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

experiment: validate cold-start project recovery

Browse Source
This commit is contained in:
robbond
2026-08-06 16:11:37 +01:00
parent 544573af75
commit 51648e4b8f
4 changed files with 137 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/current-handoff.md
+12 -10
View File
@@ -7,8 +7,8 @@
- Engine experiments are paused after Experiment 25B;
- UI experiments are paused;
- Knowledge-management experiments are complete;
- Experiment 34 created a single return-to-work handoff file to replace scattered current-state notes;
- The working tree was clean at commit `1d92aa0`.
- Experiment 38 validated that a cold session recovers project state from three documents alone;
- The working tree was clean at commit `544573a` (Exp 37).
> This handoff describes the latest stopping point only. When work moves on, replace stale current-work details rather than appending another historical note. Historical experiment and commit information belongs in `docs/design-evolution-log.md`.
@@ -28,17 +28,19 @@ Engine and UI work were deliberately paused because documentation had grown larg
Experiment 37 corrected the routing defect from Experiment 36 and tested a cross-boundary engine/UI task. It validated that two context packs can be combined deliberately while keeping working context small, explicit and accurate. All seven knowledge-management criteria are now met. No source code changed. No files moved or deleted.
**Commit:** pending (experiment: validate cross-boundary context routing)
**Commit:** `544573a` (experiment: validate cross-boundary context routing)
Experiment 38 tested whether a genuinely cold session (no prior conversation context) can recover the project state from three documents alone. It recovered all capabilities, boundaries, and context-pack selection correctly without loading the full history or source code. All seven knowledge-management criteria confirmed met. One handoff update required: the open item "whether the handoff stays accurate after further advances" was resolved (handoff is accurate). The cold-start test passed.
**Commit:** pending (experiment: validate cold-start project recovery) — to be committed this session.
## 5. What Remains Open
- Whether the handoff stays accurate and concise after further project advances (tested by this experiment);
- Whether tasks crossing pack boundaries can still stay concise without loading excessive context;
- When knowledge-management work is complete enough to resume engine experiments.
- Whether tasks crossing pack boundaries can still stay concise without loading excessive context (not tested by this experiment).
### When This Knowledge-Management Phase Is Complete
Provisional criteria for review:
Provisional criteria for review (all confirmed met by Experiment 38 cold-start test):
1. A fresh session can resume from the handoff and one context pack; — **met**
2. Current state has been verified against implementation; — **met**
@@ -80,8 +82,8 @@ Answer before continuing:
---
*Created by Experiment 34. Updated by Experiment 37. Branch: `feature/user-workspace-ux-v0.7`.*
*Created by Experiment 34. Updated by Experiment 38. Branch: `feature/user-workspace-ux-v0.7`.*
### Return-to-Work Note (Experiment 37)
### Return-to-Work Note (Experiment 38)
The routing defect from Experiment 36 was corrected (Routing Test B now names `docs/ui-mock-reference.md` as the source of mock scenario names). A cross-boundary engine/UI task was tested: displaying passive condition-status information in the workspace. Primary pack — Knowledge-Management; second pack — UI and Mock (ui-mock-reference.md for scenario routing). All seven knowledge-management completion criteria are met. Engine and UI experiments remain paused pending Rob's review. First file to inspect when resuming: `docs/current-handoff.md`, then `docs/task-context-packs.md`.
Experiment 38 was performed from a cold session with no prior conversation context and confirmed that the reduced context system works as designed. A genuinely fresh session recovered the complete project state—active capabilities, passive diagnostic layers, paused work items, and context-pack routing—from just three documents without reading the full design-evolution log or any archived material. All seven knowledge-management completion criteria are confirmed met. The handoff itself was found to be accurate with no stale or ambiguous statements; one structural update was made (resolving the open item about handoff longevity). Engine and UI experiments remain paused pending Rob's review. Branch: `feature/user-workspace-ux-v0.7`. First file to inspect when returning: `docs/current-handoff.md`, then `docs/current-project-state.md` and the Engine Experiment pack per the routing table. The next action is discussion, not automatic implementation.