vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-06 15:10:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: gate max thinking by model support

Browse Source
This commit is contained in:
Peter Steinberger
2026-04-21 06:47:06 +01:00
parent f89740a62c
commit 6ce17db11a
49 changed files with 510 additions and 73 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/concepts/active-memory.md
View File

@@ -625,7 +625,7 @@ The most important fields are:
| `config.model` | `string` | Optional blocking memory sub-agent model ref; when unset, active memory uses the current session model |
| `config.queryMode` | `"message" \| "recent" \| "full"` | Controls how much conversation the blocking memory sub-agent sees |
| `config.promptStyle` | `"balanced" \| "strict" \| "contextual" \| "recall-heavy" \| "precision-heavy" \| "preference-only"` | Controls how eager or strict the blocking memory sub-agent is when deciding whether to return memory |
| `config.thinking` | `"off" \| "minimal" \| "low" \| "medium" \| "high" \| "xhigh" \| "adaptive"` | Advanced thinking override for the blocking memory sub-agent; default `off` for speed |
| `config.thinking` | `"off" \| "minimal" \| "low" \| "medium" \| "high" \| "xhigh" \| "adaptive" \| "max"` | Advanced thinking override for the blocking memory sub-agent; default `off` for speed |
| `config.promptOverride` | `string` | Advanced full prompt replacement; not recommended for normal use |
| `config.promptAppend` | `string` | Advanced extra instructions appended to the default or overridden prompt |
| `config.timeoutMs` | `number` | Hard timeout for the blocking memory sub-agent, capped at 120000 ms |

3
docs/concepts/model-providers.md
View File

@@ -43,7 +43,7 @@ For model selection rules, see [/concepts/models](/concepts/models).
`matchesContextOverflowError`, `classifyFailoverReason`,
`isCacheTtlEligible`, `buildMissingAuthMessage`, `suppressBuiltInModel`,
`augmentModelCatalog`, `isBinaryThinking`, `supportsXHighThinking`,
`supportsAdaptiveThinking`,
`supportsAdaptiveThinking`, `supportsMaxThinking`,
`resolveDefaultThinkingLevel`, `applyConfigDefaults`, `isModernModelRef`,
`prepareRuntimeAuth`, `resolveUsageAuth`, `fetchUsageSnapshot`, and
`onModelSelected`.
@@ -135,6 +135,7 @@ Typical split:
- `isBinaryThinking`: provider owns binary on/off thinking UX
- `supportsXHighThinking`: provider opts selected models into `xhigh`
- `supportsAdaptiveThinking`: provider opts selected models into `adaptive`
- `supportsMaxThinking`: provider opts selected models into `max`
- `resolveDefaultThinkingLevel`: provider owns default `/think` policy for a
model family
- `applyConfigDefaults`: provider applies provider-specific global defaults