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(

optional-skills/dogfood/adversarial-ux-test/SKILL.md

@@ -1,190 +0,0 @@
----
-name: adversarial-ux-test
-description: Roleplay the most difficult, tech-resistant user for your product. Browse the app as that persona, find every UX pain point, then filter complaints through a pragmatism layer to separate real problems from noise. Creates actionable tickets from genuine issues only.
-version: 1.0.0
-author: Omni @ Comelse
-license: MIT
-metadata:
-  hermes:
-    tags: [qa, ux, testing, adversarial, dogfood, personas, user-testing]
-    related_skills: [dogfood]
----
-
-# Adversarial UX Test
-
-Roleplay the worst-case user for your product — the person who hates technology, doesn't want your software, and will find every reason to complain. Then filter their feedback through a pragmatism layer to separate real UX problems from "I hate computers" noise.
-
-Think of it as an automated "mom test" — but angry.
-
-## Why This Works
-
-Most QA finds bugs. This finds **friction**. A technically correct app can still be unusable for real humans. The adversarial persona catches:
-- Confusing terminology that makes sense to developers but not users
-- Too many steps to accomplish basic tasks
-- Missing onboarding or "aha moments"
-- Accessibility issues (font size, contrast, click targets)
-- Cold-start problems (empty states, no demo content)
-- Paywall/signup friction that kills conversion
-
-The **pragmatism filter** (Phase 3) is what makes this useful instead of just entertaining. Without it, you'd add a "print this page" button to every screen because Grandpa can't figure out PDFs.
-
-## How to Use
-
-Tell the agent:
-```
-"Run an adversarial UX test on [URL]"
-"Be a grumpy [persona type] and test [app name]"
-"Do an asshole user test on my staging site"
-```
-
-You can provide a persona or let the agent generate one based on your product's target audience.
-
-## Step 1: Define the Persona
-
-If no persona is provided, generate one by answering:
-
-1. **Who is the HARDEST user for this product?** (age 50+, non-technical role, decades of experience doing it "the old way")
-2. **What is their tech comfort level?** (the lower the better — WhatsApp-only, paper notebooks, wife set up their email)
-3. **What is the ONE thing they need to accomplish?** (their core job, not your feature list)
-4. **What would make them give up?** (too many clicks, jargon, slow, confusing)
-5. **How do they talk when frustrated?** (blunt, sweary, dismissive, sighing)
-
-### Good Persona Example
-> **"Big Mick" McAllister** — 58-year-old S&C coach. Uses WhatsApp and that's it. His "spreadsheet" is a paper notebook. "If I can't figure it out in 10 seconds I'm going back to my notebook." Needs to log session results for 25 players. Hates small text, jargon, and passwords.
-
-### Bad Persona Example
-> "A user who doesn't like the app" — too vague, no constraints, no voice.
-
-The persona must be **specific enough to stay in character** for 20 minutes of testing.
-
-## Step 2: Become the Asshole (Browse as the Persona)
-
-1. Read any available project docs for app context and URLs
-2. **Fully inhabit the persona** — their frustrations, limitations, goals
-3. Navigate to the app using browser tools
-4. **Attempt the persona's ACTUAL TASKS** (not a feature tour):
-   - Can they do what they came to do?
-   - How many clicks/screens to accomplish it?
-   - What confuses them?
-   - What makes them angry?
-   - Where do they get lost?
-   - What would make them give up and go back to their old way?
-
-5. Test these friction categories:
-   - **First impression** — would they even bother past the landing page?
-   - **Core workflow** — the ONE thing they need to do most often
-   - **Error recovery** — what happens when they do something wrong?
-   - **Readability** — text size, contrast, information density
-   - **Speed** — does it feel faster than their current method?
-   - **Terminology** — any jargon they wouldn't understand?
-   - **Navigation** — can they find their way back? do they know where they are?
-
-6. Take screenshots of every pain point
-7. Check browser console for JS errors on every page
-
-## Step 3: The Rant (Write Feedback in Character)
-
-Write the feedback AS THE PERSONA — in their voice, with their frustrations. This is not a bug report. This is a real human venting.
-
-```
-[PERSONA NAME]'s Review of [PRODUCT]
-
-Overall: [Would they keep using it? Yes/No/Maybe with conditions]
-
-THE GOOD (grudging admission):
-- [things even they have to admit work]
-
-THE BAD (legitimate UX issues):
-- [real problems that would stop them from using the product]
-
-THE UGLY (showstoppers):
-- [things that would make them uninstall/cancel immediately]
-
-SPECIFIC COMPLAINTS:
-1. [Page/feature]: "[quote in persona voice]" — [what happened, expected]
-2. ...
-
-VERDICT: "[one-line persona quote summarizing their experience]"
-```
-
-## Step 4: The Pragmatism Filter (Critical — Do Not Skip)
-
-Step OUT of the persona. Evaluate each complaint as a product person:
-
-- **RED: REAL UX BUG** — Any user would have this problem, not just grumpy ones. Fix it.
-- **YELLOW: VALID BUT LOW PRIORITY** — Real issue but only for extreme users. Note it.
-- **WHITE: PERSONA NOISE** — "I hate computers" talking, not a product problem. Skip it.
-- **GREEN: FEATURE REQUEST** — Good idea hidden in the complaint. Consider it.
-
-### Filter Criteria
-1. Would a 35-year-old competent-but-busy user have the same complaint? → RED
-2. Is this a genuine accessibility issue (font size, contrast, click targets)? → RED
-3. Is this "I want it to work like paper" resistance to digital? → WHITE
-4. Is this a real workflow inefficiency the persona stumbled on? → YELLOW or RED
-5. Would fixing this add complexity for the 80% who are fine? → WHITE
-6. Does the complaint reveal a missing onboarding moment? → GREEN
-
-**This filter is MANDATORY.** Never ship raw persona complaints as tickets.
-
-## Step 5: Create Tickets
-
-For **RED** and **GREEN** items only:
-- Clear, actionable title
-- Include the persona's verbatim quote (entertaining + memorable)
-- The real UX issue underneath (objective)
-- A suggested fix (actionable)
-- Tag/label: "ux-review"
-
-For **YELLOW** items: one catch-all ticket with all notes.
-
-**WHITE** items appear in the report only. No tickets.
-
-**Max 10 tickets per session** — focus on the worst issues.
-
-## Step 6: Report
-
-Deliver:
-1. The persona rant (Step 3) — entertaining and visceral
-2. The filtered assessment (Step 4) — pragmatic and actionable
-3. Tickets created (Step 5) — with links
-4. Screenshots of key issues
-
-## Tips
-
-- **One persona per session.** Don't mix perspectives.
-- **Stay in character during Steps 2-3.** Break character only at Step 4.
-- **Test the CORE WORKFLOW first.** Don't get distracted by settings pages.
-- **Empty states are gold.** New user experience reveals the most friction.
-- **The best findings are RED items the persona found accidentally** while trying to do something else.
-- **If the persona has zero complaints, your persona is too tech-savvy.** Make them older, less patient, more set in their ways.
-- **Run this before demos, launches, or after shipping a batch of features.**
-- **Register as a NEW user when possible.** Don't use pre-seeded admin accounts — the cold start experience is where most friction lives.
-- **Zero WHITE items is a signal, not a failure.** If the pragmatism filter finds no noise, your product has real UX problems, not just a grumpy persona.
-- **Check known issues in project docs AFTER the test.** If the persona found a bug that's already in the known issues list, that's actually the most damning finding — it means the team knew about it but never felt the user's pain.
-- **Subscription/paywall testing is critical.** Test with expired accounts, not just active ones. The "what happens when you can't pay" experience reveals whether the product respects users or holds their data hostage.
-- **Count the clicks to accomplish the persona's ONE task.** If it's more than 5, that's almost always a RED finding regardless of persona tech level.
-
-## Example Personas by Industry
-
-These are starting points — customize for your specific product:
-
-| Product Type | Persona | Age | Key Trait |
-|-------------|---------|-----|-----------|
-| CRM | Retirement home director | 68 | Filing cabinet is the current CRM |
-| Photography SaaS | Rural wedding photographer | 62 | Books clients by phone, invoices on paper |
-| AI/ML Tool | Department store buyer | 55 | Burned by 3 failed tech startups |
-| Fitness App | Old-school gym coach | 58 | Paper notebook, thick fingers, bad eyes |
-| Accounting | Family bakery owner | 64 | Shoebox of receipts, hates subscriptions |
-| E-commerce | Market stall vendor | 60 | Cash only, smartphone is for calls |
-| Healthcare | Senior GP | 63 | Dictates notes, nurse handles the computer |
-| Education | Veteran teacher | 57 | Chalk and talk, worksheets in ring binders |
-
-## Rules
-
-- Stay in character during Steps 2-3
-- Be genuinely mean but fair — find real problems, not manufactured ones
-- The pragmatism filter (Step 4) is **MANDATORY**
-- Screenshots required for every complaint
-- Max 10 tickets per session
-- Test on staging/deployed app, not local dev
-- One persona, one session, one report

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/test_optional_adversarial_ux_skill_catalog.py

@@ -1,25 +0,0 @@
-from pathlib import Path
-
-from tools.skills_hub import OptionalSkillSource
-
-
-REPO_ROOT = Path(__file__).resolve().parents[1]
-
-
-def test_optional_skill_source_scans_adversarial_ux_test():
-    source = OptionalSkillSource()
-    metas = {meta.identifier: meta for meta in source._scan_all()}
-
-    assert "official/dogfood/adversarial-ux-test" in metas
-    assert metas["official/dogfood/adversarial-ux-test"].name == "adversarial-ux-test"
-    assert "tech-resistant user" in metas["official/dogfood/adversarial-ux-test"].description
-
-
-def test_optional_skill_catalog_docs_list_adversarial_ux_test():
-    optional_catalog = (REPO_ROOT / "website" / "docs" / "reference" / "optional-skills-catalog.md").read_text(encoding="utf-8")
-    bundled_catalog = (REPO_ROOT / "website" / "docs" / "reference" / "skills-catalog.md").read_text(encoding="utf-8")
-
-    assert "**adversarial-ux-test**" in optional_catalog
-    assert "official/dogfood/adversarial-ux-test" in optional_catalog
-    assert "`adversarial-ux-test`" in bundled_catalog
-    assert "dogfood/adversarial-ux-test" in bundled_catalog

website/docs/reference/optional-skills-catalog.md

@@ -16,7 +16,6 @@ For example:
 
 ```bash
 hermes skills install official/blockchain/solana
-hermes skills install official/dogfood/adversarial-ux-test
 hermes skills install official/mlops/flash-attention
 ```
 
@@ -57,12 +56,6 @@ hermes skills uninstall <skill-name>
 | **blender-mcp** | Control Blender directly from Hermes via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python (bpy) code. |
 | **meme-generation** | Generate real meme images by picking a template and overlaying text with Pillow. Produces actual `.png` meme files. |
 
-## Dogfood
-
-| Skill | Description |
-|-------|-------------|
-| **adversarial-ux-test** | Roleplay the most difficult, tech-resistant user for a product — browse in-persona, rant, then filter through a RED/YELLOW/WHITE/GREEN pragmatism layer so only real UX friction becomes tickets. |
-
 ## DevOps
 
 | Skill | Description |

website/docs/reference/skills-catalog.md

@@ -59,12 +59,9 @@ DevOps and infrastructure automation skills.
 
 ## dogfood
 
-Internal dogfooding and QA skills used to test Hermes Agent itself.
-
 | Skill | Description | Path |
 |-------|-------------|------|
 | `dogfood` | Systematic exploratory QA testing of web applications — find bugs, capture evidence, and generate structured reports. | `dogfood/dogfood` |
-| `adversarial-ux-test` | Roleplay the most difficult, tech-resistant user for a product — browse in-persona, rant, then filter through a RED/YELLOW/WHITE/GREEN pragmatism layer so only real UX friction becomes tickets. | `dogfood/adversarial-ux-test` |
 | `hermes-agent-setup` | Help users configure Hermes Agent — CLI usage, setup wizard, model/provider selection, tools, skills, voice/STT/TTS, gateway, and troubleshooting. | `dogfood/hermes-agent-setup` |
 
 ## email