fix(extractor): streaming with guardrails + catalyst_type normalization

- Switch Ollama calls from non-streaming to streaming with early termination
- Add loop detection, max token limit, and stall timeout guards
- Add catalyst_type alias normalizer to handle model hallucinations
- Add explicit enum values in extraction prompt for catalyst_type
- Add streaming config knobs to OllamaConfig

services/shared/config.py

@@ -47,6 +47,10 @@ class OllamaConfig:
     retry_base_delay: float = 1.0
     retry_max_delay: float = 10.0
     retry_backoff_multiplier: float = 2.0
+    max_tokens: int = 4096
+    stall_timeout: float = 30.0
+    loop_window: int = 64
+    loop_threshold: float = 0.5
 
 
 @dataclass