Add todo tool for task management and enhance CLI features

- Introduced a new `todo_tool.py` for planning and tracking multi-step tasks, enhancing the agent's capabilities.
- Updated CLI to include a floating autocomplete dropdown for commands and improved user instructions for better navigation.
- Revised toolsets to incorporate the new `todo` tool and updated documentation to reflect changes in available tools and commands.
- Enhanced user experience with new keybindings and clearer command descriptions in the CLI.

AGENTS.md

@@ -25,6 +25,7 @@ hermes-agent/
 │   ├── uninstall.py      # Uninstaller
 │   └── cron.py           # Cron job management
 ├── tools/                # Tool implementations
+│   ├── todo_tool.py            # Planning & task management (in-memory TodoStore)
 │   ├── process_registry.py     # Background process management (spawn, poll, wait, kill)
 │   ├── transcription_tools.py  # Speech-to-text (Whisper API)
 ├── gateway/              # Messaging platform adapters
@@ -151,13 +152,23 @@ For models that support chain-of-thought reasoning:
 
 The interactive CLI uses:
 - **Rich** - For the welcome banner and styled panels
-- **prompt_toolkit** - For fixed input area with history and `patch_stdout`
+- **prompt_toolkit** - For fixed input area with history, `patch_stdout`, slash command autocomplete, and floating completion menus
-- **KawaiiSpinner** (in run_agent.py) - Animated feedback during API calls and tool execution
+- **KawaiiSpinner** (in run_agent.py) - Animated kawaii faces during API calls; clean `┊` activity feed for tool execution results
 
 Key components:
 - `HermesCLI` class - Main CLI controller with commands and conversation loop
+- `SlashCommandCompleter` - Autocomplete dropdown for `/commands` (type `/` to see all)
 - `load_cli_config()` - Loads config, sets environment variables for terminal
 - `build_welcome_banner()` - Displays ASCII art logo, tools, and skills summary
+
+CLI UX notes:
+- Thinking spinner (during LLM API call) shows animated kawaii face + verb (`(⌐■_■) deliberating...`)
+- When LLM returns tool calls, the spinner clears silently (no "got it!" noise)
+- Tool execution results appear as a clean activity feed: `┊ {emoji} {verb} {detail} {duration}`
+- "got it!" only appears when the LLM returns a final text response (`⚕ ready`)
+- The prompt shows `⚕ ❯` when the agent is working, `❯` when idle
+- Pasting 5+ lines auto-saves to `~/.hermes/pastes/` and collapses to a reference
+- Multi-line input via Alt+Enter or Ctrl+J
 - `/commands` - Process user commands like `/help`, `/clear`, `/personality`, etc.
 
 CLI uses `quiet_mode=True` when creating AIAgent to suppress verbose logging.
@@ -472,7 +483,12 @@ Follow this strict order to maintain consistency:
    - Add to `OPTIONAL_ENV_VARS` in `hermes_cli/config.py`
    - The tool will be auto-disabled if the key is missing
 
-6. Optionally add to `toolset_distributions.py` for batch processing
+6. Add `"todo"` to the relevant platform toolsets (`hermes-cli`, `hermes-telegram`, etc.)
+
+7. Optionally add to `toolset_distributions.py` for batch processing
+
+**Special case: tools that need agent-level state** (like `todo`):
+If your tool needs access to the AIAgent instance (e.g., in-memory state per session), intercept it directly in `run_agent.py`'s tool dispatch loop *before* `handle_function_call()`. Add a fallback error in `handle_function_call()` for safety. See `todo_tool.py` and the `if function_name == "todo":` block in `run_agent.py` for the pattern. For RL environments, add the same intercept in `environments/agent_loop.py`.
 
 ### Tool Implementation Pattern
 

README.md

@@ -107,16 +107,32 @@ hermes version            # Show version info
 
 ### CLI Commands (inside chat)
 
+Type `/` to see an autocomplete dropdown of all commands.
+
 | Command | Description |
 |---------|-------------|
 | `/help` | Show available commands |
 | `/tools` | List available tools |
+| `/toolsets` | List available toolsets |
 | `/model [name]` | Show or change model |
+| `/prompt` | View/set custom system prompt |
 | `/personality [name]` | Set personality (kawaii, pirate, etc.) |
-| `/clear` | Clear screen and reset |
+| `/clear` | Clear screen and reset conversation |
-| `/cron` | Manage scheduled tasks |
+| `/history` | Show conversation history |
+| `/reset` | Reset conversation only (keep screen) |
+| `/retry` | Retry the last message |
+| `/undo` | Remove the last exchange |
+| `/save` | Save the current conversation |
 | `/config` | Show current configuration |
-| `/quit` | Exit |
+| `/cron` | Manage scheduled tasks |
+| `/platforms` | Show gateway/messaging platform status |
+| `/quit` | Exit (also: `/exit`, `/q`) |
+
+**Keybindings:**
+- `Enter` — send message
+- `Alt+Enter` or `Ctrl+J` — new line (multi-line input)
+- `Ctrl+C` — interrupt agent (double-press to force exit)
+- `Ctrl+D` — exit
 
 ---
 
@@ -134,7 +150,7 @@ hermes --toolsets "web,terminal"
 hermes --list-tools
 ```
 
-**Available toolsets:** `web`, `terminal`, `browser`, `vision`, `creative`, `reasoning`, `skills`, `tts`, `cronjob`, and more.
+**Available toolsets:** `web`, `terminal`, `file`, `browser`, `vision`, `image_gen`, `moa`, `skills`, `tts`, `todo`, `cronjob`, and more.
 
 ### 🔊 Text-to-Speech
 

TODO.md

@@ -4,7 +4,7 @@
 
 ## What We Already Have (for reference)
 
-**42+ tools** across 12 toolsets: web (search, extract), terminal + process management, file ops (read, write, patch, search), vision, MoA reasoning, image gen, browser (10 tools via Browserbase), skills (41 skills), cronjobs, RL training (10 tools via Tinker-Atropos), TTS, cross-channel messaging.
+**43+ tools** across 13 toolsets: web (search, extract), terminal + process management, file ops (read, write, patch, search), vision, MoA reasoning, image gen, browser (10 tools via Browserbase), skills (41 skills), **todo (task planning)**, cronjobs, RL training (10 tools via Tinker-Atropos), TTS, cross-channel messaging.
 
 **4 platform adapters**: Telegram, Discord, WhatsApp, Slack -- all with typing indicators, image/voice auto-analysis, dangerous command approval, interrupt support, background process watchers.
 
@@ -41,9 +41,9 @@ The main agent becomes an orchestrator that delegates context-heavy tasks to sub
 
 ---
 
-## 2. Planning & Task Management 📋
+## 2. Planning & Task Management 📋 ✅
 
-**Status:** Not started
+**Status:** Implemented
 **Priority:** High -- every serious agent has this now
 
 A `todo` tool the agent uses to decompose complex tasks, track progress, and recover from failures. Must be **cache-friendly** -- no system prompt mutation, no injected messages that invalidate the KV cache prefix.
@@ -935,7 +935,7 @@ This goes in the tool description:
 **Tier 1 (High impact, foundation for everything else):**
 1. Programmatic Tool Calling (code-mediated tool use) -- #20
 2. Memory System (Phase 1: MEMORY.md + USER.md) -- #5
-3. Planning & Task Management (todo tool) -- #2
+3. ~~Planning & Task Management (todo tool) -- #2~~ **DONE**
 4. Session Transcript Search -- #6
 5. Self-Learning from Errors -- #16
 

cli-config.yaml.example

@@ -185,15 +185,20 @@ agent:
 #
 #   web          - Web search and content extraction (web_search, web_extract)
 #   search       - Web search only, no scraping (web_search)
-#   terminal     - Command execution (terminal)
+#   terminal     - Command execution and process management (terminal, process)
+#   file         - File operations: read, write, patch, search
 #   browser      - Full browser automation (navigate, click, type, screenshot, etc.)
 #   vision       - Image analysis (vision_analyze)
 #   image_gen    - Image generation with FLUX (image_generate)
-#   skills       - Load skill documents (skills_categories, skills_list, skill_view)
+#   skills       - Load skill documents (skills_list, skill_view)
 #   moa          - Mixture of Agents reasoning (mixture_of_agents)
+#   todo         - Task planning and tracking for multi-step work
+#   tts          - Text-to-speech (Edge TTS free, ElevenLabs, OpenAI)
+#   cronjob      - Schedule and manage automated tasks (CLI-only)
+#   rl           - RL training tools (Tinker-Atropos)
 #
 # Composite toolsets:
-#   debugging    - terminal + web (for troubleshooting)
+#   debugging    - terminal + web + file (for troubleshooting)
 #   safe         - web + vision + moa (no terminal access)
 
 # -----------------------------------------------------------------------------

docs/tools.md

@@ -47,6 +47,7 @@ async def web_search(query: str) -> dict:
 | **TTS** | `tts_tool.py` | `text_to_speech` (Edge TTS free / ElevenLabs / OpenAI) |
 | **Reasoning** | `mixture_of_agents_tool.py` | `mixture_of_agents` |
 | **Skills** | `skills_tool.py` | `skills_list`, `skill_view` |
+| **Todo** | `todo_tool.py` | `todo` (read/write task list for multi-step planning) |
 | **Cronjob** | `cronjob_tools.py` | `schedule_cronjob`, `list_cronjobs`, `remove_cronjob` |
 | **RL Training** | `rl_training_tool.py` | `rl_list_environments`, `rl_start_training`, `rl_check_status`, etc. |
 
@@ -83,7 +84,11 @@ TOOLSETS = {
     },
     "terminal": {
         "description": "Command execution",
-        "tools": ["terminal"]
+        "tools": ["terminal", "process"]
+    },
+    "todo": {
+        "description": "Task planning and tracking for multi-step work",
+        "tools": ["todo"]
     },
     # ...
 }

hermes_cli/setup.py

@@ -202,6 +202,9 @@ def _print_setup_summary(config: dict, hermes_home):
     # Terminal (always available if system deps met)
     tool_status.append(("Terminal/Commands", True, None))
     
+    # Task planning (always available, in-memory)
+    tool_status.append(("Task Planning (todo)", True, None))
+    
     # Skills (always available if skills dir exists)
     tool_status.append(("Skills Knowledge Base", True, None))
     

toolsets.py

@@ -189,6 +189,11 @@ TOOLSETS = {
             "image_generate",
             # Text-to-speech
             "text_to_speech",
+            # Browser automation (requires Browserbase API key)
+            "browser_navigate", "browser_snapshot", "browser_click",
+            "browser_type", "browser_scroll", "browser_back",
+            "browser_press", "browser_close", "browser_get_images",
+            "browser_vision",
             # Skills - access knowledge base
             "skills_list", "skill_view",
             # Planning & task management
@@ -216,6 +221,11 @@ TOOLSETS = {
             "image_generate",
             # Text-to-speech
             "text_to_speech",
+            # Browser automation (requires Browserbase API key)
+            "browser_navigate", "browser_snapshot", "browser_click",
+            "browser_type", "browser_scroll", "browser_back",
+            "browser_press", "browser_close", "browser_get_images",
+            "browser_vision",
             # Skills - access knowledge base
             "skills_list", "skill_view",
             # Planning & task management
@@ -243,6 +253,11 @@ TOOLSETS = {
             "image_generate",
             # Text-to-speech
             "text_to_speech",
+            # Browser automation (requires Browserbase API key)
+            "browser_navigate", "browser_snapshot", "browser_click",
+            "browser_type", "browser_scroll", "browser_back",
+            "browser_press", "browser_close", "browser_get_images",
+            "browser_vision",
             # Skills
             "skills_list", "skill_view",
             # Planning & task management
@@ -270,6 +285,11 @@ TOOLSETS = {
             "image_generate",
             # Text-to-speech
             "text_to_speech",
+            # Browser automation (requires Browserbase API key)
+            "browser_navigate", "browser_snapshot", "browser_click",
+            "browser_type", "browser_scroll", "browser_back",
+            "browser_press", "browser_close", "browser_get_images",
+            "browser_vision",
             # Skills - access knowledge base
             "skills_list", "skill_view",
             # Planning & task management