feat: layered precise generation for A4 report images

3-phase pipeline to solve LLM prompt overflow from too many OCR elements: Phase 1 (generate_skeleton): compressed layout schema → skeleton JRXML Phase 2 (refine_layout): sampled coordinates → pixel-level position tuning Phase 3 (map_fields): OCR field names → replace $F{field_N} placeholders Only triggered when layout_schema.total_rows > 0 on initial_generation intent. Text requests and all other intents are unaffected (zero behavior change).
2026-05-21 08:34:32 +08:00
parent 9bb011e429
commit 43a0542a11
14 changed files with 882 additions and 81 deletions
@@ -20,7 +20,10 @@ _NAME_MAP = {
    "modification":       "modification.md",
    "correction":         "correction.md",
    "explain_error":      "explain_error.md",
-    "compression":        "compression.md",
+    "compression":         "compression.md",
+    "skeleton_generation": "skeleton_generation.md",
+    "refine_layout":       "refine_layout.md",
+    "field_mapping":       "field_mapping.md",
 }