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 +1,45 @@
+import type { HarnessKind } from "@/src/dict/harness-dict";
+import type { HarnessModelInfo } from "../types";
+
+type Params = {
+    model: Pick<
+        HarnessModelInfo,
+        "input_modalities" | "output_modalities" | "supports_tools"
+    >;
+    harness: HarnessKind;
+};
+
+/**
+ * Whether a model can do a harness's job:
+ * - text: reads and writes text, and calls tools (bots work through tools)
+ * - vision: reads images, writes text
+ * - transcription: a speech-to-text model, or a chat model that hears audio
+ * - speech: a text-to-speech model
+ * - image: makes images
+ */
+export default function modelServesHarness({ model, harness }: Params) {
+    const input = new Set(model.input_modalities);
+    const output = new Set(model.output_modalities);
+
+    switch (harness) {
+        case "text":
+            return (
+                input.has("text") && output.has("text") && model.supports_tools
+            );
+
+        case "vision":
+            return input.has("image") && output.has("text");
+
+        case "transcription":
+            return (
+                output.has("transcription") ||
+                (input.has("audio") && output.has("text"))
+            );
+
+        case "speech":
+            return output.has("speech");
+
+        case "image":
+            return output.has("image");
+    }
+}