Fix broken qualityflow agent reference in .fullsend/config.yaml

Aperta
  • Qualcosa non va?
#55 3 commenti 0 reazioni 0 assegnatari Vedi su GitHub

@fullsend-ai-coder ci sta già lavorando.

Dal 22/8/2026.

  • #56 di @fullsend-ai-coder — aperta

Valutazione

Difficoltà
2/5
Tempo stimato
1-3 ore
Idoneità per principianti
25/100
Tipo di issue
Bug
Chiarezza
Abbastanza chiara
Stato di attività
Ferma
Stack tecnologico
github-actions
Ambito
ci-cd

Direzione di ricerca

Start in .fullsend/config.yaml, where the qualityflow agent reference pins commit b26c947 of redhat-community-ai-tools/qualityflow-fullsend, and check the allowed_remote_resources entry. Check the external repo's history for a commit where qualityflow.md exists, or remove the entry if the agent is unused. Pull request #56 is already open against this issue, so review it before starting new work. Done means the next workflow runs no longer log a 404 for qualityflow.

Scritto dal modello di indicizzazione a partire dal testo della issue.

Descrizione

bug ready-for-triage ready-to-code

What happened

Every agent run on this repo logs a 404 error when trying to load the qualityflow agent definition. The error appears in all three review runs triggered by PR #54 (32591507621, 32591974169, 32591991370):

skipping agent qualityflow: load failed: resolving URL-sourced resources:
base agent: fetching https://raw.githubusercontent.com/redhat-community-ai-tools/
qualityflow-fullsend/.../qualityflow.md: fetch: non-200 status code: got 404

The .fullsend/config.yaml references the qualityflow harness YAML at commit b26c947 of redhat-community-ai-tools/qualityflow-fullsend, but the agent definition file (qualityflow.md) referenced within that harness YAML does not exist at that commit. PR #54 deliberately kept this reference (the PR description says it is not covered by CLI fallback), but the reference is non-functional.

What could go better

The qualityflow agent should either resolve successfully or be removed from the config. Currently it fails silently on every run, adding noise to logs and potentially masking other resolution errors. Confidence is high that this is a broken reference — the 404 is a genuine HTTP response from GitHub's raw content service, not an access control issue (the allowed_remote_resources list includes the qualityflow domain).

The root cause is likely one of: (a) the external repo restructured its files after the pinned commit, (b) the agent definition file was never at that path, or (c) the pinned commit predates the addition of qualityflow.md. Investigation with the qualityflow maintainers would confirm which.

Proposed change

In .fullsend/config.yaml, either:

  1. Update the qualityflow reference to a commit SHA where qualityflow.md exists in the expected location within the redhat-community-ai-tools/qualityflow-fullsend repo. This requires checking the external repo's commit history to find a valid commit.

  2. Remove the qualityflow agent entry and its allowed_remote_resources entry if the qualityflow agent is not actively used in this repo. This eliminates the 404 noise entirely.

Option 2 is simpler and safer if qualityflow is not currently providing value. Option 1 is preferred if the experiment is still active.

Validation criteria

After the fix, agent runs on fullsend-ai/experiments should no longer log skipping agent qualityflow: load failed with a 404 status. Verify by checking the next 3 fullsend workflow runs on the repo — the qualityflow agent should either resolve successfully (option 1) or not appear in the agent resolution log at all (option 2).

Generated by retro agent from https://github.com/fullsend-ai/experiments/pull/54

Lingua principale
Python
Stelle
1
Fork
9
Merge medio
1g 13h
PR unite (30g)
7

Preparare l'ambiente

Questo progetto non fornisce container di sviluppo, Dockerfile né guida per i contributori, quindi l'ambiente è a tuo carico: parti dal suo README e consulta la nostra guida al primo contributo per i passaggi generali.

Come iniziare

  1. Leggi tutta la issue e poi la guida ai contributi del progetto.
  2. Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
  3. Fai un fork del repository e lavora su un branch.
  4. Apri una pull request che faccia riferimento al numero della issue.

Altre issue di fullsend-ai/experiments

Tutte le issue di fullsend-ai/experiments

Issue simili

Altre issue su Python

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.