Factory keeps long coding conversations manageable by updating a persistent summary as older messages leave the model's working context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition →. Its compression design summarizes the newly removed span and merges it into the existing summary, avoiding repeated summarization of the entire earlier conversation. Separate thresholds determine when compression starts and how much recent material remains afterward. The summary preserves requirements, file changes, test outcomes and references that help recover details. This makes compression a choice about retaining useful working state: removing too much can force the AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → to retrieve information again.
Terms in this piece · Glossary
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
