mirror of
https://github.com/SikongJueluo/pi-extensions.git
synced 2026-10-05 11:52:55 +08:00
SikongJueluo
72c9366f07
Two strict corpus-replay rounds against deepseek/deepseek-v4-flash (api openai-completions, 30000ms timeout): - run -01: 20/21, covered-compound judged defer (non-repeating sampling miss, not systematic) - run -02: 21/21, zero infrastructure failures, p50 1448ms / p95 1682ms / max 2146ms Qualified. Adds the catalog entry (recommended, advisory data per ADR 0008) and retains both reports; run -01 notes the single miss. Full repo check+test green (236 + 48).
36 lines
1.6 KiB
JSON
36 lines
1.6 KiB
JSON
{
|
|
"version": 1,
|
|
"entries": [
|
|
{
|
|
"provider": "openai-codex",
|
|
"model": "gpt-5.6-sol",
|
|
"api": "openai-codex-responses",
|
|
"status": "recommended",
|
|
"promptVersion": "bash-shadow-v4",
|
|
"corpusVersion": "2026-08-21.2",
|
|
"testedAt": "2026-08-21T15:00:47.219Z",
|
|
"corpusCases": 21,
|
|
"matched": 21,
|
|
"infrastructureFailures": 0,
|
|
"latencyMs": { "p50": 5823, "p95": 10396, "max": 10396 },
|
|
"reportPath": "reports/corpus-replay-gpt-5.6-sol-20260821-03.json",
|
|
"notes": "30000ms timeout cohort. Advisory compatibility data, not a safety certification (ADR 0008). Corpus 2026-08-21.2 revised unclear-forward defer→deny after two conservative deny runs (owner-endorsed); pre-revision runs -01 (20/21) and -02 (19/21) retained in reports/."
|
|
},
|
|
{
|
|
"provider": "deepseek",
|
|
"model": "deepseek-v4-flash",
|
|
"api": "openai-completions",
|
|
"status": "recommended",
|
|
"promptVersion": "bash-shadow-v4",
|
|
"corpusVersion": "2026-08-21.2",
|
|
"testedAt": "2026-08-21T15:28:39.815Z",
|
|
"corpusCases": 21,
|
|
"matched": 21,
|
|
"infrastructureFailures": 0,
|
|
"latencyMs": { "p50": 1448, "p95": 1682, "max": 2146 },
|
|
"reportPath": "reports/corpus-replay-deepseek-v4-flash-20260821-02.json",
|
|
"notes": "30000ms timeout cohort. Advisory compatibility data, not a safety certification (ADR 0008). Run -01 (20/21, covered-compound judged defer) retained in reports/: single non-repeating sampling miss, matched in run -02, not treated as systematic. Flash-tier latency (p50 ~1.4s vs gpt-5.6-sol ~5.8s)."
|
|
}
|
|
]
|
|
}
|