refactor: Update IDMA and TSASPDMA field names to V1.9.3 spec - #1
Conversation
- Add MessageType type alias ('user' | 'agent' | 'system' | 'error')
- Add optional message_type field to ConversationMessage interface
- Add getEffectiveMessageType() for backward compatibility with is_agent
- Add getMessageStyles() helper for type-based styling
- Add InfoIcon and WarningIcon components for system/error messages
- Update message rendering: system (blue, centered), error (red, centered)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Types (types.ts): - Add IDMAResult interface (k_eff, correlation_risk, fragility_flag, phase) - Add TSASPDMAResult interface (tool_name, tool_parameters, reasoning, approved) Dashboard (page.tsx): - Add idma_result and tsaspdma_result to stageNames array - Add specialized rendering for IDMA with identity coherence metrics display - Add specialized rendering for TSASPDMA with tool info and approval status - Add stage indicators with defensive null checks for malformed events - Purple theme for IDMA, cyan theme for TSASPDMA, orange for fragility warnings 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- IDMA: k_eff → epistemic_humility, correlation_risk → diversity_score, fragility_flag → is_fragile, added fragility_reason and correlation_factors - TSASPDMA: tool_name → original_tool_name/final_tool_name, tool_parameters → final_parameters, reasoning → tsaspdma_rationale, approved → final_action (tool/speak/ponder) - Updated stage order: TSASPDMA now comes before ASPDMA per spec 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
|
This pull request sets up GitHub code scanning for this repository. Once the scans have completed and the checks have passed, the analysis results for this pull request branch will appear on this overview. Once you merge this pull request, the 'Security' tab will show more code scanning analysis results (for example, for the default branch). Depending on your configuration and choice of analysis tool, future pull requests will be annotated with code scanning analysis results. For more information about GitHub code scanning, check out the documentation. |
|
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 6f636c9a8f
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| export interface IDMAResult { | ||
| k_eff: number; // Effective identity coherence | ||
| correlation_risk: number; // Risk of identity drift | ||
| fragility_flag: boolean; // Identity stability warning | ||
| phase: string; // Current identity phase |
There was a problem hiding this comment.
The new UI logic in apps/agui/app/page.tsx reads data.is_fragile, data.epistemic_humility, data.diversity_score, and data.correlation_factors, but the exported IDMAResult type still requires the old k_eff, correlation_risk, fragility_flag, and phase fields. Any consumer using these SDK types will now be steered toward the deprecated schema and will either fail type-checking or continue to read the wrong fields. Please align IDMAResult with the V1.9.3 field names to match the actual data shape.
Useful? React with 👍 / 👎.
| export interface TSASPDMAResult { | ||
| tool_name: string; | ||
| tool_parameters: Record<string, any>; | ||
| reasoning: string; | ||
| approved: boolean; |
There was a problem hiding this comment.
The UI now expects the TSASPDMA payload to expose original_tool_name, final_action, final_tool_name, final_parameters, and tsaspdma_rationale, but the SDK type still defines tool_name, tool_parameters, reasoning, and approved. This mismatch makes any typed client code treat the new server response as invalid and risks continued use of removed fields. The TSASPDMAResult interface should be updated to the V1.9.3 names to avoid type-level regressions.
Useful? React with 👍 / 👎.
2 participants
Summary
IDMA Changes
k_effepistemic_humilitycorrelation_riskdiversity_scorefragility_flagis_fragilephasefragility_reasoncorrelation_factorsTSASPDMA Changes
tool_nameoriginal_tool_nametool_parametersfinal_parametersreasoningtsaspdma_rationaleapprovedfinal_action(tool/speak/ponder)final_tool_nameTest plan
🤖 Generated with Claude Code