From fd6790641793e031ac45c46936fd49655b635e76 Mon Sep 17 00:00:00 2001 From: karl Date: Tue, 13 Oct 2026 16:04:45 +0200 Subject: [PATCH] Measure published Windows MCP genuine Google CPU first and warm searches --- docs/AGENT-INTEGRATION.md | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/docs/AGENT-INTEGRATION.md b/docs/AGENT-INTEGRATION.md index c9bdca5..5b63692 100644 --- a/docs/AGENT-INTEGRATION.md +++ b/docs/AGENT-INTEGRATION.md @@ -206,3 +206,21 @@ Archive: 8784871 bytes, SHA-256 Public full-byte archive and checksum downloads matched. This does not prove clean-machine installation or GPU behavior. Earlier evidence describes older assets. Rebuild with `python tools/package_windows_cli.py --executable target/release/searchi.exe`. + +## Published Windows MCP genuine Google timing + +The extracted CLI package encoded two genuine PDF/DOCX passages using the +installer's Google worker and verified local assets, explicitly CPU, one thread. +This isolated CLI directory has no media decoders: initial default embedding +correctly rejected missing helpers, then the explicit `--text-only` run encoded +two chunks successfully. Ordinary desktop setup remains unchanged. + +A retained MCP session validated hybrid mode/semantic availability and page or +paragraph citations for all twelve queries. Initialize RPC: 1082.28 ms; first +search RPC: 77.53 ms; nearest-rank p95 across eleven different warm queries: +108.78 ms. An earlier diagnostic run observed 1072.04/71.64/69.56 ms; small sample +variation is visible. These measure RPC plus shared-engine search on a tiny +synthetic corpus, exclude native UI and large-library/cold-disk claims, and do +not compare GPU performance. No timing-driven cache/architecture changes made. +Raw ignored verified report: `.searchi/qa/windows-mcp-013-timing-verified.json`, +SHA-256 `03c0a21aa35686077fca25e0b4fe7b7014d8f8aa7a07233af6518ac1b694db08`.