feat: Replace ChatAgent single_iteration with max_iteration #2483
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Replaces the boolean `single_iteration` parameter in `ChatAgent` with an integer `max_iteration` to provide more flexible control over the number of model calling iterations within a single agent step. Key changes: - `ChatAgent.__init__` now accepts `max_iteration: Optional[int] = None`. - If `max_iteration` is `None` (default): No explicit limit on internal model/tool iterations (mimics old `single_iteration=False`). - If `max_iteration=1`: Agent performs one model call; if a tool is called, the step ends after tool execution (mimics old `single_iteration=True`). - If `max_iteration=N > 1`: Agent performs up to N model calls and tool executions within a step. - Logic in `ChatAgent.step` and `ChatAgent.astep` updated to respect `max_iteration`. - `ChatAgent.clone` method updated to carry over `max_iteration`. - Docstrings for `ChatAgent` updated to reflect the new parameter. - All codebase instantiations of `ChatAgent` using `single_iteration` have been updated: - `single_iteration=True` changed to `max_iteration=1`. - `single_iteration=False` (explicitly set) changed to `max_iteration=None`. - Implicit defaults now correctly use `max_iteration=None`. - Tests in `test/agents/test_chat_agent.py` have been updated and new tests added to cover various `max_iteration` scenarios (1, N, None) and ensure graceful termination.
|
Important Review skippedAuto reviews are disabled on this repository. Please check the settings in the CodeRabbit UI or the You can disable this status message by setting the Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This is a test using Jules, PR automaticlly generated by Jules Agent
Replaces the boolean
single_iterationparameter inChatAgentwith an integermax_iterationto provide more flexible control over the number of model calling iterations within a single agent step.Key changes:
ChatAgent.__init__now acceptsmax_iteration: Optional[int] = None.max_iterationisNone(default): No explicit limit on internal model/tool iterations (mimics oldsingle_iteration=False).max_iteration=1: Agent performs one model call; if a tool is called, the step ends after tool execution (mimics oldsingle_iteration=True).max_iteration=N > 1: Agent performs up to N model calls and tool executions within a step.ChatAgent.stepandChatAgent.astepupdated to respectmax_iteration.ChatAgent.clonemethod updated to carry overmax_iteration.ChatAgentupdated to reflect the new parameter.ChatAgentusingsingle_iterationhave been updated:single_iteration=Truechanged tomax_iteration=1.single_iteration=False(explicitly set) changed tomax_iteration=None.max_iteration=None.test/agents/test_chat_agent.pyhave been updated and new tests added to cover variousmax_iterationscenarios (1, N, None) and ensure graceful termination.Description
Describe your changes in detail (optional if the linked issue already contains a detailed description of the changes).
Checklist
Go over all the following points, and put an
xin all the boxes that apply.Fixes #issue-numberin the PR description (required)pyproject.tomlanduv lockIf you are unsure about any of these, don't hesitate to ask. We are here to help!