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]>
2026-10-19 03:38:38 +01:00
parent d49f524fe8
commit 6a2665dae9
223 changed files with 12342 additions and 162 deletions
@@ -0,0 +1,50 @@
+import grabHarnessAdapter from "../providers/grab-harness-adapter";
+import resolveHarnessCandidates from "../resolve/resolve-harness-candidates";
+import withCandidates from "../resolve/with-candidates";
+
+type Params = {
+    prompt: string;
+    n?: number;
+    size?: string;
+    /**
+     * Reference images: https or `data:` URLs.
+     */
+    references?: string[];
+    signal?: AbortSignal;
+    /**
+     * Uses this bot's image model when it has its own.
+     */
+    bot_id?: number | string;
+};
+
+/**
+ * Makes images with the image generation harness. Returns their bytes.
+ */
+export default async function generateImage({
+    prompt,
+    n,
+    size,
+    references,
+    signal,
+    bot_id,
+}: Params) {
+    const candidates = await resolveHarnessCandidates({ harness: "image", bot_id });
+
+    const { result } = await withCandidates({
+        harness: "image",
+        candidates,
+        run: async (candidate) =>
+            await grabHarnessAdapter({
+                kind: candidate.provider.kind,
+            }).generateImage({
+                candidate,
+                prompt,
+                n,
+                size,
+                references,
+                signal: signal || new AbortController().signal,
+            }),
+    });
+
+    return result.images;
+}