feat(pipeline): per-stage max_tokens, LLM provenance, processing log

- PipelineStage now supports max_tokens to override the 4096 default
- SourcePipeline records provider/model on each entity file as HTML comment
- output/processing-log.yaml tracks tokens, cost, duration, retries, errors
- _call_llm returns (content, metadata) for downstream traceability
- _http.py wraps JSON parse errors with body preview for debugging
- infospace.yaml stages: extract/map=6000 tokens, synthesize=3000 tokens

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

markitect/infospace/cli.py

@@ -575,7 +575,13 @@ def process(
     # Run pipeline
     from markitect.infospace.pipeline import SourcePipeline
 
-    pipeline = SourcePipeline(cfg, root, adapter=adapter, no_commit=no_commit)
+    pipeline = SourcePipeline(
+        cfg, root,
+        adapter=adapter,
+        provider=provider or "",
+        model=(model or _PROVIDER_DEFAULTS.get(provider or "", "")) if provider else "",
+        no_commit=no_commit,
+    )
 
     total = len(source_files)
     completed = 0