Skip to content

feat(cli): two-stage /model autocomplete with ghost text suggestions#1622

Closed
lmvdz wants to merge 2 commits into
NousResearch:mainfrom
lmvdz:feat/model-autocomplete
Closed

feat(cli): two-stage /model autocomplete with ghost text suggestions#1622
lmvdz wants to merge 2 commits into
NousResearch:mainfrom
lmvdz:feat/model-autocomplete

Conversation

@lmvdz

@lmvdz lmvdz commented Mar 17, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor

What does this PR do?

  • enhances all the commands with tab key auto complete & ghost complete
  • model has special two-stage autocomplete due to the complexity of <provider>:<model>
  • helps when you don't exactly know what commands have subcommands
  • this approach is the right one in my mind, open to debating

Type of Change

  • ✨ New feature (non-breaking change that adds functionality)

Changes Made

cli.py

  • added import SlashCommandAutoSuggest
  • fixed some color stuff with unknown command
  • added tab keybind for accepting auto-complete
  • auto suggest for models

hermes_cli/commands.py

  • command definitions are the single source of truth for autocomplete
  • added more structure to allow for automated parsing for auto complete
  • ghost text for slash commands
  • derive flat structure for commands & subcommands

tests/test_cli_prefix_matching.py

  • fix some color issues

tests/hermes_cli/test_commands.py

  • add tests for autocomplete & two-stage model auto complete

How to Test

  1. type /model (with a space)
  2. you will see dropdown of providers
  3. arrow keys up and down or type
  4. hit tab, will autocomplete and show the models available
  5. try any other /<command> <subcommand> combo

Checklist

Code

  • I've read the Contributing Guide
  • My commit messages follow Conventional Commits (fix(scope):, feat(scope):, etc.)
  • I searched for existing PRs to make sure this isn't a duplicate
  • My PR contains only changes related to this fix/feature (no unrelated commits)
  • I've run pytest tests/ -q and all tests pass
  • I've added tests for my changes (required for bug fixes, strongly encouraged for features)
  • I've tested on my platform: Ubuntu 24.04 - WSL 2

Documentation & Housekeeping

  • I've updated relevant documentation (README, docs/, docstrings) — or N/A [x]
  • I've updated cli-config.yaml.example if I added/changed config keys — or N/A [x]
  • I've updated CONTRIBUTING.md or AGENTS.md if I changed architecture or workflows — or N/A [x]
  • I've considered cross-platform impact (Windows, macOS) per the compatibility guide — or N/A [x]
  • I've updated tool descriptions/schemas if I changed tool behavior — or N/A [x]

Screenshots / Logs

Recording.2026-03-17.010451.mp4

@lmvdz lmvdz force-pushed the feat/model-autocomplete branch 2 times, most recently from 1fb386e to ffc00c9 Compare March 17, 2026 06:22
@lmvdz
feat(cli): two-stage /model autocomplete with ghost text suggestions
d7c1409 
- 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
@lmvdz lmvdz force-pushed the feat/model-autocomplete branch from ffc00c9 to d7c1409 Compare March 17, 2026 06:39
@lmvdz lmvdz marked this pull request as ready for review March 17, 2026 06:45
teknium1 added a commit that referenced this pull request Mar 17, 2026
@teknium1
fix: repair test regression and restore gold color from PR #1622
e931b74 
- 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
@teknium1 teknium1 mentioned this pull request Mar 17, 2026
Merged
teknium1 added a commit that referenced this pull request Mar 17, 2026
@teknium1 @lmvdz
feat(cli): two-stage /model autocomplete with ghost text suggestions (#…
3744118 
…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>
@teknium1

teknium1 commented Mar 17, 2026

Copy link
Copy Markdown
Contributor

Merged via PR #1641. Your substantive commit was cherry-picked onto current main with authorship preserved. Added a follow-up fix for a missed test (test_unknown_command_still_shows_error) and restored the gold color on help hints. Thanks for the great feature, @lmvdz!

@teknium1 teknium1 mentioned this pull request Apr 18, 2026
Closed
angelburgosrosado pushed a commit to angelburgosrosado/hermes-agent that referenced this pull request Apr 27, 2026
@teknium1 @lmvdz
feat(cli): two-stage /model autocomplete with ghost text suggestions (N…
6d2dc04 
…ousResearch#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 NousResearch#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>
02356abc pushed a commit to 02356abc/hermes-agent that referenced this pull request May 14, 2026
@teknium1 @lmvdz
feat(cli): two-stage /model autocomplete with ghost text suggestions (N…
9b3d26a 
…ousResearch#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 NousResearch#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>
olympus-terminal pushed a commit to olympus-terminal/hermes-agent that referenced this pull request May 16, 2026
@teknium1 @lmvdz
feat(cli): two-stage /model autocomplete with ghost text suggestions (N…
f3556f8 
…ousResearch#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 NousResearch#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>
Egavasyug pushed a commit to Egavasyug/hermes-agent that referenced this pull request Jun 10, 2026
@teknium1 @lmvdz
feat(cli): two-stage /model autocomplete with ghost text suggestions (N…
546e5c9 
…ousResearch#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 NousResearch#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>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@lmvdz @teknium1