Issue Station
Sign In
Tools hereToolbox

openclaw - 💡(How to fix) Fix Ollama onboarding rejects the ollama-local marker as usable auth [1 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#63093•Fetched 2026-04-09 07:58:41
View on GitHub
Comments
0
Participants
1
Timeline
1
Reactions
0
Author
jskoizjskoiz
Participants
jskoizjskoiz
Timeline (top)
closed ×1
RAW_BUFFERClick to expand / collapse

Problem

Fresh onboarding for local Ollama can still fail even when OpenClaw writes the documented models.providers.ollama.apiKey = "ollama-local" marker and the default model is set to ollama/gemma4.

Reproduction

  1. Start from a fresh install or remove ~/.openclaw state.
  2. Run openclaw onboard.
  3. Choose Ollama and the local setup path.
  4. Let onboarding write the local Ollama marker and select ollama/gemma4.
  5. Start the gateway / open the dashboard and try a chat turn.

Actual behavior

The auth resolver treats ollama-local as a non-usable placeholder instead of synthetic local auth, so the agent path can still report missing Ollama auth unless OLLAMA_API_KEY=ollama-local is exported in the shell.

Expected behavior

The documented Ollama onboarding path should work without any extra shell env when the config contains the local marker.

Notes

This showed up during initial onboarding on a fresh machine while trying to use local Gemma via Ollama.

extent analysis

TL;DR

Setting the OLLAMA_API_KEY environment variable to ollama-local may resolve the onboarding issue for local Ollama.

Guidance

  • Verify that the models.providers.ollama.apiKey is correctly set to ollama-local in the configuration after onboarding.
  • Check if the auth resolver is correctly interpreting the ollama-local marker as synthetic local auth.
  • Test if exporting OLLAMA_API_KEY=ollama-local in the shell resolves the issue temporarily.
  • Investigate why the documented onboarding path is not working as expected without extra shell environment variables.

Example

No code snippet is provided as it is not clearly supported by the issue.

Notes

The issue seems to be related to the auth resolver not correctly handling the ollama-local marker. The provided workaround may not be the final solution, but it can help mitigate the issue.

Recommendation

Apply workaround: Export OLLAMA_API_KEY=ollama-local in the shell, as it seems to resolve the issue temporarily, while further investigation is done to fix the root cause.

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

The documented Ollama onboarding path should work without any extra shell env when the config contains the local marker.

#api#agent setup#task chaining#parallel task#integration issue

Still need to ship something?

×6

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

Back to top recommendations

TRENDING