add

agentgraph/methods/production/openai_structured_extractor.py

@@ -91,7 +91,7 @@ For each entity provide:
 - name: descriptive name
 - importance: HIGH, MEDIUM, or LOW
 - raw_prompt: actual prompt/specification content that defines this entity
-- raw_prompt_ref: list of content references with line_start and line_end (use <L#> markers if available)
+- raw_prompt_ref: list of content references ONLY if <L#> markers are present in the input. If no <L#> markers, use empty list []
 
 For each relation provide:
 - id: unique identifier
@@ -99,7 +99,9 @@ For each relation provide:
 - type: one of the types above
 - importance: HIGH, MEDIUM, or LOW
 - interaction_prompt: runtime evidence showing this relationship occurred
-- interaction_prompt_ref: list of content references (use <L#> markers if available)
+- interaction_prompt_ref: list of content references ONLY if <L#> markers are present in the input. If no <L#> markers, use empty list []
+
+IMPORTANT: Only create content references when you see explicit <L#> line markers in the input text. Do not invent line numbers.
 
 Also provide system_name and system_summary for the overall system.