The TUI slash menu leads with the skills you actually use - #75931
Merged
Conversation
The `/` menu was a flat first-30 slice of the completer's output, and the completer emits every registry command before the first skill. On a 230-skill install that meant a bare `/` filled all 30 rows with commands and offered no skill at all, while `/p` cut off inside the alphabetical skill block — dropping /proving-a-fix-works (471 invocations) and /pr-update (160) but keeping /pretext (2). Spend the limit per kind and rank the skill block by recorded usage (the same .usage.json count Capabilities shows), most-used first and A-Z within a tie. A bare `/` is browsing, so bundled skills that shipped with Hermes and were never opened are dropped as noise; a typed query is a search, and a search that hides a match is broken, so there nothing is pruned and the ranking only reorders. An argument stage keeps the order its own command chose.
Typing a second slash command went dead whenever the message started with one: `/work /cle` offered nothing while `do /work then /cle` completed fine, which reads as an intermittent glitch rather than a rule. Only the first slash can be an invocation, so detect the inline shape first. The leading-command branch claimed the whole line and handed it to the backend's completer, which has nothing to say about a slash sitting in a command's argument tail. The inline trigger requires a whitespace-preceded slash at the caret, so ordinary argument completion (`/cron ad`, `/personality alic`) is untouched — it fires only where completion was already dead.
Contributor
૮ >ﻌ< ა ci reviewran on 40ec983 ℹ️ InfoDesktop E2E visual evidence · View test artifacts · View job2 visual diffs. inline evidence upload failed. Failed to upload diff-1508682a2ae8-boot-ready-diff.png with gh image (exit code 1): Error uploading /home/runner/work/_temp/e2e-evidence/diff-1508682a2ae8-boot-ready-diff.png: step 0 (get upload token): uploadToken not found on repo page — do you have write access to NousResearch/hermes-agent? (or, if NousResearch enforces SAML SSO, authorize at https://github.com/orgs/NousResearch/sso) |
randlee
pushed a commit
to randlee/hermes-agent
that referenced
this pull request
Aug 11, 2026
…priority The TUI slash menu leads with the skills you actually use
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The TUI's
/menu was a flat first-30 slice of the completer's output, and the completer emits every registry command before the first skill. On a 230-skill install that means the cap is reached while still inside the command block: a bare/offered zero skills, and/pcut off mid-alphabet, dropping/proving-a-fix-works(471 invocations) and/pr-update(160) while keeping/pretext(2). Separately, a second slash in a line that already started with a command went dead —/work /cleoffered nothing whiledo /work then /clecompleted fine.This brings the TUI to the same rules the desktop composer got in #73704: the menu is ordered by what you actually use, and what it offers depends on where the slash sits.
/on a 230-skill install/p/pretext(2 uses) in,/proving-a-fix-works(471) out/proving-a-fix-works,/pr-update,/pr-merge-blockerslead/, still found by typing its name/work /cle/cleanas a skill reference/personality alic,/details cRanking rides on the
.usage.jsonsidecar the Capabilities page already shows — most-used first, A-Z within a tie. The limit is spent per kind rather than as one flat truncation, since a flat cut is positional rather than editorial.The browse/search split governs the pruning: a bare
/is browsing, so bundled skills with no recorded activity are noise and go; a typed query is a search, and a search that hides a match is broken, so nothing is pruned there. An argument stage keeps the order its own command chose.