braintrustdata · Abhijeet Prasad (AbhiPrasad) · Jul 21, 2026 · Jul 20, 2026 · Jul 21, 2026
diff --git a/py/pyproject.toml b/py/pyproject.toml
@@ -318,45 +318,45 @@ conflicts = [
 [tool.braintrust.matrix]
 
 [tool.braintrust.matrix.openai]
-latest = "openai==2.45.0"
+latest = "openai==2.46.0"
 "1.92.0" = "openai==1.92.0"
 "1.77.0" = "openai==1.77.0"
 "1.71.0" = "openai==1.71.0"
 
 [tool.braintrust.matrix.anthropic]
-latest = "anthropic==0.116.0"
+latest = "anthropic==0.117.0"
 "0.48.0" = "anthropic==0.48.0"
 
 [tool.braintrust.matrix.cohere]
 latest = "cohere==7.0.5"
 "5.0.0" = "cohere==5.0.0"
 
 [tool.braintrust.matrix.openai-agents]
-latest = "openai-agents==0.18.2"
+latest = "openai-agents==0.18.3"
 "0.13.6" = "openai-agents==0.13.6"
 "0.0.19" = "openai-agents==0.0.19"
 
 [tool.braintrust.matrix.litellm]
 # 1.92.0 only publishes Linux wheels through CPython 3.13, but the test
 # matrix also covers Windows and CPython 3.14.
-latest = "litellm==1.91.2"
+latest = "litellm==1.93.0"
 "1.74.0" = "litellm==1.74.0"
 
 [tool.braintrust.matrix.livekit-agents]
-latest = "livekit-agents==1.6.5"
+latest = "livekit-agents==1.6.6"
 "1.3.1" = "livekit-agents==1.3.1"
 
 [tool.braintrust.matrix.claude-agent-sdk]
-latest = "claude-agent-sdk==0.2.116"
+latest = "claude-agent-sdk==0.2.123"
 "0.1.10" = "claude-agent-sdk==0.1.10"
 
 [tool.braintrust.matrix.agno]
-latest = "agno==2.7.2"
+latest = "agno==2.7.4"
 "2.4.0" = "agno==2.4.0"
 "2.1.0" = "agno==2.1.0"
 
 [tool.braintrust.matrix.agentscope]
-latest = "agentscope==2.0.4"
+latest = "agentscope==2.0.4.post1"
 "1.0.0" = "agentscope==1.0.0"
 
 [tool.braintrust.matrix.autogen-agentchat]
@@ -368,15 +368,15 @@ latest = "autogen-ext[openai]==0.7.5"
 "0.7.0" = "autogen-ext[openai]==0.7.0"
 
 [tool.braintrust.matrix.strands-agents]
-latest = "strands-agents==1.47.0"
+latest = "strands-agents==1.48.0"
 "1.20.0" = "strands-agents==1.20.0"
 
 [tool.braintrust.matrix.pydantic-ai-integration]
-latest = "pydantic-ai==2.9.0"
+latest = "pydantic-ai==2.13.0"
 "1.10.0" = "pydantic-ai==1.10.0"
 
 [tool.braintrust.matrix.pydantic-ai-wrap-openai]
-latest = "pydantic-ai==2.9.0"
+latest = "pydantic-ai==2.13.0"
 "1.0.1" = "pydantic-ai==1.0.1"
 "0.1.9" = "pydantic-ai==0.1.9"
 
@@ -389,7 +389,7 @@ latest = "instructor==1.15.4"
 "1.11.0" = "instructor==1.11.0"
 
 [tool.braintrust.matrix.google-genai]
-latest = "google-genai==2.11.0"
+latest = "google-genai==2.12.1"
 "1.75.0" = "google-genai==1.75.0"
 "1.30.0" = "google-genai==1.30.0"
 
@@ -405,11 +405,11 @@ latest = "deepagents==0.6.12"
 # 1.13.0 is the first release with the full causal-id surface (event_id /
 # parent_event_id / started_event_id on BaseEvent) plus the ``usage`` field on
 # LLMCallCompletedEvent that the Braintrust CrewAI integration depends on.
-latest = "crewai==1.15.2"
+latest = "crewai==1.15.4"
 "1.13.0" = "crewai==1.13.0"
 
 [tool.braintrust.matrix.google-adk]
-latest = "google-adk[mcp]==2.4.0"
+latest = "google-adk[mcp]==2.5.0"
 "1.14.1" = "google-adk[mcp]==1.14.1"
 
 [tool.braintrust.matrix.langchain-core]
@@ -421,19 +421,19 @@ latest = "llama-index-core==0.14.23"
 "0.13.0" = "llama-index-core==0.13.0"
 
 [tool.braintrust.matrix.openrouter]
-latest = "openrouter==0.11.23"
+latest = "openrouter==0.11.45"
 "0.6.0" = "openrouter==0.6.0"
 
 [tool.braintrust.matrix.mistralai]
-latest = "mistralai==2.6.0"
+latest = "mistralai==2.7.0"
 "1.12.4" = "mistralai==1.12.4"
 
 [tool.braintrust.matrix.huggingface-hub]
 # Floor pinned to 0.32.0: the earliest release that exposes the
 # ``provider="auto"`` routing mode the integration relies on for multi-
 # provider use, while still keeping the same chat_completion /
 # text_generation / feature_extraction / sentence_similarity method names.
-latest = "huggingface-hub==1.23.0"
+latest = "huggingface-hub==1.24.0"
 "0.32.0" = "huggingface-hub==0.32.0"
 
 [tool.braintrust.matrix.temporalio]
@@ -451,11 +451,11 @@ latest = "pytest==9.1.1"
 latest = "braintrust-core==0.0.59"
 
 [tool.braintrust.matrix.boto3]
-latest = "boto3==1.43.46"
+latest = "boto3==1.43.51"
 "1.34.116" = "boto3==1.34.116"
 
 [tool.braintrust.matrix.botocore]
-latest = "botocore==1.43.46"
+latest = "botocore==1.43.51"
 "1.34.116" = "botocore==1.34.116"
 
 # ---------------------------------------------------------------------------

diff --git a/...intrust/integrations/adk/cassettes/latest/test_adk_binary_data_attachment_conversion.yaml b/...intrust/integrations/adk/cassettes/latest/test_adk_binary_data_attachment_conversion.yaml
@@ -6,62 +6,62 @@ interactions:
       analyze images.\n\nYou are an agent. Your internal name is \"vision_agent\"."}],
       "role": "user"}, "generationConfig": {"maxOutputTokens": 150}}'
     headers:
-      Accept:
+      accept:
       - '*/*'
-      Accept-Encoding:
+      accept-encoding:
       - gzip, deflate
-      Connection:
+      connection:
       - keep-alive
-      Content-Length:
+      content-length:
       - '464'
-      Content-Type:
+      content-type:
       - application/json
-      Host:
+      host:
       - generativelanguage.googleapis.com
       user-agent:
-      - google-genai-sdk/2.8.0 gl-python/3.13.5 google-adk/2.2.0 gl-python/3.13.5
+      - google-genai-sdk/2.11.0 gl-python/3.14.6 google-adk/2.5.0 gl-python/3.14.6
       x-goog-api-client:
-      - google-genai-sdk/2.8.0 gl-python/3.13.5 google-adk/2.2.0 gl-python/3.13.5
+      - google-genai-sdk/2.11.0 gl-python/3.14.6 google-adk/2.5.0 gl-python/3.14.6
     method: POST
     uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-lite:generateContent
   response:
     body:
       string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
-        [\n          {\n            \"text\": \"The image is **red**.\"\n          }\n
+        [\n          {\n            \"text\": \"This image is **red**.\"\n          }\n
         \       ],\n        \"role\": \"model\"\n      },\n      \"finishReason\":
         \"STOP\",\n      \"index\": 0\n    }\n  ],\n  \"usageMetadata\": {\n    \"promptTokenCount\":
         291,\n    \"candidatesTokenCount\": 6,\n    \"totalTokenCount\": 297,\n    \"promptTokensDetails\":
         [\n      {\n        \"modality\": \"TEXT\",\n        \"tokenCount\": 33\n
         \     },\n      {\n        \"modality\": \"IMAGE\",\n        \"tokenCount\":
         258\n      }\n    ],\n    \"serviceTier\": \"standard\"\n  },\n  \"modelVersion\":
-        \"gemini-2.5-flash-lite\",\n  \"responseId\": \"-FUwarC7KoLRjrEPvMLz6Qc\"\n}\n"
+        \"gemini-2.5-flash-lite\",\n  \"responseId\": \"1rpeas3NOYCs1MkPjtDhsAM\"\n}\n"
     headers:
-      Alt-Svc:
+      alt-svc:
       - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Content-Type:
+      content-length:
+      - '643'
+      content-type:
       - application/json; charset=UTF-8
-      Date:
-      - Mon, 15 Jun 2026 19:43:52 GMT
-      Server:
+      date:
+      - Tue, 21 Jul 2026 00:18:31 GMT
+      server:
       - scaffolding on HTTPServer2
-      Server-Timing:
-      - gfet4t7; dur=307
-      Transfer-Encoding:
+      server-timing:
+      - gfet4t7; dur=634
+      transfer-encoding:
       - chunked
-      Vary:
+      vary:
       - Origin
       - X-Origin
       - Referer
-      X-Content-Type-Options:
+      x-content-type-options:
       - nosniff
-      X-Frame-Options:
+      x-frame-options:
       - SAMEORIGIN
-      X-Gemini-Service-Tier:
+      x-gemini-service-tier:
       - standard
-      X-XSS-Protection:
+      x-xss-protection:
       - '0'
-      content-length:
-      - '642'
     status:
       code: 200
       message: OK

diff --git a/py/src/braintrust/integrations/adk/cassettes/latest/test_adk_braintrust_integration.yaml b/py/src/braintrust/integrations/adk/cassettes/latest/test_adk_braintrust_integration.yaml
@@ -9,22 +9,22 @@ interactions:
       {"title": "Location", "type": "string"}}, "required": ["location"], "title":
       "get_weatherParams", "type": "object"}}]}], "generationConfig": {}}'
     headers:
-      Accept:
+      accept:
       - '*/*'
-      Accept-Encoding:
+      accept-encoding:
       - gzip, deflate
-      Connection:
+      connection:
       - keep-alive
-      Content-Length:
+      content-length:
       - '624'
-      Content-Type:
+      content-type:
       - application/json
-      Host:
+      host:
       - generativelanguage.googleapis.com
       user-agent:
-      - google-genai-sdk/2.8.0 gl-python/3.13.5 google-adk/2.2.0 gl-python/3.13.5
+      - google-genai-sdk/2.11.0 gl-python/3.14.6 google-adk/2.5.0 gl-python/3.14.6
       x-goog-api-client:
-      - google-genai-sdk/2.8.0 gl-python/3.13.5 google-adk/2.2.0 gl-python/3.13.5
+      - google-genai-sdk/2.11.0 gl-python/3.14.6 google-adk/2.5.0 gl-python/3.14.6
     method: POST
     uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-lite:generateContent
   response:
@@ -39,34 +39,34 @@ interactions:
         16,\n    \"totalTokenCount\": 100,\n    \"promptTokensDetails\": [\n      {\n
         \       \"modality\": \"TEXT\",\n        \"tokenCount\": 84\n      }\n    ],\n
         \   \"serviceTier\": \"standard\"\n  },\n  \"modelVersion\": \"gemini-2.5-flash-lite\",\n
-        \ \"responseId\": \"9VUwaqDyPM2C-8YPyc_HuAo\"\n}\n"
+        \ \"responseId\": \"1Lpeatu8IeLC-8YPnZj1uQQ\"\n}\n"
     headers:
-      Alt-Svc:
+      alt-svc:
       - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Content-Type:
+      content-length:
+      - '751'
+      content-type:
       - application/json; charset=UTF-8
-      Date:
-      - Mon, 15 Jun 2026 19:43:50 GMT
-      Server:
+      date:
+      - Tue, 21 Jul 2026 00:18:28 GMT
+      server:
       - scaffolding on HTTPServer2
-      Server-Timing:
-      - gfet4t7; dur=298
-      Transfer-Encoding:
+      server-timing:
+      - gfet4t7; dur=280
+      transfer-encoding:
       - chunked
-      Vary:
+      vary:
       - Origin
       - X-Origin
       - Referer
-      X-Content-Type-Options:
+      x-content-type-options:
       - nosniff
-      X-Frame-Options:
+      x-frame-options:
       - SAMEORIGIN
-      X-Gemini-Service-Tier:
+      x-gemini-service-tier:
       - standard
-      X-XSS-Protection:
+      x-xss-protection:
       - '0'
-      content-length:
-      - '751'
     status:
       code: 200
       message: OK
@@ -84,62 +84,62 @@ interactions:
       {"title": "Location", "type": "string"}}, "required": ["location"], "title":
       "get_weatherParams", "type": "object"}}]}], "generationConfig": {}}'
     headers:
-      Accept:
+      accept:
       - '*/*'
-      Accept-Encoding:
+      accept-encoding:
       - gzip, deflate
-      Connection:
+      connection:
       - keep-alive
-      Content-Length:
+      content-length:
       - '944'
-      Content-Type:
+      content-type:
       - application/json
-      Host:
+      host:
       - generativelanguage.googleapis.com
       user-agent:
-      - google-genai-sdk/2.8.0 gl-python/3.13.5 google-adk/2.2.0 gl-python/3.13.5
+      - google-genai-sdk/2.11.0 gl-python/3.14.6 google-adk/2.5.0 gl-python/3.14.6
       x-goog-api-client:
-      - google-genai-sdk/2.8.0 gl-python/3.13.5 google-adk/2.2.0 gl-python/3.13.5
+      - google-genai-sdk/2.11.0 gl-python/3.14.6 google-adk/2.5.0 gl-python/3.14.6
     method: POST
     uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-lite:generateContent
   response:
     body:
       string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
         [\n          {\n            \"text\": \"The weather in San Francisco is sunny
-        with a temperature of 72\xB0F, 45% humidity, and winds of 5 mph NW.\"\n          }\n
-        \       ],\n        \"role\": \"model\"\n      },\n      \"finishReason\":
+        with a temperature of 72\xB0F, humidity at 45%, and wind at 5 mph NW.\"\n
+        \         }\n        ],\n        \"role\": \"model\"\n      },\n      \"finishReason\":
         \"STOP\",\n      \"index\": 0\n    }\n  ],\n  \"usageMetadata\": {\n    \"promptTokenCount\":
         146,\n    \"candidatesTokenCount\": 31,\n    \"totalTokenCount\": 177,\n    \"promptTokensDetails\":
         [\n      {\n        \"modality\": \"TEXT\",\n        \"tokenCount\": 146\n
         \     }\n    ],\n    \"serviceTier\": \"standard\"\n  },\n  \"modelVersion\":
-        \"gemini-2.5-flash-lite\",\n  \"responseId\": \"9lUwav7nGYSD-8YP6MTeyA0\"\n}\n"
+        \"gemini-2.5-flash-lite\",\n  \"responseId\": \"1LpearK9OIin1MkPuMSikAw\"\n}\n"
     headers:
-      Alt-Svc:
+      alt-svc:
       - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Content-Type:
+      content-length:
+      - '656'
+      content-type:
       - application/json; charset=UTF-8
-      Date:
-      - Mon, 15 Jun 2026 19:43:50 GMT
-      Server:
+      date:
+      - Tue, 21 Jul 2026 00:18:29 GMT
+      server:
       - scaffolding on HTTPServer2
-      Server-Timing:
-      - gfet4t7; dur=390
-      Transfer-Encoding:
+      server-timing:
+      - gfet4t7; dur=405
+      transfer-encoding:
       - chunked
-      Vary:
+      vary:
       - Origin
       - X-Origin
       - Referer
-      X-Content-Type-Options:
+      x-content-type-options:
       - nosniff
-      X-Frame-Options:
+      x-frame-options:
       - SAMEORIGIN
-      X-Gemini-Service-Tier:
+      x-gemini-service-tier:
       - standard
-      X-XSS-Protection:
+      x-xss-protection:
       - '0'
-      content-length:
-      - '654'
     status:
       code: 200
       message: OK