robbond/confidence-engine
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add investigation map workspace view

Browse Source
This commit is contained in:
robbond
2026-08-05 10:10:16 +01:00
parent a4dc165385
commit ce673b8eb4
5 changed files with 247 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/reasoning-contract-backlog.md
+7
View File
@@ -97,6 +97,13 @@ temporary workaround and the desired eventual contract.
| OriginalSituation | Central statement display | `scenario` prop (user input) or `graph.centralStatement` | Engine-derived central statement from user input | Start case | UI already handles both; engine should normalise |
| DeveloperDetails | Node descriptions | Mock nodes have `label === description` | Distinct, detailed description per node | Graph construction | Current mock uses label as description; separate fields needed |
## Investigation Map (Workspace UX)
| Feature | UI need | Temporary mock | Desired reasoning output | Likely stage | Notes |
| ---------------------- | ---------------------------------- | --------------------------------------------------- | -------------------------------------------------------------- | ---------------------- | -------------------------------------------------------- |
| InvestigationMap | Visible investigation progress | Mock topic set with manual turn-based status progression | Engine emits `investigationTopics: [{ title, status, ordering?, evidenceCount? }]` | Each turn — start and update response | UI displays topics in engine-determined order; statuses: "established" / "current" / "unknown" |
| InvestigationMap | Topic status evolution across turns | Hardcoded PROGRESSION array indexed by `investigationHistory.length` | Engine determines which topics are established, active, or unknown at each turn | Question selection phase | Topics should not expose graph internals; plain-language labels only |
## Open Questions / Future Work
1. **Structured confidence scores**: The UI currently mocks ordinal confidence (low/medium/high). The reasoning engine should eventually emit numeric confidence values per node and a computed conclusion confidence, enabling richer visual indicators.