Merge pull request #42000 from BerriAI/litellm_cherrypick_1_100_x

fix(bedrock): backport #41870 and the GPT-6 reasoning gate fix to stable/1.100.x for v1.100.2

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
@@ -104,6 +105,7 @@ 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
@@ -292,6 +294,14 @@ 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
+
+    @staticmethod
+    def _is_openai_gpt_reasoning_model(model: str) -> bool:
+        return re.search(r"openai\.gpt-\d", 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.
@@ -422,14 +432,14 @@ class AmazonConverseConfig(BaseConfig):
         Handle the reasoning_effort parameter based on the model type.
 
         - GPT-OSS models: passed through unchanged via additionalModelRequestFields.
-        - OpenAI GPT-5.x models: mapped to ``reasoning.effort`` via additionalModelRequestFields.
+        - OpenAI GPT-5.x and GPT-6 models: mapped to ``reasoning.effort`` via additionalModelRequestFields.
         - Nova 2 models: transformed to reasoningConfig.
         - Anthropic models: mapped to ``thinking`` (and ``output_config.effort`` on
           adaptive Claude 4.6 / 4.7).
         """
         if "gpt-oss" in model:
             optional_params["reasoning_effort"] = reasoning_effort
-        elif "openai.gpt-5" in model:
+        elif self._is_openai_gpt_reasoning_model(model):
             reasoning: Final[BedrockConverseGptReasoningEffortBlock] = {"effort": reasoning_effort}
             optional_params["reasoning"] = reasoning
         elif self._is_nova_2_model(model):
@@ -563,7 +573,11 @@ class AmazonConverseConfig(BaseConfig):
             # only anthropic and mistral support tool choice config. otherwise (E.g. cohere) will fail the call - https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_ToolChoice.html
             supported_params.append("tool_choice")
 
-        if "gpt-oss" in model or "openai.gpt-5" in model or "openai.gpt-5" in base_model:
+        if (
+            "gpt-oss" in model
+            or self._is_openai_gpt_reasoning_model(model)
+            or self._is_openai_gpt_reasoning_model(base_model)
+        ):
             supported_params.append("reasoning_effort")
         elif self._is_nova_2_model(model):
             # Nova 2 models support reasoning_effort (transformed to reasoningConfig)
@@ -874,7 +888,11 @@ 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":
@@ -911,7 +929,7 @@ class AmazonConverseConfig(BaseConfig):
                 optional_params["_parallel_tool_use_config"] = {
                     "tool_choice": {"type": "auto", "disable_parallel_tool_use": not value}
                 }
-            if param == "thinking" and "openai.gpt-5" not in model:
+            if param == "thinking" and not self._is_openai_gpt_reasoning_model(model):
                 if (
                     isinstance(value, dict)
                     and value.get("type") == "adaptive"

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "litellm"
-version = "1.100.1"
+version = "1.100.2"
 description = "Library to easily interface with LLM API providers"
 readme = "README.md"
 requires-python = ">=3.10, <3.15"
@@ -311,7 +311,7 @@ members = ["enterprise", "litellm-proxy-extras"]
 profile = "black"
 
 [tool.commitizen]
-version = "1.100.1"
+version = "1.100.2"
 version_files = [
     "pyproject.toml:^version",
 ]

tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py

@@ -375,12 +375,42 @@ 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",
     [
         "us.openai.gpt-5.6-sol",
         "global.openai.gpt-5.6-terra",
         "bedrock/converse/us.openai.gpt-5.6-luna",
+        "us.openai.gpt-6-astra",
+        "bedrock/converse/global.openai.gpt-6-astra",
     ],
 )
 def test_reasoning_effort_maps_to_reasoning_effort_for_openai_gpt5_converse(model, local_model_cost_map):
@@ -411,6 +441,7 @@ def test_reasoning_effort_maps_to_reasoning_effort_for_openai_gpt5_converse(mode
     [
         "us.openai.gpt-5.6-sol",
         "bedrock/converse/global.openai.gpt-5.6-luna",
+        "us.openai.gpt-6-astra",
     ],
 )
 def test_openai_gpt5_converse_never_forwards_thinking(model, local_model_cost_map):

uv.lock

@@ -4266,7 +4266,7 @@ wheels = [
 
 [[package]]
 name = "litellm"
-version = "1.100.1"
+version = "1.100.2"
 source = { editable = "." }
 dependencies = [
     { name = "aiohttp" },