docs: refresh claude-cli model ref mirrors

docs/concepts/oauth.md

@@ -113,9 +113,10 @@ openclaw onboard --auth-choice anthropic-cli
 ```
 
 This keeps existing Anthropic auth profiles for rollback, but rewrites the main
-default-model path from `anthropic/...` to `claude-cli/...`, rewrites matching
-Anthropic Claude fallbacks, and adds matching `claude-cli/...` allowlist
-entries under `agents.defaults.models`.
+default-model path from `anthropic/...` to a canonical
+`claude-cli/claude-*` ref, rewrites matching Anthropic Claude fallbacks, and
+adds matching canonical `claude-cli/claude-*` allowlist entries under
+`agents.defaults.models`.
 
 Verify:
 
@@ -135,7 +136,8 @@ Claude CLI path:
 
 1. sign in with `claude auth login` on the gateway host
 2. run `openclaw models auth login --provider anthropic --method cli --set-default`
-3. store no new auth profile; switch model selection to `claude-cli/...`
+3. store no new auth profile; switch model selection to a canonical
+   `claude-cli/claude-*` ref
 4. keep existing Anthropic auth profiles for rollback
 
 Interactive assistant path:

docs/gateway/authentication.md

@@ -130,8 +130,8 @@ openclaw models auth login --provider anthropic --method cli --set-default
 ```
 
 This keeps your existing Anthropic auth profiles for rollback, but changes the
-default model selection to `claude-cli/...` and adds matching Claude CLI
-allowlist entries under `agents.defaults.models`.
+default model selection to a canonical `claude-cli/claude-*` ref and adds
+matching Claude CLI allowlist entries under `agents.defaults.models`.
 
 Verify:
 

docs/gateway/cli-backends.md

@@ -30,7 +30,7 @@ You can use Claude CLI **without any config** (the bundled Anthropic plugin
 registers a default backend):
 
 ```bash
-openclaw agent --message "hi" --model claude-cli/opus-4.6
+openclaw agent --message "hi" --model claude-cli/claude-sonnet-4-6
 ```
 
 Codex CLI also works out of the box (via the bundled OpenAI plugin):
@@ -73,12 +73,12 @@ Add a CLI backend to your fallback list so it only runs when primary models fail
     defaults: {
       model: {
         primary: "anthropic/claude-opus-4-6",
-        fallbacks: ["claude-cli/opus-4.6", "claude-cli/opus-4.5"],
+        fallbacks: ["claude-cli/claude-sonnet-4-6", "claude-cli/claude-opus-4-6"],
       },
       models: {
         "anthropic/claude-opus-4-6": { alias: "Opus" },
-        "claude-cli/opus-4.6": {},
-        "claude-cli/opus-4.5": {},
+        "claude-cli/claude-sonnet-4-6": {},
+        "claude-cli/claude-opus-4-6": {},
       },
     },
   },
@@ -90,6 +90,9 @@ Notes:
 - If you use `agents.defaults.models` (allowlist), you must include `claude-cli/...`.
 - If the primary provider fails (auth, rate limits, timeouts), OpenClaw will
   try the CLI backend next.
+- The bundled Claude CLI backend still accepts shorter aliases like
+  `claude-cli/opus`, `claude-cli/opus-4.6`, or `claude-cli/sonnet`, but docs
+  and config examples use the canonical `claude-cli/claude-*` refs.
 
 ## Configuration overview
 

docs/providers/anthropic.md

@@ -209,6 +209,10 @@ with model refs like:
 - `claude-cli/claude-sonnet-4-6`
 - `claude-cli/claude-opus-4-6`
 
+Shorter aliases like `claude-cli/sonnet`, `claude-cli/opus`, or
+`claude-cli/opus-4.6` still normalize through the bundled backend, but docs
+and config examples use the canonical `claude-cli/claude-*` refs.
+
 How it works:
 
 1. OpenClaw launches `claude -p --output-format stream-json --include-partial-messages ...`
@@ -300,10 +304,11 @@ Claude CLI** first and **Anthropic API key** second.
 What this does:
 
 - verifies Claude CLI is already signed in on the gateway host
-- switches the default model to `claude-cli/...`
+- switches the default model to a canonical `claude-cli/claude-*` ref
 - rewrites Anthropic default-model fallbacks like `anthropic/claude-opus-4-6`
   to `claude-cli/claude-opus-4-6`
-- adds matching `claude-cli/...` entries to `agents.defaults.models`
+- adds matching canonical `claude-cli/claude-*` entries to
+  `agents.defaults.models`
 
 Quick verification:
 
@@ -311,7 +316,8 @@ Quick verification:
 openclaw models status
 ```
 
-You should see the resolved primary model under `claude-cli/...`.
+You should see the resolved primary model under a canonical
+`claude-cli/claude-*` ref.
 
 What it does **not** do:
 

docs/reference/wizard.md

@@ -31,7 +31,7 @@ For a high-level overview, see [Onboarding (CLI)](/start/wizard).
   </Step>
   <Step title="Model/Auth">
     - **Anthropic API key**: uses `ANTHROPIC_API_KEY` if present or prompts for a key, then saves it for daemon use.
-    - **Anthropic Claude CLI**: preferred Anthropic assistant choice in onboarding/configure. On macOS onboarding checks Keychain item "Claude Code-credentials" (choose "Always Allow" so launchd starts don't block); on Linux/Windows it reuses `~/.claude/.credentials.json` if present and switches model selection to `claude-cli/...`.
+    - **Anthropic Claude CLI**: preferred Anthropic assistant choice in onboarding/configure. On macOS onboarding checks Keychain item "Claude Code-credentials" (choose "Always Allow" so launchd starts don't block); on Linux/Windows it reuses `~/.claude/.credentials.json` if present and switches model selection to a canonical `claude-cli/claude-*` ref.
     - **Anthropic OAuth/token profiles**: still honored at runtime if already configured, but onboarding/configure no longer offers Anthropic setup-token as a new setup path.
     - **OpenAI Code (Codex) subscription (Codex CLI)**: if `~/.codex/auth.json` exists, onboarding can reuse it. Reused Codex CLI credentials stay managed by Codex CLI; on expiry OpenClaw re-reads that source first and, when the provider can refresh it, writes the refreshed credential back to Codex storage instead of taking ownership itself.
     - **OpenAI Code (Codex) subscription (OAuth)**: browser flow; paste the `code#state`.

docs/start/wizard-cli-reference.md

@@ -131,7 +131,7 @@ What you set:
   </Accordion>
   <Accordion title="Anthropic Claude CLI">
     Reuses a local Claude CLI login on the gateway host and switches model
-    selection to `claude-cli/...`.
+    selection to a canonical `claude-cli/claude-*` ref.
 
     This is the preferred interactive Anthropic path in `openclaw onboard` and
     `openclaw configure`.