docs: update subagents docs for PR #20#781
Open
markbackman wants to merge 1 commit into
Open
Conversation
Updated the DebateWorker example to use the new LLMContextAgent class instead of manually creating LLMContext and LLMContextAggregatorPair. This simplifies the code and demonstrates the recommended pattern for worker agents that need their own conversation context. Changes: - Import LLMContextAgent instead of LLMAgent - Replace build_pipeline() with on_ready() hook - Access aggregators via self.assistant_aggregator property - Added explanatory note about LLMContextAgent benefits Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
markbackman
added
the
auto-docs
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Automated documentation update for pipecat-subagents PR #20.
Changes
Updated guides
subagents/learn/task-coordination.mdx- Updated theDebateWorkerexample to use the newLLMContextAgentclass instead of manually creatingLLMContextandLLMContextAggregatorPair. This demonstrates the simplified pattern for worker agents that need their own conversation context. Added an explanatory note aboutLLMContextAgentbenefits.Gaps identified
New API requiring documentation
LLMContextAgent- New class insrc/pipecat_subagents/agents/llm/llm_context_agent.pyneeds its own API reference page atapi-reference/pipecat-subagents/llm-context-agent.mdx. This is a subclass ofLLMAgentthat includes built-inLLMContextandLLMContextAggregatorPair, simplifying the pattern for worker agents.File renames (no content changes)
agents/llm/agent.py→agents/llm/llm_agent.py(content unchanged, mapping updated)agents/flows/agent.py→agents/flows/flows_agent.py(content unchanged, mapping updated)The source-to-doc mapping file (
.claude/skills/update-docs/SOURCE_DOC_MAPPING.md) was already updated in PR #20 to reflect the new filenames.🤖 Generated with automated docs sync workflow