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

backend/config.py

@@ -74,13 +74,20 @@ MAX_PAGES     = int(os.getenv("MAX_PAGES",     "60"))
 MAX_DIMENSION = int(os.getenv("MAX_DIMENSION", "2400"))  # px cap on the long edge
 LLM_TIMEOUT   = int(os.getenv("LLM_TIMEOUT",   "180"))   # seconds per call
 # Gemini 2.5 Pro counts thinking tokens against max_tokens, so the visible
-# JSON budget is well under this number on dense sheets. 32768 leaves real
-# headroom; raise via env if a set still truncates.
-EXTRACT_MAX_TOKENS = int(os.getenv("EXTRACT_MAX_TOKENS", "32768"))
+# JSON budget is well under this number on dense sheets. 65536 is the model's
+# output ceiling - give thinking all the room it wants so visible JSON never
+# truncates; the thinking budget itself is capped separately below.
+EXTRACT_MAX_TOKENS = int(os.getenv("EXTRACT_MAX_TOKENS", "65536"))
 # Reasoning effort for the per-sheet extractor (OpenRouter reasoning knob).
 # Extraction is perceptive, not deliberative - "low" keeps thinking tokens
 # from eating the output budget. Empty string disables the parameter.
 EXTRACT_REASONING_EFFORT = os.getenv("EXTRACT_REASONING_EFFORT", "low").strip()
+# Hard thinking-token budget for the extractor (OpenRouter reasoning
+# max_tokens -> Gemini thinking_budget). "low" effort alone still let Gemini
+# burn ~25k thinking tokens per sheet (job 98194fa8d215); a hard cap forces
+# the budget into visible output. 0 disables -> falls back to the effort knob.
+# Mutually exclusive with effort when set (OpenRouter rejects both together).
+EXTRACT_REASONING_MAX_TOKENS = int(os.getenv("EXTRACT_REASONING_MAX_TOKENS", "2048"))
 REASON_MAX_TOKENS  = int(os.getenv("REASON_MAX_TOKENS",  "4096"))
 
 # -- QAQC stage knobs (Stages 0-1, 3, 6-11) -------------------------