feat(integrations): NYT sort, Guardian por tag y topic con Field (E4-04)#49
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
E4-04 — Ajustes de tools tras validación E2E
Closes #47
La validación E2E destapó 3 problemas al buscar por tema (p.ej. "artificial intelligence"); todos corregidos.
Cambios
sort=relevancecuando hay topic (antessort=newesthacía queqno filtrara → devolvía noticia general).nyt/client.py.tag:/tags?q=topic→ top tag →/search?tag=…, con fallback aq. Quita el ruido de palabra suelta ("intelligence" = espías/música).guardian/client.py.Field(description=…)entopic(NYT + Guardian) → el LLM deja de inventarsequery.Tests (
respx)sort=relevance/newestsegún topic.tago cae aq; los existentes ahora son deterministas (mockean/tags).Verificación empírica
Llamadas reales: NYT → IA limpia; Guardian tag → contenido curado de IA, sin falsos positivos de palabra suelta. (Un test mockeado no destapaba esto — solo la llamada real.)