Garde-fous contexte/MCP & descriptions d'outils du chat#18
Merged
Conversation
- Garde-fou budget de contexte : un bloc unique surdimensionné (gros document joint, jamais rogné car parmi les derniers messages) est plafonné avec un marqueur neutre, au lieu de faire échouer l'appel sur un petit modèle. - Circuit-breaker MCP : après 3 échecs d'affilée sur un serveur, fail-fast pendant 60 s au lieu de repayer le timeout à chaque appel d'outil. - generate_document : .describe() sur les sections (listes, blockquotes, tableaux) pour un meilleur remplissage d'arguments par le modèle. Tests : 216 passants.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Ce que cette branche apporte
Garde-fous et finitions sur le mécanisme du chat (suite directe de #17).
search_documents/read_document.generate_document:.describe()ajoutés sur les sections (listes, blockquotes, tableaux) pour un meilleur remplissage d'arguments par le modèle.Tests : 216 passants ·
tsc0 · build OK.