docs: raise live model sweep concurrency · openclaw/openclaw@b98a6a4
steipete
·
2026-04-24
·
via Recent Commits to openclaw:main
| Original file line number | Diff line number | Diff line change |
|---|
@@ -53,7 +53,7 @@ Live tests are split into two layers so we can isolate failures:
|
53 | 53 | - or `OPENCLAW_LIVE_MODELS="openai/gpt-5.2,openai-codex/gpt-5.2,anthropic/claude-opus-4-6,..."` (comma allowlist) |
54 | 54 | - Modern/all sweeps default to a curated high-signal cap; set `OPENCLAW_LIVE_MAX_MODELS=0` for an exhaustive modern sweep or a positive number for a smaller cap. |
55 | 55 | - Exhaustive sweeps use `OPENCLAW_LIVE_TEST_TIMEOUT_MS` for the whole direct-model test timeout. Default: 60 minutes. |
56 | | -- Set `OPENCLAW_LIVE_MODEL_CONCURRENCY=10` to run direct-model probes in parallel. Default: 1. |
| 56 | +- Set `OPENCLAW_LIVE_MODEL_CONCURRENCY=20` to run direct-model probes in parallel. Default: 1. |
57 | 57 | - How to select providers: |
58 | 58 | - `OPENCLAW_LIVE_PROVIDERS="google,google-antigravity,google-gemini-cli"` (comma allowlist) |
59 | 59 | - Where keys come from: |
|
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。
