fix: add docker-setup action, runtime Dockerfile, and align release workflow

- Add .github/actions/docker-setup composite action (from rivet)
- Add docker/runtime/Dockerfile for Docker image builds
- Update release.yaml to match rivet patterns:
  - Use corepack enable instead of pnpm/action-setup
  - Add reuse_engine_version input
  - Add Docker job with Depot runners
  - Use --no-frozen-lockfile for pnpm install
  - Add id-token permission for setup job

docs/building-chat-ui.mdx

@@ -21,6 +21,7 @@ Capabilities tell you which features are supported for the selected agent:
 - `tool_calls` and `tool_results` indicate tool execution events.
 - `questions` and `permissions` indicate HITL flows.
 - `plan_mode` indicates that the agent supports plan-only execution.
+- `reasoning` and `status` indicate that the agent can emit reasoning/status content parts.
 
 Use these to enable or disable UI affordances (tool panels, approval buttons, etc.).
 

docs/openapi.json

@@ -4,7 +4,8 @@
     "title": "sandbox-agent",
     "description": "",
     "contact": {
-      "name": "Sandbox Agent Contributors"
+      "name": "Rivet Gaming, LLC",
+      "email": "developer@rivet.gg"
     },
     "license": {
       "name": "Apache-2.0"
@@ -662,6 +663,7 @@
           "sessionLifecycle",
           "errorEvents",
           "reasoning",
+          "status",
           "commandExecution",
           "fileChanges",
           "mcpTools",
@@ -706,6 +708,9 @@
             "type": "boolean",
             "description": "Whether this agent uses a shared long-running server process (vs per-turn subprocess)"
           },
+          "status": {
+            "type": "boolean"
+          },
           "streamingDeltas": {
             "type": "boolean"
           },