From aec3026860829cc8704a5253204ce4825719bbe7 Mon Sep 17 00:00:00 2001 From: Mateo Wang <277851410+mateo-berri@users.noreply.github.com> Date: Fri, 18 Sep 2026 17:44:18 -0700 Subject: [PATCH 1/3] Merge pull request #41870 from BerriAI/litellm_bedrock_openai_gpt_min_max_tokens fix(bedrock): clamp maxTokens to the 16-token minimum for OpenAI GPT and xAI Grok models on Converse (cherry picked from commit a6e3a72ed8266cf3ffa6c1d52976455ff707a187) --- .../bedrock/chat/converse_transformation.py | 12 +++++++- .../chat/test_converse_transformation.py | 28 +++++++++++++++++++ 2 files changed, 39 insertions(+), 1 deletion(-) diff --git a/litellm/llms/bedrock/chat/converse_transformation.py b/litellm/llms/bedrock/chat/converse_transformation.py index e097805f54a..af9948056d8 100644 --- a/litellm/llms/bedrock/chat/converse_transformation.py +++ b/litellm/llms/bedrock/chat/converse_transformation.py @@ -4,6 +4,7 @@ Translating between OpenAI's `/chat/completion` format and Amazon's `/converse` import copy import json +import re import time import types from collections.abc import Mapping @@ -105,6 +106,7 @@ BEDROCK_COMPUTER_USE_TOOLS: Final = [ "bash_", "text_editor_", ] +BEDROCK_OPENAI_COMPAT_MIN_MAX_TOKENS: Final = 16 # Beta header patterns that are not supported by Bedrock Converse API # These will be filtered out to prevent errors @@ -293,6 +295,10 @@ class AmazonConverseConfig(BaseConfig): llm_provider="bedrock", ) + @staticmethod + def _requires_min_max_tokens(model: str) -> bool: + return re.search(r"openai\.gpt-\d|xai\.grok-", model) is not None + def _is_nova_2_model(self, model: str) -> bool: """ Check if the model is a Nova 2 model that supports reasoningConfig. @@ -883,7 +889,11 @@ class AmazonConverseConfig(BaseConfig): is_thinking_enabled=is_thinking_enabled, ) if param == "max_tokens" or param == "max_completion_tokens": - optional_params["maxTokens"] = value + optional_params["maxTokens"] = ( + max(value, BEDROCK_OPENAI_COMPAT_MIN_MAX_TOKENS) + if isinstance(value, int) and self._requires_min_max_tokens(model) + else value + ) if param == "stream": optional_params["stream"] = value if param == "stop": diff --git a/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py b/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py index cb05cdb9451..6e51b583a65 100644 --- a/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py +++ b/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py @@ -375,6 +375,34 @@ def test_reasoning_with_forced_tool_choice_switches_to_auto(): assert optional_params["tool_choice"] == {"auto": {}} +@pytest.mark.parametrize( + "model, param, value, expected_max_tokens", + [ + ("us.openai.gpt-6-astra", "max_tokens", 1, 16), + ("us.openai.gpt-6-astra", "max_completion_tokens", 1, 16), + ("us.openai.gpt-6-astra", "max_tokens", 64, 64), + ("us.xai.grok-4.6", "max_tokens", 1, 16), + ("global.xai.grok-4.6", "max_completion_tokens", 1, 16), + ("us.xai.grok-4.6", "max_tokens", 32, 32), + ("anthropic.claude-sonnet-4-5-20250929-v1:0", "max_tokens", 1, 1), + ("arn:aws:bedrock:us-east-1:123456789012:inference-profile/us.openai.gpt-6-astra", "max_tokens", 1, 16), + ("arn:aws:bedrock:us-east-1:123456789012:inference-profile/global.xai.grok-4.6", "max_tokens", 1, 16), + ("arn:aws:bedrock:us-east-1:123456789012:application-inference-profile/abc123xyz", "max_tokens", 1, 1), + ], +) +def test_map_openai_params_enforces_minimum_max_tokens_for_openai_compat_models( + model: str, param: str, value: int, expected_max_tokens: int +): + optional_params = AmazonConverseConfig().map_openai_params( + non_default_params={param: value}, + optional_params={}, + model=model, + drop_params=False, + ) + + assert optional_params["maxTokens"] == expected_max_tokens + + @pytest.mark.parametrize( "model", [ From 07a3aef0b20326ab2025dda332649ee6737158f5 Mon Sep 17 00:00:00 2001 From: Yuneng Jiang Date: Mon, 21 Sep 2026 14:16:47 -0700 Subject: [PATCH 2/3] chore(deps): bump anyio to 4.14.2 --- uv.lock | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/uv.lock b/uv.lock index ac36cc17213..67ec7af756d 100644 --- a/uv.lock +++ b/uv.lock @@ -10,7 +10,7 @@ resolution-markers = [ ] [options] -exclude-newer = "2026-09-02T16:58:34.594994Z" +exclude-newer = "2026-09-18T21:16:34.348134Z" exclude-newer-span = "P3D" [manifest] @@ -315,16 +315,16 @@ vertex = [ [[package]] name = "anyio" -version = "4.13.0" +version = "4.14.2" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "exceptiongroup", marker = "python_full_version < '3.11'" }, { name = "idna" }, { name = "typing-extensions", marker = "python_full_version < '3.13'" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/19/14/2c5dd9f512b66549ae92767a9c7b330ae88e1932ca57876909410251fe13/anyio-4.13.0.tar.gz", hash = "sha256:334b70e641fd2221c1505b3890c69882fe4a2df910cba14d97019b90b24439dc", size = 231622, upload-time = "2026-03-24T12:59:09.671Z" } +sdist = { url = "https://files.pythonhosted.org/packages/61/cc/a381afa6efea9f496eff839d4a6a1aed3bfafc7b3ab4b0d1b243a12573dd/anyio-4.14.2.tar.gz", hash = "sha256:cfa139f3ed1a23ee8f88a145ddb5ac7605b8bbfd8592baacd7ce3d8bb4313c7f", size = 260176, upload-time = "2026-07-12T20:29:07.082Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/da/42/e921fccf5015463e32a3cf6ee7f980a6ed0f395ceeaa45060b61d86486c2/anyio-4.13.0-py3-none-any.whl", hash = "sha256:08b310f9e24a9594186fd75b4f73f4a4152069e3853f1ed8bfbf58369f4ad708", size = 114353, upload-time = "2026-03-24T12:59:08.246Z" }, + { url = "https://files.pythonhosted.org/packages/da/35/f2287558c17e29fafc8ef3daf819bb9834061cfa43bff8014f7df7f63bdc/anyio-4.14.2-py3-none-any.whl", hash = "sha256:9f505dda5ac9f0c8309b5e8bd445a8c2bf7246f3ce950121e45ea15bc41d1494", size = 125813, upload-time = "2026-07-12T20:29:05.763Z" }, ] [[package]] From 5b1a90397652f5b7fdb6daeb7e564451be3c3059 Mon Sep 17 00:00:00 2001 From: Yuneng Jiang Date: Mon, 21 Sep 2026 14:16:52 -0700 Subject: [PATCH 3/3] chore(deps): bump soupsieve to 2.9.0 --- uv.lock | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/uv.lock b/uv.lock index 67ec7af756d..7e8c172bf08 100644 --- a/uv.lock +++ b/uv.lock @@ -10,7 +10,7 @@ resolution-markers = [ ] [options] -exclude-newer = "2026-09-18T21:16:34.348134Z" +exclude-newer = "2026-09-18T21:16:47.134955Z" exclude-newer-span = "P3D" [manifest] @@ -9076,11 +9076,11 @@ wheels = [ [[package]] name = "soupsieve" -version = "2.8.4" +version = "2.9" source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/47/2c/0a5f6f8ee0d5589e48c7640213ed5175d52cf540a06725b628cc1a45d6ce/soupsieve-2.8.4.tar.gz", hash = "sha256:e121fd02e975c695e4e9e8774a5ee35d74714b59307868dcc5319ad2d9e3328e", size = 121110, upload-time = "2026-05-24T13:55:57.154Z" } +sdist = { url = "https://files.pythonhosted.org/packages/80/f1/93422647dd7e461f23d254e6b2bfa687a85b53aeb4903fcdbb74474d4584/soupsieve-2.9.tar.gz", hash = "sha256:acee8417325c5653e1377dc31eccad59eb82cbc65942afe6174c53b3aaad63fc", size = 122122, upload-time = "2026-07-19T01:35:18.425Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/5e/f5/0c41cb68dcae6b7de4fac4188a3a9589e21fb31df21ea3a2e888db95e6c9/soupsieve-2.8.4-py3-none-any.whl", hash = "sha256:e7e6b0769c8f51ed59acab6e994b00621096cfb1c640a7509295987388fbaf65", size = 37304, upload-time = "2026-05-24T13:55:55.406Z" }, + { url = "https://files.pythonhosted.org/packages/7b/d6/3185ab5ad1280319b31986898f3206dd7227cd75e293d4dba2a5e6bf27a0/soupsieve-2.9-py3-none-any.whl", hash = "sha256:a2b2c76d67df2382d245409fd71e321a571717e58463efa32ace87dcadac2c12", size = 37387, upload-time = "2026-07-19T01:35:17.106Z" }, ] [[package]]