From abc38935fa8dc0f1e9c0b33d2c4256e22f76e33d Mon Sep 17 00:00:00 2001
From: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Date: Sat, 11 Jul 2026 12:11:17 -0700
Subject: [PATCH] fix(anthropic): override custom_llm_provider in provider
 config subclasses so capability probes use the right namespace

---
 litellm/llms/anthropic/common_utils.py        | 30 +++++++++-
 .../anthropic/messages_transformation.py      |  4 ++
 .../llms/databricks/chat/transformation.py    |  4 ++
 .../github_copilot/messages/transformation.py |  4 ++
 .../openai_like/messages/transformation.py    |  4 ++
 .../transformation.py                         |  4 ++
 ...azure_anthropic_messages_transformation.py | 56 +++++++++++++++++++
 .../test_databricks_chat_transformation.py    |  7 +++
 ..._github_copilot_messages_transformation.py |  8 +++
 ..._like_anthropic_messages_transformation.py | 18 ++++++
 ...artner_models_anthropic_messages_config.py | 56 +++++++++++++++++++
 11 files changed, 192 insertions(+), 3 deletions(-)

diff --git a/litellm/llms/anthropic/common_utils.py b/litellm/llms/anthropic/common_utils.py
index cc5db407e3f..0bcf34a45d6 100644
--- a/litellm/llms/anthropic/common_utils.py
+++ b/litellm/llms/anthropic/common_utils.py
@@ -359,16 +359,40 @@ class AnthropicModelInfo(BaseLLMModelInfo):
         value = litellm.model_cost.get(model, {}).get(key)
         return value if isinstance(value, bool) else None
 
+    @staticmethod
+    def _get_provider_resolved_capability(model: str, key: str, custom_llm_provider: str) -> Optional[bool]:
+        """Resolve boolean capability ``key`` for ``model`` under the caller's provider.
+
+        Returns the flag when the provider-aware lookup resolves ``model`` to an
+        entry (or fallback rule) that sets it explicitly, and ``None`` when the
+        model does not resolve under that provider or the resolved entry has no
+        opinion on ``key``.
+        """
+        from litellm.utils import _get_model_info_helper
+
+        try:
+            resolved_model, resolved_provider, _, _ = litellm.get_llm_provider(
+                model=model, custom_llm_provider=custom_llm_provider
+            )
+            value = _get_model_info_helper(model=resolved_model, custom_llm_provider=resolved_provider).get(key)
+        except Exception:  # noqa: BLE001  # _get_model_info_helper raises bare Exception for unmapped models
+            return None
+        return value if isinstance(value, bool) else None
+
     @staticmethod
     def _supports_model_capability(model: str, key: str, custom_llm_provider: str) -> bool:
         """Check a boolean capability ``key`` in the model map under the caller's provider.
 
-        The provider-aware lookup makes exact provider-namespaced entries (e.g. the
-        Bedrock ``global.anthropic.*`` ids) authoritative; the raw model-map walk
-        remains as a provider-less backstop for alias forms the lookup misses.
+        The provider-aware lookup is authoritative when it resolves an explicit flag,
+        so ``key: false`` on the provider-namespaced entry wins over every fallback.
+        Otherwise ``_supports_factory``'s provider-level fallbacks and the raw
+        model-map walk remain as backstops for alias forms the lookup misses.
         """
         from litellm.utils import _supports_factory
 
+        resolved = AnthropicModelInfo._get_provider_resolved_capability(model, key, custom_llm_provider)
+        if resolved is not None:
+            return resolved
         try:
             if _supports_factory(
                 model=model,
diff --git a/litellm/llms/azure_ai/anthropic/messages_transformation.py b/litellm/llms/azure_ai/anthropic/messages_transformation.py
index 1de18701a2f..8cee35989af 100644
--- a/litellm/llms/azure_ai/anthropic/messages_transformation.py
+++ b/litellm/llms/azure_ai/anthropic/messages_transformation.py
@@ -21,6 +21,10 @@ class AzureAnthropicMessagesConfig(AnthropicMessagesConfig):
     and Azure endpoint format.
     """
 
+    @property
+    def custom_llm_provider(self) -> Optional[str]:
+        return "azure_ai"
+
     def should_strip_billing_metadata(self) -> bool:
         return True
 
diff --git a/litellm/llms/databricks/chat/transformation.py b/litellm/llms/databricks/chat/transformation.py
index 9b53dee3453..9c05899c719 100644
--- a/litellm/llms/databricks/chat/transformation.py
+++ b/litellm/llms/databricks/chat/transformation.py
@@ -181,6 +181,10 @@ class DatabricksConfig(DatabricksBase, OpenAILikeChatConfig, AnthropicConfig):
             if key != "self" and value is not None:
                 setattr(self.__class__, key, value)
 
+    @property
+    def custom_llm_provider(self) -> Optional[str]:
+        return "databricks"
+
     @classmethod
     def get_config(cls):
         return super().get_config()
diff --git a/litellm/llms/github_copilot/messages/transformation.py b/litellm/llms/github_copilot/messages/transformation.py
index fb3f0a4e159..4d7b003c48f 100644
--- a/litellm/llms/github_copilot/messages/transformation.py
+++ b/litellm/llms/github_copilot/messages/transformation.py
@@ -25,6 +25,10 @@ class GithubCopilotAnthropicMessagesConfig(AnthropicMessagesConfig):
         super().__init__()
         self.authenticator = Authenticator()
 
+    @property
+    def custom_llm_provider(self) -> Optional[str]:
+        return "github_copilot"
+
     def handles_web_search_natively(self) -> bool:
         """
         Copilot's /v1/messages endpoint does not execute ``web_search`` tools, so
diff --git a/litellm/llms/openai_like/messages/transformation.py b/litellm/llms/openai_like/messages/transformation.py
index 4963bcca9ac..0d593d8d0f4 100644
--- a/litellm/llms/openai_like/messages/transformation.py
+++ b/litellm/llms/openai_like/messages/transformation.py
@@ -85,6 +85,10 @@ class JSONProviderAnthropicMessagesConfig(OpenAILikeAnthropicMessagesConfig):
         super().__init__()
         self._provider = provider
 
+    @property
+    def custom_llm_provider(self) -> Optional[str]:
+        return self._provider.slug
+
     def should_strip_billing_metadata(self) -> bool:
         return True
 
diff --git a/litellm/llms/vertex_ai/vertex_ai_partner_models/anthropic/experimental_pass_through/transformation.py b/litellm/llms/vertex_ai/vertex_ai_partner_models/anthropic/experimental_pass_through/transformation.py
index 8566496bf9c..de72795cabc 100644
--- a/litellm/llms/vertex_ai/vertex_ai_partner_models/anthropic/experimental_pass_through/transformation.py
+++ b/litellm/llms/vertex_ai/vertex_ai_partner_models/anthropic/experimental_pass_through/transformation.py
@@ -17,6 +17,10 @@ from ..output_params_utils import sanitize_vertex_anthropic_output_params
 
 
 class VertexAIPartnerModelsAnthropicMessagesConfig(AnthropicMessagesConfig, VertexBase):
+    @property
+    def custom_llm_provider(self) -> Optional[str]:
+        return "vertex_ai"
+
     def should_strip_billing_metadata(self) -> bool:
         return True
 
diff --git a/tests/test_litellm/llms/azure_ai/claude/test_azure_anthropic_messages_transformation.py b/tests/test_litellm/llms/azure_ai/claude/test_azure_anthropic_messages_transformation.py
index 5983597196a..5e9af6bd34d 100644
--- a/tests/test_litellm/llms/azure_ai/claude/test_azure_anthropic_messages_transformation.py
+++ b/tests/test_litellm/llms/azure_ai/claude/test_azure_anthropic_messages_transformation.py
@@ -331,3 +331,59 @@ class TestProviderConfigManagerAzureAnthropicMessages:
         )
 
         assert config is None
+
+
+@pytest.fixture
+def local_model_cost_map(monkeypatch):
+    """Force the bundled backup cost map so capability flags match this branch."""
+    import litellm
+
+    original = litellm.model_cost
+    monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
+    litellm.model_cost = litellm.get_model_cost_map(url="")
+    litellm.get_model_info.cache_clear()
+    try:
+        yield
+    finally:
+        litellm.model_cost = original
+        litellm.get_model_info.cache_clear()
+
+
+def test_messages_thinking_shape_follows_exact_azure_entry_flag(local_model_cost_map, monkeypatch):
+    """The Azure messages config must probe capabilities under ``azure_ai`` so an
+    operator setting ``supports_adaptive_thinking: false`` on the exact
+    ``azure_ai/claude-opus-4-8`` entry beats the unmodified ``anthropic`` entry.
+    With the inherited ``"anthropic"`` provider default the flip was ignored and
+    the transform kept emitting ``thinking.type='adaptive'``."""
+    import litellm
+
+    config = AzureAnthropicMessagesConfig()
+
+    def transform():
+        return config.transform_anthropic_messages_request(
+            model="claude-opus-4-8",
+            messages=[{"role": "user", "content": "Hello"}],
+            anthropic_messages_optional_request_params={
+                "max_tokens": 4096,
+                "reasoning_effort": "medium",
+            },
+            litellm_params=GenericLiteLLMParams(),
+            headers={},
+        )
+
+    result = transform()
+    assert result.get("thinking") == {"type": "adaptive"}
+    assert result.get("output_config") == {"effort": "medium"}
+
+    monkeypatch.setitem(
+        litellm.model_cost["azure_ai/claude-opus-4-8"], "supports_adaptive_thinking", False
+    )
+    litellm.get_model_info.cache_clear()
+    assert litellm.model_cost["claude-opus-4-8"]["supports_adaptive_thinking"] is True
+
+    flipped = transform()
+    thinking = flipped.get("thinking")
+    assert isinstance(thinking, dict)
+    assert thinking.get("type") == "enabled"
+    assert isinstance(thinking.get("budget_tokens"), int)
+    assert "output_config" not in flipped
diff --git a/tests/test_litellm/llms/databricks/chat/test_databricks_chat_transformation.py b/tests/test_litellm/llms/databricks/chat/test_databricks_chat_transformation.py
index cfdb76a97f4..00f3e7a6faf 100644
--- a/tests/test_litellm/llms/databricks/chat/test_databricks_chat_transformation.py
+++ b/tests/test_litellm/llms/databricks/chat/test_databricks_chat_transformation.py
@@ -416,3 +416,10 @@ def test_transform_request_keeps_parallel_tool_calls_for_claude():
     )["messages"]
 
     assert len([m for m in result if m.get("role") == "assistant"]) == 1
+
+
+def test_databricks_config_probes_capabilities_under_databricks_namespace():
+    """Inherited AnthropicConfig capability probes read ``self.custom_llm_provider``;
+    without this override they probed the ``anthropic`` cost-map namespace and
+    ignored the exact ``databricks/databricks-claude-*`` entries."""
+    assert DatabricksConfig().custom_llm_provider == "databricks"
diff --git a/tests/test_litellm/llms/github_copilot/messages/test_github_copilot_messages_transformation.py b/tests/test_litellm/llms/github_copilot/messages/test_github_copilot_messages_transformation.py
index 01787c07d27..8ed84b3ed8d 100644
--- a/tests/test_litellm/llms/github_copilot/messages/test_github_copilot_messages_transformation.py
+++ b/tests/test_litellm/llms/github_copilot/messages/test_github_copilot_messages_transformation.py
@@ -326,3 +326,11 @@ def test_github_copilot_config_does_not_handle_web_search_natively():
 
     assert GithubCopilotAnthropicMessagesConfig().handles_web_search_natively() is False
     assert AnthropicMessagesConfig().handles_web_search_natively() is True
+
+
+def test_github_copilot_messages_config_probes_capabilities_under_copilot_namespace():
+    """Capability probes in the shared pass-through helpers read
+    ``self.custom_llm_provider``; without this override they probed the
+    ``anthropic`` namespace and ignored the exact ``github_copilot/claude-*``
+    cost-map entries."""
+    assert GithubCopilotAnthropicMessagesConfig().custom_llm_provider == "github_copilot"
diff --git a/tests/test_litellm/llms/openai_like/messages/test_openai_like_anthropic_messages_transformation.py b/tests/test_litellm/llms/openai_like/messages/test_openai_like_anthropic_messages_transformation.py
index 534d7aefda4..33e677b000e 100644
--- a/tests/test_litellm/llms/openai_like/messages/test_openai_like_anthropic_messages_transformation.py
+++ b/tests/test_litellm/llms/openai_like/messages/test_openai_like_anthropic_messages_transformation.py
@@ -299,3 +299,21 @@ def test_anthropic_beta_survives_provider_filter_on_passthrough_path(config):
 
     stripped = update_headers_with_filtered_beta(headers=dict(headers), provider="openai")
     assert "anthropic-beta" not in stripped
+
+
+def test_json_provider_messages_config_probes_capabilities_under_provider_slug():
+    """Capability probes in the shared pass-through helpers read
+    ``self.custom_llm_provider``. The JSON-provider config knows its slug, so it
+    must expose it; the generic OpenAI-like config has no class-level namespace
+    and keeps the inherited ``anthropic`` default."""
+    from litellm.llms.openai_like.json_loader import SimpleProviderConfig
+    from litellm.llms.openai_like.messages.transformation import (
+        JSONProviderAnthropicMessagesConfig,
+    )
+
+    provider = SimpleProviderConfig(
+        slug="exampleprovider",
+        data={"base_url": "https://api.example.com/v1", "api_key_env": "EXAMPLE_API_KEY"},
+    )
+    assert JSONProviderAnthropicMessagesConfig(provider).custom_llm_provider == "exampleprovider"
+    assert OpenAILikeAnthropicMessagesConfig().custom_llm_provider == "anthropic"
diff --git a/tests/test_litellm/llms/vertex_ai/vertex_ai_partner_models/anthropic/test_vertex_ai_partner_models_anthropic_messages_config.py b/tests/test_litellm/llms/vertex_ai/vertex_ai_partner_models/anthropic/test_vertex_ai_partner_models_anthropic_messages_config.py
index bfd37f73b2d..ce770221ceb 100644
--- a/tests/test_litellm/llms/vertex_ai/vertex_ai_partner_models/anthropic/test_vertex_ai_partner_models_anthropic_messages_config.py
+++ b/tests/test_litellm/llms/vertex_ai/vertex_ai_partner_models/anthropic/test_vertex_ai_partner_models_anthropic_messages_config.py
@@ -509,3 +509,59 @@ def test_vertex_claude_completion_does_not_mutate_shared_extra_headers():
     assert (
         shared_extra_headers == {}
     ), "extra_headers must not be mutated by completion()"
+
+
+@pytest.fixture
+def local_model_cost_map(monkeypatch):
+    """Force the bundled backup cost map so capability flags match this branch."""
+    import litellm
+
+    original = litellm.model_cost
+    monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
+    litellm.model_cost = litellm.get_model_cost_map(url="")
+    litellm.get_model_info.cache_clear()
+    try:
+        yield
+    finally:
+        litellm.model_cost = original
+        litellm.get_model_info.cache_clear()
+
+
+def test_messages_thinking_shape_follows_exact_vertex_entry_flag(local_model_cost_map, monkeypatch):
+    """The Vertex messages config must probe capabilities under ``vertex_ai`` so an
+    operator setting ``supports_adaptive_thinking: false`` on the exact
+    ``vertex_ai/claude-opus-4-8`` entry beats the unmodified ``anthropic`` entry.
+    With the inherited ``"anthropic"`` provider default the flip was ignored and
+    the transform kept emitting ``thinking.type='adaptive'``."""
+    import litellm
+
+    config = VertexAIPartnerModelsAnthropicMessagesConfig()
+
+    def transform():
+        return config.transform_anthropic_messages_request(
+            model="claude-opus-4-8",
+            messages=[{"role": "user", "content": "Hello"}],
+            anthropic_messages_optional_request_params={
+                "max_tokens": 4096,
+                "reasoning_effort": "medium",
+            },
+            litellm_params=GenericLiteLLMParams(),
+            headers={},
+        )
+
+    result = transform()
+    assert result.get("thinking") == {"type": "adaptive"}
+    assert result.get("output_config") == {"effort": "medium"}
+
+    monkeypatch.setitem(
+        litellm.model_cost["vertex_ai/claude-opus-4-8"], "supports_adaptive_thinking", False
+    )
+    litellm.get_model_info.cache_clear()
+    assert litellm.model_cost["claude-opus-4-8"]["supports_adaptive_thinking"] is True
+
+    flipped = transform()
+    thinking = flipped.get("thinking")
+    assert isinstance(thinking, dict)
+    assert thinking.get("type") == "enabled"
+    assert isinstance(thinking.get("budget_tokens"), int)
+    assert "output_config" not in flipped