Promote v0.32.0 to production

CHANGELOG.md

@@ -2,6 +2,27 @@
 
 This file tracks product releases for Roomote (single monorepo version). Automated release entries are prepended by `pnpm run version`.
 
+## 0.32.0 (2026-08-03)
+
+This release adds OpenCode Go subscriptions, restores convenient automation test runs, refreshes recommended models, and makes license syncing more resilient.
+
+### Highlights
+
+- Let operators connect an OpenCode Go subscription independently from OpenCode Zen and use supported Go models across Roomote task roles.
+- Run enabled custom automations on demand and test newly created automations immediately.
+- Use current Qwen and DeepSeek recommendations across supported model providers.
+- Retry license usage reporting after transient Roomote Cloud failures.
+
+### Minor changes
+
+- Let operators connect an OpenCode Go subscription independently from OpenCode Zen and use supported Go models across Roomote task roles.
+
+### Patch changes
+
+- Let administrators run enabled custom automations on demand from Automations settings, and offer an immediate test run after an automation is created conversationally.
+- Recommend Qwen3.8 Max through supported providers and use OpenCode Zen's supported DeepSeek V4 Flash model identifier.
+- Retry license usage reports after transient Roomote Cloud failures and report concurrent license-key changes accurately instead of dropping usage observations or reporting a false success.
+
 ## 0.31.0 (2026-08-03)
 
 This release expands Amazon Bedrock and deployment controls, refreshes Automations and self-hosted licensing, and adds copyable Cookbook recipes for common workflows.

SELF_HOSTING.md

@@ -404,6 +404,7 @@ common provider keys into worker containers:
 - `ZAI_CODING_PLAN_API_KEY` (Z.AI Coding Plan, `zai-coding-plan/...` models,
   with `ZAI_CODING_PLAN_REGION`)
 - `OPENCODE_API_KEY`
+- `OPENCODE_GO_API_KEY` (OpenCode Go subscription, `opencode-go/...` models)
 
 If your provider uses another env var name, list it in
 `R_MODEL_ENV_KEYS`:

apps/docs/docs.json

@@ -77,6 +77,7 @@
               "providers/inference/openai",
               "providers/inference/openai-compatible",
               "providers/inference/opencode",
+              "providers/inference/opencode-go",
               "providers/inference/openrouter",
               "providers/inference/together-ai",
               "providers/inference/vercel-ai-gateway",

apps/docs/environment-variables.mdx

@@ -201,7 +201,8 @@ as per-task auth tokens or workspace paths.
 | `ZAI_REGION`                           | Provider key | Z.AI region: `global` (International) or `china`. Defaults to `global` when unset.                                                      |
 | `ZAI_CODING_PLAN_API_KEY`              | Provider key | Z.AI Coding Plan API key for `zai-coding-plan/...` models. Not a general platform key.                                                  |
 | `ZAI_CODING_PLAN_REGION`               | Provider key | Z.AI Coding Plan region: `global` (International) or `china`. Defaults to `global` when unset.                                          |
-| `OPENCODE_API_KEY`                     | Provider key | OpenCode Zen / Go API key.                                                                                                              |
+| `OPENCODE_API_KEY`                     | Provider key | OpenCode Zen API key.                                                                                                                   |
+| `OPENCODE_GO_API_KEY`                  | Provider key | OpenCode API key for an active Go subscription and `opencode-go/...` models.                                                           |
 | `GEMINI_API_KEY`                       | Provider key | Google Gemini API key. Can also be saved from **Settings > Models**.                                                                    |
 | `GOOGLE_GENERATIVE_AI_API_KEY`         | Provider key | Alternate Google/Gemini provider key forwarded when configured or inferred.                                                             |
 | `AWS_BEARER_TOKEN_BEDROCK`             | Provider key | Amazon Bedrock Mantle API key. Can also be saved from **Settings > Models**.                                                            |

apps/docs/models.mdx

@@ -51,7 +51,7 @@ These connections use metered API billing or a provider-managed gateway:
 | [MiniMax](/providers/inference/minimax) | MiniMax API key | MiniMax account |
 | [Moonshot AI (Kimi)](/providers/inference/moonshot-ai) | Kimi Open Platform key | Moonshot Open Platform balance |
 | [OpenAI](/providers/inference/openai) | OpenAI API key | OpenAI API project |
-| [OpenCode Zen / Go](/providers/inference/opencode) | OpenCode API key | OpenCode account |
+| [OpenCode Zen](/providers/inference/opencode) | OpenCode API key | OpenCode account |
 | [OpenRouter](/providers/inference/openrouter) | OpenRouter API key | OpenRouter balance and key limit |
 | [Together AI](/providers/inference/together-ai) | Together AI API key | Together AI account |
 | [Vercel AI Gateway](/providers/inference/vercel-ai-gateway) | AI Gateway API key | Vercel team |
@@ -68,6 +68,7 @@ general API balance:
 | [ChatGPT Subscription](/providers/inference/chatgpt) | OpenAI device authorization | ChatGPT plan windows |
 | [GitHub Copilot](/providers/inference/github-copilot) | GitHub device authorization | Copilot plan allowance |
 | [Kimi for Coding](/providers/inference/kimi-for-coding) | Kimi membership key | Coding membership allowance |
+| [OpenCode Go](/providers/inference/opencode-go) | OpenCode API key | Go plan allowance |
 | [xAI Grok Subscription](/providers/inference/xai-subscription) | xAI account authorization | SuperGrok or eligible X plan allowance |
 | [Z.AI Coding Plan](/providers/inference/zai-coding-plan) | Regional Coding Plan key | Coding Plan quota windows |
 

apps/docs/providers/inference/opencode-go.mdx

@@ -0,0 +1,55 @@
+---
+title: OpenCode Go
+icon: 'https://unpkg.com/@lobehub/icons-static-svg@1.94.0/icons/opencode.svg'
+description: Use an OpenCode Go subscription with Roomote.
+---
+
+OpenCode Go is a subscription for a curated catalog of coding models. Use this
+provider when you want Roomote tasks to consume the allowance included with
+your Go plan.
+
+## Subscribe and get an API key
+
+Sign in to [OpenCode](https://opencode.ai/auth), subscribe to Go, and copy your
+API key. OpenCode currently allows one Go subscription per workspace.
+
+## Configuration
+
+Add **OpenCode Go** in **Settings > Models** and paste the key, or set:
+
+```sh
+OPENCODE_GO_API_KEY=...
+```
+
+Roomote uses a separate environment variable so Zen and Go can be configured
+independently. Paste the OpenCode API key issued for the workspace; Roomote
+binds it to OpenCode's `opencode-go` provider at runtime.
+
+Go models use the `opencode-go/` prefix. Connecting the provider adds a curated
+set of eligible models and recommends lower-cost options for helper work.
+
+## Usage behavior
+
+Requests consume the rolling and monthly allowances defined by your Go plan.
+The OpenCode account console is authoritative for current usage and resets. If
+you enable **Use balance** in OpenCode, requests can fall back to your Zen
+balance after the included allowance is exhausted.
+
+See [OpenCode Go documentation](https://opencode.ai/docs/go/) for current
+models, limits, pricing, and retention details.
+
+## Verify setup
+
+1. save `OPENCODE_GO_API_KEY`
+2. confirm OpenCode Go models appear in **Settings > Models**
+3. apply a preset or assign an `opencode-go/...` model manually
+4. run a small task and confirm it appears in OpenCode usage
+
+## Common issues
+
+- **The key is rejected.** Confirm the workspace has an active Go subscription
+  and that you copied its OpenCode API key.
+- **A model is unavailable.** Go's catalog can change; select another model
+  shown in the OpenCode Go console.
+- **Requests stop after sustained use.** Check the plan's rolling, weekly, and
+  monthly allowance windows in OpenCode.

apps/docs/providers/inference/opencode.mdx

@@ -1,5 +1,5 @@
 ---
-title: OpenCode Zen / Go
+title: OpenCode Zen
 icon: 'https://unpkg.com/@lobehub/icons-static-svg@1.94.0/icons/opencode.svg'
 description: Use OpenCode's routed Zen model service with Roomote.
 ---
@@ -16,13 +16,13 @@ selected models.
 
 ## Configuration
 
-Add **OpenCode Zen / Go** in **Settings > Models** and paste the key, or set:
+Add **OpenCode Zen** in **Settings > Models** and paste the key, or set:
 
 ```sh
 OPENCODE_API_KEY=...
 ```
 
-Roomote exposes routed models under the `opencode/` prefix and adds a recommended
+Roomote exposes routed Zen models under the `opencode/` prefix and adds a recommended
 set after connection. The preset can use inexpensive routed models for helper
 work and stronger models for coding, planning, vision, and review.
 

apps/web/src/app/(onboarding)/setup/setup-docs.ts

@@ -66,6 +66,7 @@ const MODEL_PROVIDER_DOC_PATHS: Partial<
   openai: 'providers/inference/openai',
   'openai-compatible': 'providers/inference/openai-compatible',
   opencode: 'providers/inference/opencode',
+  'opencode-go': 'providers/inference/opencode-go',
   openrouter: 'providers/inference/openrouter',
   togetherai: 'providers/inference/together-ai',
   vercel: 'providers/inference/vercel-ai-gateway',

apps/web/src/components/settings/automations/CustomAutomationsSection.tsx

@@ -24,6 +24,7 @@ import {
   DialogTitle,
   Input,
   Label,
+  Play,
   Plus,
   Select,
   SelectContent,
@@ -284,6 +285,35 @@ export function CustomAutomationsSection() {
     }),
   );
 
+  const triggerMutation = useMutation(
+    trpc.automations.triggerCustomAutomation.mutationOptions({
+      onSuccess: (result) => {
+        switch (result.outcome) {
+          case 'launched':
+            toast.success('Custom automation started a task.', {
+              action: {
+                label: 'Open task',
+                onClick: () => window.open(`/task/${result.taskId}`, '_blank'),
+              },
+            });
+            break;
+          case 'completed':
+            toast.success('Custom automation ran successfully.');
+            break;
+          case 'skipped':
+            toast.info(`Custom automation had nothing to do: ${result.reason}`);
+            break;
+          case 'failed':
+            toast.error(`Custom automation failed: ${result.error}`);
+            break;
+        }
+      },
+      onError: (error) => {
+        toast.error(error.message || 'Failed to run custom automation');
+      },
+    }),
+  );
+
   const resolveScheduleMutation = useMutation(
     trpc.automations.resolveCustomAutomationSchedule.mutationOptions({
       onSuccess: (result, variables) => {
@@ -336,7 +366,8 @@ export function CustomAutomationsSection() {
     createMutation.isPending ||
     updateMutation.isPending ||
     deleteMutation.isPending ||
-    toggleMutation.isPending;
+    toggleMutation.isPending ||
+    triggerMutation.isPending;
 
   const closeEditor = () => {
     setIsCreating(false);
@@ -898,6 +929,18 @@ export function CustomAutomationsSection() {
                       </p>
                     </div>
                     <div className="col-start-2 row-start-2 flex shrink-0 items-center gap-1 sm:col-start-3 sm:row-start-1">
+                      <BasicTooltip content="Run now">
+                        <Button
+                          type="button"
+                          size="icon"
+                          variant="ghost"
+                          disabled={busy || !row.enabled}
+                          aria-label={`Run ${row.name} now`}
+                          onClick={() => triggerMutation.mutate({ id: row.id })}
+                        >
+                          <Play />
+                        </Button>
+                      </BasicTooltip>
                       <BasicTooltip content="Configure">
                         <Button
                           type="button"

apps/worker/src/mcp/roomote-mcp-server/index.ts

@@ -84,7 +84,7 @@ roomoteMcpServer.registerTool(
   {
     title: 'Manage Custom Automations',
     description:
-      'Admin-only management of deployment custom automations. List existing automations, resolve a cron or natural-language schedule, create or update an automation, delete an automation by exact ID, or run an enabled automation now. Natural-language schedules are converted to validated five-field cron in the deployment scheduling timezone.',
+      'Admin-only management of deployment custom automations. List existing automations, resolve a cron or natural-language schedule, create or update an automation, delete an automation by exact ID, or run an enabled automation now. Natural-language schedules are converted to validated five-field cron in the deployment scheduling timezone. After successfully creating an automation in response to a conversational request, ask the user whether they want to run it now to test it.',
     inputSchema: {
       action: z.enum([
         'list',