Merge pull request 'feat(calibration): כיול-אמפירי model×effort מול הסופיים (#208)' (#360) from worktree-agent-a5a22be0318670871 into main

mcp-server/src/legal_mcp/services/block_writer.py

@@ -355,6 +355,7 @@ async def write_block(
     case_id: UUID,
     block_id: str,
     instructions: str = "",
+    effort_override: str | None = None,
 ) -> dict:
     """כתיבת בלוק יחיד בהחלטה.
 
@@ -362,6 +363,11 @@ async def write_block(
         case_id: מזהה התיק
         block_id: מזהה הבלוק (block-alef, block-he, block-yod, ...)
         instructions: הנחיות נוספות
+        effort_override: optional per-call reasoning effort (low/medium/high/
+            xhigh/max). When set, overrides BLOCK_CONFIG[block_id].effort for
+            THIS call only — used by the #208 model/effort calibration harness
+            to A/B efforts without mutating the pinned defaults. Production
+            callers leave it None and get the deterministic per-block effort.
 
     Returns:
         dict עם content, word_count, block_id, generation_type
@@ -472,7 +478,7 @@ async def write_block(
     # reasoning effort so generation is structurally deterministic — these were
     # previously NOT forwarded (the source of inconsistency). model/effort flow
     # through claude_session.query → `claude -p --model … --effort …`.
-    effort = block_cfg.get("effort", DEFAULT_EFFORT)
+    effort = effort_override or block_cfg.get("effort", DEFAULT_EFFORT)
     timeout = claude_session.LONG_TIMEOUT if effort in _LONG_EFFORTS else claude_session.DEFAULT_TIMEOUT
     content = await claude_session.query(
         prompt,
@@ -485,6 +491,10 @@ async def write_block(
     sources = await _collect_block_sources(case_id, block_id)
     sources["case_law_ids"] = _precedent_case_law_ids
     result = _build_result(block_id, content, block_cfg)
+    # Record the EFFECTIVE effort (override wins) so the harness can attribute
+    # the measured distance to the effort that actually produced the text.
+    if result.get("effort") is not None:
+        result["effort"] = effort
     result["sources"] = sources
     return result