ctx 1.0 adds a way to connect changed code to 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 → sessions that produced it. Its pro feature, ctx blame, accepts a file, commit or pull request and returns attribution with supporting evidence. It explicitly reports cases where the evidence is missing, ambiguous or stale.
The release notes also describe activating history indexes only after verifying a complete generation, meaning a consistent snapshot of the indexed records. Interrupted updates retain the last verified snapshot. That keeps attribution and search from mixing partially refreshed records, making the provenance of a code change easier to inspect.
Terms in this piece · Glossary
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.
multi-agent — Using several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.
