feat(cli): two-stage /model autocomplete with ghost text suggestions (#1641)

* feat(cli): two-stage /model autocomplete with ghost text suggestions

- SlashCommandCompleter: Tab-complete providers first (anthropic:, openrouter:, etc.)
  then models within the selected provider
- SlashCommandAutoSuggest: inline ghost text for slash commands, subcommands,
  and /model provider:model two-stage suggestions
- Custom Tab key binding: accepts provider completion and immediately
  re-triggers completions to show that provider's models
- COMMANDS_BY_CATEGORY: structured format with explicit subcommands for
  tab completion and ghost text (prompt, reasoning, voice, skills, cron, browser)
- SUBCOMMANDS dict auto-extracted from command definitions
- Model/provider info cached 60s for responsive completions

* fix: repair test regression and restore gold color from PR #1622

- Fix test_unknown_command_still_shows_error: patch _cprint instead of
  console.print to match the _cprint switch in process_command()
- Restore gold color on 'Type /help' hint using _DIM + _GOLD constants
  instead of bare \033[2m (was losing the #B8860B gold)
- Use _GOLD constant for ambiguous command message for consistency
- Add clarifying comment on SUBCOMMANDS regex fallback

---------

Co-authored-by: Lars van der Zande <lmvanderzande@gmail.com>

cli.py

@@ -468,7 +468,7 @@ from hermes_cli.banner import (
     VERSION, RELEASE_DATE, HERMES_AGENT_LOGO, HERMES_CADUCEUS, COMPACT_BANNER,
     build_welcome_banner,
 )
-from hermes_cli.commands import COMMANDS, SlashCommandCompleter
+from hermes_cli.commands import COMMANDS, SlashCommandCompleter, SlashCommandAutoSuggest
 from hermes_cli import callbacks as _callbacks
 from toolsets import get_all_toolsets, get_toolset_info, resolve_toolset, validate_toolset
 
@@ -3618,18 +3618,18 @@ class HermesCLI:
                     full_name = matches[0]
                     if full_name == typed_base:
                         # Already an exact token — no expansion possible; fall through
-                        self.console.print(f"[bold red]Unknown command: {cmd_lower}[/]")
-                        self.console.print("[dim #B8860B]Type /help for available commands[/]")
+                        _cprint(f"\033[1;31mUnknown command: {cmd_lower}{_RST}")
+                        _cprint(f"{_DIM}{_GOLD}Type /help for available commands{_RST}")
                     else:
                         remainder = cmd_original.strip()[len(typed_base):]
                         full_cmd = full_name + remainder
                         return self.process_command(full_cmd)
                 elif len(matches) > 1:
-                    self.console.print(f"[bold yellow]Ambiguous command: {cmd_lower}[/]")
-                    self.console.print(f"[dim]Did you mean: {', '.join(sorted(matches))}?[/]")
+                    _cprint(f"{_GOLD}Ambiguous command: {cmd_lower}{_RST}")
+                    _cprint(f"{_DIM}Did you mean: {', '.join(sorted(matches))}?{_RST}")
                 else:
-                    self.console.print(f"[bold red]Unknown command: {cmd_lower}[/]")
-                    self.console.print("[dim #B8860B]Type /help for available commands[/]")
+                    _cprint(f"\033[1;31mUnknown command: {cmd_lower}{_RST}")
+                    _cprint(f"{_DIM}{_GOLD}Type /help for available commands{_RST}")
         
         return True
     
@@ -5746,6 +5746,34 @@ class HermesCLI:
             """Ctrl+Enter (c-j) inserts a newline. Most terminals send c-j for Ctrl+Enter."""
             event.current_buffer.insert_text('\n')
 
+        @kb.add('tab', eager=True)
+        def handle_tab(event):
+            """Tab: accept completion and re-trigger if we just completed a provider.
+
+            After accepting a provider like 'anthropic:', the completion menu
+            closes and complete_while_typing doesn't fire (no keystroke).
+            This binding re-triggers completions so stage-2 models appear
+            immediately.
+            """
+            buf = event.current_buffer
+            if buf.complete_state:
+                completion = buf.complete_state.current_completion
+                if completion is None:
+                    # Menu open but nothing selected — select first then grab it
+                    buf.go_to_completion(0)
+                    completion = buf.complete_state and buf.complete_state.current_completion
+                if completion is None:
+                    return
+                # Accept the selected completion
+                buf.apply_completion(completion)
+                # If text now looks like "/model provider:", re-trigger completions
+                text = buf.document.text_before_cursor
+                if text.startswith("/model ") and text.endswith(":"):
+                    buf.start_completion()
+            else:
+                # No menu open — start completions from scratch
+                buf.start_completion()
+
         # --- Clarify tool: arrow-key navigation for multiple-choice questions ---
 
         @kb.add('up', filter=Condition(lambda: bool(self._clarify_state) and not self._clarify_freetext))
@@ -6012,6 +6040,39 @@ class HermesCLI:
             return cli_ref._get_tui_prompt_fragments()
 
         # Create the input area with multiline (shift+enter), autocomplete, and paste handling
+        from prompt_toolkit.auto_suggest import AutoSuggestFromHistory
+
+        def _get_model_completer_info() -> dict:
+            """Return provider/model info for /model autocomplete."""
+            try:
+                from hermes_cli.models import (
+                    _PROVIDER_LABELS, _PROVIDER_MODELS, normalize_provider,
+                    provider_model_ids,
+                )
+                current = getattr(cli_ref, "provider", None) or getattr(cli_ref, "requested_provider", "openrouter")
+                current = normalize_provider(current)
+
+                # Provider map: id -> label (only providers with known models)
+                providers = {}
+                for pid, plabel in _PROVIDER_LABELS.items():
+                    providers[pid] = plabel
+
+                def models_for(provider_name: str) -> list[str]:
+                    norm = normalize_provider(provider_name)
+                    return provider_model_ids(norm)
+
+                return {
+                    "current_provider": current,
+                    "providers": providers,
+                    "models_for": models_for,
+                }
+            except Exception:
+                return {}
+
+        _completer = SlashCommandCompleter(
+            skill_commands_provider=lambda: _skill_commands,
+            model_completer_provider=_get_model_completer_info,
+        )
         input_area = TextArea(
             height=Dimension(min=1, max=8, preferred=1),
             prompt=get_prompt,
@@ -6020,8 +6081,12 @@ class HermesCLI:
             wrap_lines=True,
             read_only=Condition(lambda: bool(cli_ref._command_running)),
             history=FileHistory(str(self._history_file)),
-            completer=SlashCommandCompleter(skill_commands_provider=lambda: _skill_commands),
+            completer=_completer,
             complete_while_typing=True,
+            auto_suggest=SlashCommandAutoSuggest(
+                history_suggest=AutoSuggestFromHistory(),
+                completer=_completer,
+            ),
         )
 
         # Dynamic height: accounts for both explicit newlines AND visual

hermes_cli/commands.py

@@ -11,11 +11,13 @@ To add an alias: set ``aliases=("short",)`` on the existing ``CommandDef``.
 from __future__ import annotations
 
 import os
+import re
 from collections.abc import Callable, Mapping
 from dataclasses import dataclass, field
 from pathlib import Path
 from typing import Any
 
+from prompt_toolkit.auto_suggest import AutoSuggest, Suggestion
 from prompt_toolkit.completion import Completer, Completion
 
 
@@ -32,6 +34,7 @@ class CommandDef:
     category: str                      # "Session", "Configuration", etc.
     aliases: tuple[str, ...] = ()      # alternative names: ("bg",)
     args_hint: str = ""                # argument placeholder: "<prompt>", "[name]"
+    subcommands: tuple[str, ...] = ()  # tab-completable subcommands
     cli_only: bool = False             # only available in CLI
     gateway_only: bool = False         # only available in gateway/messaging
 
@@ -75,17 +78,18 @@ COMMAND_REGISTRY: list[CommandDef] = [
     CommandDef("provider", "Show available providers and current provider",
                "Configuration"),
     CommandDef("prompt", "View/set custom system prompt", "Configuration",
-               cli_only=True, args_hint="[text]"),
+               cli_only=True, args_hint="[text]", subcommands=("clear",)),
     CommandDef("personality", "Set a predefined personality", "Configuration",
                args_hint="[name]"),
     CommandDef("verbose", "Cycle tool progress display: off -> new -> all -> verbose",
                "Configuration", cli_only=True),
     CommandDef("reasoning", "Manage reasoning effort and display", "Configuration",
-               args_hint="[level|show|hide]"),
+               args_hint="[level|show|hide]",
+               subcommands=("none", "low", "minimal", "medium", "high", "xhigh", "show", "hide", "on", "off")),
     CommandDef("skin", "Show or change the display skin/theme", "Configuration",
                cli_only=True, args_hint="[name]"),
     CommandDef("voice", "Toggle voice mode", "Configuration",
-               args_hint="[on|off|tts|status]"),
+               args_hint="[on|off|tts|status]", subcommands=("on", "off", "tts", "status")),
 
     # Tools & Skills
     CommandDef("tools", "List available tools", "Tools & Skills",
@@ -93,9 +97,11 @@ COMMAND_REGISTRY: list[CommandDef] = [
     CommandDef("toolsets", "List available toolsets", "Tools & Skills",
                cli_only=True),
     CommandDef("skills", "Search, install, inspect, or manage skills",
-               "Tools & Skills", cli_only=True),
+               "Tools & Skills", cli_only=True,
+               subcommands=("search", "browse", "inspect", "install")),
     CommandDef("cron", "Manage scheduled tasks", "Tools & Skills",
-               cli_only=True, args_hint="[subcommand]"),
+               cli_only=True, args_hint="[subcommand]",
+               subcommands=("list", "add", "create", "edit", "pause", "resume", "run", "remove")),
     CommandDef("reload-mcp", "Reload MCP servers from config", "Tools & Skills",
                aliases=("reload_mcp",)),
     CommandDef("plugins", "List installed plugins and their status",
@@ -169,6 +175,26 @@ for _cmd in COMMAND_REGISTRY:
             _cat[f"/{_alias}"] = COMMANDS[f"/{_alias}"]
 
 
+# Subcommands lookup: "/cmd" -> ["sub1", "sub2", ...]
+SUBCOMMANDS: dict[str, list[str]] = {}
+for _cmd in COMMAND_REGISTRY:
+    if _cmd.subcommands:
+        SUBCOMMANDS[f"/{_cmd.name}"] = list(_cmd.subcommands)
+
+# Also extract subcommands hinted in args_hint via pipe-separated patterns
+# e.g. args_hint="[on|off|tts|status]" for commands that don't have explicit subcommands.
+# NOTE: If a command already has explicit subcommands, this fallback is skipped.
+# Use the `subcommands` field on CommandDef for intentional tab-completable args.
+_PIPE_SUBS_RE = re.compile(r"[a-z]+(?:\|[a-z]+)+")
+for _cmd in COMMAND_REGISTRY:
+    key = f"/{_cmd.name}"
+    if key in SUBCOMMANDS or not _cmd.args_hint:
+        continue
+    m = _PIPE_SUBS_RE.search(_cmd.args_hint)
+    if m:
+        SUBCOMMANDS[key] = m.group(0).split("|")
+
+
 # ---------------------------------------------------------------------------
 # Gateway helpers
 # ---------------------------------------------------------------------------
@@ -237,13 +263,34 @@ def slack_subcommand_map() -> dict[str, str]:
 # ---------------------------------------------------------------------------
 
 class SlashCommandCompleter(Completer):
-    """Autocomplete for built-in slash commands and optional skill commands."""
+    """Autocomplete for built-in slash commands, subcommands, and skill commands."""
 
     def __init__(
         self,
         skill_commands_provider: Callable[[], Mapping[str, dict[str, Any]]] | None = None,
+        model_completer_provider: Callable[[], dict[str, Any]] | None = None,
     ) -> None:
         self._skill_commands_provider = skill_commands_provider
+        # model_completer_provider returns {"current_provider": str,
+        #   "providers": {id: label, ...}, "models_for": callable(provider) -> list[str]}
+        self._model_completer_provider = model_completer_provider
+        self._model_info_cache: dict[str, Any] | None = None
+        self._model_info_cache_time: float = 0
+
+    def _get_model_info(self) -> dict[str, Any]:
+        """Get cached model/provider info for /model autocomplete."""
+        import time
+        now = time.monotonic()
+        if self._model_info_cache is not None and now - self._model_info_cache_time < 60:
+            return self._model_info_cache
+        if self._model_completer_provider is None:
+            return {}
+        try:
+            self._model_info_cache = self._model_completer_provider() or {}
+            self._model_info_cache_time = now
+        except Exception:
+            self._model_info_cache = self._model_info_cache or {}
+        return self._model_info_cache
 
     def _iter_skill_commands(self) -> Mapping[str, dict[str, Any]]:
         if self._skill_commands_provider is None:
@@ -348,6 +395,70 @@ class SlashCommandCompleter(Completer):
                 yield from self._path_completions(path_word)
             return
 
+        # Check if we're completing a subcommand (base command already typed)
+        parts = text.split(maxsplit=1)
+        base_cmd = parts[0].lower()
+        if len(parts) > 1 or (len(parts) == 1 and text.endswith(" ")):
+            sub_text = parts[1] if len(parts) > 1 else ""
+            sub_lower = sub_text.lower()
+
+            # /model gets two-stage completion:
+            #   Stage 1: provider names (with : suffix)
+            #   Stage 2: after "provider:", list that provider's models
+            if base_cmd == "/model" and " " not in sub_text:
+                info = self._get_model_info()
+                if info:
+                    current_prov = info.get("current_provider", "")
+                    providers = info.get("providers", {})
+                    models_for = info.get("models_for")
+
+                    if ":" in sub_text:
+                        # Stage 2: "anthropic:cl" → models for anthropic
+                        prov_part, model_part = sub_text.split(":", 1)
+                        model_lower = model_part.lower()
+                        if models_for:
+                            try:
+                                prov_models = models_for(prov_part)
+                            except Exception:
+                                prov_models = []
+                            for mid in prov_models:
+                                if mid.lower().startswith(model_lower) and mid.lower() != model_lower:
+                                    full = f"{prov_part}:{mid}"
+                                    yield Completion(
+                                        full,
+                                        start_position=-len(sub_text),
+                                        display=mid,
+                                    )
+                    else:
+                        # Stage 1: providers sorted: non-current first, current last
+                        for pid, plabel in sorted(
+                            providers.items(),
+                            key=lambda kv: (kv[0] == current_prov, kv[0]),
+                        ):
+                            display_name = f"{pid}:"
+                            if display_name.lower().startswith(sub_lower):
+                                meta = f"({plabel})" if plabel != pid else ""
+                                if pid == current_prov:
+                                    meta = f"(current — {plabel})" if plabel != pid else "(current)"
+                                yield Completion(
+                                    display_name,
+                                    start_position=-len(sub_text),
+                                    display=display_name,
+                                    display_meta=meta,
+                                )
+                return
+
+            # Static subcommand completions
+            if " " not in sub_text and base_cmd in SUBCOMMANDS:
+                for sub in SUBCOMMANDS[base_cmd]:
+                    if sub.startswith(sub_lower) and sub != sub_lower:
+                        yield Completion(
+                            sub,
+                            start_position=-len(sub_text),
+                            display=sub,
+                        )
+            return
+
         word = text[1:]
 
         for cmd, desc in COMMANDS.items():
@@ -373,6 +484,90 @@ class SlashCommandCompleter(Completer):
                 )
 
 
+# ---------------------------------------------------------------------------
+# Inline auto-suggest (ghost text) for slash commands
+# ---------------------------------------------------------------------------
+
+class SlashCommandAutoSuggest(AutoSuggest):
+    """Inline ghost-text suggestions for slash commands and their subcommands.
+
+    Shows the rest of a command or subcommand in dim text as you type.
+    Falls back to history-based suggestions for non-slash input.
+    """
+
+    def __init__(
+        self,
+        history_suggest: AutoSuggest | None = None,
+        completer: SlashCommandCompleter | None = None,
+    ) -> None:
+        self._history = history_suggest
+        self._completer = completer  # Reuse its model cache
+
+    def get_suggestion(self, buffer, document):
+        text = document.text_before_cursor
+
+        # Only suggest for slash commands
+        if not text.startswith("/"):
+            # Fall back to history for regular text
+            if self._history:
+                return self._history.get_suggestion(buffer, document)
+            return None
+
+        parts = text.split(maxsplit=1)
+        base_cmd = parts[0].lower()
+
+        if len(parts) == 1 and not text.endswith(" "):
+            # Still typing the command name: /upd → suggest "ate"
+            word = text[1:].lower()
+            for cmd in COMMANDS:
+                cmd_name = cmd[1:]  # strip leading /
+                if cmd_name.startswith(word) and cmd_name != word:
+                    return Suggestion(cmd_name[len(word):])
+            return None
+
+        # Command is complete — suggest subcommands or model names
+        sub_text = parts[1] if len(parts) > 1 else ""
+        sub_lower = sub_text.lower()
+
+        # /model gets two-stage ghost text
+        if base_cmd == "/model" and " " not in sub_text and self._completer:
+            info = self._completer._get_model_info()
+            if info:
+                providers = info.get("providers", {})
+                models_for = info.get("models_for")
+                current_prov = info.get("current_provider", "")
+
+                if ":" in sub_text:
+                    # Stage 2: after provider:, suggest model
+                    prov_part, model_part = sub_text.split(":", 1)
+                    model_lower = model_part.lower()
+                    if models_for:
+                        try:
+                            for mid in models_for(prov_part):
+                                if mid.lower().startswith(model_lower) and mid.lower() != model_lower:
+                                    return Suggestion(mid[len(model_part):])
+                        except Exception:
+                            pass
+                else:
+                    # Stage 1: suggest provider name with :
+                    for pid in sorted(providers, key=lambda p: (p == current_prov, p)):
+                        candidate = f"{pid}:"
+                        if candidate.lower().startswith(sub_lower) and candidate.lower() != sub_lower:
+                            return Suggestion(candidate[len(sub_text):])
+
+        # Static subcommands
+        if base_cmd in SUBCOMMANDS and SUBCOMMANDS[base_cmd]:
+            if " " not in sub_text:
+                for sub in SUBCOMMANDS[base_cmd]:
+                    if sub.startswith(sub_lower) and sub != sub_lower:
+                        return Suggestion(sub[len(sub_text):])
+
+        # Fall back to history
+        if self._history:
+            return self._history.get_suggestion(buffer, document)
+        return None
+
+
 def _file_size_label(path: str) -> str:
     """Return a compact human-readable file size, or '' on error."""
     try:

tests/hermes_cli/test_commands.py

@@ -9,6 +9,8 @@ from hermes_cli.commands import (
     COMMANDS_BY_CATEGORY,
     CommandDef,
     GATEWAY_KNOWN_COMMANDS,
+    SUBCOMMANDS,
+    SlashCommandAutoSuggest,
     SlashCommandCompleter,
     gateway_help_lines,
     resolve_command,
@@ -323,3 +325,182 @@ class TestSlashCommandCompleter:
         completions = _completions(completer, "/no-desc")
         assert len(completions) == 1
         assert "Skill command" in completions[0].display_meta_text
+
+
+# ── SUBCOMMANDS extraction ──────────────────────────────────────────────
+
+
+class TestSubcommands:
+    def test_explicit_subcommands_extracted(self):
+        """Commands with explicit subcommands on CommandDef are extracted."""
+        assert "/prompt" in SUBCOMMANDS
+        assert "clear" in SUBCOMMANDS["/prompt"]
+
+    def test_reasoning_has_subcommands(self):
+        assert "/reasoning" in SUBCOMMANDS
+        subs = SUBCOMMANDS["/reasoning"]
+        assert "high" in subs
+        assert "show" in subs
+        assert "hide" in subs
+
+    def test_voice_has_subcommands(self):
+        assert "/voice" in SUBCOMMANDS
+        assert "on" in SUBCOMMANDS["/voice"]
+        assert "off" in SUBCOMMANDS["/voice"]
+
+    def test_cron_has_subcommands(self):
+        assert "/cron" in SUBCOMMANDS
+        assert "list" in SUBCOMMANDS["/cron"]
+        assert "add" in SUBCOMMANDS["/cron"]
+
+    def test_commands_without_subcommands_not_in_dict(self):
+        """Plain commands should not appear in SUBCOMMANDS."""
+        assert "/help" not in SUBCOMMANDS
+        assert "/quit" not in SUBCOMMANDS
+        assert "/clear" not in SUBCOMMANDS
+
+
+# ── Subcommand tab completion ───────────────────────────────────────────
+
+
+class TestSubcommandCompletion:
+    def test_subcommand_completion_after_space(self):
+        """Typing '/reasoning ' then Tab should show subcommands."""
+        completions = _completions(SlashCommandCompleter(), "/reasoning ")
+        texts = {c.text for c in completions}
+        assert "high" in texts
+        assert "show" in texts
+
+    def test_subcommand_prefix_filters(self):
+        """Typing '/reasoning sh' should only show 'show'."""
+        completions = _completions(SlashCommandCompleter(), "/reasoning sh")
+        texts = {c.text for c in completions}
+        assert texts == {"show"}
+
+    def test_subcommand_exact_match_suppressed(self):
+        """Typing the full subcommand shouldn't re-suggest it."""
+        completions = _completions(SlashCommandCompleter(), "/reasoning show")
+        texts = {c.text for c in completions}
+        assert "show" not in texts
+
+    def test_no_subcommands_for_plain_command(self):
+        """Commands without subcommands yield nothing after space."""
+        completions = _completions(SlashCommandCompleter(), "/help ")
+        assert completions == []
+
+
+# ── Two-stage /model completion ─────────────────────────────────────────
+
+
+def _model_completer() -> SlashCommandCompleter:
+    """Build a completer with mock model/provider info."""
+    return SlashCommandCompleter(
+        model_completer_provider=lambda: {
+            "current_provider": "openrouter",
+            "providers": {
+                "anthropic": "Anthropic",
+                "openrouter": "OpenRouter",
+                "nous": "Nous Research",
+            },
+            "models_for": lambda p: {
+                "anthropic": ["claude-sonnet-4-20250514", "claude-opus-4-20250414"],
+                "openrouter": ["anthropic/claude-sonnet-4", "google/gemini-2.5-pro"],
+                "nous": ["hermes-3-llama-3.1-405b"],
+            }.get(p, []),
+        }
+    )
+
+
+class TestModelCompletion:
+    def test_stage1_shows_providers(self):
+        completions = _completions(_model_completer(), "/model ")
+        texts = {c.text for c in completions}
+        assert "anthropic:" in texts
+        assert "openrouter:" in texts
+        assert "nous:" in texts
+
+    def test_stage1_current_provider_last(self):
+        completions = _completions(_model_completer(), "/model ")
+        texts = [c.text for c in completions]
+        assert texts[-1] == "openrouter:"
+
+    def test_stage1_current_provider_labeled(self):
+        completions = _completions(_model_completer(), "/model ")
+        for c in completions:
+            if c.text == "openrouter:":
+                assert "current" in c.display_meta_text.lower()
+                break
+        else:
+            raise AssertionError("openrouter: not found in completions")
+
+    def test_stage1_prefix_filters(self):
+        completions = _completions(_model_completer(), "/model an")
+        texts = {c.text for c in completions}
+        assert texts == {"anthropic:"}
+
+    def test_stage2_shows_models(self):
+        completions = _completions(_model_completer(), "/model anthropic:")
+        texts = {c.text for c in completions}
+        assert "anthropic:claude-sonnet-4-20250514" in texts
+        assert "anthropic:claude-opus-4-20250414" in texts
+
+    def test_stage2_prefix_filters_models(self):
+        completions = _completions(_model_completer(), "/model anthropic:claude-s")
+        texts = {c.text for c in completions}
+        assert "anthropic:claude-sonnet-4-20250514" in texts
+        assert "anthropic:claude-opus-4-20250414" not in texts
+
+    def test_stage2_no_model_provider_returns_empty(self):
+        completions = _completions(SlashCommandCompleter(), "/model ")
+        assert completions == []
+
+
+# ── Ghost text (SlashCommandAutoSuggest) ────────────────────────────────
+
+
+def _suggestion(text: str, completer=None) -> str | None:
+    """Get ghost text suggestion for given input."""
+    suggest = SlashCommandAutoSuggest(completer=completer)
+    doc = Document(text=text)
+
+    class FakeBuffer:
+        pass
+
+    result = suggest.get_suggestion(FakeBuffer(), doc)
+    return result.text if result else None
+
+
+class TestGhostText:
+    def test_command_name_suggestion(self):
+        """/he → 'lp'"""
+        assert _suggestion("/he") == "lp"
+
+    def test_command_name_suggestion_reasoning(self):
+        """/rea → 'soning'"""
+        assert _suggestion("/rea") == "soning"
+
+    def test_no_suggestion_for_complete_command(self):
+        assert _suggestion("/help") is None
+
+    def test_subcommand_suggestion(self):
+        """/reasoning h → 'igh'"""
+        assert _suggestion("/reasoning h") == "igh"
+
+    def test_subcommand_suggestion_show(self):
+        """/reasoning sh → 'ow'"""
+        assert _suggestion("/reasoning sh") == "ow"
+
+    def test_no_suggestion_for_non_slash(self):
+        assert _suggestion("hello") is None
+
+    def test_model_stage1_ghost_text(self):
+        """/model a → 'nthropic:'"""
+        completer = _model_completer()
+        assert _suggestion("/model a", completer=completer) == "nthropic:"
+
+    def test_model_stage2_ghost_text(self):
+        """/model anthropic:cl → rest of first matching model"""
+        completer = _model_completer()
+        s = _suggestion("/model anthropic:cl", completer=completer)
+        assert s is not None
+        assert s.startswith("aude-")

tests/test_cli_prefix_matching.py

@@ -72,15 +72,17 @@ class TestSlashCommandPrefixMatching:
     def test_ambiguous_prefix_shows_suggestions(self):
         """/re matches multiple commands — should show ambiguous message."""
         cli_obj = _make_cli()
+        with patch("cli._cprint") as mock_cprint:
             cli_obj.process_command("/re")
-        printed = " ".join(str(c) for c in cli_obj.console.print.call_args_list)
+            printed = " ".join(str(c) for c in mock_cprint.call_args_list)
         assert "Ambiguous" in printed or "Did you mean" in printed
 
     def test_unknown_command_shows_error(self):
         """/xyz should show unknown command error."""
         cli_obj = _make_cli()
+        with patch("cli._cprint") as mock_cprint:
             cli_obj.process_command("/xyz")
-        printed = " ".join(str(c) for c in cli_obj.console.print.call_args_list)
+            printed = " ".join(str(c) for c in mock_cprint.call_args_list)
         assert "Unknown command" in printed
 
     def test_exact_command_still_works(self):

tests/test_quick_commands.py

@@ -72,10 +72,11 @@ class TestCLIQuickCommands:
 
     def test_unknown_command_still_shows_error(self):
         cli = self._make_cli({})
+        with patch("cli._cprint") as mock_cprint:
             cli.process_command("/nonexistent")
-        cli.console.print.assert_called()
-        args = cli.console.print.call_args_list[0][0][0]
-        assert "unknown command" in args.lower()
+            mock_cprint.assert_called()
+            printed = " ".join(str(c) for c in mock_cprint.call_args_list)
+            assert "unknown command" in printed.lower()
 
     def test_timeout_shows_error(self):
         cli = self._make_cli({"slow": {"type": "exec", "command": "sleep 100"}})