         "stop_sequence": "stop",
-        "refusal": "content_filter",
-        "model_context_window_exceeded": "length",
     }
     finish_reason = stop_reason_map.get(response.stop_reason, "stop")
 
@@ -1411,42 +1409,3 @@ def normalize_anthropic_response(
         ),
         finish_reason,
     )
-
-
-def normalize_anthropic_response_v2(
-    response,
-    strip_tool_prefix: bool = False,
-) -> "NormalizedResponse":
-    """Normalize Anthropic response to NormalizedResponse.
-
-    Wraps the existing normalize_anthropic_response() and maps its output
-    to the shared transport types. This allows incremental migration
-    without disturbing the legacy call sites.
-    """
-    from agent.transports.types import NormalizedResponse, build_tool_call
-
-    assistant_msg, finish_reason = normalize_anthropic_response(response, strip_tool_prefix)
-
-    tool_calls = None
-    if assistant_msg.tool_calls:
-        tool_calls = [
-            build_tool_call(
-                id=tc.id,
-                name=tc.function.name,
-                arguments=tc.function.arguments,
-            )
-            for tc in assistant_msg.tool_calls
-        ]
-
-    provider_data = {}
-    if getattr(assistant_msg, "reasoning_details", None):
-        provider_data["reasoning_details"] = assistant_msg.reasoning_details
-
-    return NormalizedResponse(
-        content=assistant_msg.content,
-        tool_calls=tool_calls,
-        finish_reason=finish_reason,
-        reasoning=getattr(assistant_msg, "reasoning", None),
-        usage=None,
-        provider_data=provider_data or None,
-    )

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,

agent/transports/__init__.py

@@ -1,57 +0,0 @@
-"""Transport layer types and registry for provider response normalization.
-
-Usage:
-    from agent.transports import get_transport
-    transport = get_transport("anthropic_messages")
-    result = transport.normalize_response(raw_response)
-"""
-
-from agent.transports.types import (  # noqa: F401
-    NormalizedResponse,
-    ToolCall,
-    Usage,
-    build_tool_call,
-    map_finish_reason,
-)
-
-_REGISTRY: dict = {}
-
-
-def register_transport(api_mode: str, transport_cls: type) -> None:
-    """Register a transport class for an api_mode string."""
-    _REGISTRY[api_mode] = transport_cls
-
-
-def get_transport(api_mode: str):
-    """Get a transport instance for the given api_mode.
-
-    Returns None if no transport is registered for this api_mode.
-    This allows gradual migration — call sites can check for None
-    and fall back to the legacy code path.
-    """
-    if not _REGISTRY:
-        _discover_transports()
-    cls = _REGISTRY.get(api_mode)
-    if cls is None:
-        return None
-    return cls()
-
-
-def _discover_transports() -> None:
-    """Import all transport modules to trigger auto-registration."""
-    try:
-        import agent.transports.anthropic  # noqa: F401
-    except ImportError:
-        pass
-    try:
-        import agent.transports.codex  # noqa: F401
-    except ImportError:
-        pass
-    try:
-        import agent.transports.chat_completions  # noqa: F401
-    except ImportError:
-        pass
-    try:
-        import agent.transports.bedrock  # noqa: F401
-    except ImportError:
-        pass

agent/transports/anthropic.py

@@ -1,95 +0,0 @@
-"""Anthropic Messages API transport.
-
-Delegates to the existing adapter functions in agent/anthropic_adapter.py.
-This transport owns format conversion and normalization — NOT client lifecycle.
-"""
-
-from typing import Any, Dict, List, Optional
-
-from agent.transports.base import ProviderTransport
-from agent.transports.types import NormalizedResponse
-
-
-class AnthropicTransport(ProviderTransport):
-    """Transport for api_mode='anthropic_messages'."""
-
-    @property
-    def api_mode(self) -> str:
-        return "anthropic_messages"
-
-    def convert_messages(self, messages: List[Dict[str, Any]], **kwargs) -> Any:
-        from agent.anthropic_adapter import convert_messages_to_anthropic
-
-        base_url = kwargs.get("base_url")
-        return convert_messages_to_anthropic(messages, base_url=base_url)
-
-    def convert_tools(self, tools: List[Dict[str, Any]]) -> Any:
-        from agent.anthropic_adapter import convert_tools_to_anthropic
-
-        return convert_tools_to_anthropic(tools)
-
-    def build_kwargs(
-        self,
-        model: str,
-        messages: List[Dict[str, Any]],
-        tools: Optional[List[Dict[str, Any]]] = None,
-        **params,
-    ) -> Dict[str, Any]:
-        from agent.anthropic_adapter import build_anthropic_kwargs
-
-        return build_anthropic_kwargs(
-            model=model,
-            messages=messages,
-            tools=tools,
-            max_tokens=params.get("max_tokens", 16384),
-            reasoning_config=params.get("reasoning_config"),
-            tool_choice=params.get("tool_choice"),
-            is_oauth=params.get("is_oauth", False),
-            preserve_dots=params.get("preserve_dots", False),
-            context_length=params.get("context_length"),
-            base_url=params.get("base_url"),
-            fast_mode=params.get("fast_mode", False),
-        )
-
-    def normalize_response(self, response: Any, **kwargs) -> NormalizedResponse:
-        from agent.anthropic_adapter import normalize_anthropic_response_v2
-
-        strip_tool_prefix = kwargs.get("strip_tool_prefix", False)
-        return normalize_anthropic_response_v2(response, strip_tool_prefix=strip_tool_prefix)
-
-    def validate_response(self, response: Any) -> bool:
-        if response is None:
-            return False
-        content_blocks = getattr(response, "content", None)
-        if not isinstance(content_blocks, list):
-            return False
-        if not content_blocks:
-            return False
-        return True
-
-    def extract_cache_stats(self, response: Any):
-        usage = getattr(response, "usage", None)
-        if usage is None:
-            return None
-        cached = getattr(usage, "cache_read_input_tokens", 0) or 0
-        written = getattr(usage, "cache_creation_input_tokens", 0) or 0
-        if cached or written:
-            return {"cached_tokens": cached, "creation_tokens": written}
-        return None
-
-    _STOP_REASON_MAP = {
-        "end_turn": "stop",
-        "tool_use": "tool_calls",
-        "max_tokens": "length",
-        "stop_sequence": "stop",
-        "refusal": "content_filter",
-        "model_context_window_exceeded": "length",
-    }
-
-    def map_finish_reason(self, raw_reason: str) -> str:
-        return self._STOP_REASON_MAP.get(raw_reason, "stop")
-
-
-from agent.transports import register_transport  # noqa: E402
-
-register_transport("anthropic_messages", AnthropicTransport)

agent/transports/base.py

@@ -1,61 +0,0 @@
-"""Abstract base for provider transports.
-
-A transport owns the data path for one api_mode:
-  convert_messages → convert_tools → build_kwargs → normalize_response
-
-It does NOT own: client construction, streaming, credential refresh,
-prompt caching, interrupt handling, or retry logic. Those stay on AIAgent.
-"""
-
-from abc import ABC, abstractmethod
-from typing import Any, Dict, List, Optional
-
-from agent.transports.types import NormalizedResponse
-
-
-class ProviderTransport(ABC):
-    """Base class for provider-specific format conversion and normalization."""
-
-    @property
-    @abstractmethod
-    def api_mode(self) -> str:
-        """The api_mode string this transport handles."""
-        ...
-
-    @abstractmethod
-    def convert_messages(self, messages: List[Dict[str, Any]], **kwargs) -> Any:
-        """Convert OpenAI-format messages to provider-native format."""
-        ...
-
-    @abstractmethod
-    def convert_tools(self, tools: List[Dict[str, Any]]) -> Any:
-        """Convert OpenAI-format tool definitions to provider-native format."""
-        ...
-
-    @abstractmethod
-    def build_kwargs(
-        self,
-        model: str,
-        messages: List[Dict[str, Any]],
-        tools: Optional[List[Dict[str, Any]]] = None,
-        **params,
-    ) -> Dict[str, Any]:
-        """Build the complete provider kwargs dict."""
-        ...
-
-    @abstractmethod
-    def normalize_response(self, response: Any, **kwargs) -> NormalizedResponse:
-        """Normalize a raw provider response to the shared NormalizedResponse type."""
-        ...
-
-    def validate_response(self, response: Any) -> bool:
-        """Optional structural validation for raw responses."""
-        return True
-
-    def extract_cache_stats(self, response: Any) -> Optional[Dict[str, int]]:
-        """Optional cache stats extraction."""
-        return None
-
-    def map_finish_reason(self, raw_reason: str) -> str:
-        """Optional stop-reason mapping. Defaults to passthrough."""
-        return raw_reason

agent/transports/types.py

@@ -1,58 +0,0 @@
-"""Shared types for normalized provider responses."""
-
-from __future__ import annotations
-
-import json
-from dataclasses import dataclass, field
-from typing import Any, Dict, List, Optional
-
-
-@dataclass
-class ToolCall:
-    """A normalized tool call from any provider."""
-
-    id: Optional[str]
-    name: str
-    arguments: str
-    provider_data: Optional[Dict[str, Any]] = field(default=None, repr=False)
-
-
-@dataclass
-class Usage:
-    """Token usage from an API response."""
-
-    prompt_tokens: int = 0
-    completion_tokens: int = 0
-    total_tokens: int = 0
-    cached_tokens: int = 0
-
-
-@dataclass
-class NormalizedResponse:
-    """Normalized API response from any provider."""
-
-    content: Optional[str]
-    tool_calls: Optional[List[ToolCall]]
-    finish_reason: str
-    reasoning: Optional[str] = None
-    usage: Optional[Usage] = None
-    provider_data: Optional[Dict[str, Any]] = field(default=None, repr=False)
-
-
-def build_tool_call(
-    id: Optional[str],
-    name: str,
-    arguments: Any,
-    **provider_fields: Any,
-) -> ToolCall:
-    """Build a ToolCall, auto-serialising dict arguments."""
-    args_str = json.dumps(arguments) if isinstance(arguments, dict) else str(arguments)
-    provider_data = dict(provider_fields) if provider_fields else None
-    return ToolCall(id=id, name=name, arguments=args_str, provider_data=provider_data)
-
-
-def map_finish_reason(reason: Optional[str], mapping: Dict[str, str]) -> str:
-    """Translate a provider-specific stop reason to the normalized set."""
-    if reason is None:
-        return "stop"
-    return mapping.get(reason, "stop")

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(

tests/agent/test_anthropic_normalize_v2.py

@@ -1,213 +0,0 @@
-"""Regression tests: normalize_anthropic_response_v2 vs v1.
-
-Constructs mock Anthropic responses and asserts that the v2 function
-(returning NormalizedResponse) produces identical field values to the
-original v1 function (returning SimpleNamespace + finish_reason).
-"""
-
-from types import SimpleNamespace
-
-import pytest
-
-from agent.anthropic_adapter import (
-    normalize_anthropic_response,
-    normalize_anthropic_response_v2,
-)
-from agent.transports.types import NormalizedResponse
-
-
-def _text_block(text: str):
-    return SimpleNamespace(type="text", text=text)
-
-
-def _thinking_block(thinking: str, signature: str = "sig_abc"):
-    return SimpleNamespace(type="thinking", thinking=thinking, signature=signature)
-
-
-def _tool_use_block(id: str, name: str, input: dict):
-    return SimpleNamespace(type="tool_use", id=id, name=name, input=input)
-
-
-def _response(content_blocks, stop_reason="end_turn"):
-    return SimpleNamespace(
-        content=content_blocks,
-        stop_reason=stop_reason,
-        usage=SimpleNamespace(input_tokens=10, output_tokens=5),
-    )
-
-
-class TestTextOnly:
-    def setup_method(self):
-        self.resp = _response([_text_block("Hello world")])
-        self.v1_msg, self.v1_finish = normalize_anthropic_response(self.resp)
-        self.v2 = normalize_anthropic_response_v2(self.resp)
-
-    def test_type(self):
-        assert isinstance(self.v2, NormalizedResponse)
-
-    def test_content_matches(self):
-        assert self.v2.content == self.v1_msg.content
-
-    def test_finish_reason_matches(self):
-        assert self.v2.finish_reason == self.v1_finish
-
-    def test_no_tool_calls(self):
-        assert self.v2.tool_calls is None
-        assert self.v1_msg.tool_calls is None
-
-    def test_no_reasoning(self):
-        assert self.v2.reasoning is None
-        assert self.v1_msg.reasoning is None
-
-
-class TestWithToolCalls:
-    def setup_method(self):
-        self.resp = _response(
-            [
-                _text_block("I'll check that"),
-                _tool_use_block("toolu_abc", "terminal", {"command": "ls"}),
-                _tool_use_block("toolu_def", "read_file", {"path": "/tmp"}),
-            ],
-            stop_reason="tool_use",
-        )
-        self.v1_msg, self.v1_finish = normalize_anthropic_response(self.resp)
-        self.v2 = normalize_anthropic_response_v2(self.resp)
-
-    def test_finish_reason(self):
-        assert self.v2.finish_reason == "tool_calls"
-        assert self.v1_finish == "tool_calls"
-
-    def test_tool_call_count(self):
-        assert len(self.v2.tool_calls) == 2
-        assert len(self.v1_msg.tool_calls) == 2
-
-    def test_tool_call_ids_match(self):
-        for i in range(2):
-            assert self.v2.tool_calls[i].id == self.v1_msg.tool_calls[i].id
-
-    def test_tool_call_names_match(self):
-        assert self.v2.tool_calls[0].name == "terminal"
-        assert self.v2.tool_calls[1].name == "read_file"
-        for i in range(2):
-            assert self.v2.tool_calls[i].name == self.v1_msg.tool_calls[i].function.name
-
-    def test_tool_call_arguments_match(self):
-        for i in range(2):
-            assert self.v2.tool_calls[i].arguments == self.v1_msg.tool_calls[i].function.arguments
-
-    def test_content_preserved(self):
-        assert self.v2.content == self.v1_msg.content
-        assert "check that" in self.v2.content
-
-
-class TestWithThinking:
-    def setup_method(self):
-        self.resp = _response([
-            _thinking_block("Let me think about this carefully..."),
-            _text_block("The answer is 42."),
-        ])
-        self.v1_msg, self.v1_finish = normalize_anthropic_response(self.resp)
-        self.v2 = normalize_anthropic_response_v2(self.resp)
-
-    def test_reasoning_matches(self):
-        assert self.v2.reasoning == self.v1_msg.reasoning
-        assert "think about this" in self.v2.reasoning
-
-    def test_reasoning_details_in_provider_data(self):
-        v1_details = self.v1_msg.reasoning_details
-        v2_details = self.v2.provider_data.get("reasoning_details") if self.v2.provider_data else None
-        assert v1_details is not None
-        assert v2_details is not None
-        assert len(v2_details) == len(v1_details)
-
-    def test_content_excludes_thinking(self):
-        assert self.v2.content == "The answer is 42."
-
-
-class TestMixed:
-    def setup_method(self):
-        self.resp = _response(
-            [
-                _thinking_block("Planning my approach..."),
-                _text_block("I'll run the command"),
-                _tool_use_block("toolu_xyz", "terminal", {"command": "pwd"}),
-            ],
-            stop_reason="tool_use",
-        )
-        self.v1_msg, self.v1_finish = normalize_anthropic_response(self.resp)
-        self.v2 = normalize_anthropic_response_v2(self.resp)
-
-    def test_all_fields_present(self):
-        assert self.v2.content is not None
-        assert self.v2.tool_calls is not None
-        assert self.v2.reasoning is not None
-        assert self.v2.finish_reason == "tool_calls"
-
-    def test_content_matches(self):
-        assert self.v2.content == self.v1_msg.content
-
-    def test_reasoning_matches(self):
-        assert self.v2.reasoning == self.v1_msg.reasoning
-
-    def test_tool_call_matches(self):
-        assert self.v2.tool_calls[0].id == self.v1_msg.tool_calls[0].id
-        assert self.v2.tool_calls[0].name == self.v1_msg.tool_calls[0].function.name
-
-
-class TestStopReasons:
-    @pytest.mark.parametrize("stop_reason,expected", [
-        ("end_turn", "stop"),
-        ("tool_use", "tool_calls"),
-        ("max_tokens", "length"),
-        ("stop_sequence", "stop"),
-        ("refusal", "content_filter"),
-        ("model_context_window_exceeded", "length"),
-        ("unknown_future_reason", "stop"),
-    ])
-    def test_stop_reason_mapping(self, stop_reason, expected):
-        resp = _response([_text_block("x")], stop_reason=stop_reason)
-        _v1_msg, v1_finish = normalize_anthropic_response(resp)
-        v2 = normalize_anthropic_response_v2(resp)
-        assert v2.finish_reason == v1_finish == expected
-
-
-class TestStripToolPrefix:
-    def test_prefix_stripped(self):
-        resp = _response(
-            [_tool_use_block("toolu_1", "mcp_terminal", {"cmd": "ls"})],
-            stop_reason="tool_use",
-        )
-        v1_msg, _ = normalize_anthropic_response(resp, strip_tool_prefix=True)
-        v2 = normalize_anthropic_response_v2(resp, strip_tool_prefix=True)
-        assert v1_msg.tool_calls[0].function.name == "terminal"
-        assert v2.tool_calls[0].name == "terminal"
-
-    def test_prefix_kept(self):
-        resp = _response(
-            [_tool_use_block("toolu_1", "mcp_terminal", {"cmd": "ls"})],
-            stop_reason="tool_use",
-        )
-        v1_msg, _ = normalize_anthropic_response(resp, strip_tool_prefix=False)
-        v2 = normalize_anthropic_response_v2(resp, strip_tool_prefix=False)
-        assert v1_msg.tool_calls[0].function.name == "mcp_terminal"
-        assert v2.tool_calls[0].name == "mcp_terminal"
-
-
-class TestEdgeCases:
-    def test_empty_content_blocks(self):
-        resp = _response([])
-        v1_msg, _v1_finish = normalize_anthropic_response(resp)
-        v2 = normalize_anthropic_response_v2(resp)
-        assert v2.content == v1_msg.content
-        assert v2.content is None
-
-    def test_no_reasoning_details_means_none_provider_data(self):
-        resp = _response([_text_block("hi")])
-        v2 = normalize_anthropic_response_v2(resp)
-        assert v2.provider_data is None
-
-    def test_v2_returns_dataclass_not_namespace(self):
-        resp = _response([_text_block("hi")])
-        v2 = normalize_anthropic_response_v2(resp)
-        assert isinstance(v2, NormalizedResponse)
-        assert not isinstance(v2, SimpleNamespace)

tests/agent/transports/test_transport.py

@@ -1,208 +0,0 @@
-"""Tests for the transport ABC, registry, and AnthropicTransport."""
-
-from types import SimpleNamespace
-
-import pytest
-
-from agent.transports import _REGISTRY, get_transport, register_transport
-from agent.transports.base import ProviderTransport
-from agent.transports.types import NormalizedResponse
-
-
-class TestProviderTransportABC:
-    def test_cannot_instantiate_abc(self):
-        with pytest.raises(TypeError):
-            ProviderTransport()
-
-    def test_concrete_must_implement_all_abstract(self):
-        class Incomplete(ProviderTransport):
-            @property
-            def api_mode(self):
-                return "test"
-
-        with pytest.raises(TypeError):
-            Incomplete()
-
-    def test_minimal_concrete(self):
-        class Minimal(ProviderTransport):
-            @property
-            def api_mode(self):
-                return "test_minimal"
-
-            def convert_messages(self, messages, **kw):
-                return messages
-
-            def convert_tools(self, tools):
-                return tools
-
-            def build_kwargs(self, model, messages, tools=None, **params):
-                return {"model": model, "messages": messages}
-
-            def normalize_response(self, response, **kw):
-                return NormalizedResponse(content="ok", tool_calls=None, finish_reason="stop")
-
-        t = Minimal()
-        assert t.api_mode == "test_minimal"
-        assert t.validate_response(None) is True
-        assert t.extract_cache_stats(None) is None
-        assert t.map_finish_reason("end_turn") == "end_turn"
-
-
-class TestTransportRegistry:
-    def test_get_unregistered_returns_none(self):
-        assert get_transport("nonexistent_mode") is None
-
-    def test_anthropic_registered_on_import(self):
-        import agent.transports.anthropic  # noqa: F401
-
-        t = get_transport("anthropic_messages")
-        assert t is not None
-        assert t.api_mode == "anthropic_messages"
-
-    def test_register_and_get(self):
-        class DummyTransport(ProviderTransport):
-            @property
-            def api_mode(self):
-                return "dummy_test"
-
-            def convert_messages(self, messages, **kw):
-                return messages
-
-            def convert_tools(self, tools):
-                return tools
-
-            def build_kwargs(self, model, messages, tools=None, **params):
-                return {}
-
-            def normalize_response(self, response, **kw):
-                return NormalizedResponse(content=None, tool_calls=None, finish_reason="stop")
-
-        register_transport("dummy_test", DummyTransport)
-        t = get_transport("dummy_test")
-        assert t.api_mode == "dummy_test"
-        _REGISTRY.pop("dummy_test", None)
-
-
-class TestAnthropicTransport:
-    @pytest.fixture
-    def transport(self):
-        import agent.transports.anthropic  # noqa: F401
-
-        return get_transport("anthropic_messages")
-
-    def test_api_mode(self, transport):
-        assert transport.api_mode == "anthropic_messages"
-
-    def test_convert_tools_simple(self, transport):
-        tools = [{
-            "type": "function",
-            "function": {
-                "name": "test_tool",
-                "description": "A test",
-                "parameters": {"type": "object", "properties": {}},
-            },
-        }]
-        result = transport.convert_tools(tools)
-        assert len(result) == 1
-        assert result[0]["name"] == "test_tool"
-        assert "input_schema" in result[0]
-
-    def test_validate_response_none(self, transport):
-        assert transport.validate_response(None) is False
-
-    def test_validate_response_empty_content(self, transport):
-        r = SimpleNamespace(content=[])
-        assert transport.validate_response(r) is False
-
-    def test_validate_response_valid(self, transport):
-        r = SimpleNamespace(content=[SimpleNamespace(type="text", text="hello")])
-        assert transport.validate_response(r) is True
-
-    def test_map_finish_reason(self, transport):
-        assert transport.map_finish_reason("end_turn") == "stop"
-        assert transport.map_finish_reason("tool_use") == "tool_calls"
-        assert transport.map_finish_reason("max_tokens") == "length"
-        assert transport.map_finish_reason("stop_sequence") == "stop"
-        assert transport.map_finish_reason("refusal") == "content_filter"
-        assert transport.map_finish_reason("model_context_window_exceeded") == "length"
-        assert transport.map_finish_reason("unknown") == "stop"
-
-    def test_extract_cache_stats_none_usage(self, transport):
-        r = SimpleNamespace(usage=None)
-        assert transport.extract_cache_stats(r) is None
-
-    def test_extract_cache_stats_with_cache(self, transport):
-        usage = SimpleNamespace(cache_read_input_tokens=100, cache_creation_input_tokens=50)
-        r = SimpleNamespace(usage=usage)
-        result = transport.extract_cache_stats(r)
-        assert result == {"cached_tokens": 100, "creation_tokens": 50}
-
-    def test_extract_cache_stats_zero(self, transport):
-        usage = SimpleNamespace(cache_read_input_tokens=0, cache_creation_input_tokens=0)
-        r = SimpleNamespace(usage=usage)
-        assert transport.extract_cache_stats(r) is None
-
-    def test_normalize_response_text(self, transport):
-        r = SimpleNamespace(
-            content=[SimpleNamespace(type="text", text="Hello world")],
-            stop_reason="end_turn",
-            usage=SimpleNamespace(input_tokens=10, output_tokens=5),
-            model="claude-sonnet-4-6",
-        )
-        nr = transport.normalize_response(r)
-        assert isinstance(nr, NormalizedResponse)
-        assert nr.content == "Hello world"
-        assert nr.tool_calls is None or nr.tool_calls == []
-        assert nr.finish_reason == "stop"
-
-    def test_normalize_response_tool_calls(self, transport):
-        r = SimpleNamespace(
-            content=[
-                SimpleNamespace(type="tool_use", id="toolu_123", name="terminal", input={"command": "ls"}),
-            ],
-            stop_reason="tool_use",
-            usage=SimpleNamespace(input_tokens=10, output_tokens=20),
-            model="claude-sonnet-4-6",
-        )
-        nr = transport.normalize_response(r)
-        assert nr.finish_reason == "tool_calls"
-        assert len(nr.tool_calls) == 1
-        tc = nr.tool_calls[0]
-        assert tc.name == "terminal"
-        assert tc.id == "toolu_123"
-        assert '"command"' in tc.arguments
-
-    def test_normalize_response_thinking(self, transport):
-        r = SimpleNamespace(
-            content=[
-                SimpleNamespace(type="thinking", thinking="Let me think..."),
-                SimpleNamespace(type="text", text="The answer is 42"),
-            ],
-            stop_reason="end_turn",
-            usage=SimpleNamespace(input_tokens=10, output_tokens=15),
-            model="claude-sonnet-4-6",
-        )
-        nr = transport.normalize_response(r)
-        assert nr.content == "The answer is 42"
-        assert nr.reasoning == "Let me think..."
-
-    def test_build_kwargs_returns_dict(self, transport):
-        messages = [{"role": "user", "content": "Hello"}]
-        kw = transport.build_kwargs(
-            model="claude-sonnet-4-6",
-            messages=messages,
-            max_tokens=1024,
-        )
-        assert isinstance(kw, dict)
-        assert "model" in kw
-        assert "max_tokens" in kw
-        assert "messages" in kw
-
-    def test_convert_messages_extracts_system(self, transport):
-        messages = [
-            {"role": "system", "content": "You are helpful."},
-            {"role": "user", "content": "Hi"},
-        ]
-        system, msgs = transport.convert_messages(messages)
-        assert system is not None
-        assert len(msgs) >= 1

tests/agent/transports/test_types.py

@@ -1,130 +0,0 @@
-"""Tests for agent/transports/types.py — dataclass construction + helpers."""
-
-import json
-
-from agent.transports.types import (
-    NormalizedResponse,
-    ToolCall,
-    Usage,
-    build_tool_call,
-    map_finish_reason,
-)
-
-
-class TestToolCall:
-    def test_basic_construction(self):
-        tc = ToolCall(id="call_abc", name="terminal", arguments='{"cmd": "ls"}')
-        assert tc.id == "call_abc"
-        assert tc.name == "terminal"
-        assert tc.arguments == '{"cmd": "ls"}'
-        assert tc.provider_data is None
-
-    def test_none_id(self):
-        tc = ToolCall(id=None, name="read_file", arguments="{}")
-        assert tc.id is None
-
-    def test_provider_data(self):
-        tc = ToolCall(
-            id="call_x",
-            name="t",
-            arguments="{}",
-            provider_data={"call_id": "call_x", "response_item_id": "fc_x"},
-        )
-        assert tc.provider_data["call_id"] == "call_x"
-        assert tc.provider_data["response_item_id"] == "fc_x"
-
-
-class TestUsage:
-    def test_defaults(self):
-        u = Usage()
-        assert u.prompt_tokens == 0
-        assert u.completion_tokens == 0
-        assert u.total_tokens == 0
-        assert u.cached_tokens == 0
-
-    def test_explicit(self):
-        u = Usage(prompt_tokens=100, completion_tokens=50, total_tokens=150, cached_tokens=80)
-        assert u.total_tokens == 150
-
-
-class TestNormalizedResponse:
-    def test_text_only(self):
-        r = NormalizedResponse(content="hello", tool_calls=None, finish_reason="stop")
-        assert r.content == "hello"
-        assert r.tool_calls is None
-        assert r.finish_reason == "stop"
-        assert r.reasoning is None
-        assert r.usage is None
-        assert r.provider_data is None
-
-    def test_with_tool_calls(self):
-        tcs = [ToolCall(id="call_1", name="terminal", arguments='{"cmd":"pwd"}')]
-        r = NormalizedResponse(content=None, tool_calls=tcs, finish_reason="tool_calls")
-        assert r.finish_reason == "tool_calls"
-        assert len(r.tool_calls) == 1
-        assert r.tool_calls[0].name == "terminal"
-
-    def test_with_reasoning(self):
-        r = NormalizedResponse(
-            content="answer",
-            tool_calls=None,
-            finish_reason="stop",
-            reasoning="I thought about it",
-        )
-        assert r.reasoning == "I thought about it"
-
-    def test_with_provider_data(self):
-        r = NormalizedResponse(
-            content=None,
-            tool_calls=None,
-            finish_reason="stop",
-            provider_data={"reasoning_details": [{"type": "thinking", "thinking": "hmm"}]},
-        )
-        assert r.provider_data["reasoning_details"][0]["type"] == "thinking"
-
-
-class TestBuildToolCall:
-    def test_dict_arguments_serialized(self):
-        tc = build_tool_call(id="call_1", name="terminal", arguments={"cmd": "ls"})
-        assert tc.arguments == json.dumps({"cmd": "ls"})
-        assert tc.provider_data is None
-
-    def test_string_arguments_passthrough(self):
-        tc = build_tool_call(id="call_2", name="read_file", arguments='{"path": "/tmp"}')
-        assert tc.arguments == '{"path": "/tmp"}'
-
-    def test_provider_fields(self):
-        tc = build_tool_call(
-            id="call_3",
-            name="terminal",
-            arguments="{}",
-            call_id="call_3",
-            response_item_id="fc_3",
-        )
-        assert tc.provider_data == {"call_id": "call_3", "response_item_id": "fc_3"}
-
-    def test_none_id(self):
-        tc = build_tool_call(id=None, name="t", arguments="{}")
-        assert tc.id is None
-
-
-class TestMapFinishReason:
-    ANTHROPIC_MAP = {
-        "end_turn": "stop",
-        "tool_use": "tool_calls",
-        "max_tokens": "length",
-        "stop_sequence": "stop",
-        "refusal": "content_filter",
-    }
-
-    def test_known_reason(self):
-        assert map_finish_reason("end_turn", self.ANTHROPIC_MAP) == "stop"
-        assert map_finish_reason("tool_use", self.ANTHROPIC_MAP) == "tool_calls"
-        assert map_finish_reason("max_tokens", self.ANTHROPIC_MAP) == "length"
-        assert map_finish_reason("refusal", self.ANTHROPIC_MAP) == "content_filter"
-
-    def test_unknown_reason_defaults_to_stop(self):
-        assert map_finish_reason("something_new", self.ANTHROPIC_MAP) == "stop"
-
-    def test_none_reason(self):
-        assert map_finish_reason(None, self.ANTHROPIC_MAP) == "stop"

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()