Quarantine transport-invalid oracle trial

This commit is contained in:
2026-07-13 23:16:04 +08:00
parent a9e7e9991e
commit d3bc63a972
3 changed files with 71 additions and 9 deletions

View File

@@ -1,11 +1,29 @@
# Static-policy oracle-gap protocol
Status: **FROZEN WITH A-OG-1 AMENDMENT**.
Status: **FROZEN WITH A-OG-1 AND A-OG-2 AMENDMENTS**.
Date frozen: 2026-07-13 (Asia/Singapore). Existing Phase-3 measurements were
inspected only to choose the workload pair and rate brackets. They are
exploratory calibration data, not primary observations in this protocol.
### A-OG-2 — retry one transport-invalid attempt (after 49 scored trials)
The first attempt at `P06-C01-r2.2-rep0` produced one local
`ClientOSError` 3.27 ms after admission, with HTTP status 0, no first token,
and no output. The other 399 requests completed successfully, every successful
request produced exactly 512 tokens, the server stayed healthy, and all other
client invariants passed. The controller rejected the attempt before creating
a `score.json`; no TTFT/TPOT result from this attempt was used to choose the
recovery rule.
This is a measurement-transport failure, not an observed server SLO outcome.
The entire attempt is content-hashed and moved under `invalid-attempts/`, then
the identical logical trial (phase, config, rate, repetition, derived manifest,
seeds, timeline, and SLO) is run once on a fresh C01 server. All 49 existing
scores remain immutable. A second client transport failure in the retry is a
stop condition and makes the experiment inconclusive; it must not be retried
again. No grid, policy, threshold, order, or oracle calculation changes.
### A-OG-1 — extend the P06 upper bracket (after trial 33)
The controller stopped as registered after C00/P06 remained SLO-feasible at