Skip to content

Add direct Ollama inference preflight and failure diagnostics - #52197

Merged
pelikhan merged 2 commits into
mainfrom
copilot/aw-failures-fix-ollama-backend
Aug 12, 2026
Merged

Add direct Ollama inference preflight and failure diagnostics#52197
pelikhan merged 2 commits into
mainfrom
copilot/aw-failures-fix-ollama-backend

Conversation

Copilot AI commented Aug 12, 2026

Copy link
Copy Markdown
Contributor

The Ollama warm-up and readiness probes succeeded, but inference through AWF returned proxy-generated HTTP 503 responses. Existing checks did not exercise the OpenAI-compatible chat endpoint or preserve post-failure server diagnostics.

  • Preflight inference

    • Call /v1/chat/completions directly before AWF starts.
    • Require HTTP 200 and a non-empty completion.
  • Failure diagnostics

    • Always capture loaded models, Ollama processes, and recent server logs after agent execution.
  • Workflow output

    • Regenerate the compiled lock workflow.

Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
Copilot AI changed the title [WIP] Fix Ollama backend availability for BYOK test Add direct Ollama inference preflight and failure diagnostics Aug 12, 2026
Copilot AI requested a review from pelikhan August 12, 2026 01:44
@pelikhan
pelikhan marked this pull request as ready for review August 12, 2026 01:46
Copilot AI balanced review requested due to automatic review settings August 12, 2026 01:46
@pelikhan
pelikhan merged commit 4f7c006 into main Aug 12, 2026
@pelikhan
pelikhan deleted the copilot/aw-failures-fix-ollama-backend branch August 12, 2026 01:46

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Adds Ollama inference preflight checks and post-agent diagnostics to the daily BYOK workflow.

Changes:

  • Adds direct chat-completion validation.
  • Captures Ollama process, model, and log diagnostics.
  • Regenerates the compiled workflow.
Show a summary per file
File Description
.github/workflows/daily-byok-ollama-test.md Adds preflight inference and diagnostics.
.github/workflows/daily-byok-ollama-test.lock.yml Regenerates the compiled workflow.

Review details

Tip

Add a code-review agent skill for context-aware, tailored reviews. Learn more in the docs.

  • Files reviewed: 2/2 changed files
  • Comments generated: 1
  • Review effort level: Balanced

Comment on lines +139 to +140
http://localhost:11434/v1/chat/completions \
-d "{\"model\":\"${OLLAMA_MODEL}\",\"messages\":[{\"role\":\"user\",\"content\":\"Reply with one word confirming that inference works.\"}],\"stream\":false}")"; then
@github-actions

Copy link
Copy Markdown
Contributor

🎉 This pull request is included in a new release.

Release: v0.86.3

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[aw-failures] [P1] Daily BYOK Ollama Test — local Ollama backend returns 503 on real inference despite passing warm-up

3 participants