ENG-12238: document Reflex app scaling and recovery (#7570)

* ENG-12238: document Reflex app scaling and recovery

* ENG-12238: illustrate scaling architecture and job recovery

* ENG-12238: address scaling guide review and test job recovery

* ENG-12238: reset report selection on authentication changes

* ENG-12238: require explicit report requests and isolate docs tests

---------

Co-authored-by: Farhan Ali Raza <62690310+FarhanAliRaza@users.noreply.github.com>

Author: Kastier1

docs/advanced_onboarding/performance_and_execution.md

@@ -5,6 +5,9 @@ meta_description: Compare Reflex performance with Streamlit and Dash using publi
 
 # Performance and execution
 
+For deployment-level capacity and recovery, see [Scaling Reflex Apps](/docs/hosting/scaling/),
+including shared state, independent job workers, and Redis diagnostics.
+
 Reflex combines a customizable React interface with explicit Python state and event handlers. Published comparisons show concrete performance gains over Streamlit and Dash: faster initial data visibility in an NBA dashboard and faster bulk updates in a component-heavy form. The measurements below explain where those gains appeared and how to apply the same rendering and state-management techniques in your app.
 
 ## Reflex vs Streamlit: faster time to visible data

docs/ai_builder/integrations/mcp_overview.md

@@ -12,11 +12,16 @@ The hosted server is available at:
 https://build.reflex.dev/mcp
 ```
 
-## Available tool
+## Documentation tools
 
-The server currently exposes one read-only tool:
+Check your server's `tools/list` response for the tools available in its deployed version. Releases with the knowledge tools provide two read-only documentation operations:
 
-- `search_docs(query)` searches the Reflex documentation index and returns the relevant documentation sections and their source paths.
+- `search_reflex_knowledge(queries)` accepts up to five short keyword queries and returns candidate keys, summaries, and source labels from the bundled documentation and curated knowledge.
+- `get_reflex_knowledge(keys)` fetches the full text for the exact keys returned by search. Fetch the relevant entries before relying on a summary; the server reports unknown keys separately.
+
+For example, search with `{"queries": ["horizontal scaling", "durable jobs", "Redis Sentinel"]}`, then pass the relevant returned key to `get_reflex_knowledge`. The [scaling guide](/docs/hosting/scaling/) explains version compatibility, regional session state, and recovery assumptions. Split more than five topics into separate search calls.
+
+Older deployments may expose `search_docs` instead. Follow the tool schema advertised by the connected server. The knowledge tools use a packaged documentation snapshot, so a website update alone does not refresh the server's corpus; the server release must also update its locked documentation bundle.
 
 Use it for questions about Reflex APIs, components, configuration, and development workflows. Review the returned source before applying a change that depends on version-specific behavior.
 

docs/app/assets/hosting/scaling-architecture.svg

@@ -0,0 +1 @@
+Add a scaling guide with production architecture and job lifecycle diagrams and a Reflex report-job example, covering horizontal backends, state-store version compatibility, durable jobs, regional data routing, telemetry, and Redis recovery checks.

docs/app/assets/hosting/scaling-job-lifecycle.svg

@@ -260,6 +260,7 @@ def get_sidebar_items_hosting():
             "Self Hosting",
             children=[
                 hosting.self_hosting,
+                hosting.scaling,
                 hosting.databricks,
                 hosting.cloud_providers,
                 hosting.bring_your_own_cloud,