prompt caching docs; and edge out of alpha (#7056)

Author: akshaydeo

docs/deployment-guides/config-json/providers.mdx

@@ -67,6 +67,14 @@ Concurrency and buffering per provider:
 | `concurrency_and_buffer_size.concurrency` | integer | Max concurrent requests to this provider |
 | `concurrency_and_buffer_size.buffer_size` | integer | Request queue depth |
 
+Prompt-cache breakpoint injection per provider (see [Auto Prompt Caching](/features/prompt-caching)):
+
+| Field | Type | Description |
+|-------|------|-------------|
+| `prompt_cache.auto_inject` | boolean | Mark the first cacheable block when the caller sent no cache markers. Off by default |
+| `prompt_cache.ttl` | string | Lifetime for injected markers. Only `"1h"` is accepted; omit for the provider default |
+| `prompt_cache.cache_control_injection_points` | array | Target specific messages by `role` and/or `index`. Replaces the first-block strategy when set |
+
 ---
 
 <Tabs>

docs/deployment-guides/config-json/storage.mdx

@@ -135,10 +135,6 @@ This is the recommended setup for [multinode OSS deployments](/deployment-guides
 
 Use `client.hidden_request_types` to hide selected request types from dashboard and log API reads while continuing to store their logs. The same setting is editable in the UI under **Logs Settings**. See [Hiding request types from the dashboard](/architecture/framework/log-store#hiding-request-types-from-the-dashboard) for configuration examples and behavior.
 
-<Tabs>
-
-<Tab title="SQLite">
-
 ### SQLite
 
 ```json

docs/edge/overview.mdx

@@ -8,24 +8,6 @@ icon: "globe"
 <img src="/media/edge/edge-hero.png" alt="Bifrost edge"/>
 </Frame>
 
-<Tip>
-**Bifrost Edge is in alpha.** Be among the first to bring AI on every computer of your organization under governance. Register below and our team will reach out to onboard you.
-
-<button
-  data-tally-open="aQzaGb"
-  data-tally-layout="modal"
-  data-tally-width="700"
-  data-tally-hide-title="1"
-  data-tally-transparent-background="1"
-  className="not-prose mt-2 inline-flex cursor-pointer items-center gap-2 rounded-lg border-0 bg-[rgb(var(--primary-dark))] px-5 py-2.5 text-sm font-semibold text-white no-underline transition-opacity hover:opacity-90"
->
-  Register for Alpha
-  <svg width="14" height="14" viewBox="0 0 16 16" fill="none" xmlns="http://www.w3.org/2000/svg" aria-hidden="true">
-    <path d="M3 8h10M9 4l4 4-4 4" stroke="currentColor" strokeWidth="1.5" strokeLinecap="round" strokeLinejoin="round" />
-  </svg>
-</button>
-</Tip>
-
 ---
 
 Bifrost Edge extends your AI gateway all the way to the endpoint. Instead of relying on every user to point their tools at Bifrost, Edge runs quietly on each machine and brings **all** AI traffic under governance automatically: desktop chat apps, AI in the browser, coding agents in the terminal and IDE, and the MCP servers those tools connect to. Your existing virtual keys, budgets, audit logs, and guardrails now apply to the AI people actually use, not just the traffic that happened to be configured.