Add the harness, envs, per-bot models and chat attachments

- Harness: providers, model catalog synced hourly, automatic free picks,
  cooldowns, tool loop with context trimming, MCP computer tools
- Bots queue runs replies and tasks through the harness; jobs wait
  (attempt refunded) while every model is resting
- Envs: Settings > Environment, scoped general/workspace/computer,
  written to computers and redacted from tool output
- Models: Settings > Models, per-harness provider select defaulting to
  OpenRouter, and a models modal on each bot's chat (the coordinator's
  edits the defaults)
- Chat: thinking row while a reply runs, file attachments (upload,
  paste, drop) that replies read as images, audio and document text
- Fix media uploads failing after a user's first file, and private
  files being served from the public media path

Co-Authored-By: Claude Opus 5.5 <[email protected]>

src/harness/resolve/create-cooldowns.ts

@@ -0,0 +1,34 @@
+/**
+ * Keys (candidates or providers) that shouldn't be tried until a time.
+ * In memory, per process: a restart forgets them, which only costs one
+ * failed call each.
+ */
+export default function createCooldowns() {
+    const until = new Map<string, number>();
+
+    return {
+        set({ key, at }: { key: string; at: number }) {
+            until.set(key, Math.max(at, until.get(key) || 0));
+        },
+        /**
+         * When the key can be tried again, or undefined if it can now.
+         */
+        get({ key, now = Date.now() }: { key: string; now?: number }) {
+            const at = until.get(key);
+
+            if (at === undefined) return undefined;
+
+            if (at <= now) {
+                until.delete(key);
+                return undefined;
+            }
+
+            return at;
+        },
+        clear() {
+            until.clear();
+        },
+    };
+}
+
+export type HarnessCooldowns = ReturnType<typeof createCooldowns>;