docs: refresh openai compatible proxy guides

docs/concepts/model-providers.md

@@ -628,6 +628,10 @@ Notes:
   - `maxTokens: 8192`
 - Recommended: set explicit values that match your proxy/model limits.
 - For `api: "openai-completions"` on non-native endpoints (any non-empty `baseUrl` whose host is not `api.openai.com`), OpenClaw forces `compat.supportsDeveloperRole: false` to avoid provider 400 errors for unsupported `developer` roles.
+- Proxy-style OpenAI-compatible routes also skip native OpenAI-only request
+  shaping: no `service_tier`, no Responses `store`, no prompt-cache hints, no
+  OpenAI reasoning-compat payload shaping, and no hidden OpenClaw attribution
+  headers.
 - If `baseUrl` is empty/omitted, OpenClaw keeps the default OpenAI behavior (which resolves to `api.openai.com`).
 - For safety, an explicit `compat.supportsDeveloperRole: true` is still overridden on non-native `openai-completions` endpoints.
 

docs/providers/claude-max-api-proxy.md

@@ -94,6 +94,15 @@ You can point OpenClaw at the proxy as a custom OpenAI-compatible endpoint:
 }
 ```
 
+This path uses the same proxy-style OpenAI-compatible route as other custom
+`/v1` backends:
+
+- native OpenAI-only request shaping does not apply
+- no `service_tier`, no Responses `store`, no prompt-cache hints, and no
+  OpenAI reasoning-compat payload shaping
+- hidden OpenClaw attribution headers (`originator`, `version`, `User-Agent`)
+  are not injected on the proxy URL
+
 ## Available Models
 
 | Model ID          | Maps To         |

docs/providers/litellm.md

@@ -145,8 +145,13 @@ curl "http://localhost:4000/spend/logs" \
 ## Notes
 
 - LiteLLM runs on `http://localhost:4000` by default
-- OpenClaw connects via the OpenAI-compatible `/v1/chat/completions` endpoint
-- All OpenClaw features work through LiteLLM — no limitations
+- OpenClaw connects through LiteLLM's proxy-style OpenAI-compatible `/v1`
+  endpoint
+- Native OpenAI-only request shaping does not apply through LiteLLM:
+  no `service_tier`, no Responses `store`, no prompt-cache hints, and no
+  OpenAI reasoning-compat payload shaping
+- Hidden OpenClaw attribution headers (`originator`, `version`, `User-Agent`)
+  are not injected on custom LiteLLM base URLs
 
 ## See also
 

docs/providers/sglang.md

@@ -102,3 +102,14 @@ curl http://127.0.0.1:30000/v1/models
 - If requests fail with auth errors, set a real `SGLANG_API_KEY` that matches
   your server configuration, or configure the provider explicitly under
   `models.providers.sglang`.
+
+## Proxy-style behavior
+
+SGLang is treated as a proxy-style OpenAI-compatible `/v1` backend, not a
+native OpenAI endpoint.
+
+- native OpenAI-only request shaping does not apply here
+- no `service_tier`, no Responses `store`, no prompt-cache hints, and no
+  OpenAI reasoning-compat payload shaping
+- hidden OpenClaw attribution headers (`originator`, `version`, `User-Agent`)
+  are not injected on custom SGLang base URLs

docs/providers/vllm.md

@@ -90,3 +90,14 @@ curl http://127.0.0.1:8000/v1/models
 ```
 
 - If requests fail with auth errors, set a real `VLLM_API_KEY` that matches your server configuration, or configure the provider explicitly under `models.providers.vllm`.
+
+## Proxy-style behavior
+
+vLLM is treated as a proxy-style OpenAI-compatible `/v1` backend, not a native
+OpenAI endpoint.
+
+- native OpenAI-only request shaping does not apply here
+- no `service_tier`, no Responses `store`, no prompt-cache hints, and no
+  OpenAI reasoning-compat payload shaping
+- hidden OpenClaw attribution headers (`originator`, `version`, `User-Agent`)
+  are not injected on custom vLLM base URLs