openclaw/docs
openclaw/docs
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore(sync): mirror docs from openclaw/openclaw@d4d307e07a

Browse Source
This commit is contained in:
openclaw-docs-sync[bot] 2026-04-24 00:33:15 +00:00
parent 85b3366a93
commit dba19f41f6
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
.openclaw-sync/source.json
View File

@ -1,5 +1,5 @@
{
"repository": "openclaw/openclaw",
"sha": "d16b879334eeec07e610b1ea0063fbd134b61048",
"syncedAt": "2026-04-23T23:37:00.444Z"
"sha": "d4d307e07a863823bbb401fdaeb6c00ebeaf4dfa",
"syncedAt": "2026-04-24T00:31:44.575Z"
}

2
docs/tools/thinking.md
View File

@ -13,7 +13,7 @@ title: "Thinking levels"
- low → “think hard”
- medium → “think harder”
- high → “ultrathink” (max budget)
- xhigh → “ultrathink+” (GPT-5.2 + Codex models and Anthropic Claude Opus 4.7 effort)
- xhigh → “ultrathink+” (GPT-5.2+ and Codex models, plus Anthropic Claude Opus 4.7 effort)
- adaptive → provider-managed adaptive thinking (supported for Claude 4.6 on Anthropic/Bedrock and Anthropic Claude Opus 4.7)
- max → provider max reasoning (currently Anthropic Claude Opus 4.7)
- `x-high`, `x_high`, `extra-high`, `extra high`, and `extra_high` map to `xhigh`.