tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-07-15 14:21:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(vertex_ai): Vertex AI 400 Error: Model used by GenerateContent request (models/gemini-3-*) and CachedContent (models/gemini-3-*) has to be the same (#19193)

Browse Source 
* fix(vertex_ai): include model in context cache key generation

* test(vertex_ai): update context caching tests to verify model in cache key
This commit is contained in:
Anand Kamble
2026-01-17 00:56:15 +05:30
committed by GitHub
parent 3d41f10a81
commit 2c75194b49
2 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
litellm/llms/vertex_ai/context_caching/vertex_ai_context_caching.py
+2 -2
View File
@@ -304,7 +304,7 @@ class ContextCachingEndpoints(VertexBase):
## CHECK IF CACHED ALREADY
generated_cache_key = local_cache_obj.get_cache_key(
messages=cached_messages, tools=tools
messages=cached_messages, tools=tools, model=model
)
google_cache_name = self.check_cache(
cache_key=generated_cache_key,
@@ -433,7 +433,7 @@ class ContextCachingEndpoints(VertexBase):
## CHECK IF CACHED ALREADY
generated_cache_key = local_cache_obj.get_cache_key(
messages=cached_messages, tools=tools
messages=cached_messages, tools=tools, model=model
)
google_cache_name = await self.async_check_cache(
cache_key=generated_cache_key,
tests/test_litellm/llms/vertex_ai/context_caching/test_vertex_ai_context_caching.py
+4 -4
View File
@@ -187,9 +187,9 @@ class TestContextCachingEndpoints:
assert returned_params == optional_params
assert returned_cache == "existing_cache_name"
# Verify cache key was generated with tools
# Verify cache key was generated with tools and model
mock_cache_obj.get_cache_key.assert_called_once_with(
messages=cached_messages, tools=self.sample_tools
messages=cached_messages, tools=self.sample_tools, model="gemini-1.5-pro"
)
@pytest.mark.parametrize(
@@ -460,9 +460,9 @@ class TestContextCachingEndpoints:
assert returned_params == optional_params
assert returned_cache == "existing_cache_name"
# Verify cache key was generated with tools
# Verify cache key was generated with tools and model
mock_cache_obj.get_cache_key.assert_called_once_with(
messages=cached_messages, tools=self.sample_tools
messages=cached_messages, tools=self.sample_tools, model="gemini-1.5-pro"
)
@pytest.mark.asyncio