1811 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Greyson LaLonde	9e75055c3e	chore: adjust cassette dir and regenerate openai	2025-11-08 02:26:18 -05:00
Greyson LaLonde	b9bc5714c3	chore: delete all cassettes and update conftest	2025-11-08 01:54:25 -05:00
Greyson LaLonde	996c53228b	chore: organize pyproject, update pytest ini	2025-11-08 01:50:29 -05:00
Greyson LaLonde	d0d22038f5	chore: remove telemetry mocks	2025-11-07 17:28:32 -05:00
Greyson LaLonde	2ba0434eb8	Merge branch 'main' into gl/chore/pytest-vcr-cassette-updates	2025-11-07 17:09:45 -05:00
Greyson Lalonde	cad3251721	chore: delete cassettes and make vcr_config session scope	2025-11-07 17:07:11 -05:00
Greyson Lalonde	19f4ef0982	chore: remove decorator kwarg to ensure global conftest applies	2025-11-07 17:01:30 -05:00
Greyson Lalonde	54f8cc685f	chore: update pytest-vcr config	2025-11-07 17:00:28 -05:00
Lorenze Jay	0f1c173d02	feat: bump versions to 1.4.1 (#3862) ... * feat: bump versions to 1.4.1 * chore: update crewAI tools dependency to version 1.4.1 in project templates 1.4.1	2025-11-07 11:19:07 -08:00
Greyson LaLonde	19c5b9a35e	fix: properly handle agent max iterations ... fixes #3847	2025-11-07 13:54:11 -05:00
Greyson LaLonde	1ed307b58c	fix: route llm model syntax to litellm ... * fix: route llm model syntax to litellm * wip: add list of supported models	2025-11-07 13:34:15 -05:00
Lorenze Jay	d29867bbb6	chore: update version numbers to 1.4.0 1.4.0	2025-11-06 23:04:44 -05:00
Lorenze Jay	b2c278ed22	refactor: improve MCP tool execution handling with concurrent futures (#3854) ... - Enhanced the MCP tool execution in both synchronous and asynchronous contexts by utilizing for better event loop management. - Updated error handling to provide clearer messages for connection issues and task cancellations. - Added tests to validate MCP tool execution in both sync and async scenarios, ensuring robust functionality across different contexts.	2025-11-06 19:28:08 -08:00
Greyson LaLonde	f6aed9798b	feat: allow non-ast plot routes	2025-11-06 21:17:29 -05:00
Greyson LaLonde	40a2d387a1	fix: keep stopwords updated	2025-11-06 21:10:25 -05:00
Lorenze Jay	6f36d7003b	Lorenze/feat mcp first class support (#3850) ... * WIP transport support mcp * refactor: streamline MCP tool loading and error handling * linted * Self type from typing with typing_extensions in MCP transport modules * added tests for mcp setup * added tests for mcp setup * docs: enhance MCP overview with detailed integration examples and structured configurations * feat: implement MCP event handling and logging in event listener and client - Added MCP event types and handlers for connection and tool execution events. - Enhanced MCPClient to emit events on connection status and tool execution. - Updated ConsoleFormatter to handle MCP event logging. - Introduced new MCP event types for better integration and monitoring.	2025-11-06 17:45:16 -08:00
Greyson LaLonde	9e5906c52f	feat: add pydantic validation dunder to BaseInterceptor	2025-11-06 15:27:07 -05:00
Lorenze Jay	fc521839e4	Lorenze/fix duplicating doc ids for knowledge (#3840) ... * fix: update document ID handling in ChromaDB utility functions to use SHA-256 hashing and include index for uniqueness * test: add tests for hash-based ID generation in ChromaDB utility functions * drop idx for preventing dups, upsert should handle dups * fix: update document ID extraction logic in ChromaDB utility functions to check for doc_id at the top level of the document * fix: enhance document ID generation in ChromaDB utility functions to deduplicate documents and ensure unique hash-based IDs without suffixes * fix: improve error handling and document ID generation in ChromaDB utility functions to ensure robust processing and uniqueness	2025-11-06 10:59:52 -08:00
Greyson LaLonde	e4cc9a664c	fix: handle unpickleable values in flow state	2025-11-06 01:29:21 -05:00
Greyson LaLonde	7e6171d5bc	fix: ensure lite agents course-correct on validation errors ... * fix: ensure lite agents course-correct on validation errors * chore: update cassettes and test expectations * fix: ensure multiple guardrails propogate	2025-11-05 19:02:11 -05:00
Greyson LaLonde	61ad1fb112	feat: add support for llm message interceptor hooks	2025-11-05 11:38:44 -05:00
Greyson LaLonde	54710a8711	fix: hash callback args correctly to ensure caching works	2025-11-05 07:19:09 -05:00
Lucas Gomide	5abf976373	fix: allow adding RAG source content from valid URLs (#3831)	2025-11-04 07:58:40 -05:00
Greyson LaLonde	329567153b	fix: make plot node selection smoother	2025-11-03 07:49:31 -05:00
Greyson LaLonde	60332e0b19	feat: cache i18n prompts for efficient use	2025-11-03 07:39:05 -05:00
Lorenze Jay	40932af3fa	feat: bump versions to 1.3.0 (#3820) ... * feat: bump versions to 1.3.0 * chore: update crew and flow templates to use crewai[tools] version 1.3.0 1.3.0	2025-10-31 18:54:02 -07:00
Greyson LaLonde	e134e5305b	Gl/feat/a2a refactor (#3793) ... * feat: agent metaclass, refactor a2a to wrappers * feat: a2a schemas and utils * chore: move agent class, update imports * refactor: organize imports to avoid circularity, add a2a to console * feat: pass response_model through call chain * feat: add standard openapi spec serialization to tools and structured output * feat: a2a events * chore: add a2a to pyproject * docs: minimal base for learn docs * fix: adjust a2a conversation flow, allow llm to decide exit until max_retries * fix: inject agent skills into initial prompt * fix: format agent card as json in prompt * refactor: simplify A2A agent prompt formatting and improve skill display * chore: wide cleanup * chore: cleanup logic, add auth cache, use json for messages in prompt * chore: update docs * fix: doc snippets formatting * feat: optimize A2A agent card fetching and improve error reporting * chore: move imports to top of file * chore: refactor hasattr check * chore: add httpx-auth, update lockfile * feat: create base public api * chore: cleanup modules, add docstrings, types * fix: exclude extra fields in prompt * chore: update docs * tests: update to correct import * chore: lint for ruff, add missing import * fix: tweak openai streaming logic for response model * tests: add reimport for test * tests: add reimport for test * fix: don't set a2a attr if not set * fix: don't set a2a attr if not set * chore: update cassettes * tests: fix tests * fix: use instructor and dont pass response_format for litellm * chore: consolidate event listeners, add typing * fix: address race condition in test, update cassettes * tests: add correct mocks, rerun cassette for json * tests: update cassette * chore: regenerate cassette after new run * fix: make token manager access-safe * fix: make token manager access-safe * merge * chore: update test and cassete for output pydantic * fix: tweak to disallow deadlock * chore: linter * fix: adjust event ordering for threading * fix: use conditional for batch check * tests: tweak for emission * tests: simplify api + event check * fix: ensure non-function calling llms see json formatted string * tests: tweak message comparison * fix: use internal instructor for litellm structure responses --------- Co-authored-by: Mike Plachta <mike@crewai.com>	2025-10-31 18:42:03 -07:00
Greyson LaLonde	e229ef4e19	refactor: improve flow handling, typing, and logging; update UI and tests ... fix: refine nested flow conditionals and ensure router methods and routes are fully parsed fix: improve docstrings, typing, and logging coverage across all events feat: update flow.plot feature with new UI enhancements chore: apply Ruff linting, reorganize imports, and remove deprecated utilities/files chore: split constants and utils, clean JS comments, and add typing for linters tests: strengthen test coverage for flow execution paths and router logic	2025-10-31 21:15:06 -04:00
Greyson LaLonde	2e9eb8c32d	fix: refactor use_stop_words to property, add check for stop words	2025-10-29 19:14:01 +01:00
Lucas Gomide	4ebb5114ed	Fix Firecrawl tools & adding tests (#3810) ... * fix: fix Firecrawl Scrape tool * fix: fix Firecrawl Search tool * fix: fix Firecrawl Website tool * tests: adding tests for Firecrawl	2025-10-29 13:37:57 -04:00
Daniel Barreto	70b083945f	Enhance QdrantVectorSearchTool (#3806)	2025-10-28 13:42:40 -04:00
Tony Kipkemboi	410db1ff39	docs: migrate embedder→embedding_model and require vectordb across tool docs; add provider examples (en/ko/pt-BR) (#3804) ... * docs(tools): migrate embedder->embedding_model, require vectordb; add Chroma/Qdrant examples across en/ko/pt-BR PDF/TXT/XML/MDX/DOCX/CSV/Directory docs * docs(observability): apply latest Datadog tweaks in ko and pt-BR	2025-10-27 13:29:21 -04:00
Lorenze Jay	5d6b4c922b	feat: bump versions to 1.2.1 (#3800) ... * feat: bump versions to 1.2.1 * updated templates too 1.2.1	2025-10-27 09:12:04 -07:00
Lucas Gomide	b07c0fc45c	docs: describe mandatory env-var to call Platform tools for each integration (#3803)	2025-10-27 10:01:41 -04:00
Sam Brenner	97853199c7	Add Datadog Integration Documentation (#3642) ... * add datadog llm observability integration guide * spacing fix * wording changes * alphabetize docs listing * Update docs/en/observability/datadog.mdx Co-authored-by: Barry Eom <31739208+barieom@users.noreply.github.com> * add translations * fix korean code block --------- Co-authored-by: Barry Eom <31739208+barieom@users.noreply.github.com> Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>	2025-10-27 09:48:38 -04:00
Lorenze Jay	494ed7e671	liteagent supports apps and mcps (#3794) ... * liteagent supports apps and mcps * generated cassettes for these	2025-10-24 18:42:08 -07:00
Lorenze Jay	a83c57a2f2	feat: bump versions to 1.2.0 (#3787) ... * feat: bump versions to 1.2.0 * also include projects 1.2.0	2025-10-23 18:04:34 -07:00
Lorenze Jay	08e15ab267	fix: update default LLM model and improve error logging in LLM utilities (#3785) ... * fix: update default LLM model and improve error logging in LLM utilities * Updated the default LLM model from "gpt-4o-mini" to "gpt-4.1-mini" for better performance. * Enhanced error logging in the LLM utilities to use logger.error instead of logger.debug, ensuring that errors are properly reported and raised. * Added tests to verify behavior when OpenAI API key is missing and when Anthropic dependency is not available, improving robustness and error handling in LLM creation. * fix: update test for default LLM model usage * Refactored the test_create_llm_with_none_uses_default_model to use the imported DEFAULT_LLM_MODEL constant instead of a hardcoded string. * Ensured that the test correctly asserts the model used is the current default, improving maintainability and consistency across tests. * change default model to gpt-4.1-mini * change default model use defualt	2025-10-23 17:54:11 -07:00
Greyson LaLonde	9728388ea7	fix: change flow viz del dir; method inspection ... * chore: update flow viz deletion dir, add typing * tests: add flow viz tests to ensure lib dir is not deleted	2025-10-22 19:32:38 -04:00
Greyson LaLonde	4371cf5690	chore: remove aisuite ... Little usage + blocking some features	2025-10-21 23:18:06 -04:00
Lorenze Jay	d28daa26cd	feat: bump versions to 1.1.0 (#3770) ... * feat: bump versions to 1.1.0 * chore: bump template versions --------- Co-authored-by: Greyson Lalonde <greyson.r.lalonde@gmail.com> 1.1.0	2025-10-21 15:52:44 -07:00
Lorenze Jay	a850813f2b	feat: enhance InternalInstructor to support multiple LLM providers (#3767) ... * feat: enhance InternalInstructor to support multiple LLM providers - Updated InternalInstructor to conditionally create an instructor client based on the LLM provider. - Introduced a new method _create_instructor_client to handle client creation using the modern from_provider pattern. - Added functionality to extract the provider from the LLM model name. - Implemented tests for InternalInstructor with various LLM providers including OpenAI, Anthropic, Gemini, and Azure, ensuring robust integration and error handling. This update improves flexibility and extensibility for different LLM integrations. * fix test	2025-10-21 15:24:59 -07:00
Cameron Warren	5944a39629	fix: correct broken integration documentation links ... Fix navigation paths for two integration tool cards that were redirecting to the introduction page instead of their intended documentation pages. Fixes #3516 Co-authored-by: Cwarre33 <cwarre33@charlotte.edu> Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>	2025-10-21 18:12:08 -04:00
Greyson LaLonde	c594859ed0	feat: mypy plugin base ... * feat: base mypy plugin with CrewBase * fix: add crew method to protocol	2025-10-21 17:36:08 -04:00
Daniel Barreto	2ee27efca7	feat: improvements on QdrantVectorSearchTool ... * Implement improvements on QdrantVectorSearchTool - Allow search filters to be set at the constructor level - Fix issue that prevented multiple records from being returned * Implement improvements on QdrantVectorSearchTool - Allow search filters to be set at the constructor level - Fix issue that prevented multiple records from being returned --------- Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>	2025-10-21 16:50:08 -04:00
Greyson LaLonde	f6e13eb890	chore: update codeql config paths to new folders ... * chore: update codeql config paths to new folders * tests: use threading.Condition for event check --------- Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>	2025-10-21 14:43:25 -04:00
Lorenze Jay	e7b3ce27ca	docs: update LLM integration details and examples ... * docs: update LLM integration details and examples - Changed references from LiteLLM to native SDKs for LLM providers. - Enhanced OpenAI and AWS Bedrock sections with new usage examples and advanced configuration options. - Added structured output examples and supported environment variables for better clarity. - Improved documentation on additional parameters and features for LLM configurations. * drop this example - should use strucutred output from task instead --------- Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>	2025-10-21 14:39:50 -04:00
Greyson LaLonde	dba27cf8b5	fix: fix double trace call; add types ... * fix: fix double trace call; add types * tests: skip long running uv install test, refactor in future --------- Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>	2025-10-21 14:15:39 -04:00
Greyson LaLonde	6469f224f6	chore: improve CrewBase typing	2025-10-21 13:58:35 -04:00
Greyson LaLonde	f3a63be215	tests: cassettes, threading for flow tests	2025-10-21 13:48:21 -04:00