feat(core): reintento ante timeout/503 en llamadas a HF (E4-02)#46
Merged
Conversation
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
E4-02 — Reintento ante fallos transitorios de HF
Closes #45
Contexto
El smoke test E2E del MVP (2026-06-03) confirmó que la inferencia remota de HF falla de forma transitoria: ~1 de cada 5 llamadas dio timeout (recurrente durante E3).
Qué incluye
BaseAPI.make_request— bucle de reintento opt-in por clase:MAX_RETRIES(default0→ Guardian/NYT no reintentan) yRETRY_BACKOFF;HFClientlo activa conMAX_RETRIES = 3.httpx.TimeoutExceptiony HTTP503. Cualquier otro error falla al instante.ToolResult.failsi se agotan los reintentos.respx):503→200ytimeout→200(recupera al reintentar),503perpetuo → agota (MAX_RETRIES+1intentos), y500→ falla inmediato. UsanRETRY_BACKOFF = 0para no esperar.Suite: 30 passed, 9 deselected.