Kill extract-wave truncation: 65k ceiling, hard thinking budget, reasoning-token telemetry

Job 98194fa8d215 showed every extract call hitting the 32k cap with only
~20k chars visible despite reasoning effort=low - Gemini 2.5 Pro still
burned ~25k thinking tokens per sheet.

- EXTRACT_MAX_TOKENS default 32768 -> 65536 (model output ceiling)
- new EXTRACT_REASONING_MAX_TOKENS (default 2048): OpenRouter reasoning
  max_tokens / Gemini thinking_budget; takes precedence over effort
- log per-call reasoning token counts (usage.completion_tokens_details)
  and include thinking count in the finish_reason=length marker

tests/agents/test_sheet_extractor_fallback.py

@@ -50,8 +50,9 @@ def test_run_accepts_bare_list_response():
     assert len(sheet["assertions"]) == 5
     # No compact retry needed when the first call yields data.
     assert mock_call.call_count == 1
-    # Reasoning effort knob is forwarded (None when config is blank in tests).
+    # Reasoning knobs are forwarded (None when config is blank in tests).
     assert "reasoning_effort" in mock_call.call_args.kwargs
+    assert "reasoning_max_tokens" in mock_call.call_args.kwargs
 
 
 def test_run_compact_retry_after_hard_failure():