adolf/extensions/open-prose/skills/prose/examples/46-run-endpoint-ux-test-fast.prose

# /run Endpoint UX Test - Fast Loop
#
# Streamlined version optimized for speed:
# - Sonnet for most tasks (Opus only for complex synthesis)
# - Hardcoded defaults (no prompts for standard config)
# - Single-agent investigation (not 3 parallel)
# - Early exit on blocking errors
# - Auto-proceed for obvious decisions
# - Combined implement + test + review

# ============================================================================
# Configuration (hardcoded defaults - no user prompts)
# ============================================================================

const API_URL = "https://api-v2.prose.md"
const TEST_PROGRAM = """
# Quick Hello
session "Say hello and count to 5"
"""

# Auth: Read from .env.test synchronously (no LLM needed)
const AUTH_CREDS = env("TEST_EMAIL", "TEST_PASSWORD") from ".env.test"
let auth_token = http.post("{API_URL}/auth/login", AUTH_CREDS).token

# ============================================================================
# Agents (Sonnet default, Opus only where complexity requires)
# ============================================================================

agent observer:
  model: sonnet
  persist: true
  prompt: """UX researcher watching execution.
  Focus on: latency, status clarity, error messages.
  Signal IMMEDIATELY if you detect a blocking error (don't wait for completion).
  Output: { blocking_error: bool, error_summary: string, observations: [...] }"""

agent investigator:
  model: sonnet  # Fast investigation
  prompt: """Senior engineer diagnosing production errors.

  COMBINED WORKFLOW (do all in one pass):
  1. Check code path that produced the error
  2. Examine logs/observations for timing and state
  3. Check execution context (env status, DB records)
  4. Self-verify: does evidence support conclusion?

  Output a VERIFIED diagnosis:
  - root_cause: specific and actionable
  - evidence: concrete supporting data
  - confidence: high/medium/low
  - affected_files: list of files to change
  - fix_approach: how to fix it"""

agent fixer:
  model: sonnet
  prompt: """Engineer implementing and verifying fixes.

  COMBINED WORKFLOW:
  1. Implement the smallest fix that addresses root cause
  2. Run build/tests to verify
  3. Self-review: does it fix the issue without regressions?
  4. Commit if passing

  Output: { implemented: bool, files_changed: [...], tests_pass: bool, commit_sha: string }"""

agent triage:
  model: sonnet
  prompt: """Tech lead classifying fixes.
  QUICK: <3 files, <1hr, no architecture changes, low risk
  BIGGER: anything else
  Output: { decision: "quick"|"bigger", rationale: string }"""

# ============================================================================
# Main Flow (streamlined)
# ============================================================================

# Phase 1: Execute and observe (single agent, early exit on error)
let exec = http.post("{API_URL}/run", { program: TEST_PROGRAM, token: auth_token })

let observation = session: observer
  prompt: """Connect to WebSocket: {exec.wsUrl}&token={auth_token}
  Send: {"type":"execute","program":{TEST_PROGRAM}}

  Watch the stream. If you see a BLOCKING ERROR (hung >10s, repeated failures,
  stopped environment), signal immediately with blocking_error: true.

  Otherwise observe until completion and summarize UX."""
  timeout: 120s
  early_exit: **blocking_error detected**

# Phase 2: Handle result
if observation.blocking_error:

  # Auto-investigate (no user prompt - if there's an error, we investigate)
  let diagnosis = session: investigator
    prompt: """Investigate this blocking error:

    ERROR: {observation.error_summary}
    OBSERVATIONS: {observation.observations}
    EXEC_INFO: {exec}

    Search code, check logs, verify your diagnosis before outputting."""
    context: { observation, exec }

  # Skip if low confidence (needs human)
  if diagnosis.confidence == "low":
    output { status: "needs_human", diagnosis }

  # Auto-triage
  let triage_result = session: triage
    prompt: """Triage: {diagnosis}"""
    context: diagnosis

  if triage_result.decision == "bigger":
    # Bigger changes need human oversight
    output { status: "needs_planning", diagnosis, triage: triage_result }

  # Quick fix: implement + test + deploy in one flow
  let fix = session: fixer
    prompt: """Fix this issue:

    DIAGNOSIS: {diagnosis}
    APPROACH: {diagnosis.fix_approach}

    Implement, test, self-review, commit."""
    context: diagnosis

  if not fix.tests_pass:
    output { status: "fix_failed", diagnosis, fix }

  # Deploy (auto if tests pass)
  let deploy = session "Deploy"
    prompt: """Deploy per docs/DEPLOYMENT.md. Verify health endpoint."""
    retry: 2

  # Quick smoke test
  let smoke = http.get("{API_URL}/health")

  output {
    status: smoke.status == "ok" ? "fixed" : "deploy_failed",
    diagnosis,
    fix,
    deploy
  }

else:
  # No blocking error - just output UX feedback
  output { status: "ok", ux_feedback: observation }