FEAT: Implement Anticipatory Ethics DMA (AE-DMA) for tool veto#507
Open
phahim1 wants to merge 1 commit intoCIRISAI:mainfrom
Open
FEAT: Implement Anticipatory Ethics DMA (AE-DMA) for tool veto#507phahim1 wants to merge 1 commit intoCIRISAI:mainfrom
phahim1 wants to merge 1 commit intoCIRISAI:mainfrom
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
✨ Summary of Changes
This PR introduces the Anticipatory Ethics Decision-Making Algorithm (AE-DMA) as a core safety feature to prevent the agent from executing actions that violate mandated critical integrity rules (e.g., uptime requirements).
The feature is demonstrated by implementing a core Veto rule on a newly registered high-risk tool.
🛡️ Core Feature: The Veto Rule
The system now contains the following enforceable safety boundary:
patch_critical_serverAnticipatoryDMA.process()method intercepts the action if the tool is called.VETOstatus (P(Harm)=0.95), forcing the Action Selection DMA to reject the thought.🔍 Key Files for Audit
Please review the following files:
ciris_engine/logic/dma/anticipatory_dma.pyciris_modular_services/tools/sentinel_tools.pyciris_engine/logic/services/tools/core_tool_service/service.pySentinelToolsservice so the LLM can see it.ciris_engine/logic/runtime/ciris_runtime.pycirisagent/config/essential.yamlplatform: clientry that caused validation errors.🐛 Known Issues / Follow-up
During testing, strict Pydantic configuration validation repeatedly blocked the runtime from starting in the required interactive CLI mode.
ciris_engine/logic/runtime/ciris_runtime.pyto force adapter loading (adapter_types = ["cli"]). This override should be reviewed and reverted post-merge, pending a framework fix.EssentialConfigvalidation schema forbids external configuration overrides forplatform/adapter_mode.