mirror of
https://github.com/catlog22/Claude-Code-Workflow.git
synced 2026-02-10 02:24:35 +08:00
Add benchmark results and tests for LSP graph builder and staged search
- Introduced a new benchmark results file for performance comparison on 2026-02-09. - Added a test for LspGraphBuilder to ensure it does not expand nodes at maximum depth. - Created a test for the staged search pipeline to validate fallback behavior when stage 1 returns empty results.
This commit is contained in:
@@ -134,7 +134,10 @@ class LspGraphBuilder:
|
||||
# Skip if already visited or at max depth
|
||||
if node.id in visited:
|
||||
return []
|
||||
if depth > self.max_depth:
|
||||
# Depth is 0 for seeds. To limit expansion to N hops from seeds,
|
||||
# we expand nodes with depth < max_depth.
|
||||
if depth >= self.max_depth:
|
||||
visited.add(node.id)
|
||||
return []
|
||||
if len(graph.nodes) >= self.max_nodes:
|
||||
return []
|
||||
|
||||
Reference in New Issue
Block a user