* Decouple model_context from AssistantAgent
* add UnboundedBufferedChatCompletionContext to mimic pervious model_context behaviour on AssistantAgent
* moving unbounded buffered chat to a different file
* fix model_context assertions in test_group_chat
* Refactor model context, introduce states
* fixes
* update
---------
Co-authored-by: aditya.kurniawan <aditya.kurniawan@core42.ai>
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
Co-authored-by: Victor Dibia <victordibia@microsoft.com>
* Move LLMUsageTracker to a cookbook
* rename, add to index
* fmt and remove test
* Update python/packages/autogen-core/docs/src/user-guide/core-user-guide/cookbook/llm-usage-logger.ipynb
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Fix missing quotation marks in notebook
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* add protobuf serialization test
* proto file regeneration
---------
Co-authored-by: Ryan Sweet <rysweet@microsoft.com>
Co-authored-by: Mohammad Mazraeh <Mazraeh.Mohammad@Gmail.com>
When the tool expects complex inputs that require nested models, pydantic will generate a JSON Schema that will include references to other schemas using the `$ref` keyword (cf https://json-schema.org/understanding-json-schema/structuring#dollarref).
But the `$ref` keyword is not supported by OpenAI.
This fix:
1. Resolves the references and inlines the corresponding schemas.
2. Removes the then useless root `$defs` field of the JSON schema to save tokens.
Co-authored-by: Jean-Marc Le Roux <contact@jmlx.io>
Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
* Remove isinstance check from FunctionTool (#3987)
* Move __init__ Args to class docstring
---------
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* Run LocalCommandLineCodeExecutor within venv
* Remove create_virtual_env func and add docstring
* Add explanation for LocalCommandLineExecutor docstring example
* Enhance docstring example explanation
---------
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* WIP implementation for agentchat
* WIP
* WIP
* wip
* WIP
* WIP
* WIP
* WIP
* fix types
* format
* fix build
* Fix build
* use a simpler implementation of thread -- list
* Select speaker to return speaker topic type
* add parent topic type to agent container
* Address comments
* Add check to make sure agent id is constant in a team run.
* Fix build
* add subscription deduplication
* format
---------
Co-authored-by: Mohammad Mazraeh <mmazraeh@microsoft.com>
Co-authored-by: Ryan Sweet <rysweet@microsoft.com>
* host agent runtime API and docs
* graceful shutdown of worker
* HostAgentRuntime --> WorkerAgentRuntimeHost
* Add unit tests for worker runtime
* Fix bug in worker runtime adding sender filed to proto. Documentation.
* wip
* Fix unit tests; refactor API
* fix formatting
* Fix
* Update
* Make source field optional in Event proto
* add tests to ruff for core
* fmt
* lint
* lint fixes
* fixup more dirs
* dont include non python
* lint fixes
* lint fixes
* fix dir name
* dont relative include
