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

docs(confidence-engine): route design evolution provenance through archive index

Browse Source
This commit is contained in:
robbond
2026-09-03 11:56:36 +01:00
parent fb2384cff1
commit 37a9a12f93
4 changed files with 18 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/project-knowledge-inventory.md
+9 -11
View File
@@ -30,16 +30,14 @@ These are the documents Claude should normally read before continuing Confidence
- **Why required:** Provides only the guidance that should influence work today, verified against current implementation. Reduces ambiguity about which principles are active versus aspirational.
- **Size:** small
### docs/design-evolution-log.md (selected sections only)
- **Purpose:** Chronological record of design decisions, experiments, and their conclusions.
### docs/design-evolution/README.md (selected chapters only)
- **Purpose:** Chronological record of design decisions, experiments, and their conclusions. Load the specific chapter via the archive index — do not load all chapters.
- **Sections to read:**
- Lines 1–90: Phases 1–4 overview (context for where we came from);
- Lines 824–838: Experiment 16 "What did we learn?";
- Lines 889–910: Experiment 17 summary;
- Lines 1218–1520: Experiments 23 through 25B (current engine experiments);
- Final ~40 lines of the file (Return-to-Work Note for each recent experiment).
- **Why required:** The minimum history needed to understand what was learned in the active experiment chain (23–25B) and where the pause decision sits. Do not read experiments before v23 unless you need historical context.
- **Size:** medium (targeted sections ≈ 400 lines of ~1,540 total)
- ch4: Experiments 23 through 25B (current engine experiments);
- ch8: Experiments 47–51;
- The Return-to-Work Note entries in each relevant chapter for recent experiment closeout.
- **Why required:** The minimum history needed to understand what was learned in the active experiment chain and where the pause decision sits. Do not read experiments before v23 unless you need historical context.
- **Size:** varies by chapter (progressive loading recommended)
### docs/project-knowledge-inventory.md (this file — Section 1 only)
- **Purpose:** Your own cross-reference for what to load next.
@@ -195,7 +193,7 @@ These documents document the path from Phase 1 through Experiment 25B. Archiving
After creating this inventory, I simulated a fresh-session context load using only:
- `.claude/project-context.md` (entire file)
- `.claude/architecture-guardrails.md` (entire file)
- `docs/design-evolution-log.md` (lines 1–90 + lines 824–838 + lines 889–910 + lines 1218–1520)
- `docs/design-evolution/README.md` ch4 (Experiments 23–25B), plus relevant chapter sections as needed
- `docs/03_Confidence_Engine_Language_Guide.md` (entire file)
Five questions answered from this set:
@@ -215,4 +213,4 @@ None. The five questions were answered accurately from the minimum context set.
## Return-to-Work Note
Engine experiments paused after Experiment 25B, which established scope-aware condition status classification — distinguishing direct evidence from relevant-but-different claims by checking subject, timeframe, and claim type. Present-state evidence does not settle future-feasibility conditions. The passive classifier layers remain isolated; no active integration yet. Knowledge-management experiments continue: five historical documents archived per Experiment 29; backlog info.md split in Experiment 31 into `docs/ui-mock-reference.md` (mock scenarios reference) and `docs/archive/deferred-ux-backlog.md` (deferred UX planning). Neither backlog item deleted or promoted. **Phase 2B context audit (2026-08-19):** ~76 historical experiment files moved to `docs/archive/experiments/` under eight subdirectories — preserved as evidence, removed from default context loading paths. No methodology or current operational paths changed. First file to inspect when resuming: `.claude/project-context.md`, then Experiments 23–25B in `docs/design-evolution-log.md` (lines 1218–1520).
Engine experiments paused after Experiment 25B, which established scope-aware condition status classification — distinguishing direct evidence from relevant-but-different claims by checking subject, timeframe, and claim type. Present-state evidence does not settle future-feasibility conditions. The passive classifier layers remain isolated; no active integration yet. Knowledge-management experiments continue: five historical documents archived per Experiment 29; backlog info.md split in Experiment 31 into `docs/ui-mock-reference.md` (mock scenarios reference) and `docs/archive/deferred-ux-backlog.md` (deferred UX planning). Neither backlog item deleted or promoted. **Phase 2B context audit (2026-08-19):** ~76 historical experiment files moved to `docs/archive/experiments/` under eight subdirectories — preserved as evidence, removed from default context loading paths. No methodology or current operational paths changed. First file to inspect when resuming: `.claude/project-context.md`, then consult `docs/design-evolution/README.md` (ch4 for Experiments 23–25B).