feat: add type-signature-based fallback for unregistered nodes

GenericNodeExtractor (previously a no-op) now inspects
RETURN_TYPES to detect MODEL loaders and CONDITIONING
encoders in nodes not registered in NODE_EXTRACTORS.

- Propagate return_types from the hook layer through the
  registry to GenericNodeExtractor.extract() and update().
- MODEL detection: scan ckpt_name/unet_name/model_path/
  model_name/gguf_name fields, validate by extension.
- CONDITIONING detection: scan text/clip_l/t5xxl/prompt
  fields, store prompt text and conditioning tensor.
- _fill_missing_metadata also checks node_cache, so
  GenericNodeExtractor-handled nodes survive cache.

py/metadata_collector/metadata_hook.py

@@ -83,7 +83,8 @@ class MetadataHook:
                         
                         # Record inputs before execution
                         if node_id is not None:
-                            registry.record_node_execution(node_id, class_type, input_data_all, None)
+                            return_types = getattr(obj.__class__, 'RETURN_TYPES', None)
+                            registry.record_node_execution(node_id, class_type, input_data_all, None, return_types=return_types)
                 except Exception as e:
                     logger.error(f"Error collecting metadata (pre-execution): {str(e)}")
             
@@ -114,7 +115,8 @@ class MetadataHook:
                         
                         # Record outputs after execution
                         if node_id is not None:
-                            registry.update_node_execution(node_id, class_type, results)
+                            return_types = getattr(obj.__class__, 'RETURN_TYPES', None)
+                            registry.update_node_execution(node_id, class_type, results, return_types=return_types)
                 except Exception as e:
                     logger.error(f"Error collecting metadata (post-execution): {str(e)}")
             
@@ -166,7 +168,8 @@ class MetadataHook:
                         class_type = obj.__class__.__name__
                         node_id = unique_id
                         if node_id is not None:
-                            registry.record_node_execution(node_id, class_type, input_data_all, None)
+                            return_types = getattr(obj.__class__, 'RETURN_TYPES', None)
+                            registry.record_node_execution(node_id, class_type, input_data_all, None, return_types=return_types)
                 except Exception as e:
                     logger.error(f"Error collecting metadata (pre-execution): {str(e)}")
 
@@ -183,7 +186,8 @@ class MetadataHook:
                         class_type = obj.__class__.__name__
                         node_id = unique_id
                         if node_id is not None:
-                            registry.update_node_execution(node_id, class_type, results)
+                            return_types = getattr(obj.__class__, 'RETURN_TYPES', None)
+                            registry.update_node_execution(node_id, class_type, results, return_types=return_types)
                 except Exception as e:
                     logger.error(f"Error collecting metadata (post-execution): {str(e)}")
 

py/metadata_collector/metadata_registry.py

@@ -128,7 +128,7 @@ class MetadataRegistry:
             cache_key = f"{node_id}:{class_type}"
 
             # Check if this node type is relevant for metadata collection
-            if class_type in NODE_EXTRACTORS:
+            if class_type in NODE_EXTRACTORS or cache_key in self.node_cache:
                 # Check if we have cached metadata for this node
                 if cache_key in self.node_cache:
                     cached_data = self.node_cache[cache_key]
@@ -141,7 +141,7 @@ class MetadataRegistry:
                                     node_id
                                 ]
 
-    def record_node_execution(self, node_id, class_type, inputs, outputs):
+    def record_node_execution(self, node_id, class_type, inputs, outputs, return_types=None):
         """Record information about a node's execution"""
         if not self.current_prompt_id:
             return
@@ -164,17 +164,18 @@ class MetadataRegistry:
 
         # Extract node-specific metadata
         extractor = NODE_EXTRACTORS.get(class_type, GenericNodeExtractor)
-        extractor.extract(
-            node_id,
-            processed_inputs,
-            outputs,
-            self.prompt_metadata[self.current_prompt_id],
-        )
+        if type(extractor) is GenericNodeExtractor:
+            extractor.extract(node_id, processed_inputs, outputs,
+                              self.prompt_metadata[self.current_prompt_id],
+                              return_types=return_types)
+        else:
+            extractor.extract(node_id, processed_inputs, outputs,
+                              self.prompt_metadata[self.current_prompt_id])
 
         # Cache this node's metadata
         self._cache_node_metadata(node_id, class_type)
 
-    def update_node_execution(self, node_id, class_type, outputs):
+    def update_node_execution(self, node_id, class_type, outputs, return_types=None):
         """Update node metadata with output information"""
         if not self.current_prompt_id:
             return
@@ -185,9 +186,17 @@ class MetadataRegistry:
         # Use the same extractor to update with outputs
         extractor = NODE_EXTRACTORS.get(class_type, GenericNodeExtractor)
         if hasattr(extractor, "update"):
-            extractor.update(
-                node_id, processed_outputs, self.prompt_metadata[self.current_prompt_id]
-            )
+            if type(extractor) is GenericNodeExtractor:
+                extractor.update(
+                    node_id, processed_outputs,
+                    self.prompt_metadata[self.current_prompt_id],
+                    return_types=return_types,
+                )
+            else:
+                extractor.update(
+                    node_id, processed_outputs,
+                    self.prompt_metadata[self.current_prompt_id],
+                )
 
         # Update the cached metadata for this node
         self._cache_node_metadata(node_id, class_type)

py/metadata_collector/node_extractors.py

@@ -31,11 +31,78 @@ class NodeMetadataExtractor:
         pass
         
 class GenericNodeExtractor(NodeMetadataExtractor):
-    """Default extractor for nodes without specific handling"""
+    """Fallback extractor with type-signature-based detection.
+
+    When a node is not in the NODE_EXTRACTORS registry, the hook layer
+    passes ``return_types`` from ``obj.RETURN_TYPES``:
+
+    * ``MODEL`` output: common input fields (ckpt_name, unet_name, etc.)
+      are checked for a model file name and stored as checkpoint metadata.
+    * ``CONDITIONING`` output: common text input fields are checked for
+      prompt text and stored as prompt metadata.
+    """
+
+    # Input field names that carry a model path in loader-style nodes.
+    _MODEL_NAME_FIELDS = (
+        "ckpt_name", "unet_name", "model_path", "model_name", "gguf_name",
+    )
+
+    # Extensions used by checkpoint_scanner.py — only record values that look
+    # like real model filenames to avoid capturing unrelated string fields.
+    _MODEL_EXTENSIONS = {
+        ".ckpt", ".pt", ".pt2", ".bin", ".pth", ".safetensors", ".pkl", ".sft", ".gguf",
+    }
+
+    # Input field names that may carry prompt text in encoder-style nodes.
+    _TEXT_FIELDS = ("text", "clip_l", "t5xxl", "prompt", "positive", "negative")
+
     @staticmethod
-    def extract(node_id, inputs, outputs, metadata):
-        pass
-        
+    def extract(node_id, inputs, outputs, metadata, return_types=None):
+        if return_types is None:
+            return
+
+        # — MODEL loader detection (checkpoint / UNET / GGUF) —
+        if "MODEL" in return_types or any("MODEL" in str(t) for t in return_types):
+            for field in GenericNodeExtractor._MODEL_NAME_FIELDS:
+                val = inputs.get(field)
+                if val and isinstance(val, str) and val.strip():
+                    name = val.strip()
+                    if not any(name.lower().endswith(ext) for ext in GenericNodeExtractor._MODEL_EXTENSIONS):
+                        continue
+                    _store_checkpoint_metadata(metadata, node_id, name)
+                    return
+
+        # — CONDITIONING encoder detection (CLIPTextEncode, Flux, custom) —
+        if "CONDITIONING" in return_types or any("CONDITIONING" in str(t) for t in return_types):
+            text = None
+            for field in GenericNodeExtractor._TEXT_FIELDS:
+                val = inputs.get(field)
+                if val and isinstance(val, str) and val.strip():
+                    text = val.strip()
+                    break
+            if text:
+                prompt_data = metadata.setdefault(PROMPTS, {})
+                prompt_data[node_id] = {
+                    "text": text,
+                    "node_id": node_id,
+                }
+
+    @staticmethod
+    def update(node_id, outputs, metadata, return_types=None):
+        if return_types is None:
+            return
+        if "CONDITIONING" not in return_types and not any(
+            "CONDITIONING" in str(t) for t in return_types
+        ):
+            return
+        if node_id not in metadata.get(PROMPTS, {}):
+            return
+        if outputs and isinstance(outputs, list) and len(outputs) > 0:
+            if isinstance(outputs[0], tuple) and len(outputs[0]) > 0:
+                cond = outputs[0][0]
+                if cond is not None:
+                    metadata[PROMPTS][node_id]["conditioning"] = cond
+
 class CheckpointLoaderExtractor(NodeMetadataExtractor):
     @staticmethod
     def extract(node_id, inputs, outputs, metadata):

tests/metadata_collector/test_metadata_collector.py

@@ -30,10 +30,10 @@ def test_metadata_hook_installs_and_traces_execution(monkeypatch, metadata_regis
 
     calls = []
 
-    def record_stub(self, node_id, class_type, inputs, outputs):
+    def record_stub(self, node_id, class_type, inputs, outputs, return_types=None):
         calls.append(("record", node_id, class_type, inputs))
 
-    def update_stub(self, node_id, class_type, outputs):
+    def update_stub(self, node_id, class_type, outputs, return_types=None):
         calls.append(("update", node_id, class_type, outputs))
 
     monkeypatch.setattr(MetadataRegistry, "record_node_execution", record_stub)