Target: every skill's description fits in a one-line gateway menu and leads with trigger keywords an agent would match on. Drops filler like 'Use this skill to', 'A skill for', 'This skill provides'. Before: max description length was 791 chars (architecture-diagram), 74 of 81 built-in skills were >60 chars. After: max 60, mean 54, all 81 built-in skills <=60. Rewritten with double-quoted YAML scalars to preserve Chinese/arrow glyphs (baoyu-comic, yuanbao, youtube-content).
7.7 KiB
name, description, version, author, license, metadata
| name | description | version | author | license | metadata | |||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| debugging-hermes-tui-commands | Debug Hermes TUI slash commands: Python, gateway, Ink UI. | 1.0.0 | Hermes Agent | MIT |
|
Debugging Hermes TUI Slash Commands
Overview
Hermes slash commands span three layers — Python command registry, tui_gateway JSON-RPC bridge, and the Ink/TypeScript frontend. When a command misbehaves (missing from autocomplete, works in CLI but not TUI, config persists but UI doesn't update), the bug is almost always one layer being out of sync with another.
Use this skill when you encounter issues with slash commands in the Hermes TUI, particularly when commands aren't showing in autocomplete, aren't working properly in the TUI, or need to be added/updated.
When to Use
- A slash command exists in one part of the codebase but doesn't work fully
- A command needs to be added to both backend and frontend
- Command autocomplete isn't working for specific commands
- Command behavior is inconsistent between CLI and TUI
- A command persists config but doesn't apply live in the TUI
Architecture Overview
Python backend (hermes_cli/commands.py) <- canonical COMMAND_REGISTRY
│
▼
TUI gateway (tui_gateway/server.py) <- slash.exec / command.dispatch
│
▼
TUI frontend (ui-tui/src/app/slash/) <- local handlers + fallthrough
Command definitions must be registered consistently across Python and TypeScript to work properly. The Python COMMAND_REGISTRY is the source of truth for: CLI dispatch, gateway help, Telegram BotCommand menu, Slack subcommand map, and autocomplete data shipped to Ink.
Investigation Steps
-
Check if the command exists in the TUI frontend:
search_files --pattern "/commandname" --file_glob "*.ts" --path ui-tui/ search_files --pattern "/commandname" --file_glob "*.tsx" --path ui-tui/ -
Examine the TUI command definition:
read_file ui-tui/src/app/slash/commands/core.ts # If not there: search_files --pattern "commandname" --path ui-tui/src/app/slash/commands --target files -
Check if the command exists in the Python backend:
search_files --pattern "CommandDef" --file_glob "*.py" --path hermes_cli/ search_files --pattern "commandname" --path hermes_cli/commands.py --context 3 -
Examine the gateway implementation:
search_files --pattern "complete.slash|slash.exec" --path tui_gateway/
Fix: Missing Command Autocomplete
If a command exists in the TUI but doesn't show in autocomplete:
-
Add a
CommandDefentry toCOMMAND_REGISTRYinhermes_cli/commands.py:CommandDef("commandname", "Description of the command", "Session", cli_only=True, aliases=("alias",), args_hint="[arg1|arg2|arg3]", subcommands=("arg1", "arg2", "arg3")), -
Pick
cli_onlyvs gateway availability carefully:cli_only=True— only in the interactive CLI/TUIgateway_only=True— only in messaging platforms- neither — available everywhere
gateway_config_gate="display.foo"— config-gated availability in the gateway
-
Ensure
subcommandsmatches the expected tab-completion options shown by the TUI. -
If the command runs server-side, add a handler in
HermesCLI.process_command()incli.py:elif canonical == "commandname": self._handle_commandname(cmd_original) -
For gateway-available commands, add a handler in
gateway/run.py:if canonical == "commandname": return await self._handle_commandname(event)
Common Issues
-
Command shows in TUI but not in autocomplete. The command is defined in the TUI codebase but missing from
COMMAND_REGISTRYinhermes_cli/commands.py. Autocomplete data ships from Python. -
Command shows in autocomplete but doesn't work. Check the command handler in
tui_gateway/server.pyand the frontend handler inui-tui/src/app/createSlashHandler.ts. If the command is local-only in Ink, it must be handled inapp.tsxbuilt-in branch; otherwise it falls through toslash.execand must have a Python handler. -
Command behavior differs between CLI and TUI. The command might have different implementations. Check both
cli.py::process_commandand the TUI's local handler. Local TUI handlers take precedence over gateway dispatch. -
Command persists config but doesn't apply live. For TUI-local commands, updating
config.setis not enough. Also patch the relevant nanostore state immediately (usuallypatchUiState(...)) and pass any new state through rendering components. Example:/details collapsedmust update live detail visibility, not just savedetails_mode; in-session global/details <mode>may need a separate command-override flag so live commands can override built-in section defaults while startup/config sync preserves default-expanded thinking/tools behavior. -
Gateway dispatch silently ignores the command. The gateway only dispatches commands it knows about. Check
GATEWAY_KNOWN_COMMANDS(derived fromCOMMAND_REGISTRYautomatically) includes the canonical name. If the command iscli_onlywith agateway_config_gate, verify the gated config value is truthy.
Debugging Tactics
When surface-level inspection doesn't reveal the bug:
- Python side hangs or misbehaves: use the
python-debugpyskill to break inside_SlashWorker.execor the command handler.remote-pdbset at the handler entry is the fastest path. - Ink side not reacting: use the
node-inspect-debuggerskill to break inapp.tsx's slash dispatch or the local command branch.sb('dist/app.js', <line>)afternpm run build. - Registry mismatch / unclear which side is wrong: compare the canonical
COMMAND_REGISTRYentry against the TUI's local command list side-by-side.
Pitfalls
- Don't forget to set the appropriate category for the command in
CommandDef(e.g., "Session", "Configuration", "Tools & Skills", "Info", "Exit") - Make sure any aliases are properly registered in the
aliasestuple — no other file changes are needed, everything downstream (Telegram menu, Slack mapping, autocomplete, help) derives from it - For commands with subcommands, ensure the
subcommandstuple inCommandDefmatches what's in the TUI code cli_only=Truecommands won't work in gateway/messaging platforms — unless you add agateway_config_gateand the gate is truthy- After adding live UI state, search every consumer of the old prop/helper and thread the new state through all render paths, not just the active streaming path. TUI detail rendering has at least two important paths: live
StreamingAssistant/ToolTrailand transcript/pendingMessageLinerows. A/cleanpass should explicitly check both. - Rebuild the TUI (
npm --prefix ui-tui run build) before testing — tsx watch mode may lag on first launch
Verification
After fixing:
-
Rebuild the TUI:
cd /home/bb/hermes-agent && npm --prefix ui-tui run build -
Run the TUI and test the command:
hermes --tui -
Type
/and verify the command appears in autocomplete suggestions with the expected description and args hint. -
Execute the command and confirm:
- Expected behavior fires
- Any persisted config updates correctly (
read_file ~/.hermes/config.yaml) - Live UI state reflects the change immediately (not just after restart)
-
If the command is also gateway-available, test it from at least one messaging platform (or run the gateway tests:
scripts/run_tests.sh tests/gateway/).