feat(infospace): add process command for batch source file processing

- Extend PipelineStage with name, output_dir, output_macro,
  split_entities, and macros fields for declarative pipeline config
- Add SourcePipeline class (pipeline.py) using simple @{macro}
  substitution — no SQLite dependency, skip-if-exists per stage,
  LLM retry on rate limits, git commit per source
- Add `markitect infospace process [GLOB_PATTERN]` CLI command with
  --all, --provider, --model, --check-after-each, --no-commit flags
- Update infospace.yaml with output_dir, output_macro, split_entities,
  and macros for each pipeline stage in the WoN example

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

markitect/infospace/config.py

@@ -155,13 +155,41 @@ class ViabilityThreshold:
 
 @dataclass
 class PipelineStage:
-    """A single stage in the processing pipeline."""
+    """A single stage in the processing pipeline.
+
+    Attributes:
+        template: Path to the template file (relative to infospace root).
+        name: Human-readable stage name used in progress output.
+        output_dir: Directory for stage outputs (relative to root).
+        output_macro: Macro name for this stage's output, also used as
+            the filename suffix (e.g. ``entities`` → ``<id>-entities.md``).
+        split_entities: If True, parse ``--- ENTITY: <name> ---`` delimiters
+            from LLM output and write individual entity files.
+        macros: Static macros loaded from files (macro name → relative path).
+        spaces: Legacy space IDs for SQLite-based resolver (unused by
+            :class:`SourcePipeline`).
+    """
 
     template: str
+    name: str = ""
+    output_dir: str = ""
+    output_macro: str = ""
+    split_entities: bool = False
+    macros: Dict[str, str] = field(default_factory=dict)
     spaces: List[str] = field(default_factory=list)
 
     def to_dict(self) -> Dict[str, Any]:
         d: Dict[str, Any] = {"template": self.template}
+        if self.name:
+            d["name"] = self.name
+        if self.output_dir:
+            d["output_dir"] = self.output_dir
+        if self.output_macro:
+            d["output_macro"] = self.output_macro
+        if self.split_entities:
+            d["split_entities"] = self.split_entities
+        if self.macros:
+            d["macros"] = self.macros
         if self.spaces:
             d["spaces"] = self.spaces
         return d
@@ -170,6 +198,11 @@ class PipelineStage:
     def from_dict(cls, data: Dict[str, Any]) -> PipelineStage:
         return cls(
             template=data["template"],
+            name=data.get("name", ""),
+            output_dir=data.get("output_dir", ""),
+            output_macro=data.get("output_macro", ""),
+            split_entities=data.get("split_entities", False),
+            macros=data.get("macros", {}),
             spaces=data.get("spaces", []),
         )