Issue Station
Sign In
Tools hereToolbox

openclaw - 💡(How to fix) Fix [Feature]: /model command should list available models (Discord autocomplete or inline list) [4 comments, 2 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
openclaw/openclaw#49298•Fetched 2026-04-08 00:56:45
View on GitHub
Comments
4
Participants
2
Timeline
6
Reactions
0
Author
LittleMeHereLittleMeHere
Participants
ArtyomkunArtyomkunLittleMeHereLittleMeHere
Timeline (top)
commented ×4mentioned ×1subscribed ×1

Root Cause

New users (and experienced ones) discovering models via Discord have no discoverability path. This is especially painful when new models drop and you're not sure of the exact ID — which is a recurring problem given how fast the model landscape moves.

RAW_BUFFERClick to expand / collapse

Problem

When using /model in Discord to switch models, you need to already know the exact model string (e.g. openai-codex/gpt-5.3-codex). There's no way to see what's available without leaving Discord and checking config or docs.

Expected behavior

/model should either:

  • Show Discord slash command autocomplete options populated from the configured/available model list, OR
  • Accept /model list to print available models inline in the channel

Current behavior

You have to know the exact string or run openclaw models list at the terminal. If you get it wrong, you get no useful feedback.

Why this matters

New users (and experienced ones) discovering models via Discord have no discoverability path. This is especially painful when new models drop and you're not sure of the exact ID — which is a recurring problem given how fast the model landscape moves.

Related

  • #10687 (dynamic model discovery — this is the Discord UX surface for the same gap)
  • #23354 (structured Discord slash command options — this is a specific instance of that broader feature)

Environment

  • Channel: Discord
  • OpenClaw version: 2026.3.13

extent analysis

Fix Plan

To address the issue, we will implement a Discord slash command that accepts /model list to print available models inline in the channel. We will also explore adding autocomplete options populated from the configured/available model list.

Implementation Steps

  • Update the /model command to accept a list parameter
  • Query the available models from the configuration or database
  • Return the list of available models as a response to the /model list command
  • Consider using Discord's autocomplete feature to populate options for the /model command

Example Code

import discord
from discord.ext import commands

# Assume 'models' is a list of available models
models = ["openai-codex/gpt-5.3-codex", "other-model"]

@bot.slash_command()
async def model(ctx, model_name: str = None):
    if model_name == "list":
        # Return the list of available models
        await ctx.respond("Available models: " + ", ".join(models))
    else:
        # Handle model selection or return an error if not found
        if model_name in models:
            await ctx.respond(f"Selected model: {model_name}")
        else:
            await ctx.respond("Model not found. Use `/model list` to see available models.")

# Autocomplete example (requires Discord.py 2.0+)
@model.autocomplete("model_name")
async def model_autocomplete(ctx: discord.AutocompleteContext):
    return [model for model in models if model.startswith(ctx.value)]

Verification

To verify the fix, test the /model list command in Discord and ensure it returns the list of available models. Also, test the autocomplete feature by typing /model and selecting from the options.

Extra Tips

  • Make sure to handle errors and edge cases, such as an empty list of models or invalid user input.
  • Consider adding a help message or documentation for the /model command to explain its usage and available options.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

FAQ

Expected behavior

/model should either:

  • Show Discord slash command autocomplete options populated from the configured/available model list, OR
  • Accept /model list to print available models inline in the channel
#api#ssr#installation#tensor shape#autograd error#pipeline error#runtime error#dependency conflict#environment setup#docker error

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

openclaw - 💡(How to fix) Fix [Feature]: /model command should list available models (Discord autocomplete or inline list) [4 comments, 2 participants]