perf: audit EmbeddingGemma 2 and reuse measured query embeddings

docs/ROADMAP.md

@@ -80,6 +80,29 @@ Status: implementation started; no production release yet. Windows VM tests use
 - [ ] Native UI interaction and chosen-provider quality/latency checks before
   claiming production-ready answers or compatibility with every provider.
 
+## 7. EmbeddingGemma 2 efficiency
+
+Audit and measured priorities: [EMBEDDINGGEMMA2-AUDIT.md](EMBEDDINGGEMMA2-AUDIT.md).
+
+- [x] Audit actual required model, task prefixes, pooling/normalization, native
+  sequence processing and CPU/runtime policies against primary sources.
+- [x] Record real CPU 1/2/4-thread query/first-use/document measurements and
+  paired repeated-query/filter-change results with unchanged retrieval evidence.
+- [x] Bounded provider-scoped actual-query vector LRU with accurate cache traces;
+  preserve filtering, source freshness, failures and actual warmup probes.
+- [x] Reduce semantic settle delay to 120 ms and retain old ready generation
+  during rebuilding; test initial-generation and activation readiness boundaries.
+- [ ] Bound whole IPC write/read deadlines and recover from a nonreading helper.
+- [ ] Declare/test x86 CPU minimum or baseline/AVX2 runtime selection.
+- [ ] Incrementally reuse unchanged document/media vectors in atomic generations.
+- [ ] Benchmark genuine token-budgeted multi-sequence batching and isolation.
+- [ ] Implement and measure shared foreground/indexer resource budgets/priority.
+- [ ] Attribute startup cost; measure smaller query context and selective encoders.
+- [ ] Buffered bounded media IPC and linear UTF-8 source-window offset processing.
+- [ ] Evaluate 256d MRL and content-specific vision budgets on independent data.
+- [ ] Validate GPU precision, synchronization-aware timings, parity and fallback
+  on actual accelerator hardware; CPU VM checks do not satisfy this gate.
+
 Completion requires recorded evidence; targets are not measured results.
 
 ## Completed foundation details