Merge remote-tracking branch 'origin/main' into worktree-anti-pattern-directive-position

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

@@ -371,6 +371,7 @@ async def write_block(
     block_id: str,
     instructions: str = "",
     effort_override: str | None = None,
+    model_override: str | None = None,
 ) -> dict:
     """כתיבת בלוק יחיד בהחלטה.
 
@@ -383,6 +384,12 @@ async def write_block(
             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.
+        model_override: optional per-call generation model id (e.g.
+            "claude-opus-5"). Same contract as effort_override — the #208
+            harness A/Bs MODELS without mutating the pinned GENERATION_MODEL.
+            Pass the BASE id only: the 1M-context escalation (#216) is applied
+            on top automatically for large prompts, so an override never
+            silently loses the 1M window. Production callers leave it None.
 
     Returns:
         dict עם content, word_count, block_id, generation_type
@@ -486,7 +493,12 @@ async def write_block(
     # escalate to the 1M-context build (`[1m]`) instead of failing the block —
     # block-yod legitimately carries the whole case as source-context. The 400K
     # ceiling was an artifact of the old 200K-only build, NOT a model limit.
-    gen_model = GENERATION_MODEL_1M if len(prompt) > _CTX_1M_THRESHOLD_CHARS else GENERATION_MODEL
+    # model_override (#208 harness) swaps the BASE id only — the 1M decision below
+    # still applies, so an A/B'd model keeps the same context-window behaviour as
+    # the pinned default instead of silently falling back to the 200K build.
+    _base_model = model_override or GENERATION_MODEL
+    _model_1m = GENERATION_MODEL_1M if _base_model == GENERATION_MODEL else f"{_base_model}[1m]"
+    gen_model = _model_1m if len(prompt) > _CTX_1M_THRESHOLD_CHARS else _base_model
 
     # Final guard: even the 1M build is finite (~2M Hebrew chars of input). Cap at
     # 1.5M chars (~750K tokens) to leave room for output + a safety margin under 1M.