#Help me config Github Copilot plan into openclaw

1 messages · Page 1 of 1 (latest)

vale dawnBOT
#

To help others find answers, you can mark your question as solved via Right click solution message -> Apps -> ✅ Mark Solution

fierce daggerBOT
#

Yep — this works, and your Copilot plan can be used in OpenClaw ✅

Use the github-copilot provider (not openai-codex).

On your VPS, run:

openclaw --version
openclaw models auth login --provider github-copilot --method device --set-default
openclaw models status

What happens:

  • it gives you a GitHub device-login URL + code
  • you approve it in browser
  • OpenClaw saves the auth profile and sets a Copilot model as default
#

If login works but model auth still looks missing (common with daemon env issues), put token in:

~/.openclaw/.env

with one of:

COPILOT_GITHUB_TOKEN=...
# or GH_TOKEN=...
# or GITHUB_TOKEN=...

then restart:

openclaw gateway restart
left canopy
#

Github copilot mentioned i got acces to GPT 5 Mini on the Pro plan, how do i enable GPT 5 Mini?

fierce daggerBOT
#

Nice — don’t hardcode the name. Use the exact model ID your Copilot account exposes.

On the VPS:

openclaw models list | rg github-copilot
openclaw models set <EXACT_ID_FROM_ABOVE>
openclaw models status

Or in chat:

  • /model list
  • pick the GitHub Copilot GPT‑5 Mini entry by number (/model <number>)

If GPT‑5 Mini doesn’t appear in models list, OpenClaw can’t force-enable it yet for your account/token — re-login once:

left canopy
fierce daggerBOT
#

Yep — from that URL:

  • Model slug/name: gpt-5-mini
  • Provider path on GitHub Marketplace: azure-openai/gpt-5-mini

Just note: that marketplace path is not always the same as the OpenClaw model ID.
For OpenClaw, still pick the exact ID shown by:

openclaw models list | rg -i "github-copilot|gpt-5"
left canopy
#

now can you give me the full comand for gpt 5 mini?

fierce daggerBOT
#

Yep — if that model is available in your Copilot entitlement, the command is:

openclaw models set github-copilot/gpt-5-mini
openclaw models status

If you get “unknown/not allowed”, run:

openclaw models list | rg github-copilot

and use the exact ID it shows.

left canopy
#

root@vmi3165854:~# openclaw models set github-copilot/gpt-5-mini
openclaw models status

🦞 OpenClaw 2026.4.2 (d74a122)
Running on your hardware, reading your logs, judging nothing (mostly).

Config overwrite: /root/.openclaw/openclaw.json (sha256 2c6193e5fbef50b6848fd4c4d092969548b307e2c3811eaf9cbfe1e19c1ffb10 -> 6717ef6a7aa4d98c110eff77afa75352e0fb03a8d2092b9c4be92b1ca7eda174, backup=/root/.openclaw/openclaw.json.bak)
Updated ~/.openclaw/openclaw.json
Default model: github-copilot/gpt-5-mini

minimax/MiniMax-M2.7, minimax/MiniMax-M2.5, github-copilot/gpt-4o, github-copilot/gpt-5-mini

Auth overview
Auth store : ~/.openclaw/agents/main/agent/auth-profiles.json
Shell env : off
Providers w/ OAuth/tokens (1): github-copilot (1)

  • github-copilot effective=profiles:~/.openclaw/agents/main/agent/auth-profiles.json | profiles=1 (oauth=0, token=1, api_key=0) | github-copilot:github=token:ghu_BFp4...JT3xMliv
  • minimax effective=profiles:~/.openclaw/agents/main/agent/auth-profiles.json | profiles=1 (oauth=0, token=0, api_key=1) | minimax:global=sk-cp-NN...HqP-MgBk | env=sk-cp-ij...SJdZDJMo | source=env: MINIMAX_API_KEY
  • nvidia effective=models.json:nvapi-aO...UEsAtWWN | models.json=nvapi-aO...UEsAtWWN | source=models.json: ~/.openclaw/agents/main/agent/models.json
  • openrouter effective=profiles:~/.openclaw/agents/main/agent/auth-profiles.json | profiles=1 (oauth=0, token=0, api_key=1) | openrouter:default=sk-or-v1...36ff1ea7 | models.json=sk-or-v1...w5x6y7z8 | source=models.json: ~/.openclaw/agents/main/agent/models.json

OAuth/token status

  • github-copilot usage: Premium 100% left · Chat 100% left
    • github-copilot:github static
      root@vmi3165854:~#