fix: disable dltb priors for gf3 water workflow

.env.example

@@ -119,7 +119,8 @@ IDL_DINSAR_DEM_BASE_FILE=D:\SRTM30m\SRTMDEM_RSP_SARscape
 SRTM_DEM_DIR=D:\SRTM30m
 GF3_GEO_DEM_PATH=D:\DEM\gf3_dem.jp2
 WATER_RESULTS_DIR=D:\WaterResult
-GF3_WATER_DLTB_CACHE_DIR=D:\production_assets\gf3_water\priors\dltb_cache\heilongjiang
+GF3_WATER_USE_DLTB=false
+GF3_WATER_DLTB_CACHE_DIR=
 GF3_WATER_DEM_PATH=
 GF3_WATER_DEFAULT_CARTOGRAPHIC=true
 GF3_WATER_DEFAULT_OUT_VECTOR=true

backend/app/config.py

@@ -215,6 +215,7 @@ class Settings(BaseSettings):
     RADAR_PREVIEW_BUILD_ON_DEMAND: bool = True
 
     WATER_RESULTS_DIR: str = ""
+    GF3_WATER_USE_DLTB: bool = False
     GF3_WATER_DLTB_CACHE_DIR: str = ""
     GF3_WATER_DEM_PATH: str = ""
     GF3_WATER_DEFAULT_CARTOGRAPHIC: bool = True

backend/app/services/gf3_water_extraction_service.py

@@ -134,10 +134,15 @@ def run_gf3_hh_hv_water_extraction(
 
     hh = _existing_path(hh_path, label="HH input")
     hv = _existing_path(hv_path, label="HV input")
-    dltb_cache_dir = _optional_existing_path(
+    use_dltb = _as_bool(params.get("use_dltb"), bool(settings.GF3_WATER_USE_DLTB))
+    dltb_cache_dir = (
+        _optional_existing_path(
             params.get("dltb_cache_dir") or settings.GF3_WATER_DLTB_CACHE_DIR,
             label="GF3_WATER_DLTB_CACHE_DIR",
         )
+        if use_dltb
+        else None
+    )
     dem = _optional_existing_path(
         params.get("dem") or params.get("dem_path") or settings.GF3_WATER_DEM_PATH,
         label="GF3_WATER_DEM_PATH",
@@ -224,6 +229,7 @@ def run_gf3_hh_hv_water_extraction(
             "dltb_cache_dir": str(dltb_cache_dir) if dltb_cache_dir else None,
         },
         "runtime": {
+            "dltb_enabled": use_dltb and dltb_cache_dir is not None,
             "vector_requested": out_vector,
             "vector_runtime_available": vector_runtime_available,
             "vector_output_enabled": vector_output_enabled,

docs/GF3_WATER_EXTRACTION_INTEGRATION_20260615.md

@@ -86,12 +86,14 @@ System integration should be written around existing services:
 
 Do not store runtime data in Git.
 
-Required/valuable runtime assets:
+Current integration does not use DLTB priors. The GF-3 HH/HV processor runs from SAR backscatter, morphology and optional vector/DEM inputs only.
+
+Optional future runtime assets:
 
 - `D:\Code\Water\data\priors\dltb_cache\heilongjiang`
   - Current size observed: 25 files, about 8.5 GB.
-  - Transfer to a managed runtime asset path, for example `D:\production_assets\gf3_water\priors\dltb_cache\heilongjiang`.
-  - Configure by `GF3_WATER_DLTB_CACHE_DIR`.
+  - Do not transfer for the current workflow.
+  - If DLTB is re-enabled later, transfer to a managed runtime asset path, for example `D:\production_assets\gf3_water\priors\dltb_cache\heilongjiang`, then set `GF3_WATER_USE_DLTB=true` and `GF3_WATER_DLTB_CACHE_DIR`.
 
 Optional runtime assets:
 
@@ -116,6 +118,7 @@ These are large model artifacts and should stay outside the application until a
 
 Add configuration keys:
 
+- `GF3_WATER_USE_DLTB=false`
 - `GF3_WATER_DLTB_CACHE_DIR`
 - `GF3_WATER_DEM_PATH`
 - `GF3_WATER_DEFAULT_CARTOGRAPHIC=true`
@@ -153,5 +156,5 @@ flowchart TD
 ## Open Decisions
 
 - Whether runtime execution should be in-process Python API first or always subprocess CLI. Initial integration should use in-process API because it fits the existing worker model and keeps job accounting simple.
-- Whether to transfer the 8.5 GB DLTB cache automatically. This should be a deployment operation, not a Git operation.
+- DLTB priors are disabled for the current workflow. Re-enabling them later should be a deployment decision because the cache is about 8.5 GB.
 - Whether legacy AI4G U-Net should be supported later. It should not block the current HH/HV production chain.