Conversation
Add AgentService that orchestrates the tool calling cycle: - LLM returns tool_calls -> execute tools -> send results back -> LLM continues - Implements ChatService (decorator pattern) so ChatBloc works with either PortkeyChatService (no tools) or AgentService (with tools) transparently - Constructor param named baseChatService to clarify the decoration - Full streaming: every round streams events to UI - Max tool rounds configurable (default 5), emits ChatError when exceeded - Handles unknown tool names and tool execution errors gracefully - Add tools param to ChatService.chat(), PortkeyChatService, and PortkeyClient - Integration test: LLM calls add tool, calculates 3+7=10 Co-Authored-By: Claude Code <noreply@anthropic.com>
mintminterdev
approved these changes
Mar 27, 2026
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
AgentServicethat orchestrates the tool calling cycle:LLM returns tool_calls → execute tools → send results back → LLM continues
ChatService(decorator pattern):ChatBlocworks transparently with eitherPortkeyChatService(no tools) orAgentService(with tools)baseChatServiceto clarify the decoration relationshipChatErrorwhen exceededtoolsparam toChatService.chat(),PortkeyChatService, andPortkeyClientTest plan
dart analyzepasses (chat_core + chat_adapter)dart format --set-exit-if-changed .passesdart test— chat_core: 58 tests passed (7 new), chat_adapter: 5 tests passed🤖 Generated with Claude Code
Co-Authored-By: Claude Code noreply@anthropic.com