fix(agents): name the map-branch output key in deep-research and finding-verifier

An llm node never persists its completion under `output` (the binding
is transient), so a map branch without state_updates collected the
stale inherited value: deep-research produced `None` findings and
finding-verifier errored on its first item because `output` was absent.

Both maps now declare an explicit output_key and their branch nodes
write it via state_updates. graph.example.yaml's research_subject gets
the same named-key pattern and its branch comment describes it.

Design: plans/map-subgraph-branches-design.md §2.6, §3.7 (C9).

assets/agents/deep-research/graph.yaml

@@ -115,6 +115,7 @@ nodes:
     as: question
     branch: research_one_question
     collect_into: question_findings
+    output_key: finding
     max_concurrency: 3
     next: combine_findings
 
@@ -152,6 +153,8 @@ nodes:
     max_iterations: 10
     max_attempts: 2
     temperature: 0.1
+    state_updates:
+      finding: "{{output}}"
 
   combine_findings:
     id: combine_findings