From 5c95017bc1d3b5a33f279c63311108b780cad570 Mon Sep 17 00:00:00 2001 From: yuneng-jiang Date: Mon, 27 Jul 2026 18:07:04 -0700 Subject: [PATCH] test: unstale the reasoning-effort grid count and the responses bridge test (#34868) * test(reasoning-effort-grid): bump cell-count assertion for claude-opus-5 The claude-opus-5 grid entry added in ae81625ee6 raised the Anthropic direct route to 31 model combos, but test_grid_cell_count still expected 30, so the suite went red on the tripwire rather than on any behavior change. * test(openai): swap the retired deep-research model out of the bridge test OpenAI shut down o3-deep-research and o4-mini-deep-research on 2026-07-23, so the live call in this test now comes back as a 400 'Model not found'. The test was never about deep research specifically; the bridge fires on any model whose cost-map mode is "responses", so it now uses gpt-5.5-pro, the newest responses-only OpenAI model, and is renamed to say that. gpt-5.5-pro was confirmed present on the CI account with an authenticated GET /v1/models before being picked. --- .../reasoning_effort_grid/test_reasoning_effort_grid.py | 4 ++-- tests/llm_translation/test_openai.py | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/tests/llm_translation/reasoning_effort_grid/test_reasoning_effort_grid.py b/tests/llm_translation/reasoning_effort_grid/test_reasoning_effort_grid.py index 2409067ebbe..517e3173b8c 100644 --- a/tests/llm_translation/reasoning_effort_grid/test_reasoning_effort_grid.py +++ b/tests/llm_translation/reasoning_effort_grid/test_reasoning_effort_grid.py @@ -201,8 +201,8 @@ async def test_reasoning_effort_grid( def test_grid_cell_count() -> None: - assert len(_PARAMS) == 30 * 11, ( - f"expected 330 cells (30 provider x model combos x 11 efforts), " + assert len(_PARAMS) == 31 * 11, ( + f"expected 341 cells (31 provider x model combos x 11 efforts), " f"got {len(_PARAMS)}" ) diff --git a/tests/llm_translation/test_openai.py b/tests/llm_translation/test_openai.py index 440fc36ed33..22acffd535f 100644 --- a/tests/llm_translation/test_openai.py +++ b/tests/llm_translation/test_openai.py @@ -613,13 +613,13 @@ async def test_openai_via_gemini_streaming_bridge(): assert len(printed_chunks) > 0 -def test_openai_deepresearch_model_bridge(): +def test_openai_responses_only_model_bridge(): """ - Test that the deepresearch model bridge works correctly + Test that the responses-only model bridge works correctly """ litellm._turn_on_debug() response = litellm.completion( - model="o3-deep-research-2025-06-26", + model="gpt-5.5-pro", messages=[{"role": "user", "content": "Hey, how's it going?"}], tools=[ {"type": "web_search_preview"},