…d add restart kernel instructions (#993)

* Update openai-agents SDK notebooks to install dependencies quietly and add restart kernel instructions

Co-Authored-By: Alex Reibman <meta.alex.r@gmail.com>

* Remove unnecessary comment about quiet installation

Co-Authored-By: Alex Reibman <meta.alex.r@gmail.com>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Alex Reibman <meta.alex.r@gmail.com>

* added the stream class to

* added test

)

* Enhance instrumentation module with dynamic library detection and version checks. Introduced PROVIDERS and AGENTIC_LIBRARIES dictionaries for managing instrumentors, and implemented get_active_libraries function to identify currently used libraries. Updated InstrumentorLoader to validate library versions before activation. Refactored instrument_all function to prioritize agentic libraries before standard providers.

* Refactor instrumentation module to implement InstrumentationManager for improved package monitoring and dynamic instrumentation. Added methods for managing active instrumentors, handling conflicts between agentic libraries and providers, and monitoring imports. Updated configuration for supported libraries and combined target packages for streamlined instrumentation.

* Enhance instrumentation module by introducing TypedDict for instrumentor configurations, improving type safety for PROVIDERS and AGENTIC_LIBRARIES dictionaries. This change facilitates better structure and clarity in managing instrumentor settings.

* Refactor instrumentation module to remove InstrumentationManager and implement module-level state management for active instrumentors. Introduced helper functions for package instrumentation, monitoring imports, and uninstrumenting providers, enhancing clarity and maintainability of the code. Updated instrumentation logic to handle conflicts between agentic libraries and providers more effectively.

* Refactor instrumentation module to streamline monitoring and uninstrumenting processes. Removed internal helper functions for starting and stopping monitoring, integrating their logic directly into the `instrument_all` and `uninstrument_all` functions for improved clarity and maintainability.

* Refactor instrumentation module by integrating the logic for checking existing imports directly into the `instrument_all` function. This change removes the now-unnecessary `_check_existing_imports` helper function, enhancing code clarity and maintainability while preserving the functionality of monitoring already imported packages.

---------

Co-authored-by: Pratyush Shukla <ps4534@nyu.edu>

This reverts commit 63fdd7f.

added user-agent in header

minor refactor

* correct min version for instrumentation

* get tool calls in the agents sdk

* record all the entities and the llm prompts

* remove duplicate LLM calls

* keep a single agent span

* cleanup

* correct import and variable name

* remove context propagation and fix issue with llm attributes

* linting

* some more cleanup

* its `FUNCTION_SPAN_ATTRIBUTES`

* forgot this one but now we good

* refactor for responses instructions attribute

* fix tests

* get correct library version

* oops

---------

Co-authored-by: Dwij <96073160+Dwij1704@users.noreply.github.com>

* Added the cost attribute in tool decorator along with the tests

* ruff check and tests added

* code cleanup

* minor changes

* updated the testcase

* ruff checks

---------

Co-authored-by: Dwij <96073160+Dwij1704@users.noreply.github.com>

* Added span name customization based on default tags

* added the tags/default tags in the root span

* added the test of tags in the root span

* ruff check :)

* code refactored

* ruff checks

* add `TODO` for converting tags to list

---------

Co-authored-by: Pratyush Shukla <ps4534@nyu.edu>
Co-authored-by: Dwij <96073160+Dwij1704@users.noreply.github.com>

* Implement Google ADK Instrumentation for AgentOps

* Fix import compatibility for NotRequired in instrumentation module by adding a fallback to typing_extensions. This ensures broader compatibility across Python versions.

* Update instrumentation_dependencies to require 'google-adk' instead of 'google-genai' for improved package management.

* Refactor LLM attribute extraction to handle system instructions as role messages. Updated message processing to include proper indexing and role normalization for contents, enhancing clarity and consistency in attribute assignment.

* Refactor attribute assignment in Google ADK instrumentation to use constants for span attributes. This change enhances code clarity and maintainability by replacing string literals with defined constants for agent, LLM, and tool attributes.

* Enhance Google ADK instrumentation by adding 'type' parameter to span creation for agent, LLM, and tool contexts. This improves clarity in span categorization and aligns with the existing attribute assignment structure.

* Refactor Google ADK instrumentation to remove 'type' parameter from span creation for agent, LLM, and tool contexts. This change simplifies span initialization while maintaining clarity in span categorization through attribute assignment.

* refactor version code into `__init__.py`

---------

Co-authored-by: Pratyush Shukla <ps4534@nyu.edu>

* Introduced `start_trace` and `end_trace` functions for user-managed tracing, allowing concurrent traces.

* Enhance tracing functionality by introducing new decorators and improving session handling. Added `trace`, `session`, `agent`, `task`, `workflow`, and `operation` decorators for better instrumentation. Updated `log_trace_url` to include titles for improved logging context. Refactored `Client` initialization trace name and adjusted end trace state handling. Improved error handling during trace logging in `TracingCore` and removed deprecated session decorator usage.

* cleanup

* Enhance `init` function in AgentOps SDK by adding new parameters: `tags`, `auto_init`, `skip_auto_end_session`, and `fail_safe`. Updated documentation to reflect changes and merged `tags` with `default_tags` for improved session management. Refactored client initialization to accommodate new options.

* Refactor legacy session handling by replacing `LegacySession` with `Session` in `agentops` module. This change improves code clarity and aligns with the updated session management approach.

* Enhance unit tests for URL logging in TracingCore and InternalSpanProcessor. Added tests for start and end trace URL logging, handling failures gracefully, and verifying root span tracking. Improved test coverage for session decorators and ensured proper handling of unsampled spans. Refactored existing tests for clarity and consistency.

* Refactor CrewAI workflow instrumentation to enhance span management and attribute tracking. Updated span creation to use dynamic workflow names and improved error handling. Adjusted span kinds from CLIENT to INTERNAL for better clarity in tracing. Streamlined attribute setting for agents and tasks, ensuring accurate logging of results and metrics.

* Refactor force_flush method in TracingCore to remove timeout parameter, simplifying the flush process. Updated logging to indicate completion of the flush operation.

* Refactor Client initialization logic to clarify re-initialization conditions for the API key. Only trigger a warning if a different non-None API key is provided during re-initialization, enhancing the clarity of client behavior.

* Refactor Client initialization to support backward compatibility with legacy session wrapper. Update unit tests to enhance coverage for new session management functionality, including explicit trace handling and decorator behavior. Ensure proper integration between new and legacy APIs for session and trace management.

* Improve authentication error handling in Client and V3Client. Added exception handling for token fetching and response processing, ensuring clearer error logging and re-raising of exceptions for better testability. Updated integration tests to reset client state between tests.

* Refactor integration tests for session concurrency to improve isolation and error handling. Mock API client and tracing core to avoid real authentication during tests. Simplify concurrency test descriptions and ensure proper cleanup of client state between tests.

* Enhance trace management by updating end_trace function to allow ending all active traces when no context is provided. Refactor end_all_sessions to utilize the new end_trace functionality, ensuring legacy global state is cleared. Introduce thread-safe handling of active traces in TracingCore with locking mechanisms for improved concurrency.

* Enhance trace ID handling in TracingCore by adding exception handling for invalid trace IDs. This ensures robustness when dealing with mocked spans or non-integer trace IDs, improving overall trace management reliability.

* revert crewai

* Enhance tracing functionality by adding `trace_name` parameter to configuration and initialization. This allows for customizable trace/session naming, improving trace management and clarity in logs. Updated relevant classes and methods to utilize the new parameter.

* Remove unused span variables in entity decorator function to streamline code and improve clarity.

---------

Co-authored-by: Pratyush Shukla <ps4534@nyu.edu>