docs: clarify provider attribution behavior

docs/concepts/model-providers.md

@@ -197,6 +197,9 @@ OpenClaw ships with the pi‑ai catalog. These providers require **no**
 - Default transport is `auto` (WebSocket-first, SSE fallback)
 - Override per model via `agents.defaults.models["openai-codex/<model>"].params.transport` (`"sse"`, `"websocket"`, or `"auto"`)
 - `params.serviceTier` is also forwarded on native Codex Responses requests (`chatgpt.com/backend-api`)
+- Hidden OpenClaw attribution headers (`originator`, `version`,
+  `User-Agent`) are only attached on native Codex traffic to
+  `chatgpt.com/backend-api`, not generic OpenAI-compatible proxies
 - Shares the same `/fast` toggle and `params.fastMode` config as direct `openai/*`; OpenClaw maps that to `service_tier=priority`
 - `openai-codex/gpt-5.3-codex-spark` remains available when the Codex OAuth catalog exposes it; entitlement-dependent
 - `openai-codex/gpt-5.4` keeps native `contextWindow = 1050000` and a default runtime `contextTokens = 272000`; override the runtime cap with `models.providers.openai-codex.models[].contextTokens`
@@ -290,6 +293,8 @@ See [/providers/kilocode](/providers/kilocode) for setup details.
 
 - OpenRouter: `openrouter` (`OPENROUTER_API_KEY`)
 - Example model: `openrouter/auto`
+- OpenClaw applies OpenRouter's documented app-attribution headers only when
+  the request actually targets `openrouter.ai`
 - Kilo Gateway: `kilocode` (`KILOCODE_API_KEY`)
 - Example model: `kilocode/anthropic/claude-opus-4.6`
 - MiniMax: `minimax` (`MINIMAX_API_KEY`)

docs/providers/openai.md

@@ -358,8 +358,15 @@ from generic OpenAI-compatible `/v1` proxies:
 - native `openai/*`, `openai-codex/*`, and Azure OpenAI routes keep
   `reasoning: { effort: "none" }` intact when you explicitly disable reasoning
 - native OpenAI-family routes default tool schemas to strict mode
+- hidden OpenClaw attribution headers (`originator`, `version`, and
+  `User-Agent`) are only attached on verified native OpenAI hosts
+  (`api.openai.com`) and native Codex hosts (`chatgpt.com/backend-api`)
 - proxy-style OpenAI-compatible routes keep the looser compat behavior and do
-  not force strict tool schemas or native-only request shaping
+  not force strict tool schemas, native-only request shaping, or hidden
+  OpenAI/Codex attribution headers
+
+Azure OpenAI stays in the native-routing bucket for transport and compat
+behavior, but it does not receive the hidden OpenAI/Codex attribution headers.
 
 This preserves current native OpenAI Responses behavior without forcing older
 OpenAI-compatible shims onto third-party `/v1` backends.

docs/providers/openrouter.md

@@ -37,3 +37,9 @@ openclaw onboard --auth-choice openrouter-api-key
   `openclaw models set openrouter/<provider>/<model>`.
 - For more model/provider options, see [/concepts/model-providers](/concepts/model-providers).
 - OpenRouter uses a Bearer token with your API key under the hood.
+- On real OpenRouter requests (`https://openrouter.ai/api/v1`), OpenClaw also
+  adds OpenRouter's documented app-attribution headers:
+  `HTTP-Referer: https://openclaw.ai`, `X-OpenRouter-Title: OpenClaw`, and
+  `X-OpenRouter-Categories: cli-agent`.
+- If you repoint the OpenRouter provider at some other proxy/base URL, OpenClaw
+  does not inject those OpenRouter-specific headers.