Fix history from long term memory #644
Conversation
WalkthroughThe pull request modifies the initialization process for a microchain agent by introducing a new Changes
Sequence DiagramsequenceDiagram
participant Agent
participant LongTermMemory
participant InitMethod as initialise_agent()
Agent->>InitMethod: Call initialise_agent()
InitMethod-->>LongTermMemory: Retrieve past messages
InitMethod->>Agent: Reset and build initial messages
InitMethod->>Agent: Inject filtered historical context
Agent->>Agent: Begin main working loop
Possibly related PRs
Suggested reviewers
Finishing Touches
Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media? 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
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 (
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
prediction_market_agent/agents/microchain_agent/deploy.py (1)
113-129: Optimize history injection for better performance.The history injection logic can be made more efficient by combining the filtering and reversal operations.
- messages_to_insert = [ - m.metadata_dict - for m in latest_saved_memories[ - ::-1 - ] # Revert the list to have the oldest messages first, as they were in the history. - if check_not_none(m.metadata_dict)["role"] - != "system" # Do not include system message as that one is automatically in the beginning of the history. - ] + messages_to_insert = [ + m.metadata_dict + for m in reversed(latest_saved_memories) + if check_not_none(m.metadata_dict)["role"] != "system" + ]
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
prediction_market_agent/agents/microchain_agent/deploy.py(3 hunks)prediction_market_agent/agents/microchain_agent/microchain_agent.py(1 hunks)
⏰ Context from checks skipped due to timeout of 90000ms (2)
- GitHub Check: pytest-docker
- GitHub Check: mypy
🔇 Additional comments (4)
prediction_market_agent/agents/microchain_agent/microchain_agent.py (1)
16-16: LGTM! Import cleanup aligns with code reorganization.The removal of the unused import reflects the movement of the memory import logic to deploy.py.
prediction_market_agent/agents/microchain_agent/deploy.py (3)
109-112: LGTM! Clean initialization logic.The method properly encapsulates the agent initialization steps, improving code organization.
141-142: LGTM! Proper initialization sequence.The changes ensure that:
- Agent is properly initialized before the main loop
- History is preserved by forcing resume=True in agent.run
Also applies to: 156-157
Line range hint
34-35: LGTM! Class structure maintains backward compatibility.The class structure properly supports the new initialization flow while preserving the existing configuration options.
No description provided.