Merge branch 'main' into langchain

Author: nirga

.cz.toml

@@ -4,7 +4,7 @@ tag_format = "v$version"
 version_scheme = "pep440"
 major_version_zero = true
 update_changelog_on_bump = true
-version = "0.49.1"
+version = "0.49.7"
 version_files = [
     "packages/opentelemetry-instrumentation-mcp/pyproject.toml:^version",
     "packages/opentelemetry-instrumentation-mcp/opentelemetry/instrumentation/mcp/version.py",

.github/workflows/ci.yml

@@ -74,6 +74,7 @@ jobs:
         run: npm cache clean --force || true
       - run: npx nx affected -t install --with dev
       - run: npx nx affected -t lint --parallel=3
+      - run: npx nx affected -t type-check --parallel=3
 
   build-packages:
     name: Build Packages

CHANGELOG.md

@@ -1,3 +1,48 @@
+## v0.49.7 (2025-12-08)
+
+### Fix
+
+- **exp**: Add a real agent example (#3507)
+- **evals**: Add agent evaluators to made by traceloop (#3505)
+- **exp**: Add made by traceloop evaluators (#3503)
+- **traceloop-sdk**: Fixes gRPC exporter initialisation with insecure OTLP (#3481)
+
+## v0.49.6 (2025-12-01)
+
+### Fix
+
+- **agno**: add streaming support for Agent.run() and Agent.arun() (#3483)
+
+## v0.49.5 (2025-11-27)
+
+### Fix
+
+- **openai**: responses instrumentation broken traces for async streaming (#3475)
+- **mcp**: remove faulty logic of trying to deduce HTTP errors (#3477)
+
+## v0.49.4 (2025-11-27)
+
+### Fix
+
+- **exp**: Add run in github experiment  (#3459)
+
+## v0.49.3 (2025-11-26)
+
+### Fix
+
+- **openai**: recognize NOT_GIVEN and Omit (#3473)
+- **dataset**: add support for file cells in datasets with upload and external URL linking capabilities (#3462)
+- **openai**: report request attributes in responses API instrumentation (#3471)
+- **sdk**: crewai tracing provider conflict (#3470)
+- **sdk**: watsonx warning on initialization (#3469)
+- **traceloop-sdk**: add type-checking support with mypy (#3463)
+
+## v0.49.2 (2025-11-25)
+
+### Fix
+
+- **sdk**: remove posthog (#3466)
+
 ## v0.49.1 (2025-11-24)
 
 ### Fix

README.md

@@ -117,53 +117,53 @@ See [our docs](https://traceloop.com/docs/openllmetry/integrations/exporting) fo
 
 OpenLLMetry can instrument everything that [OpenTelemetry already instruments](https://github.com/open-telemetry/opentelemetry-python-contrib/tree/main/instrumentation) - so things like your DB, API calls, and more. On top of that, we built a set of custom extensions that instrument things like your calls to OpenAI or Anthropic, or your Vector DB like Chroma, Pinecone, Qdrant or Weaviate.
 
-- ✅ [OpenAI / Azure OpenAI](https://openai.com/)
+- ✅ [Aleph Alpha](https://www.aleph-alpha.com/)
 - ✅ [Anthropic](https://www.anthropic.com/)
-- ✅ [Cohere](https://cohere.com/)
-- ✅ [Ollama](https://ollama.com/)
-- ✅ [Mistral AI](https://mistral.ai/)
-- ✅ [HuggingFace](https://huggingface.co/)
 - ✅ [Bedrock (AWS)](https://aws.amazon.com/bedrock/)
-- ✅ [SageMaker (AWS)](https://aws.amazon.com/sagemaker/)
-- ✅ [Replicate](https://replicate.com/)
-- ✅ [Vertex AI (GCP)](https://cloud.google.com/vertex-ai)
+- ✅ [Cohere](https://cohere.com/)
 - ✅ [Google Generative AI (Gemini)](https://ai.google/)
+- ✅ [Groq](https://groq.com/)
+- ✅ [HuggingFace](https://huggingface.co/)
 - ✅ [IBM Watsonx AI](https://www.ibm.com/watsonx)
+- ✅ [Mistral AI](https://mistral.ai/)
+- ✅ [Ollama](https://ollama.com/)
+- ✅ [OpenAI / Azure OpenAI](https://openai.com/)
+- ✅ [Replicate](https://replicate.com/)
+- ✅ [SageMaker (AWS)](https://aws.amazon.com/sagemaker/)
 - ✅ [Together AI](https://together.xyz/)
-- ✅ [Aleph Alpha](https://www.aleph-alpha.com/)
-- ✅ [Groq](https://groq.com/)
+- ✅ [Vertex AI (GCP)](https://cloud.google.com/vertex-ai)
 - ✅ [WRITER](https://writer.com/)
 
 ### Vector DBs
 
 - ✅ [Chroma](https://www.trychroma.com/)
+- ✅ [LanceDB](https://lancedb.com/)
+- ✅ [Marqo](https://marqo.ai/)
+- ✅ [Milvus](https://milvus.io/)
 - ✅ [Pinecone](https://www.pinecone.io/)
 - ✅ [Qdrant](https://qdrant.tech/)
 - ✅ [Weaviate](https://weaviate.io/)
-- ✅ [Milvus](https://milvus.io/)
-- ✅ [Marqo](https://marqo.ai/)
-- ✅ [LanceDB](https://lancedb.com/)
 
 ### Frameworks
 
+- ✅ [Agno](https://github.com/agno-agi/agno)
+- ✅ [AWS Strands](https://strandsagents.com/) (built-in OTEL support)
+- ✅ [CrewAI](https://docs.crewai.com/introduction)
+- ✅ [Haystack](https://haystack.deepset.ai/integrations/traceloop)
 - ✅ [LangChain](https://python.langchain.com/docs/introduction/)
+- ✅ [Langflow](https://docs.langflow.org/)
 - ✅ [LangGraph](https://langchain-ai.github.io/langgraph/concepts/why-langgraph/)
-- ✅ [LlamaIndex](https://docs.llamaindex.ai/en/stable/module_guides/observability/observability.html#openllmetry)
-- ✅ [Haystack](https://haystack.deepset.ai/integrations/traceloop)
 - ✅ [LiteLLM](https://docs.litellm.ai/docs/observability/opentelemetry_integration)
-- ✅ [CrewAI](https://docs.crewai.com/introduction)
+- ✅ [LlamaIndex](https://docs.llamaindex.ai/en/stable/module_guides/observability/observability.html#openllmetry)
 - ✅ [OpenAI Agents](https://openai.github.io/openai-agents-python/)
-- ✅ [Langflow](https://docs.langflow.org/)
 
 ### Protocol
 
 - ✅ [MCP](https://modelcontextprotocol.io/)
 
 ## 🔎 Telemetry
 
-The SDK provided with OpenLLMetry (not the instrumentations) contains a telemetry feature that collects **anonymous** usage information.
-
-You can opt out of telemetry by setting the `TRACELOOP_TELEMETRY` environment variable to `FALSE`, or passing `telemetry_enabled=False` to the `Traceloop.init()` function.
+We no longer log or collect any telemetry in the SDK or in the instrumentations. Make sure to bump to v0.49.2 and above.
 
 ### Why we collect telemetry