setup-agent-replay

You are running in the user's agent repository, not in Workshop.

Your job is to make the agent replayable from Raindrop Workshop without the user manually starting a replay server.

Target Contract

Workshop expects:

• .raindrop/agents.yaml committed in the agent repo.
• A replay server command in that yaml, plus cwd when the command must run from a subdirectory.
• A replay server with:
  • GET /health
  • POST /replay
• A local project registration via raindrop replay register.

Replay server ports must be in 61020-61044.

Workshop runs on http://localhost:5899.

If Raindrop MCP is not available or cannot reach Workshop, run:

raindrop workshop

Then retry the MCP/tool call. Do not stop just because the MCP server is unavailable.

If .raindrop/agents.yaml Already Exists

Before changing anything, read .raindrop/agents.yaml.

Ask the user whether to:

1. Start/register the existing replay setup.
2. Add a new agent replay entry.

If they choose start/register:

1. Run the configured command if needed.
2. Verify GET /health.
3. Run raindrop replay register.
4. Stop. Do not scaffold a duplicate server.

Setup Steps

1. Identify The Agent

Find:

• Event name used by tracing (eventMetadata({ eventName: ... }), equivalent SDK call, or current Workshop run).
• Agent entry point to invoke.
• Runtime context the agent requires, such as orgId, orgPublicId, convoId, userId, source.
• Model defaults and obvious supported model overrides.
• Existing script/package manager conventions.

If the agent is not instrumented with Raindrop/Workshop tracing, stop and tell the user to instrument it first.

2. Infer Input And Prefill

Create:

input:
  orgPublicId: string
  orgId: number

prefillFromTrace:
  orgPublicId: properties.orgPublicId
  orgId: properties.orgId

input is the shape passed to the replay server as request.context.

prefillFromTrace tells Workshop how to prefill that context from the selected trace. The user may edit the values in the UI before replay.