Improve IK-style artifact scanner pipeline

docs/PROJECT.md

@@ -3,6 +3,8 @@
 This document is the source of truth for project intent, scope, runtime facts, and operational expectations.
 
 For implementation structure, see [ARCHITECTURE.md](ARCHITECTURE.md). For engineering standards, see [CONVENTIONS.md](CONVENTIONS.md).
+For the latest Inventory-Kamera comparison work, see
+[scanner-ik-progress-report.md](scanner-ik-progress-report.md).
 
 ## Project Identity
 
@@ -58,6 +60,7 @@ The app is not intended to replace deep min-max tools. It prioritizes time savin
 | --- | --- | --- |
 | Safety | Never perform irreversible in-game actions. | Code review and manual test |
 | Performance | Single artifact read should feel interactive and batch scan should not stall on false progress. | Capture latency monitored manually; auto-scan stops on blocked verification |
+| IK target | First 100 artifacts should scan with accuracy at least as good as Inventory Kamera and equal or better speed. | `npm run scan:goal:compare` quality-gated report |
 | Privacy | Captures and parsed data stay local by default. | No remote upload in scanner path |
 | Reliability | Uncertain OCR must be visible to the user. | Confidence and details view |
 | Learning loop | Scanner mistakes should become reusable local review samples. | `review-samples.jsonl` |
@@ -95,6 +98,9 @@ The app is not intended to replace deep min-max tools. It prioritizes time savin
 - The parser already uses known sets, pieces, slots, stat aliases, set aliases, character aliases, and derived slot/set mapping.
 - Review samples, learned replacements, parser notes, and stored artifacts already persist locally.
 - The auto-scan loop is no longer a naive click spammer: it has preflight, verification, miss handling, page fingerprinting, and stop conditions.
+- The scanner now has an Inventory-Kamera comparison path: 32 safe artifact
+  targets per page, lookup-derived fields, fast OCR crop profile, current vs.
+  IK-traineddata benchmark endpoint, and a quality-gated live soak runner.
 - Elevated live automation is validated in the current dev environment:
   `/automation/probe-click?index=1` changed the selected artifact and
   `/scanner/start?limit=2` completed with 2/2 verified reads and 0 misses.
@@ -108,6 +114,9 @@ The app is not intended to replace deep min-max tools. It prioritizes time savin
 - Learned fixes currently focus on text replacements; they do not yet update crop offsets, UI profile variants, or scanner targeting rules in a structured way.
 - The scan page is cleaner than before, but it still exposes too much operator/debug state in the main flow.
 - Recommendations and build logic exist, but the scanner is not yet reliable enough to make them the core focus.
+- The latest source has not yet completed the final 100-artifact live comparison
+  because the current dev-control port is still owned by a stale elevated
+  Electron process. Live timing must wait for a UAC-approved restart.
 
 ### Current product conclusion
 
@@ -233,8 +242,11 @@ Status:
 2. Tighten the game data generator and parser contract, then backfill regression tests from real bad samples.
 3. Continue moving auto-scan behavior out of `App.tsx` and into isolated scanner modules.
 4. Soak-test the elevated C# helper automation path with gradually larger scan limits and page scroll transitions.
-5. Extend the learning system from text-only fixes into crop/UI profile tuning.
-6. Resume recommendation work only when scan accuracy is consistently trustworthy.
+5. Run `npm run scan:goal:compare` after `/health.appBuild.signature` matches
+   the current source and use the quality-gated 100-artifact report as the IK
+   target evidence.
+6. Extend the learning system from text-only fixes into crop/UI profile tuning.
+7. Resume recommendation work only when scan accuracy is consistently trustworthy.
 
 ## Open Questions