proxy,ui-svelte: add request/response capturing (#508)

Add saving request and response headers and bodies that go through
llama-swap in memory.

- captureBuffer added to configuration. Captures are enabled by default.
- 5MB of memory is allocated for req/response captures in a ring buffer.
Setting captureBuffer to 0 will disable captures.
- UI elements to view captured data added to Activity page. Includes
some
QOL features like json formatting and recombining SSE chat streams
- capture saving is done at the byte level and has minimal impact on
llama-swap performance

Fixes #464 
Ref #503

ui-svelte/src/stores/api.ts

@@ -1,5 +1,5 @@
 import { writable } from "svelte/store";
-import type { Model, Metrics, VersionInfo, LogData, APIEventEnvelope } from "../lib/types";
+import type { Model, Metrics, VersionInfo, LogData, APIEventEnvelope, ReqRespCapture } from "../lib/types";
 import { connectionState } from "./theme";
 
 const LOG_LENGTH_LIMIT = 1024 * 100; /* 100KB of log data */
@@ -172,3 +172,19 @@ export async function loadModel(model: string): Promise<void> {
     throw error;
   }
 }
+
+export async function getCapture(id: number): Promise<ReqRespCapture | null> {
+  try {
+    const response = await fetch(`/api/captures/${id}`);
+    if (response.status === 404) {
+      return null;
+    }
+    if (!response.ok) {
+      throw new Error(`Failed to fetch capture: ${response.status}`);
+    }
+    return await response.json();
+  } catch (error) {
+    console.error("Failed to fetch capture:", error);
+    return null;
+  }
+}