fix: align OpenAI reasoning effort handling

docs/providers/openai.md

@@ -514,7 +514,8 @@ Values are case-insensitive at runtime, so `"Off"` and `"off"` both disable the
     OpenClaw treats direct OpenAI, Codex, and Azure OpenAI endpoints differently from generic OpenAI-compatible `/v1` proxies:
 
     **Native routes** (`openai/*`, `openai-codex/*`, Azure OpenAI):
-    - Keep `reasoning: { effort: "none" }` intact when reasoning is explicitly disabled
+    - Keep `reasoning: { effort: "none" }` only for models that support the OpenAI `none` effort
+    - Omit disabled reasoning for models or proxies that reject `reasoning.effort: "none"`
     - Default tool schemas to strict mode
     - Attach hidden attribution headers on verified native hosts only
     - Keep OpenAI-only request shaping (`service_tier`, `store`, reasoning-compat, prompt-cache hints)

docs/tools/thinking.md

@@ -23,6 +23,7 @@ title: "Thinking Levels"
   - Anthropic Claude 4.6 models default to `adaptive` when no explicit thinking level is set.
   - 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.
+  - 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.
   - MiniMax (`minimax/*`) on the Anthropic-compatible streaming path defaults to `thinking: { type: "disabled" }` unless you explicitly set thinking in model params or request params. This avoids leaked `reasoning_content` deltas from MiniMax's non-native Anthropic stream format.
   - Z.AI (`zai/*`) only supports binary thinking (`on`/`off`). Any non-`off` level is treated as `on` (mapped to `low`).
   - Moonshot (`moonshot/*`) maps `/think off` to `thinking: { type: "disabled" }` and any non-`off` level to `thinking: { type: "enabled" }`. When thinking is enabled, Moonshot only accepts `tool_choice` `auto|none`; OpenClaw normalizes incompatible values to `auto`.