docs: refresh xai and zai provider refs

docs/concepts/model-providers.md

@@ -126,7 +126,11 @@ Current bundled examples:
   normalization, proxy-Gemini thought-signature sanitation, and cache-TTL
   policy
 - `zai`: GLM-5 forward-compat fallback, `tool_stream` defaults, cache-TTL
-  policy, binary-thinking/live-model policy, and usage auth + quota fetching
+  policy, binary-thinking/live-model policy, and usage auth + quota fetching;
+  unknown `glm-5*` ids synthesize from the bundled `glm-4.7` template
+- `xai`: native Responses transport normalization, `/fast` alias rewrites for
+  Grok fast variants, default `tool_stream`, and xAI-specific tool-schema /
+  reasoning-payload cleanup
 - `mistral`: plugin-owned capability metadata
 - `opencode` and `opencode-go`: plugin-owned capability metadata plus
   proxy-Gemini thought-signature sanitation
@@ -369,6 +373,12 @@ See [/providers/kilocode](/providers/kilocode) for setup details.
 - BytePlus: `byteplus` (`BYTEPLUS_API_KEY`)
 - Example model: `byteplus-plan/ark-code-latest`
 - xAI: `xai` (`XAI_API_KEY`)
+  - Native bundled xAI requests use the xAI Responses path
+  - `/fast` or `params.fastMode: true` rewrites `grok-3`, `grok-3-mini`,
+    `grok-4`, and `grok-4-0709` to their `*-fast` variants
+  - `tool_stream` defaults on; set
+    `agents.defaults.models["xai/<model>"].params.tool_stream` to `false` to
+    disable it
 - Mistral: `mistral` (`MISTRAL_API_KEY`)
 - Example model: `mistral/mistral-large-latest`
 - CLI: `openclaw onboard --auth-choice mistral-api-key`

docs/plugins/architecture.md

@@ -803,6 +803,13 @@ api.registerProvider({
   `tool_stream` defaults, binary thinking UX, modern-model matching, and both
   usage auth + quota fetching; the `tool-stream-default-on` stream family keeps
   the default-on `tool_stream` wrapper out of per-provider handwritten glue.
+- xAI uses `normalizeResolvedModel`, `normalizeTransport`,
+  `contributeResolvedModelCompat`, `prepareExtraParams`, `wrapStreamFn`,
+  `resolveSyntheticAuth`, `resolveDynamicModel`, and `isModernModelRef`
+  because it owns native xAI Responses transport normalization, Grok fast-mode
+  alias rewrites, default `tool_stream`, strict-tool / reasoning-payload
+  cleanup, fallback auth reuse for plugin-owned tools, forward-compat Grok
+  model resolution, and provider-owned compat patches.
 - Mistral, OpenCode Zen, and OpenCode Go use `capabilities` only to keep
   transcript/tooling quirks out of core.
 - Catalog-only bundled providers such as `byteplus`, `cloudflare-ai-gateway`,

docs/plugins/sdk-provider-plugins.md

@@ -317,6 +317,13 @@ API key auth, and dynamic model resolution.
     `contract-api.ts` seam. Those helpers remain Anthropic-specific because
     they also encode Claude OAuth beta handling and `context1m` gating.
 
+    Other bundled providers also keep transport-specific wrappers local when
+    the behavior is not shared cleanly across families. Current example: the
+    bundled xAI plugin keeps native xAI Responses shaping in its own
+    `wrapStreamFn`, including `/fast` alias rewrites, default `tool_stream`,
+    unsupported strict-tool cleanup, and xAI-specific reasoning-payload
+    removal.
+
     The same package-root pattern also backs other bundled providers:
 
     - `@openclaw/openai-provider`: `api.ts` exports provider builders,

docs/providers/xai.md

@@ -48,6 +48,17 @@ OpenClaw now includes these xAI model families out of the box:
 The plugin also forward-resolves newer `grok-4*` and `grok-code-fast*` ids when
 they follow the same API shape.
 
+Fast-model notes:
+
+- `grok-4-fast`, `grok-4-1-fast`, and the `grok-4.20-beta-*` variants are the
+  current image-capable Grok refs in the bundled catalog.
+- `/fast on` or `agents.defaults.models["xai/<model>"].params.fastMode: true`
+  rewrites native xAI requests as follows:
+  - `grok-3` -> `grok-3-fast`
+  - `grok-3-mini` -> `grok-3-mini-fast`
+  - `grok-4` -> `grok-4-fast`
+  - `grok-4-0709` -> `grok-4-fast`
+
 Legacy compatibility aliases still normalize to the canonical bundled ids. For
 example:
 
@@ -72,6 +83,11 @@ openclaw config set tools.web.search.provider grok
 ## Notes
 
 - OpenClaw applies xAI-specific tool-schema and tool-call compatibility fixes automatically on the shared runner path.
+- Native xAI requests default `tool_stream: true`. Set
+  `agents.defaults.models["xai/<model>"].params.tool_stream` to `false` to
+  disable it.
+- The bundled xAI wrapper strips unsupported strict tool-schema flags and
+  reasoning payload keys before sending native xAI requests.
 - `web_search`, `x_search`, and `code_execution` are exposed as OpenClaw tools. OpenClaw enables the specific xAI built-in it needs inside each tool request instead of attaching all native tools to every chat turn.
 - `x_search` and `code_execution` are owned by the bundled xAI plugin rather than hardcoded into the core model runtime.
 - `code_execution` is remote xAI sandbox execution, not local [`exec`](/tools/exec).

docs/providers/zai.md

@@ -66,6 +66,9 @@ OpenClaw currently seeds the bundled `zai` provider with:
 
 - GLM models are available as `zai/<model>` (example: `zai/glm-5`).
 - Default bundled model ref: `zai/glm-5`
+- Unknown `glm-5*` ids still forward-resolve on the bundled provider path by
+  synthesizing provider-owned metadata from the `glm-4.7` template when the id
+  matches the current GLM-5 family shape.
 - `tool_stream` is enabled by default for Z.AI tool-call streaming. Set
   `agents.defaults.models["zai/<model>"].params.tool_stream` to `false` to disable it.
 - See [/providers/glm](/providers/glm) for the model family overview.