The user chooses the connections. ThoughtDAG does not scan the whole map and guess what is relevant. A normal follow-up starts from the node you are asking from, so it gets one parent wire automatically. If you want to combine another branch or source, you explicitly connect it to the new node. Spatial proximity does not affect context; only the wires do.

At generation time, ThoughtDAG follows the reachable upstream graph of the target node rather than asking a model to compare all 300 elements. That said, navigating a 300-node canvas is still a real UI problem. Semantic zoom, condensing, and layout tools help, but larger graphs still need more optimization.

The nodes are human-readable; the wire itself is visible context.

For example, a source node might contain a passage extracted from a PDF. If it is wired into a question or synthesis node, that content is included when ThoughtDAG builds the model request.

A solid wire carries the full upstream context, while a dashed wire can carry a smaller reference. Delete the wire, and the source remains visible on the canvas but stops contributing to that downstream context.