Update concurrency settings in config.yaml and README.md

- Adjusted `thinking_budget` in `config.yaml` from 9216 to 8192 to optimize resource allocation.
- Increased `workers` from 8 to 12 in both `config.yaml` and `README.md` to enhance concurrency.
- Updated `gemini` limits from 4 to 12 in both files to improve request handling capacity.

README.md

@@ -72,8 +72,8 @@ worklist:
   field_allowlist: []           # restrict to specific field IDs while testing
 
 concurrency:
-  workers: 8                    # ThreadPoolExecutor size
+  workers: 12                   # ThreadPoolExecutor size
-  limits: { sql: 6, gemini: 4 } # see "Concurrency model" below
+  limits: { sql: 6, gemini: 12 } # see "Concurrency model" below
   gemini_requests_per_minute: 60
 
 retry:

config.yaml

@@ -26,7 +26,7 @@ llm:
     anthropic_model: claude-opus-4-5
     gemini_model: gemini-2.5-pro
     max_tokens: 5120
-    thinking_budget: 9216
+    thinking_budget: 8192
     temperature: 0.0
 
 # ── Crop-first worklist ────────────────────────────────────────────────────────
@@ -63,10 +63,10 @@ worklist:
 # collection is vectorised with text2vec-palm (gemini-embedding-001) using the
 # same GEMINI_API_KEY — they share one quota.
 concurrency:
-  workers: 8
+  workers: 12
   limits:
     sql: 6
-    gemini: 4
+    gemini: 12
   gemini_requests_per_minute: 60
 
 # ── Retry policy for transient LLM / Weaviate / SQL failures ──────────────────