show suggested link targets in agent prompts

Agents were flying blind — they could see nodes to review and the
topology header, but had no way to discover what targets to link to.
Now each node shows its top 8 text-similar semantic nodes that aren't
already neighbors, giving agents a search-like capability.

Also added section-level targeting guidance to linker.md, transfer.md,
and replay.md prompts: always target the most specific section, not
the file-level node.

Co-Authored-By: ProofOfConcept <poc@bcachefs.org>

prompts/replay.md

@@ -85,6 +85,12 @@ for the human to review.
 - **Trust the decay.** If a node is genuinely unimportant, you don't need
   to actively prune it. Just don't link it, and it'll decay below threshold
   on its own.
+- **Target sections, not files.** When linking to a topic file, always
+  target the most specific section: use `identity.md#boundaries` not
+  `identity.md`. The suggested link targets show available sections.
+- **Use the suggested targets.** Each node shows text-similar semantic nodes
+  not yet linked. These are computed by content similarity and are usually
+  the best starting point for new links.
 
 {{TOPOLOGY}}