docs: add Copilot license/inference troubleshooting section#17242
docs: add Copilot license/inference troubleshooting section#17242
Conversation
Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
There was a problem hiding this comment.
Pull request overview
Adds documentation to help users diagnose Copilot inference failures that are caused by licensing/access (and related account constraints) when using COPILOT_GITHUB_TOKEN.
Changes:
- Added a new “Copilot License or Inference Access Issues” subsection under Engine-Specific Issues in the Common Issues troubleshooting page.
- Added a TIP callout in the
COPILOT_GITHUB_TOKENreference section linking to the new troubleshooting guidance.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 3 comments.
| File | Description |
|---|---|
| docs/src/content/docs/troubleshooting/common-issues.md | Adds a new troubleshooting subsection with local diagnostic steps for Copilot inference/license access issues. |
| docs/src/content/docs/reference/auth.mdx | Adds a TIP callout pointing readers to the new troubleshooting subsection from the COPILOT_GITHUB_TOKEN guidance. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| ```bash | ||
| export COPILOT_GITHUB_TOKEN="<your-github-pat>" | ||
| ``` | ||
|
|
||
| 3. Run a simple inference test: | ||
|
|
||
| ```bash | ||
| copilot -p "write a haiku" |
There was a problem hiding this comment.
The local inference test uses copilot -p "write a haiku", but elsewhere in this repo the Copilot CLI is invoked with --prompt (see many workflow lockfiles). If -p isn’t a supported alias, this troubleshooting step will fail even for correctly licensed tokens; consider using the same copilot --prompt "…" form here.
Also, this file consistently uses fenced blocks like bash wrap; consider switching these new bash blocks to bash wrap for consistency and to avoid horizontal scrolling in the docs site.
| ```bash | |
| export COPILOT_GITHUB_TOKEN="<your-github-pat>" | |
| ``` | |
| 3. Run a simple inference test: | |
| ```bash | |
| copilot -p "write a haiku" | |
| ```bash wrap | |
| export COPILOT_GITHUB_TOKEN="<your-github-pat>" |
-
Run a simple inference test:
copilot --prompt "write a haiku"
| **Symptoms**: The workflow fails with authentication or quota errors when the Copilot CLI tries to generate a response. | ||
|
|
||
| **Diagnosis**: Verify that the account associated with the `COPILOT_GITHUB_TOKEN` can successfully run inference by testing it locally. | ||
|
|
||
| 1. Install the Copilot CLI locally by following the [GitHub Copilot CLI documentation](https://docs.github.com/en/copilot/how-tos/use-copilot-agents/use-copilot-cli). | ||
|
|
||
| 2. Export the token as an environment variable: | ||
|
|
||
| ```bash | ||
| export COPILOT_GITHUB_TOKEN="<your-github-pat>" | ||
| ``` | ||
|
|
||
| 3. Run a simple inference test: | ||
|
|
||
| ```bash | ||
| copilot -p "write a haiku" | ||
| ``` | ||
|
|
||
| If this command fails, the account associated with the token does not have a valid Copilot license or inference access. Contact your organization administrator to verify that the token owner has an active Copilot subscription with inference enabled. | ||
|
|
There was a problem hiding this comment.
This section lists “quota errors” as a symptom, but the conclusion says failures mean the token owner “does not have a valid Copilot license or inference access.” Quota exhaustion (monthly premium requests) can also cause inference failures even with a valid license. Consider updating the diagnosis/conclusion to cover both cases (license/inference access vs. quota exceeded) and point to where users can check Copilot usage/billing.
| ``` | ||
|
|
||
| > [!TIP] | ||
| > If your workflow fails at the Copilot inference step even with the token set, verify that the token owner's account has an active Copilot license. See [Copilot License or Inference Access Issues](/gh-aw/troubleshooting/common-issues/#copilot-license-or-inference-access-issues) for a local diagnostic step. |
There was a problem hiding this comment.
The TIP suggests verifying the token owner has an active Copilot license, but inference failures at runtime can also be caused by exhausted premium-request quota. Consider mentioning quota as another common cause here (or wording this as “license/inference access and available quota”) to better match the linked troubleshooting section and user expectations.
| > If your workflow fails at the Copilot inference step even with the token set, verify that the token owner's account has an active Copilot license. See [Copilot License or Inference Access Issues](/gh-aw/troubleshooting/common-issues/#copilot-license-or-inference-access-issues) for a local diagnostic step. | |
| > If your workflow fails at the Copilot inference step even with the token set, verify that the token owner's account has an active Copilot license or inference access **and** that the account has sufficient remaining premium-request quota. See [Copilot License or Inference Access Issues](/gh-aw/troubleshooting/common-issues/#copilot-license-or-inference-access-issues) for a local diagnostic step. |
docs/src/content/docs/troubleshooting/common-issues.mdCOPILOT_GITHUB_TOKENsection indocs/src/content/docs/reference/auth.mdx💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.