Record current Google CPU incremental and prepared reader checks

docs/INCREMENTAL-SEMANTIC.md

@@ -113,3 +113,29 @@ encoder calls does not mean zero work or prove fast first input.
 
 Synthetic colored-image and sine-wave fixtures prove actual vector reuse and
 citation equality; they do not establish useful media relevance.
+
+## Current Windows CPU integration rerun, 2026-10-13
+
+At source `66bf7d7b4757c1454e4cd61e514ff9376bddd728` with a clean worktree,
+the normal current worker SHA-256
+`c01cb3ec13cfca722ee768e8350e1399a8b9a4d14a24a35adc3473a5cfc82a73`
+ran all three `incremental_google_cpu` tests successfully in 75.47 seconds.
+Actual Google inference was explicitly CPU-only with one thread. Verified
+Google assets and the pinned Windows FFmpeg/FFprobe helpers were used.
+
+The checks cover completed-vector reuse after failed activation and reopen,
+document/code moves with preserved citations, title-change reencoding, mixed
+document/image/audio/video reuse, and byte-changing media overwrites with
+identical size/mtime. The prepared-reader test also passed in 14.04 seconds:
+publication preserved the real query-vector LRU and shared prepared ANN graph,
+returned updated source content, and a distinct query executed genuine inference.
+Observed service times were 2.962 ms for the cached query and 84.808 ms for the
+distinct query, on a one-document fixture. These are debug-profile integration
+observations, not desktop first-input, scale or release latency acceptance.
+
+Command: `cargo test -p searchi-service --test prepared_google_cpu --test
+incremental_google_cpu --locked -- --ignored --nocapture --test-threads=1`,
+with `SEARCHI_FORCE_CPU=1` and the verified model/worker/decoder environment
+variables described in SKILLS.md. All four tests executed, none skipped.
+The running installed user application was left untouched. Other platform,
+storage-contention and representative-corpus gates remain open.