Isolate speech transport failures and keep experimental media usable

This commit is contained in:
karl committed 2026-10-13 21:09:43 +02:00
1 parent f15ee07ed0
commit 296a39a6c2
7 files changed
+147 -3

No files matched your search

+22 -1
View File
@@ -88,7 +88,7 @@ Raw log `.searchi/qa/service-speech-google-cpu-v3.log`: 1292 bytes, SHA
The first normal auto compilation reached Vulkan setup but failed on Windows
nested MSBuild path length. Its log is retained, SHA
`59f1820d6ac6adac6f525d8084c442c1ed261753eb34fcce916dc157041f777c`.
An unchanged build in a shorter owned output directory is underway; no CPU-only
An unchanged build in a shorter owned output directory was started; no CPU-only
distribution was substituted.
The shorter-path normal auto build subsequently completed. Worker SHA
@@ -122,3 +122,24 @@ The complete report is 174868 bytes, SHA
It uses the internal v3 CPU artifact and does not establish normal auto runtime
quality parity or GPU performance. Details and the retained comparison are in
[the evaluator](../tools/speech-eval/native-validation/README.md).
## Longer-source failure and release recovery
The normal-runtime timing regression retained all five original sources and
all eight queries, but the speech session returned a transport failure on the
first source and later files inherited the unavailable session. Raw Google
indexing completed with 79 chunks and no media failures. Recognized timing
scores remain ineligible; no historical 6/8 score is claimed for this run.
An isolated native reproduction using the **exact failed PCM hash**
`03ef72d2a4cb926b7d31fbaef757a6cb954a55d6d6961085ea6992728c8d9e37`
completed all four actual VAD intervals, valid recognition responses and exit
zero. The original transport failure is unexplained; no model or memory tuning
was introduced to hide it.
The release now restarts a verified session once at the next new source after
a terminal recoverable transport failure. The original failed source remains
reported; compatible donors return before restarting and raw search stays
usable. Malformed protocol/text and invalid token points never arm this reset.
Five focused service tests and native transport/lifecycle checks passed with
strict Clippy. Media and spoken passages remain visibly experimental.