Merge branch 'feature/header-panel-agent-modes'

Replace built-in Header with a custom HeaderPanel showing model name,
mode badge, and live token usage. Add AgentMode enum (normal/plan/auto)
with mode-aware permission gating — Plan mode restricts to read-only
tools, Auto mode auto-approves everything. Includes /mode slash command
and Ctrl+P keybinding to cycle modes.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

.gitignore

@@ -34,3 +34,6 @@ htmlcov/
 
 # Worktrees
 .worktrees/
+
+# SneakyCode local data
+.sneakycode/

README.md

@@ -26,31 +26,79 @@ pip install -e ".[dev]"
 
 ## Configuration
 
-Edit `config/config.yaml` to configure the agent. Key settings:
+Edit `config/config.yaml` to configure the agent. The full configuration reference:
 
 ```yaml
 llm:
-  model: "qwen3.5:latest"        # Ollama model name
+  model: "qwen3.5:latest"              # Ollama model name
-  endpoint: "http://localhost:11434"  # Ollama endpoint
+  endpoint: "http://localhost:11434"    # Ollama endpoint
-  max_retries: 3                   # Retry attempts on transient errors
+  api_path: "/v1/chat/completions"     # API endpoint path
-  retry_backoff_base: 1.0          # Exponential backoff base (seconds)
+  temperature: 0.1                     # Sampling temperature
+  max_tokens: 4096                     # Maximum tokens in LLM response
+  timeout: 120                         # Request timeout in seconds
+  max_retries: 3                       # Retry attempts on transient errors
+  retry_backoff_base: 1.0              # Exponential backoff base (seconds)
+  retry_backoff_max: 30.0              # Maximum backoff seconds
 
 agent:
-  max_iterations: 25               # Max tool-call iterations per turn
+  max_iterations: 25                   # Max tool-call iterations per turn
-  max_conversation_tokens: 32000   # Token budget for conversation
+  max_conversation_tokens: 32000       # Token budget for conversation
-  workspace_root: "."              # Project directory for file operations
+  workspace_root: "."                  # Project directory for file operations
-  truncation_keep_recent: 10       # Messages preserved during truncation
+  truncation_keep_recent: 10           # Messages preserved during truncation
-  truncation_threshold: 0.85       # Budget fraction that triggers truncation
+  truncation_threshold: 0.85           # Budget fraction that triggers truncation
 
 session:
-  auto_save: true                  # Save session after each turn
+  session_dir: ".sneakycode/sessions"  # Directory for session files
-  max_session_age_hours: 72        # Auto-cleanup old sessions
+  auto_save: true                      # Save session after each turn
-  offer_resume: true               # Offer to resume on startup
+  max_session_age_hours: 72            # Auto-cleanup old sessions
+  offer_resume: true                   # Offer to resume on startup
 
 permissions:
   auto_approve: [read_file, list_dir, grep_files, find_files, finish]
   prompt_user: [write_file, delete_file, run_command, str_replace, patch_apply, make_dir]
   deny: []
+
+tools:
+  shell:
+    allowed_commands:                   # Commands the LLM may run
+      - git
+      - python
+      - pip
+      - pytest
+      - ruff
+      - ls
+      - cat
+      - head
+      - tail
+      - wc
+      - diff
+      - grep
+      - find
+      - echo
+    denied_commands:                    # Blocked commands
+      - rm -rf /
+      - sudo
+      - curl
+      - wget
+    max_output_bytes: 65536            # Max captured output size (bytes)
+  filesystem:
+    max_file_size_bytes: 1048576       # 1 MB — max file size for read/write
+    binary_detection: true             # Detect and reject binary files
+
+display:
+  show_tool_calls: true                # Show tool call details in output
+  show_token_usage: true               # Show token usage stats
+  stream_output: true                  # Stream LLM output to terminal
+
+skills:
+  enabled: true                        # Enable the skills system
+  directories:                         # Directories to scan for skill files
+    - ".sneakycode/skills"
+
+debug:
+  enabled: false                       # Enable debug logging
+  log_dir: ".sneakycode/logs"          # Debug log directory
+  max_files: 10                        # Max debug log files to retain
 ```
 
 Environment variable `SNEAKYCODE_CONFIG` can override the config file path.
@@ -58,9 +106,12 @@ Environment variable `SNEAKYCODE_CONFIG` can override the config file path.
 ## Usage
 
 ```bash
-# Start the interactive REPL
+# Start the interactive TUI
 sneakycode
 
+# Open a specific project directory
+sneakycode /path/to/project
+
 # Or run directly
 python -m app.main
 
@@ -68,25 +119,38 @@ python -m app.main
 sneakycode --config path/to/config.yaml --verbose --log-file sneakycode.log
 ```
 
+### CLI Options
+
+| Option                   | Description                                      |
+|--------------------------|--------------------------------------------------|
+| `DIRECTORY`              | Project directory to use as workspace root        |
+| `--config PATH`          | Path to config YAML file (default: `config/config.yaml`) |
+| `-v`, `--verbose`        | Enable verbose (DEBUG) logging                   |
+| `--log-file PATH`        | Path to log file for persistent logging          |
+
 ### REPL Commands
 
-| Command    | Description                          |
+| Command           | Description                                        |
-|------------|--------------------------------------|
+|-------------------|----------------------------------------------------|
-| `/quit`    | Save session and exit                |
+| `/help`           | Show available commands                            |
-| `/history` | Show conversation history            |
+| `/quit`           | Save session and exit (also `/exit`, `/bye`)       |
-| `/clear`   | Clear conversation history           |
+| `/history`        | Show conversation history                          |
-| `/save`    | Manually save session                |
+| `/clear`          | Clear conversation history                         |
-| `/session` | Show session info (messages, tokens) |
+| `/save`           | Manually save session                              |
+| `/session`        | Show session info (messages, tokens, start time)   |
+| `/models`         | List available Ollama models                       |
+| `/models <name>`  | Switch to a different model                        |
+| `/skills`         | List available skills                              |
 
 ### Session Persistence
 
 Sessions are automatically saved after each agent turn and on exit. On startup, SneakyCode offers to resume the most recent session for the current workspace.
 
-Session files are stored in `.sneakycode/sessions/` within the workspace root.
+Session files are stored in `.sneakycode/sessions/` within the workspace root (configurable via `session.session_dir`).
 
 ## Available Tools
 
-SneakyCode provides 11 tools across 5 categories. See [docs/tools.md](docs/tools.md) for the full reference.
+SneakyCode provides tools across 6 categories. See [docs/tools.md](docs/tools.md) for the full reference.
 
 | Category   | Tools                                           | Permission    |
 |------------|-------------------------------------------------|---------------|
@@ -96,6 +160,17 @@ SneakyCode provides 11 tools across 5 categories. See [docs/tools.md](docs/tools
 | Edit       | `str_replace`, `patch_apply`                    | User confirm  |
 | Shell      | `run_command`                                   | User confirm  |
 | Control    | `finish`                                        | Auto-approved |
+| Skills     | `load_skill`                                    | Auto-approved |
+
+The `load_skill` tool is available when `skills.enabled` is `true` in the config. It allows the LLM to load skill instructions from the configured skill directories.
+
+## Skills
+
+SneakyCode includes a skills system that lets you provide reusable instruction sets to the LLM. Skills are markdown files placed in `.sneakycode/skills/` (or any directory listed in `skills.directories`).
+
+Skills are auto-discovered on startup. The LLM can load them via the `load_skill` tool, and you can list available skills with the `/skills` command.
+
+To create a skill, add a `.md` file to your skills directory with a descriptive filename (e.g., `refactoring.md`). The file content is injected into the conversation when the skill is loaded.
 
 ## Development
 
@@ -121,6 +196,7 @@ app/
 ├── models/          # Pydantic config and message schemas
 ├── services/        # LLM client, streaming, permissions, session persistence
 ├── tools/           # Tool implementations (one file per group)
+├── ui/              # Textual TUI application and widgets
 └── utils/           # Logging, display, file helpers, token counter
 config/
 └── config.yaml      # Application configuration

app/agent/loop.py

@@ -7,7 +7,7 @@ import time
 from typing import TYPE_CHECKING, Any
 
 from app.agent.context import SessionContext
-from app.models.config import AppConfig
+from app.models.config import AgentMode, AppConfig
 from app.models.message import Message
 from app.models.tool_call import ToolCall, ToolResult, ToolResultStatus
 from app.services.llm import LLMClient, LLMConnectionError, LLMError, LLMStreamError
@@ -59,6 +59,12 @@ class AgentLoop:
         self._skills = skills_manager
         self._skill_runner = skill_runner
         self._tools_schema = registry.get_openai_tools_schema()
+        if self._permissions.mode == AgentMode.PLAN:
+            read_only = PermissionsService.READ_ONLY_TOOLS
+            self._tools_schema = [
+                t for t in self._tools_schema
+                if t["function"]["name"] in read_only
+            ]
         self._system_prompt = self._build_system_prompt()
         self._cancelled = False
 
@@ -89,29 +95,36 @@ class AgentLoop:
                 f"\n\nCurrently active skill: {self._skill_runner.active_skill_name}. "
                 "When the skill's objective is complete, call the `finish_skill` tool."
             )
+        if self._permissions.mode == AgentMode.PLAN:
+            prompt += (
+                "\n\nYou are in PLAN mode. You may only use read-only tools: "
+                "read_file, list_dir, grep_files, find_files, finish. "
+                "Do NOT attempt to write files, edit code, or run commands. "
+                "Instead, describe what changes you would make, which files "
+                "you would modify, and provide the reasoning for each change."
+            )
         return prompt
 
     def _get_messages_with_system_prompt(self) -> list[Message]:
         """Prepend the system prompt to conversation history.
 
-        When thinking is disabled, injects a /no_think tag into the last user
+        When thinking is disabled, appends a system-level /no_think directive
-        message so Qwen 3.x (and similar) chat templates see it regardless of
+        after the last user message so Qwen 3.x (and similar) chat templates
-        where tool-result messages fall in the history.
+        see it, without polluting the user's actual message content.
         """
         system_msg = Message(role="system", content=self._system_prompt)
         history = self._ctx.get_history()
 
         if not self._config.llm.thinking and history:
             history = list(history)
+            # Find last user message and insert a system hint after it
             for i in range(len(history) - 1, -1, -1):
                 if history[i].role == "user":
-                    original = history[i]
+                    no_think_msg = Message(
-                    history[i] = Message(
+                        role="system",
-                        role="user",
+                        content="/no_think",
-                        content=(original.content or "") + " /no_think",
-                        tool_call_id=original.tool_call_id,
-                        name=original.name,
                     )
+                    history.insert(i + 1, no_think_msg)
                     break
 
         return [system_msg] + history
@@ -217,10 +230,12 @@ class AgentLoop:
             # Successful response — reset streak
             reasoning_only_streak = 0
 
+            # Display any assistant text content (even if tool calls follow)
+            if self._display and assistant_msg.content:
+                self._display.write_assistant_message(assistant_msg.content)
+
             # No tool calls → task complete (plain text response)
             if not assistant_msg.tool_calls:
-                if self._display and assistant_msg.content:
-                    self._display.write_assistant_message(assistant_msg.content)
                 break
 
             # Execute tool calls

app/models/config.py

@@ -1,6 +1,7 @@
 """Pydantic configuration models mapping to config/config.yaml."""
 
 import os
+from enum import StrEnum
 from pathlib import Path
 from typing import Any
 
@@ -8,6 +9,14 @@ import yaml
 from pydantic import BaseModel, Field, model_validator
 
 
+class AgentMode(StrEnum):
+    """Runtime agent mode controlling permission behavior."""
+
+    NORMAL = "normal"
+    PLAN = "plan"
+    AUTO = "auto"
+
+
 class LLMConfig(BaseModel):
     """LLM backend configuration."""
 

app/services/permissions.py

@@ -4,16 +4,20 @@ from __future__ import annotations
 
 import json
 import logging
+import re
 import shlex
 from collections.abc import Awaitable, Callable
 
-from app.models.config import PermissionsConfig, ToolsConfig
+from app.models.config import AgentMode, PermissionsConfig, ToolsConfig
 
 logger = logging.getLogger(__name__)
 
 # Type alias for the async prompt callback
 PromptCallback = Callable[[str, str], Awaitable[bool]]
 
+# Detect shell redirects that write to files (>, >>, heredocs)
+_WRITE_REDIRECT_PATTERN = re.compile(r"(?:>\s*\S|>>|<<)")
+
 
 class PermissionDenied(Exception):
     """Raised when a tool is denied execution by permissions policy."""
@@ -26,6 +30,10 @@ class PermissionsService:
     shows a modal dialog. Without a callback, unlisted tools are denied.
     """
 
+    READ_ONLY_TOOLS: frozenset[str] = frozenset({
+        "read_file", "list_dir", "grep_files", "find_files", "finish",
+    })
+
     def __init__(
         self,
         config: PermissionsConfig,
@@ -34,6 +42,16 @@ class PermissionsService:
         self.config = config
         self._tools_config = tools_config
         self._prompt_callback: PromptCallback | None = None
+        self._mode: AgentMode = AgentMode.NORMAL
+
+    @property
+    def mode(self) -> AgentMode:
+        """Current agent mode."""
+        return self._mode
+
+    @mode.setter
+    def mode(self, value: AgentMode) -> None:
+        self._mode = value
 
     def set_prompt_callback(self, callback: PromptCallback) -> None:
         """Set the async callback used to prompt the user for permission.
@@ -63,6 +81,16 @@ class PermissionsService:
             logger.info("Tool '%s' is in deny list — blocked", tool_name)
             return False
 
+        if self._mode == AgentMode.AUTO:
+            logger.debug("Tool '%s' auto-approved (AUTO mode)", tool_name)
+            return True
+
+        if self._mode == AgentMode.PLAN:
+            if tool_name not in self.READ_ONLY_TOOLS:
+                logger.info("Tool '%s' blocked in Plan mode (read-only tools only)", tool_name)
+                return False
+            return True
+
         if tool_name in self.config.auto_approve:
             logger.debug("Tool '%s' is auto-approved", tool_name)
             return True
@@ -104,6 +132,11 @@ class PermissionsService:
                 logger.info("Shell command '%s' matches denied prefix '%s'", cmd, denied)
                 return False
 
+        # Detect shell redirects that write to files — require approval
+        if _WRITE_REDIRECT_PATTERN.search(cmd):
+            logger.info("Shell command '%s' contains file-write redirect — requiring approval", cmd)
+            return None  # fall through to user prompt
+
         # Allowed commands: base executable match
         if shell_config.allowed_commands:
             if base_cmd in shell_config.allowed_commands:

app/tools/shell.py

@@ -1,5 +1,6 @@
 """Shell tool: run_command."""
 
+import re
 import shlex
 import subprocess
 from typing import Any
@@ -11,6 +12,9 @@ from app.tools.base import BaseTool
 
 _DEFAULT_TIMEOUT = 30
 
+# Detect shell redirects that write to files (>, >>, heredocs)
+_WRITE_REDIRECT_PATTERN = re.compile(r"(?:>\s*\S|>>|<<)")
+
 
 class RunCommandParams(BaseModel):
     """Parameters for the run_command tool."""
@@ -43,6 +47,18 @@ class RunCommandTool(BaseTool):
                     error=f"Command denied: matches blocked prefix '{denied}'",
                 )
 
+        # Defense-in-depth: flag file-write redirects in tool result
+        if _WRITE_REDIRECT_PATTERN.search(command):
+            return ToolResult(
+                tool_call_id=tool_call_id,
+                tool_name=self.name,
+                status=ToolResultStatus.ERROR,
+                error=(
+                    f"Command contains file-write redirect (>, >>, or <<) "
+                    f"which bypasses file-write permissions. Use write_file instead."
+                ),
+            )
+
         # Allow check: first token must be in allowed_commands
         try:
             tokens = shlex.split(command)

app/ui/app.py

@@ -10,18 +10,19 @@ from rich.panel import Panel
 from rich.text import Text
 from textual.app import App, ComposeResult
 from textual.binding import Binding
-from textual.widgets import Header, Input, RichLog
+from textual.widgets import Input, RichLog
 from textual import work
 
 from app.agent.context import SessionContext
 from app.agent.loop import AgentLoop
-from app.models.config import AppConfig
+from app.models.config import AgentMode, AppConfig
 from app.services.llm import LLMClient
 from app.services.permissions import PermissionsService
 from app.services.session import SessionManager
 from app.services.streaming import StreamHandler
 from app.tools.registry import create_default_registry
 from app.ui.widgets import (
+    HeaderPanel,
     HistoryInput,
     PermissionModal,
     SessionResumeModal,
@@ -45,6 +46,7 @@ class SneakyCodeApp(App):
 
     BINDINGS = [
         Binding("ctrl+c", "cancel_or_quit", "Cancel/Quit", show=False),
+        Binding("ctrl+p", "cycle_mode", "Cycle Mode"),
     ]
 
     def __init__(self, config: AppConfig, session_mgr: SessionManager | None = None) -> None:
@@ -61,10 +63,9 @@ class SneakyCodeApp(App):
         self._skill_runner = None
         self._current_worker: Worker | None = None
         self._cancel_count = 0
-        self.sub_title = config.llm.model
 
     def compose(self) -> ComposeResult:
-        yield Header()
+        yield HeaderPanel(model_name=self._config.llm.model)
         yield RichLog(id="chat-log", highlight=True, markup=True)
         yield StreamingStatic("", id="streaming")
         yield StatusBar()
@@ -156,6 +157,10 @@ class SneakyCodeApp(App):
         event.input.record(user_input)
         log = self.query_one("#chat-log", RichLog)
 
+        # Echo user prompt (condensed for multi-line)
+        from app.utils.display import render_user_message
+        log.write(render_user_message(user_input))
+
         # Handle slash commands
         if user_input.startswith("/"):
             await self._handle_slash_command(user_input, log)
@@ -186,6 +191,8 @@ class SneakyCodeApp(App):
             table.add_row("/session", "Show session info (messages, tokens, start time)")
             table.add_row("/models", "List available Ollama models")
             table.add_row("/models <name>", "Switch to a different model")
+            table.add_row("/mode", "Show current agent mode")
+            table.add_row("/mode normal|plan|auto", "Switch agent mode")
             table.add_row("/skills", "List available skills")
             table.add_row("/<skill>", "Load a skill by name")
             log.write(table)
@@ -239,8 +246,23 @@ class SneakyCodeApp(App):
             else:
                 new_model = parts[1].strip()
                 self._config.llm.model = new_model
-                self.sub_title = new_model
+                self.query_one(HeaderPanel).update_model(new_model)
                 log.write(Text(f"Switched to model: {new_model}", style="bold green"))
+        elif cmd.startswith("/mode"):
+            parts = command.split(maxsplit=1)
+            if len(parts) == 1:
+                current = self._permissions.mode
+                log.write(Text(f"Current mode: {current.value}", style="cyan"))
+            else:
+                mode_str = parts[1].strip().lower()
+                try:
+                    new_mode = AgentMode(mode_str)
+                except ValueError:
+                    log.write(Text(f"Unknown mode: {mode_str}. Use normal, plan, or auto.", style="yellow"))
+                    return
+                self._permissions.mode = new_mode
+                self.query_one(HeaderPanel).update_mode(new_mode)
+                log.write(Text(f"Switched to {new_mode.value} mode", style="bold green"))
         elif cmd == "/skills":
             if self._skills_manager:
                 skills = self._skills_manager.list_skills()
@@ -302,12 +324,19 @@ class SneakyCodeApp(App):
         status_bar.start_streaming()
 
         # Set up streaming UI callbacks
+        header = self.query_one(HeaderPanel)
+
         def on_content(content: str) -> None:
             streaming_widget.update(
                 Panel(Markdown(content), title="Assistant", border_style="green", expand=True)
             )
             streaming_widget.show_streaming()
-            status_bar.update_stream_tokens(len(content) // 4)
+            stream_tokens = len(content) // 4
+            status_bar.update_stream_tokens(stream_tokens)
+            header.update_tokens(
+                self._ctx.estimated_tokens + stream_tokens,
+                self._ctx.token_counter.budget,
+            )
 
         def on_thinking() -> None:
             streaming_widget.update(Text("Thinking...", style="dim"))
@@ -331,6 +360,10 @@ class SneakyCodeApp(App):
 
         status_bar.stop_streaming()
 
+        # Update token display in header
+        header = self.query_one(HeaderPanel)
+        header.update_tokens(self._ctx.estimated_tokens, self._ctx.token_counter.budget)
+
         # Update skill indicator (skill may have been deactivated via finish_skill)
         if self._skill_runner and not self._skill_runner.is_active:
             status_bar.set_active_skill(None)
@@ -356,6 +389,21 @@ class SneakyCodeApp(App):
             log = self.query_one("#chat-log", RichLog)
             log.write(Text("⚠ Cancelling... (press Ctrl+C again to quit)", style="yellow"))
 
+    def action_cycle_mode(self) -> None:
+        """Cycle through agent modes: Normal → Plan → Auto → Normal."""
+        if self._permissions is None:
+            return
+        cycle = {
+            AgentMode.NORMAL: AgentMode.PLAN,
+            AgentMode.PLAN: AgentMode.AUTO,
+            AgentMode.AUTO: AgentMode.NORMAL,
+        }
+        new_mode = cycle[self._permissions.mode]
+        self._permissions.mode = new_mode
+        self.query_one(HeaderPanel).update_mode(new_mode)
+        log = self.query_one("#chat-log", RichLog)
+        log.write(Text(f"Mode: {new_mode.value}", style="bold green"))
+
     async def on_unmount(self) -> None:
         """Clean up the LLM client on app shutdown."""
         if self._client is not None:

app/ui/styles.tcss

@@ -55,8 +55,8 @@ Screen {
 Input {
     dock: bottom;
     margin: 0;
+    border: none;
+    padding: 0 1;
 }
 
-Header {
+/* HeaderPanel styles are in DEFAULT_CSS on the widget itself */
-    dock: top;
-}

app/ui/widgets.py

@@ -11,6 +11,82 @@ from textual.widgets import Button, Input, Static
 
 from rich.text import Text
 
+from app.models.config import AgentMode
+
+
+# ---------------------------------------------------------------------------
+# Header Panel
+# ---------------------------------------------------------------------------
+
+
+class HeaderPanel(Static):
+    """Single-line header showing model name, agent mode, and token usage."""
+
+    DEFAULT_CSS = """
+    HeaderPanel {
+        dock: top;
+        height: 1;
+        background: $accent;
+        color: $text;
+        padding: 0 2;
+    }
+    """
+
+    def __init__(self, model_name: str) -> None:
+        super().__init__("")
+        self._model_name = model_name
+        self._mode: AgentMode = AgentMode.NORMAL
+        self._tokens: int = 0
+        self._budget: int = 0
+
+    def on_resize(self) -> None:
+        self._refresh_display()
+
+    def update_model(self, name: str) -> None:
+        """Update the displayed model name."""
+        self._model_name = name
+        self._refresh_display()
+
+    def update_mode(self, mode: AgentMode) -> None:
+        """Update the displayed agent mode."""
+        self._mode = mode
+        self._refresh_display()
+
+    def update_tokens(self, tokens: int, budget: int) -> None:
+        """Update the token usage display."""
+        self._tokens = tokens
+        self._budget = budget
+        self._refresh_display()
+
+    def _refresh_display(self) -> None:
+        """Rebuild the header text."""
+        left = Text.assemble(
+            ("⚡ SneakyCode", "bold"),
+            " │ ",
+            (self._model_name, "bold"),
+        )
+
+        mode_styles = {
+            AgentMode.NORMAL: ("NORMAL", "bold black on white"),
+            AgentMode.PLAN: ("PLAN", "bold black on yellow"),
+            AgentMode.AUTO: ("AUTO", "bold white on red"),
+        }
+        mode_label, mode_style = mode_styles[self._mode]
+        mode_text = Text.assemble((" ", mode_style), (mode_label, mode_style), (" ", mode_style))
+
+        right = Text(f"~{self._tokens:,} / {self._budget:,} tokens")
+
+        # Pad between sections
+        total_content = left.plain + "  " + mode_text.plain + "  " + right.plain
+        available = self.size.width if self.size.width > 0 else 80
+        gap_left = max(1, (available - len(total_content)) // 2)
+        gap_right = max(1, available - len(total_content) - gap_left)
+
+        full = Text.assemble(
+            left, " " * gap_left, mode_text, " " * gap_right, right,
+        )
+        self.update(full)
+
 
 # ---------------------------------------------------------------------------
 # Modal Dialogs
@@ -139,8 +215,6 @@ class StatusBar(Static):
 
     def __init__(self) -> None:
         super().__init__("")
-        self._tokens: int = 0
-        self._budget: int = 0
         self._iteration: int = 0
         self._max_iterations: int = 0
         self._streaming: bool = False
@@ -149,12 +223,6 @@ class StatusBar(Static):
         self._stream_tokens: int = 0
         self._active_skill: str | None = None
 
-    def update_tokens(self, tokens: int, budget: int) -> None:
-        """Update the token usage display."""
-        self._tokens = tokens
-        self._budget = budget
-        self._refresh_display()
-
     def update_iteration(self, iteration: int, max_iterations: int) -> None:
         """Update the iteration count display."""
         self._iteration = iteration
@@ -200,8 +268,6 @@ class StatusBar(Static):
             parts.append(f"{spinner} Thinking")
             if self._stream_tokens > 0:
                 parts.append(f"~{self._stream_tokens:,} tokens")
-        if self._budget > 0:
-            parts.append(f"Tokens: ~{self._tokens:,} / {self._budget:,}")
         if self._max_iterations > 0:
             parts.append(f"Iteration {self._iteration}/{self._max_iterations}")
         self.update(Text(" \u2502 ".join(parts), style="dim"))

app/utils/display.py

@@ -44,9 +44,22 @@ if TYPE_CHECKING:
 # ---------------------------------------------------------------------------
 
 
-def render_user_message(content: str) -> Panel:
+def render_user_message(content: str) -> Text:
-    """Render a user message as a styled panel."""
+    """Render a condensed user prompt as a single styled line.
-    return Panel(content, title="You", border_style="cyan", expand=False)
+
+    Multi-line input is collapsed to the first line with a line count suffix.
+    Long single lines are truncated.
+    """
+    lines = content.splitlines()
+    first = lines[0] if lines else content
+    max_len = 120
+    if len(first) > max_len:
+        first = first[:max_len] + "…"
+    suffix = f" (+{len(lines) - 1} lines)" if len(lines) > 1 else ""
+    text = Text()
+    text.append("You: ", style="bold cyan")
+    text.append(first + suffix, style="cyan")
+    return text
 
 
 def render_assistant_message(content: str) -> Panel:
@@ -223,8 +236,8 @@ def print_success(message: str) -> None:
 
 
 def print_user_message(content: str) -> None:
-    """Print a user message in a styled panel."""
+    """Print a condensed user prompt line."""
-    console.print(Panel(content, title="You", border_style="cyan", expand=False))
+    console.print(render_user_message(content))
 
 
 def print_assistant_message(content: str) -> None:

config/config.yaml

@@ -48,7 +48,6 @@ tools:
       - pytest
       - ruff
       - ls
-      - cat
       - head
       - tail
       - wc
@@ -56,6 +55,10 @@ tools:
       - grep
       - find
       - echo
+      - which
+      - jq
+      - type
+      - file
     denied_commands:
       - rm -rf /
       - sudo

docs/ROADMAP.md

@@ -1,144 +0,0 @@
-# SneakyCode Implementation Roadmap
-
-A phased plan progressing from bare-bones foundation to full autonomous coding agent.
-
----
-
-## Phase 1 — Foundation: Models, Config, and Utilities
-
-Establish the data layer and shared infrastructure everything else builds on.
-
-| File | Description |
-|------|-------------|
-| `app/models/config.py` | Pydantic v2 config model — load and validate `config/config.yaml` |
-| `app/models/message.py` | Message schema (role, content, tool_calls) |
-| `app/models/tool_call.py` | ToolCall and ToolResult schemas |
-| `app/utils/logging.py` | Centralized logger with Rich handler |
-| `app/utils/display.py` | Rich console output helpers (stub — expanded in Phase 2) |
-| `app/utils/file_helpers.py` | Safe path resolution, binary detection, size guards |
-| `app/utils/token_counter.py` | Approximate token usage tracking (character-based heuristic for v1) |
-| `app/main.py` | Entrypoint stub — arg parsing, config load, Rich console setup |
-
-**Exit criteria:** `python -m app.main --help` runs, config loads and validates, models can be instantiated and serialized.
-
----
-
-## Phase 2 — TUI and Interactive Shell
-
-Get a working interactive terminal before wiring up the LLM.
-
-| File | Description |
-|------|-------------|
-| `app/main.py` | Rich-based interactive REPL loop — prompt for user input, display responses |
-| `app/utils/display.py` | Formatted output for agent messages, tool calls, errors, token usage |
-| `app/agent/context.py` | Session state and conversation history management |
-
-**Exit criteria:** User can type messages into a styled REPL, see them echoed back with formatting, and conversation history is tracked in memory.
-
----
-
-## Phase 3 — LLM Integration (Ollama)
-
-Connect to the local LLM and stream responses into the TUI.
-
-| File | Description |
-|------|-------------|
-| `app/services/llm.py` | Async httpx client wrapping Ollama's OpenAI-compatible `/v1/chat/completions` endpoint |
-| `app/services/streaming.py` | SSE parsing, Rich live display, tool call extraction from accumulated stream |
-
-**Integration:** Wire LLM into the REPL — user message goes to LLM, streamed response displays in real time.
-
-**Exit criteria:** User can chat with the local model through the TUI with streamed output. Tool call JSON is parsed from the stream but not yet executed.
-
----
-
-## Phase 4 — Tool Framework and Core Tools
-
-Build the tool abstraction and implement safe, read-only tools first.
-
-| File | Description |
-|------|-------------|
-| `app/tools/base.py` | `BaseTool` ABC and `ToolResult` dataclass |
-| `app/tools/registry.py` | Tool registration, discovery, and JSON schema export for LLM system prompt |
-| `app/services/permissions.py` | Two-tier approval gating (auto-approve reads; prompt for writes/deletes/shell) |
-| `app/tools/filesystem.py` | `read_file`, `list_dir` |
-| `app/tools/search.py` | `grep_files`, `find_files` |
-
-**Exit criteria:** Tools register themselves, schemas export correctly for inclusion in the system prompt, read-only tools execute and return `ToolResult` objects. Permissions service gates execution.
-
----
-
-## Phase 5 — Agent Loop (ReAct)
-
-The core autonomy layer — reason, act, observe, repeat.
-
-| File | Description |
-|------|-------------|
-| `app/agent/loop.py` | ReAct cycle: send conversation to LLM, parse tool calls, execute, feed results back, repeat |
-
-**Key behaviors:**
-- System prompt constructed with tool schemas from registry
-- Permissions checks before each tool execution
-- Loop termination on: plain-text response (no tool calls), explicit `finish` tool call, or `max_iterations` exceeded
-
-**Exit criteria:** Agent can autonomously answer questions about the codebase by chaining `read_file`, `list_dir`, `grep_files`, and `find_files` tool calls in a multi-turn loop.
-
----
-
-## Phase 6 — Write Tools and Shell
-
-Unlock the agent's ability to modify code and run commands.
-
-| File | Description |
-|------|-------------|
-| `app/tools/filesystem.py` | `write_file`, `make_dir`, `delete_file` (additions to existing module) |
-| `app/tools/edit.py` | `str_replace` (unique-match required), `patch_apply` |
-| `app/tools/shell.py` | `run_command` with command allow/deny lists and output truncation |
-
-**All write/shell operations gated through permissions service.**
-
-**Exit criteria:** Agent can autonomously create files, edit code via string replacement, and run shell commands — all with user approval for destructive operations.
-
----
-
-## Phase 7 — Polish and Hardening
-
-Production-readiness: error handling, resource limits, and documentation.
-
-| Area | Description |
-|------|-------------|
-| Error handling | Recovery from malformed tool calls, LLM errors, network timeouts in agent loop |
-| Token budget | Conversation truncation or summarization when approaching context limit |
-| Graceful shutdown | Clean Ctrl+C handling, session state preservation |
-| Testing | End-to-end integration tests (`tests/integration/`), unit tests (`tests/unit/`) |
-| Documentation | `README.md` with setup and usage instructions, `docs/tools.md` tool reference |
-
-**Exit criteria:** Agent handles edge cases gracefully, tests pass, and a new user can set up and use the project from the README alone.
-
----
-
-## File Coverage
-
-Every file from the project structure in CLAUDE.md is accounted for:
-
-| File | Phase |
-|------|-------|
-| `app/main.py` | 1, 2 |
-| `app/models/config.py` | 1 |
-| `app/models/message.py` | 1 |
-| `app/models/tool_call.py` | 1 |
-| `app/utils/logging.py` | 1 |
-| `app/utils/display.py` | 1, 2 |
-| `app/utils/file_helpers.py` | 1 |
-| `app/utils/token_counter.py` | 1 |
-| `app/agent/context.py` | 2 |
-| `app/services/llm.py` | 3 |
-| `app/services/streaming.py` | 3 |
-| `app/tools/base.py` | 4 |
-| `app/tools/registry.py` | 4 |
-| `app/services/permissions.py` | 4 |
-| `app/tools/filesystem.py` | 4, 6 |
-| `app/tools/search.py` | 4 |
-| `app/agent/loop.py` | 5 |
-| `app/tools/edit.py` | 6 |
-| `app/tools/shell.py` | 6 |

docs/superpowers/specs/2026-03-11-textual-tui-design.md

@@ -0,0 +1,192 @@
+# Textual TUI Redesign — Design Spec
+
+## Overview
+
+Replace the current sequential print-and-scroll terminal UI with a full persistent split-screen TUI using Textual. Input is pinned at the bottom, scrollable message history above, with a header showing app/model info and a footer showing token usage and iteration count.
+
+## Layout
+
+```
++------------------- Header --------------------+
+|  SneakyCode              qwen2.5-coder:32b    |
++-----------------------------------------------+
+|                                               |
+|  +--- You ---+                                |
+|  | prompt    |   <- RichLog widget             |
+|  +-----------+      (handles own scrolling)   |
+|                                               |
+|  Thinking...                                  |
+|                                               |
+|  +-- Assistant --+                            |
+|  | response...   |                            |
+|  +---------------+                            |
+|                                               |
+|  > read_file README.md -- 148 lines, 5128 ch  |
+|  > grep_files "pattern" -- 3 matches          |
+|                                               |
++-----------------------------------------------+
+| Tokens: ~1,511 / 32,000 | Iteration 5/25     |  <- StatusBar
++-----------------------------------------------+
+| > [input cursor]                              |  <- Input widget
++-----------------------------------------------+
+```
+
+**Widget hierarchy (no VerticalScroll wrapper — RichLog handles its own scrolling):**
+- `Header` — Textual built-in, title="SneakyCode", subtitle=model name
+- `RichLog` (id="chat-log") — main scroll area, accepts Rich renderables via `.write()`
+- `StreamingStatic` — persistent hidden `Static` widget, shown/hidden during streaming (avoids mount/unmount overhead)
+- `StatusBar` — custom `Static` widget, 1 row, docked above Input
+- `Input` — Textual built-in, pinned at bottom
+
+## New Files
+
+### `app/ui/app.py` — Textual App
+
+SneakyCodeApp subclasses `textual.app.App`. Responsibilities:
+
+- `compose()` yields: Header, RichLog(id="chat-log"), StreamingStatic(id="streaming"), StatusBar(id="status"), Input
+- `on_input_submitted()` handler: reads input value, clears input, writes user panel to chat log, dispatches agent turn as a worker
+- Agent turn runs via `run_worker()` (async worker, NOT threaded) so the UI stays responsive. Since the worker is async and on the event loop, widget methods can be called directly — no `call_from_thread()` needed.
+- Slash commands (/quit, /history, /clear, /save, /session) parsed from input before dispatching to agent
+- Holds references to config, SessionContext, AgentLoop (created in `on_mount`)
+- Header subtitle set to model name from config
+- `on_worker_state_changed()` handler: catches worker errors and writes error panels to RichLog
+- Ctrl+C binding: cancels the running agent worker (does NOT quit the app). A second Ctrl+C or `/quit` exits.
+
+### `app/ui/widgets.py` — Custom Widgets
+
+**StatusBar** — A simple `Static` widget styled as a footer bar. Displays token usage and iteration count. Updated by the agent loop after each LLM step via `status_bar.update(renderable)`.
+
+**StreamingStatic** — A `Static` widget that stays mounted but hidden. During streaming, it becomes visible and receives `update()` calls with partial content. When streaming ends, it is hidden and its content is cleared. This avoids the overhead of mounting/unmounting on every LLM response.
+
+### `app/ui/styles.tcss` — Textual CSS
+
+Layout rules:
+- RichLog fills available height (fraction-based sizing, e.g. `height: 1fr`)
+- StreamingStatic: `display: none` by default, shown during streaming
+- StatusBar is 1 row, docked bottom above Input
+- Input is 1 row, docked at very bottom
+- Color scheme matches existing SNEAKYCODE_THEME (cyan for user, green for assistant, magenta for tools, dim for metadata)
+
+## Modified Files
+
+### `app/main.py`
+
+- Remove `_run_repl()` async function entirely
+- Remove `console.input()` usage
+- `main()` creates config, runs preflight via `asyncio.run(_preflight(config))` (before Textual starts — this is fine, separate event loop), then instantiates and runs `SneakyCodeApp(config).run()`
+- CLI arg parsing stays (--config, -v, --log-file)
+- Session resume: `_offer_session_resume()` moves into `SneakyCodeApp.on_mount()` — instead of `console.input()`, push a modal screen asking "Resume previous session? [y/n]" with button/key handlers
+- Auto-save: triggers after each agent turn completes (in the worker completion handler)
+- SIGTERM handler: removed — Textual manages its own signal handling and shutdown lifecycle
+
+### `app/services/streaming.py`
+
+- Remove `from rich.live import Live` and `from rich.spinner import Spinner`
+- `process_stream()` no longer creates a `Rich.Live` context
+- Instead, accepts callback parameters:
+  - `on_content: Callable[[str], None]` — called with accumulated content on each content chunk
+  - `on_thinking: Callable[[], None]` — called once when first reasoning token arrives
+  - `on_done: Callable[[], None]` — called when streaming completes
+- **Throttling:** Content callback fires at most every 100ms (track last update time, skip intermediate chunks). Final content always fires on stream end.
+- Since the agent runs as an async worker (on the event loop), callbacks can directly call widget methods — no `call_from_thread()` needed.
+- All accumulation and tool-call parsing logic stays identical
+
+### `app/utils/display.py`
+
+- All `print_*` functions become `render_*` functions that return Rich renderables:
+  - `render_user_message(content) -> Panel`
+  - `render_assistant_message(content) -> Panel`
+  - `render_tool_call(name, args) -> Text`
+  - `render_tool_result(name, output, is_error) -> Text`
+  - `render_iteration_header(iteration, max_iter) -> Text`
+  - `render_warning(message) -> Text`
+  - `render_error(message) -> Text`
+- `print_banner()` removed — Header widget replaces it
+- `print_token_usage()` becomes `render_token_usage() -> Text` for the StatusBar
+- `print_history()` becomes `render_history() -> Table` — written to RichLog, may need width constraints for narrow terminals
+- A `DisplayAdapter` class wraps a `RichLog` reference and provides `write_user_message()`, `write_tool_call()`, etc. methods that call `render_*` then `rich_log.write()`
+
+### `app/agent/loop.py`
+
+- `AgentLoop.__init__()` accepts a `DisplayAdapter` instead of calling `display.py` print functions directly
+- All display calls route through the adapter: `self._display.write_tool_call(name, args)`, `self._display.write_iteration_header(i, max)`, etc.
+- `_execute_tool_calls()` becomes `async def _execute_tool_calls()` to support async permission checks
+- The loop logic (ReAct pattern, retry, truncation) is unchanged
+
+### `app/services/permissions.py`
+
+- `PermissionsService.check()` becomes `async def check()`
+- Instead of `rich.prompt.Confirm.ask()` (blocking stdin read), it:
+  1. Creates an `asyncio.Event`
+  2. Posts a custom message to the app requesting a permission modal
+  3. The app pushes a modal screen with the permission question and approve/deny buttons
+  4. When the user responds, the modal sets the event and stores the result
+  5. `check()` awaits the event and reads the result
+- Edge cases: dismiss without choosing = deny. Ctrl+C during modal = deny. Focus returns to Input after modal dismisses.
+
+### `app/utils/logging.py`
+
+- **Critical change:** The shared `console = Console()` instance will corrupt the Textual display since Textual takes exclusive terminal control
+- When running under Textual: disable `RichHandler` (console handler), keep only the file handler
+- Add a `setup_logging_for_tui()` function that reconfigures logging to file-only mode
+- Called from `SneakyCodeApp.on_mount()` before any agent work begins
+- The `console` object still exists but should not be used for output during TUI mode — all output goes through the DisplayAdapter
+- Consider: `--log-file` becomes required (or auto-set to a default) when running in TUI mode, so logs are not lost
+
+## Unchanged Files
+
+- `app/services/llm.py` — HTTP client, SSE parsing untouched
+- `app/agent/context.py` — session state untouched
+- `app/models/*` — all data models untouched
+- `app/tools/*` — all tool implementations untouched
+- `app/utils/file_helpers.py` — path safety untouched
+- `app/utils/token_counter.py` — token counting untouched
+
+## Key Patterns
+
+### Streaming in Textual
+
+The agent loop runs as an async worker (on the event loop, NOT threaded). During streaming:
+
+1. App shows `StreamingStatic` widget, writes "Thinking..." initially
+2. Worker calls `StreamHandler.process_stream(chunks, on_content=..., on_thinking=..., on_done=...)`
+3. `on_content` callback: updates `StreamingStatic` with `Panel(Markdown(partial_content), title="Assistant", border_style="green")` — throttled to ~100ms intervals
+4. `on_done` callback: hides `StreamingStatic`, writes final content to `RichLog` via `DisplayAdapter`
+
+Since the worker is async (not threaded), callbacks run on the event loop and can call widget methods directly.
+
+### Permission Prompts
+
+1. Agent loop (in async worker) calls `await permissions.check(operation, details)`
+2. `check()` creates an `asyncio.Event` and posts `PermissionRequest` message to the app
+3. App handles `PermissionRequest`: pushes a modal screen with the question, approve/deny buttons
+4. Modal screen: on button press, stores result and sets the event
+5. `check()` awaits the event, reads result, returns approved/denied
+6. Focus management: Input loses focus when modal appears, regains focus when modal dismisses
+7. Default on dismiss/Ctrl+C: deny
+
+### Cancellation
+
+- Ctrl+C (first press): cancels the running agent worker via `worker.cancel()`. The agent loop should check for cancellation between iterations.
+- Ctrl+C (second press) or `/quit`: exits the app via `app.exit()`
+
+## Dependencies
+
+- Add `textual>=4.0.0` to pyproject.toml dependencies
+
+## Verification
+
+1. Run the app — header shows app name + model, no console corruption
+2. Type a prompt — user panel appears in scroll area, input clears
+3. During LLM streaming — assistant response types out live (throttled) in the scroll area
+4. Thinking indicator shows during reasoning-only phases
+5. Tool calls appear as compact lines in the scroll area
+6. Footer shows token usage and iteration count, updating each step
+7. Scroll area auto-scrolls to bottom on new content
+8. /quit, /clear, /history commands work from the input
+9. Permission prompts show as modal, approve/deny work, focus returns to input
+10. Ctrl+C cancels running agent turn without quitting
+11. Worker errors display as error panels in the scroll area
+12. Logging goes to file only — no console corruption
+13. Session resume works on startup via modal dialog

docs/tweaks.md

@@ -1 +1,21 @@
 Pressing up should cycle history like claude code.
+
+~~Remove the user's input from output "you" - it's not needed.~~ Brought back as a condensed one-liner (first line + line count for multi-line).
+
+Smart shell auto-approve: auto-approve `run_command` when the base executable is in the `allowed_commands` list and the full command doesn't match any `denied_commands` prefix. Only prompt the user for commands whose base executable is unlisted. Currently all shell commands prompt regardless, which is tedious for safe read-only commands like `git branch` or `ls`. The allow/deny lists in `ShellToolConfig` already define what's safe — the permissions service just needs to be shell-aware.
+
+Show a token count or some other display for when the model is "thinking" for a long period of time. I want a way for the user to know the model is working on it.
+
+/models command to show models available and temporarly change models in the session
+
+pass a directory to the tool so that it uses that directory as it's root for commands.
+
+add a skills directory so we can prompt our own skills for the tool to use similar to Claude Code
+
+need not only a session log, but also a log of what the llm is thinking and how it's working somehow. I need a way to see behind the curtain.
+
+# Left of from Phase 7 of old roadmap - finish these first
+- Permission modal auto-approves (TODO: proper modal dialog)
+- Session resume auto-resumes (TODO: modal y/n)
+- LLM client cleanup on unmount not yet wired
+- No automated TUI tests (Textual's AppTest can be added later)

tests/unit/test_display.py

@@ -21,10 +21,10 @@ from app.utils.display import (
 
 
 class TestRenderFunctions:
-    def test_render_user_message_returns_panel(self) -> None:
+    def test_render_user_message_returns_text(self) -> None:
         result = render_user_message("hello")
-        assert isinstance(result, Panel)
+        assert isinstance(result, Text)
-        assert result.title == "You"
+        assert "hello" in result.plain
 
     def test_render_assistant_message_returns_panel(self) -> None:
         result = render_assistant_message("response")
@@ -72,7 +72,7 @@ class TestDisplayAdapter:
         adapter.write_user_message("hello")
         mock_log.write.assert_called_once()
         arg = mock_log.write.call_args[0][0]
-        assert isinstance(arg, Panel)
+        assert isinstance(arg, Text)
 
     def test_write_tool_call(self) -> None:
         mock_log = MagicMock()

tests/unit/test_shell.py

@@ -90,6 +90,6 @@ class TestRunCommandTool:
         # Create a file in the workspace to verify cwd
         (ws / "marker.txt").write_text("found")
         tool = RunCommandTool(ws, cfg)
-        result = tool.run("tc-9", {"command": "cat marker.txt"})
+        result = tool.run("tc-9", {"command": "head marker.txt"})
         assert result.status == ToolResultStatus.SUCCESS
         assert "found" in result.output