Add computer switching, crew reporting, job steps and markdown chat

- Bots have a current computer (bots.computer_id), switched from the chat
  header beside the model button or by clicking a computer the bot names
  ([computer:ID]); tasks run on it by default
- search_computers runs one read-only command on all of a bot's computers;
  chat replies know their computers (compose-computers-note)
- The coordinator can use every computer and grants or revokes crew access
  with assign_computer
- Delegated jobs record requested_by_bot_id; the worker's result or failure
  is reported back in the coordinator's conversation
- bots_queue_updates records each model turn of a job, pushed live and shown
  in the working-on panel
- Live relay: every process pushes new messages, job steps and bot changes
  from the database to its own sockets, so work done elsewhere shows live
- Bot messages render as markdown (react-markdown + remark-gfm, no raw HTML)
  with twui components; rail previews are plain text
- Fix header button overflow in the model and computer selects
- Bump @moduletrace/twui to 0.1.2

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

src/bots-queue/run-bot-task.ts

@@ -1,8 +1,11 @@
 import { TaskRunNote } from "@/src/data/harness-prompts";
+import grabBotComputers from "@/src/functions/backend/db/computers/grab-bot-computers";
 import grabBotPrompt from "@/src/functions/backend/db/bots/grab-bot-prompt";
 import runTextLoop from "@/src/harness/text/run-text-loop";
 import openComputerTools from "@/src/harness/tools/computer/open-computer-tools";
 import grabBotTools from "@/src/harness/tools/bot/grab-bot-tools";
+import searchComputersTool from "@/src/harness/tools/computer/search-computers-tool";
+import computerRef from "@/src/utils/computer-ref";
 import composeJobBrief from "./compose-job-brief";
 import type { BotJobContext, BotJobOutcome } from "./types";
 
@@ -12,16 +15,16 @@ type Params = BotJobContext & {
 
 /**
  * Works through a task: the bot follows its brief with its full prompt,
- * its own tools and, when the job has a computer, that computer's tools
- * (over MCP), until it answers. That answer is the report for the user.
- * Progress is saved after every model turn.
+ * its own tools, search_computers across all its computers and, when the
+ * job has a computer, that computer's tools (over MCP), until it answers. That answer is the report for the user.
+ * Every model turn is reported as a step (`report`).
  */
 export default async function runBotTask({
     bot,
     job,
     params,
     signal,
-    update,
+    report,
 }: Params): Promise<BotJobOutcome> {
     const computer = job.computer_id
         ? await openComputerTools({ computer_id: job.computer_id, bot_id: bot.id, signal })
@@ -29,6 +32,7 @@ export default async function runBotTask({
 
     try {
         const prompt = await grabBotPrompt({ bot_id: bot.id, user_id: bot.user_id });
+        const computers = await grabBotComputers({ bot_id: bot.id, user_id: bot.user_id });
 
         const result = await runTextLoop({
             system: [
@@ -37,6 +41,9 @@ export default async function runBotTask({
                 computer
                     ? `You're working on the computer "${computer.name}" (a Linux sandbox with a shell, files, code runners and a browser). Use its tools; don't ask the user to run anything.`
                     : `You have no computer for this task.`,
+                computers.length > 1
+                    ? `search_computers runs a read-only command on every computer you have. When you name one in the report, write its ref, e.g. ${computerRef({ id: computers[0]!.id || 0 })}: the user can click it to switch you to that computer.`
+                    : "",
                 computer?.envs.length
                     ? `Environment variables set on this computer (use them by name, e.g. $KEY; never print their values):\n${computer.envs
                           .map((env) => `- ${env.key}${env.description ? `: ${env.description}` : ""}`)
@@ -57,17 +64,13 @@ export default async function runBotTask({
             ],
             tools: [
                 ...grabBotTools({ user_id: bot.user_id, bot_id: bot.id }),
+                ...(computers.length ? [searchComputersTool({ bot_id: bot.id, computers })] : []),
                 ...(computer?.tools || []),
             ],
             bot_id: bot.id,
             signal,
-            onStep: async ({ text, tool_calls }) => {
-                await update({
-                    progress: tool_calls.length
-                        ? `Using ${tool_calls.map((call) => call.name).join(", ")}`
-                        : text?.slice(0, 500) || undefined,
-                });
-            },
+            onStep: (step) =>
+                report({ ...step, text: step.text && computer ? computer.redact(step.text) : step.text }),
         });
 
         return { result: computer ? computer.redact(result.text) : result.text };