vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-06 08:20:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(deepseek): expose V4 max thinking levels (#73008)

Browse Source 
Merged via squash.

Prepared head SHA: ef561a59de
Co-authored-by: ai-hpc <183861985+ai-hpc@users.noreply.github.com>
Co-authored-by: hxy91819 <8814856+hxy91819@users.noreply.github.com>
Reviewed-by: @hxy91819
This commit is contained in:
NVIDIAN
2026-04-30 08:34:05 -07:00
committed by GitHub
parent 0eb8f34000
commit 797d574dfd
7 changed files with 67 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/providers/deepseek.md
View File

@@ -79,6 +79,8 @@ is available to that process (for example, in `~/.openclaw/.env` or via
V4 models support DeepSeek's `thinking` control. OpenClaw also replays
DeepSeek `reasoning_content` on follow-up turns so thinking sessions with tool
calls can continue.
Use `/think xhigh` or `/think max` with DeepSeek V4 models to request DeepSeek's
maximum `reasoning_effort`.
</Tip>
## Thinking and tools

1
docs/tools/thinking.md
View File

@@ -26,6 +26,7 @@ title: "Thinking levels"
- Anthropic Claude Opus 4.7 does not default to adaptive thinking. Its API effort default remains provider-owned unless you explicitly set a thinking level.
- Anthropic Claude Opus 4.7 maps `/think xhigh` to adaptive thinking plus `output_config.effort: "xhigh"`, because `/think` is a thinking directive and `xhigh` is the Opus 4.7 effort setting.
- Anthropic Claude Opus 4.7 also exposes `/think max`; it maps to the same provider-owned max effort path.
- DeepSeek V4 models expose `/think xhigh|max`; both map to DeepSeek `reasoning_effort: "max"` while lower non-off levels map to `high`.
- Ollama thinking-capable models expose `/think low|medium|high|max`; `max` maps to native `think: "high"` because Ollama's native API accepts `low`, `medium`, and `high` effort strings.
- OpenAI GPT models map `/think` through model-specific Responses API effort support. `/think off` sends `reasoning.effort: "none"` only when the target model supports it; otherwise OpenClaw omits the disabled reasoning payload instead of sending an unsupported value.
- Custom OpenAI-compatible catalog entries can opt into `/think xhigh` by setting `models.providers.<provider>.models[].compat.supportedReasoningEfforts` to include `"xhigh"`. This uses the same compat metadata that maps outbound OpenAI reasoning effort payloads, so menus, session validation, agent CLI, and `llm-task` agree with transport behavior.