Fix default Ollama overlay missing api field for llmspy routing#181
Merged
Fix default Ollama overlay missing api field for llmspy routing#181
Conversation
The default Ollama overlay routes through llmspy, which only serves POST /v1/chat/completions. Without an explicit api field, OpenClaw falls back to openai-responses (POST /v1/responses) — a route llmspy doesn't handle, resulting in a 404. The llmspy cloud provider paths (buildLLMSpyRoutedOverlay) already set api: openai-completions correctly. This adds the same field to the hardcoded default Ollama block.
Sonnet is more appropriate as the default for agent tasks — better cost/performance ratio for typical OpenClaw workloads.
OisinKyne
approved these changes
Feb 18, 2026
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
http://llmspy.llm.svc.cluster.local:8000/v1), which only servesPOST /v1/chat/completionsapifield, OpenClaw falls back toopenai-responseswhich sends toPOST /v1/responses— a route llmspy doesn't handle → 404buildLLMSpyRoutedOverlay) already setapi: openai-completionscorrectly; only the hardcoded default Ollama block was missing itapi: openai-completionsto the default overlay — one line fixTest plan
obol agent initwith Ollama running → verify inference works through llmspyobol openclaw setupwith Anthropic via model gateway → verify inference worksobol openclaw setupwith direct Anthropic → verify inference works (regression check)