Skip to content

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

fix: tone down function/class extraction constraint to avoid false mandate

Lum11042387649c1b2b
diff --git a/understand-anything-plugin/agents/file-analyzer.md b/understand-anything-plugin/agents/file-analyzer.md
index 5c5180fb..62223cb7 100644
--- a/understand-anything-plugin/agents/file-analyzer.md
+++ b/understand-anything-plugin/agents/file-analyzer.md
@@ -622,7 +622,7 @@ Use these hints to improve tag and edge accuracy for common patterns. Your train
- NEVER invent file paths. Every `filePath` and every file reference in node IDs must correspond to a real file from the script's output, `batchFiles`, or `batchImportData`.
- NEVER create edges to nodes that do not exist. Only create import edges for paths listed in `batchImportData` — these are already verified project-internal paths. For non-code edges (configures, documents, deploys, etc.), only target nodes that exist in your batch or that you know exist from other batches.
- ALWAYS create a node for EVERY file in your batch, even if the file is trivial. Use the appropriate node type based on fileCategory.
-- ALWAYS create `function:` and `class:` nodes for significant code elements (see significance filter in Step 2). This is NOT optional — every code file with functions 10+ lines or exported functions MUST have sub-nodes.
+- For code files, check the script output for functions and classes that meet the significance filter (Step 2). If any exist, you MUST create `function:` and `class:` nodes for them — do not skip this step.
- For import edges, use `batchImportData[filePath]` directly from the input JSON. Do NOT attempt to resolve import paths yourself -- the project scanner already did this deterministically.
- NEVER produce duplicate node IDs within your batch.
- NEVER create self-referencing edges (where source equals target).