From 36c036cd2dab3ab4bb5f2d3ee825a7a33974e147 Mon Sep 17 00:00:00 2001
From: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Date: Sat, 29 Aug 2026 16:28:49 -0700
Subject: [PATCH] test(reasoning-effort-grid): expect capped thinking on
 messages-route budget models

---
 .../reasoning_effort_grid/grid_spec.py            | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/tests/llm_translation/reasoning_effort_grid/grid_spec.py b/tests/llm_translation/reasoning_effort_grid/grid_spec.py
index 4fa77f38940..485f78ed8c7 100644
--- a/tests/llm_translation/reasoning_effort_grid/grid_spec.py
+++ b/tests/llm_translation/reasoning_effort_grid/grid_spec.py
@@ -103,7 +103,7 @@ def _bedrock_clamps_effort(model: "ModelEntry", effort: str) -> bool:
     return _EFFORT_RANK[effort] > _EFFORT_RANK[model.bedrock_effort_ceiling]
 
 
-def expected(model: ModelEntry, effort: str) -> CellExpectation:
+def expected(route_name: str, model: ModelEntry, effort: str) -> CellExpectation:
     if effort in ("__omit__", "none"):
         if model.mode == "budget":
             return CellExpectation(
@@ -117,6 +117,15 @@ def expected(model: ModelEntry, effort: str) -> CellExpectation:
     if effort in ("xhigh", "max"):
         cap = f"supports_{effort}_reasoning_effort"
         if cap not in model.caps and not _bedrock_clamps_effort(model, effort):
+            if model.mode == "budget" and route_name == "bedrock_invoke_messages":
+                # the /v1/messages path caps the mapped budget below max_tokens
+                # (LIT-6498), so oversized tiers succeed there instead of 400ing
+                return CellExpectation(
+                    status=200,
+                    thinking_type="enabled",
+                    thinking_budget_tokens=BUDGET_MODE_MAX_TOKENS - 1,
+                    max_tokens=BUDGET_MODE_MAX_TOKENS,
+                )
             return CellExpectation(status=400, thinking_type=OMIT)
 
     if model.mode == "adaptive":
@@ -441,5 +450,7 @@ def all_cells() -> List[Tuple[str, ModelEntry, str, CellExpectation]]:
     for route in ROUTES:
         for model in route.models:
             for effort in EFFORTS:
-                cells.append((route.name, model, effort, expected(model, effort)))
+                cells.append(
+                    (route.name, model, effort, expected(route.name, model, effort))
+                )
     return cells