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

experiment: review deferred project documents

Browse Source 
Experiment 30 classified two deferred documents against verified current state:
- architectural-principles.md → keep as task-specific reference (6 current, 4 aspirational, 3 duplicates)
- backlog info.md → retain temporarily pending revision (mixed mock fixtures + deferred UX planning)
Neither moved to archive — both contain material with potential near-term utility.
Created docs/document-role-review.md with evidence, routing test, and return-to-work note.
This commit is contained in:
robbond
2026-08-06 14:33:10 +01:00
parent 97e4f3029e
commit 78c98fb973
4 changed files with 197 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/current-project-state.md
+2 -2
View File
@@ -102,9 +102,9 @@ First document to read: `docs/current-project-state.md`. Then consult `.claude/a
Nothing has been archived, moved or deleted. Before changing the documentation structure, review whether the new entry point reliably replaces the large log section and whether any historical documents should be formally archived.
### Return-to-Work Note (updated Experiment 29)
### Return-to-Work Note (updated Experiment 30)
The current-state briefing was checked against source code via targeted code inspection of API routes, orchestrator imports/calls, and cross-module traces for each passive classifier. Five active capabilities are confirmed (reconstruction, graph updates, unknown selection, question formulation, turn orchestration). Seven passive capabilities remain classified as diagnostic_only (investigation-state assessment) or isolated (behaviour selection, decision-condition status, evidence direction, evidence scope, question importance, question relevance to decision, scope-aware condition status). No corrections to the current-state document were required. Knowledge-management experiments continue: selected historical documents have been archived to `docs/archive/`; nothing was deleted. The archive index explains where older evidence lives and when to consult it. Engine and UI experiments remain paused. First file to inspect when resuming: `docs/current-project-state.md`, then `.claude/architecture-guardrails.md` before any code changes, then `lib/graph/orchestrator.js` for engine-resumption work.
The current-state briefing was checked against source code via targeted code inspection of API routes, orchestrator imports/calls, and cross-module traces for each passive classifier. Five active capabilities are confirmed (reconstruction, graph updates, unknown selection, question formulation, turn orchestration). Seven passive capabilities remain classified as diagnostic_only (investigation-state assessment) or isolated (behaviour selection, decision-condition status, evidence direction, evidence scope, question importance, question relevance to decision, scope-aware condition status). No corrections to the current-state document were required. Knowledge-management experiments continue: five historical documents have been archived to `docs/archive/` per Experiment 29; two deferred documents reviewed in Experiment 30 (architectural-principles.md kept as task-specific reference; backlog info.md retained temporarily pending revision — neither moved). Engine and UI experiments remain paused. First file to inspect when resuming: `docs/current-project-state.md`, then `.claude/architecture-guardrails.md` before any code changes, then `lib/graph/orchestrator.js` for engine-resumption work.
## Verification Marker