fix: older defects (batch C) and the second batch's review

Chats:
- New Chat right after an answer saves that chat once. Saves run one at
  a time and read the chat on screen when their turn comes; a save
  scheduled for a chat that is no longer on screen is dropped. A chat
  whose id was still on its way to the URL no longer comes back after
  New Chat (the next answer went into it).
- Crossing the 768 px breakpoint keeps the chat panel: a streaming answer,
  unsaved messages and attachments stay. The panel gets the sizes of each
  side, and a panel collapsed on desktop opens on mobile.
- The chat's export waits for its own reply: an edit's history export
  still on its way no longer answers it with the older diagram, and two
  file saves at once no longer swap results.
- A second edit in one answer is previewed on the first edit's result.
- Stop also ends a running screenshot check; a chat that cannot be saved
  (storage full) can be left with "Continue without saving".
- Small diagrams with shapes count as diagrams; the tool card no longer
  crashes on malformed operations.

Quota and providers:
- Requests that reach the server's own endpoints count toward the quota:
  EdgeOne (always its own endpoint now), a private base URL whatever key
  header is sent, keyless Ollama without a URL. With the quota on, a
  redirect is followed only to a public address. The output cap applies
  to these requests too.
- Stop records the tokens of the steps that finished; the screenshot check
  counts its tokens without counting a request.
- EdgeOne configured only by AI_PROVIDER works, also in the admin Test,
  which forwards the access code. Azure set up only in the admin panel
  works in chat. The Test sends a Bedrock session token.
- The admin panel's Test of an entry without a URL uses the server's URL
  as the server does (no private address check for it); the admin panel
  no longer writes an Ollama URL.

MCP server:
- Write tools and start_session run one at a time, so two at once never
  drop each other's change; a cancelled call waiting its turn is skipped.
  get_diagram and export_diagram keep the session they started with.
- Export to .drawio first gets the user's latest edits from the browser.
- History thumbnails: one that arrives after the next AI write is
  dropped; a sync reply keeps the image; a version that changed only page
  settings is its own entry.
- A diagram over the 10 MB limit is saved without its image, or the user
  is told to download it (the server now answers 413 instead of cutting
  the connection).
- Labels holding text like id='1' or parent='1' are no longer read as
  attributes (a layer or a parent was deleted). A broken bare
  <mxGraphModel> file is refused.
- After a sync reply the tab no longer sends its autosave copy again.

Desktop and files:
- A newer switch of the same preset is not rolled back by an older one
  that failed. .env values with escaped quotes are read whole.
- MCP saved files: a file that could not be read stays protected while a
  folder without permission hides it, and is saved again once deleted.
- The desktop app reports "no chats" only when the count was read and no
  model settings are stored.

app/api/admin/test-model/route.ts

@@ -48,6 +48,7 @@ export async function POST(req: Request) {
         sameEndpoint && stored ? [stored] : [],
     )
 
+    const serverUrl = globalBaseUrl(resolved.provider)
     return validateModel(
         new Request(new URL("/api/validate-model", req.url), {
             method: "POST",
@@ -55,14 +56,23 @@ export async function POST(req: Request) {
                 "Content-Type": "application/json",
                 // Checked again there, in place of an access code
                 "x-admin-password": req.headers.get("x-admin-password") || "",
+                // The EdgeOne function checks the access code and Pages
+                // cookies, and its URL is built from the page's origin
+                "x-access-code": req.headers.get("x-access-code") || "",
+                cookie: req.headers.get("cookie") || "",
+                ...(req.headers.get("origin") && {
+                    origin: req.headers.get("origin") as string,
+                }),
             },
             body: JSON.stringify({
                 provider: resolved.provider,
                 apiKey: resolved.apiKey,
                 // Without a URL of its own, chat sends the entry's key to
                 // the server's <P>_BASE_URL: test that endpoint, not
-                // another one
-                baseUrl: resolved.baseUrl || globalBaseUrl(resolved.provider),
+                // another one. It is the server's own, which chat uses
+                // without the checks for a URL a user typed.
+                baseUrl: resolved.baseUrl || serverUrl,
+                ...(!resolved.baseUrl && serverUrl && { serverBaseUrl: true }),
                 modelId: body.modelId,
                 awsAccessKeyId: resolved.awsAccessKeyId,
                 awsSecretAccessKey: resolved.awsSecretAccessKey,