diff --git a/.openclaw-sync/source.json b/.openclaw-sync/source.json
index 58cc1db7a..371cf0bd5 100644
--- a/.openclaw-sync/source.json
+++ b/.openclaw-sync/source.json
@@ -1,5 +1,5 @@
 {
   "repository": "openclaw/openclaw",
-  "sha": "496a5eb56f466e828e7f843a0a55dfc7fbe01199",
-  "syncedAt": "2026-04-27T22:32:18.241Z"
+  "sha": "d2320e4d4b426e16de9ca0701fb8f1bc1488a12a",
+  "syncedAt": "2026-04-27T22:33:48.088Z"
 }
diff --git a/docs/concepts/model-failover.md b/docs/concepts/model-failover.md
index 65074b4ec..db2bd0f8f 100644
--- a/docs/concepts/model-failover.md
+++ b/docs/concepts/model-failover.md
@@ -24,7 +24,7 @@ For a normal text run, OpenClaw evaluates candidates in this order:
     Resolve the active session model and auth-profile preference.
   </Step>
   <Step title="Build candidate chain">
-    Build the model candidate chain from the currently selected session model, then `agents.defaults.model.fallbacks` in order, ending with the configured primary when the run started from an override.
+    Build the model candidate chain from the configured model or an auto-selected fallback model, then `agents.defaults.model.fallbacks` in order. Explicit user model selections are strict and do not silently fall back to a different model.
   </Step>
   <Step title="Try the current provider">
     Try the current provider with auth-profile rotation/cooldown rules.
@@ -207,7 +207,7 @@ If all profiles for a provider fail, OpenClaw moves to the next model in `agents
 
 Overloaded and rate-limit errors are handled more aggressively than billing cooldowns. By default, OpenClaw allows one same-provider auth-profile retry, then switches to the next configured model fallback without waiting. Provider-busy signals such as `ModelNotReadyException` land in that overloaded bucket. Tune this with `auth.cooldowns.overloadedProfileRotations`, `auth.cooldowns.overloadedBackoffMs`, and `auth.cooldowns.rateLimitedProfileRotations`.
 
-When a run starts with a model override (hooks or CLI), fallbacks still end at `agents.defaults.model.primary` after trying any configured fallbacks.
+When a run starts from the configured primary or an auto-selected fallback override, OpenClaw can walk the configured fallback chain. Explicit user selections (for example `/model ollama/qwen3.5:27b`, the model picker, or one-off CLI provider/model overrides) are strict: if that provider/model is unreachable or fails before producing a reply, OpenClaw reports the failure instead of answering from an unrelated fallback.
 
 ### Candidate chain rules
 
@@ -264,6 +264,7 @@ That means fallback retries have to coordinate with live model switching:
 
 - Only explicit user-driven model changes mark a pending live switch. That includes `/model`, `session_status(model=...)`, and `sessions.patch`.
 - System-driven model changes such as fallback rotation, heartbeat overrides, or compaction never mark a pending live switch on their own.
+- User-driven model overrides are treated as exact selections for fallback policy, so an unreachable selected provider surfaces as a failure instead of being masked by `agents.defaults.model.fallbacks`.
 - Before a fallback retry starts, the reply runner persists the selected fallback override fields to the session entry.
 - Auto fallback overrides remain selected on subsequent turns so OpenClaw does not probe a known-bad primary on every message. `/new`, `/reset`, and `sessions.reset` clear auto-sourced overrides and return the session to the configured default.
 - `/status` shows the selected model and, when fallback state differs, the active fallback model and reason.
diff --git a/docs/concepts/models.md b/docs/concepts/models.md
index a508dce6f..0d37d7e07 100644
--- a/docs/concepts/models.md
+++ b/docs/concepts/models.md
@@ -156,6 +156,7 @@ You can switch models for the current session without restarting:
     - If the agent is idle, the next run uses the new model right away.
     - If a run is already active, OpenClaw marks a live switch as pending and only restarts into the new model at a clean retry point.
     - If tool activity or reply output has already started, the pending switch can stay queued until a later retry opportunity or the next user turn.
+    - A user-selected `/model` ref is strict for that session: if the selected provider/model is unreachable, the reply fails visibly instead of silently answering from `agents.defaults.model.fallbacks`.
     - `/model status` is the detailed view (auth candidates and, when configured, provider endpoint `baseUrl` + `api` mode).
   </Accordion>
   <Accordion title="Ref parsing">
diff --git a/docs/providers/ollama.md b/docs/providers/ollama.md
index 93e26b5e7..0176c7d10 100644
--- a/docs/providers/ollama.md
+++ b/docs/providers/ollama.md
@@ -210,6 +210,11 @@ transport, but it does not start a chat-agent turn or load MCP/tool context. If
 this succeeds while normal agent replies fail, troubleshoot the model's agent
 prompt/tool capacity next.
 
+When you switch a conversation with `/model ollama/<model>`, OpenClaw treats
+that as an exact user selection. If the configured Ollama `baseUrl` is
+unreachable, the next reply fails with the provider error instead of silently
+answering from another configured fallback model.
+
 Live-verify the local text path, native stream path, and embeddings against
 local Ollama with: