id: acp-agent-runner-debug-chat
title: "ACP AgentRunner can answer through Debug Chat using real remote Claude"
mode: agent-browser
area: pipeline
type: regression
priority: p2
risk: high
ci_eligible: false
tags:
  - agent-runner
  - acp
  - claude
  - external-runner
  - pipeline
skills:
  - langbot-env-setup
  - langbot-testing
env:
  - LANGBOT_FRONTEND_URL
  - LANGBOT_BACKEND_URL
env_any:
  - LANGBOT_ACP_AGENT_RUNNER_PIPELINE_URL|LANGBOT_ACP_AGENT_RUNNER_PIPELINE_NAME
automation: scripts/e2e/pipeline-debug-chat.mjs
automation_env:
  - LANGBOT_FRONTEND_URL
  - LANGBOT_BACKEND_URL
  - LANGBOT_BROWSER_PROFILE
  - LANGBOT_CHROMIUM_EXECUTABLE
  - LANGBOT_ACP_AGENT_RUNNER_PIPELINE_URL
  - LANGBOT_ACP_AGENT_RUNNER_PIPELINE_NAME
  - LANGBOT_E2E_PROMPT
  - LANGBOT_E2E_EXPECTED_TEXT
  - LANGBOT_E2E_EXPECTED_RUNNER_ID
  - LANGBOT_E2E_RESPONSE_TIMEOUT_MS
automation_pipeline_url_env: LANGBOT_ACP_AGENT_RUNNER_PIPELINE_URL
automation_pipeline_name_env: LANGBOT_ACP_AGENT_RUNNER_PIPELINE_NAME
automation_expected_runner_id: "plugin:langbot/acp-agent-runner/default"
automation_prompt: "Use the injected LangBot MCP server tool langbot_get_current_event once. If the MCP call succeeds, reply with exactly ACP_AGENT_RUNNER_E2E_OK."
automation_expected_text: "ACP_AGENT_RUNNER_E2E_OK"
automation_response_timeout_ms: "300000"
setup_automation:
  - "node:scripts/e2e/ensure-acp-agent-runner-pipeline.mjs --write-env"
setup_provides_env:
  - LANGBOT_ACP_AGENT_RUNNER_PIPELINE_URL
  - LANGBOT_ACP_AGENT_RUNNER_PIPELINE_NAME
preconditions:
  - "The remote machine has a working Claude Code login and can run npx -y @agentclientprotocol/claude-agent-acp."
  - "LangBot can non-interactively SSH to the remote machine; the runner opens the MCP reverse tunnel automatically."
steps:
  - "Open LANGBOT_FRONTEND_URL."
  - "Open the ACP AgentRunner QA pipeline."
  - "Confirm the pipeline AI runner is plugin:langbot/acp-agent-runner/default."
  - "Open Debug Chat."
  - "Ask the real remote Claude ACP agent to call langbot_get_current_event and return ACP_AGENT_RUNNER_E2E_OK exactly."
checks:
  - "UI: Debug Chat shows the user prompt."
  - "UI: Debug Chat shows a Bot response containing ACP_AGENT_RUNNER_E2E_OK."
  - "Logs: Backend logs include Processing request from person_websocket and Streaming completed for this run."
  - "Logs: No acp runner request error appears for this run."
  - "Console: No unexpected frontend errors appear during Debug Chat."
evidence_required:
  - ui
  - console
  - backend_log
diagnostics:
  - "Use scripts/e2e/ensure-acp-agent-runner-pipeline.mjs --write-env to create/update the pipeline."
  - "For remote Claude on 101, verify ssh yhh@101.34.71.12 can run without password prompts; no separate ssh -R process is required."
success_patterns:
  - "ACP_AGENT_RUNNER_E2E_OK"
  - "Processing request from person_websocket"
  - "Streaming completed"
failure_patterns:
  - "acp.command_not_found"
  - "acp.process_exited"
  - "Agent runner plugin:langbot/acp-agent-runner/default execution failed"
troubleshooting:
  - backend-not-listening
  - plugin-runtime-timeout
  - proxy-env-mismatch