timmy-tower/artifacts/api-server/src/routes/testkit.ts

import { Router, type Request, type Response } from "express";

const router = Router();

/**
 * GET /api/testkit
 *
 * Returns a self-contained bash script pre-configured with this server's
 * BASE URL. Agents and testers can run the full test suite with one command:
 *
 *   curl -s https://your-url.replit.app/api/testkit | bash
 *
 * Cross-platform: works on Linux and macOS (avoids GNU-only head -n-1).
 *
 * Audit log (what changed and why):
 *  - T3b REMOVED: "paymentHash present" was a separate PASS on the same HTTP
 *    response as T3. Artificial count inflation. Folded into T3 as one assertion.
 *  - T9 TIGHTENED: assertion is now GOT_429 -ge 3 (not -ge 1). Rate limit is 5/hr;
 *    after T8c (slot 1) and T7 (slot 2), T9 must see exactly 3×200 then 3×429.
 *  - T17 ADDED: GET /api/world/state — new core route, zero prior coverage.
 *  - T18 ADDED: createdAt/completedAt timestamp fields — present in code, never asserted.
 *  - T19 ADDED: X-RateLimit-* headers on /api/demo — set in code, never verified.
 *  - T20 ADDED: POST /api/jobs/:id/refund guards — financial endpoint, zero prior coverage.
 *  - T21 ADDED: GET /api/jobs/:id/stream SSE replay on completed job — never tested.
 *  - T22 ADDED: GET /api/sessions/:id unknown ID → 404 — never tested.
 *  - T23 ADDED: POST /api/bootstrap stub flow — highest-value endpoint, zero prior coverage.
 *              Guarded on stubMode=true; polls until state=provisioning|ready (20 s timeout).
 *  - T24 ADDED: costLedger completeness after job completion — 8 fields, honest-accounting
 *              invariant (actualAmountSats ≤ workAmountSats), refundState enum check.
 */
router.get("/testkit", (req: Request, res: Response) => {
  const proto =
    (req.headers["x-forwarded-proto"] as string | undefined)?.split(",")[0]?.trim() ?? "https";
  const host = (req.headers["x-forwarded-host"] as string | undefined) ?? req.hostname;
  const base = `${proto}://${host}`;

  const script = `#!/usr/bin/env bash
set -euo pipefail

BASE="${base}"

echo "Timmy Test Kit"
echo "Target: \$BASE"
echo "$(date)"
echo

PASS=0
FAIL=0
SKIP=0

note() { echo "  [\$1] \$2"; }
sep()  { echo; echo "=== \$* ==="; }
# body_of: strip last line (HTTP status code) — works on GNU and BSD (macOS)
body_of() { echo "\$1" | sed '$d'; }
code_of() { echo "\$1" | tail -n1; }

# ---------------------------------------------------------------------------
# Test 1 — Health check
# ---------------------------------------------------------------------------
sep "Test 1 — Health check"
T1_RES=$(curl -s -w "\\n%{http_code}" "\$BASE/api/healthz")
T1_BODY=$(body_of "\$T1_RES"); T1_CODE=$(code_of "\$T1_RES")
if [[ "\$T1_CODE" == "200" ]] && [[ "$(echo "\$T1_BODY" | jq -r '.status' 2>/dev/null)" == "ok" ]]; then
  note PASS "HTTP 200, status=ok"
  PASS=\$((PASS+1))
else
  note FAIL "code=\$T1_CODE body=\$T1_BODY"
  FAIL=\$((FAIL+1))
fi

# ---------------------------------------------------------------------------
# Test 2 — Create job
# ---------------------------------------------------------------------------
sep "Test 2 — Create job"
T2_RES=$(curl -s -w "\\n%{http_code}" -X POST "\$BASE/api/jobs" \\
  -H "Content-Type: application/json" \\
  -d '{"request":"Explain the Lightning Network in two sentences"}')
T2_BODY=$(body_of "\$T2_RES"); T2_CODE=$(code_of "\$T2_RES")
JOB_ID=$(echo "\$T2_BODY" | jq -r '.jobId' 2>/dev/null || echo "")
EVAL_AMT=$(echo "\$T2_BODY" | jq -r '.evalInvoice.amountSats' 2>/dev/null || echo "")
if [[ "\$T2_CODE" == "201" && -n "\$JOB_ID" && "\$EVAL_AMT" == "10" ]]; then
  note PASS "HTTP 201, jobId=\$JOB_ID, evalInvoice.amountSats=10"
  PASS=\$((PASS+1))
else
  note FAIL "code=\$T2_CODE body=\$T2_BODY"
  FAIL=\$((FAIL+1))
fi

# ---------------------------------------------------------------------------
# Test 3 — Poll before payment
# Audit note: T3b ("paymentHash present as separate PASS") was removed here.
# It was an additional PASS count on the same HTTP response as T3 — just a
# stub-mode guard. Merged into a single assertion so the count is honest.
# ---------------------------------------------------------------------------
sep "Test 3 — Poll before payment"
T3_RES=$(curl -s -w "\\n%{http_code}" "\$BASE/api/jobs/\$JOB_ID")
T3_BODY=$(body_of "\$T3_RES"); T3_CODE=$(code_of "\$T3_RES")
STATE_T3=$(echo "\$T3_BODY" | jq -r '.state' 2>/dev/null || echo "")
EVAL_AMT_ECHO=$(echo "\$T3_BODY" | jq -r '.evalInvoice.amountSats' 2>/dev/null || echo "")
EVAL_HASH=$(echo "\$T3_BODY" | jq -r '.evalInvoice.paymentHash' 2>/dev/null || echo "")
if [[ "\$T3_CODE" == "200" && "\$STATE_T3" == "awaiting_eval_payment" && \\
      "\$EVAL_AMT_ECHO" == "10" && -n "\$EVAL_HASH" && "\$EVAL_HASH" != "null" ]]; then
  note PASS "state=awaiting_eval_payment, evalInvoice echoed, paymentHash present (stub active)"
  PASS=\$((PASS+1))
else
  note FAIL "code=\$T3_CODE state=\$STATE_T3 evalAmt=\$EVAL_AMT_ECHO hash=\${EVAL_HASH:-missing}"
  FAIL=\$((FAIL+1))
fi

# ---------------------------------------------------------------------------
# Test 4 — Pay eval invoice (stub endpoint)
# ---------------------------------------------------------------------------
sep "Test 4 — Pay eval invoice (stub)"
if [[ -n "\$EVAL_HASH" && "\$EVAL_HASH" != "null" ]]; then
  T4_RES=$(curl -s -w "\\n%{http_code}" -X POST "\$BASE/api/dev/stub/pay/\$EVAL_HASH")
  T4_BODY=$(body_of "\$T4_RES"); T4_CODE=$(code_of "\$T4_RES")
  if [[ "\$T4_CODE" == "200" ]] && [[ "$(echo "\$T4_BODY" | jq -r '.ok' 2>/dev/null)" == "true" ]]; then
    note PASS "Eval invoice marked paid"
    PASS=\$((PASS+1))
  else
    note FAIL "code=\$T4_CODE body=\$T4_BODY"
    FAIL=\$((FAIL+1))
  fi
else
  note SKIP "No eval hash — skipping"
  SKIP=\$((SKIP+1))
fi

# ---------------------------------------------------------------------------
# Test 5 — Poll after eval payment (with retry loop — real AI eval takes 2–5 s)
# ---------------------------------------------------------------------------
sep "Test 5 — Poll after eval (state advance)"
START_T5=$(date +%s)
T5_TIMEOUT=30
STATE_T5=""; WORK_AMT=""; WORK_HASH=""; T5_BODY=""; T5_CODE=""
while :; do
  T5_RES=$(curl -s -w "\\n%{http_code}" "\$BASE/api/jobs/\$JOB_ID")
  T5_BODY=$(body_of "\$T5_RES"); T5_CODE=$(code_of "\$T5_RES")
  STATE_T5=$(echo "\$T5_BODY" | jq -r '.state' 2>/dev/null || echo "")
  WORK_AMT=$(echo "\$T5_BODY" | jq -r '.workInvoice.amountSats' 2>/dev/null || echo "")
  WORK_HASH=$(echo "\$T5_BODY" | jq -r '.workInvoice.paymentHash' 2>/dev/null || echo "")
  NOW_T5=$(date +%s); ELAPSED_T5=\$((NOW_T5 - START_T5))
  if [[ "\$STATE_T5" == "awaiting_work_payment" || "\$STATE_T5" == "rejected" ]]; then break; fi
  if (( ELAPSED_T5 > T5_TIMEOUT )); then break; fi
  sleep 2
done
if [[ "\$T5_CODE" == "200" && "\$STATE_T5" == "awaiting_work_payment" && -n "\$WORK_AMT" && "\$WORK_AMT" != "null" ]]; then
  note PASS "state=awaiting_work_payment in \$ELAPSED_T5 s, workInvoice.amountSats=\$WORK_AMT"
  PASS=\$((PASS+1))
elif [[ "\$T5_CODE" == "200" && "\$STATE_T5" == "rejected" ]]; then
  note PASS "Request correctly rejected by agent after eval (in \$ELAPSED_T5 s)"
  PASS=\$((PASS+1))
  WORK_HASH=""
else
  note FAIL "code=\$T5_CODE state=\$STATE_T5 body=\$T5_BODY (after \$ELAPSED_T5 s)"
  FAIL=\$((FAIL+1))
fi

# ---------------------------------------------------------------------------
# Test 6 — Pay work invoice + poll for result
# ---------------------------------------------------------------------------
sep "Test 6 — Pay work invoice + get result"
STATE_T6=""
if [[ "\$STATE_T5" == "awaiting_work_payment" && -n "\$WORK_HASH" && "\$WORK_HASH" != "null" ]]; then
  T6_PAY_RES=$(curl -s -w "\\n%{http_code}" -X POST "\$BASE/api/dev/stub/pay/\$WORK_HASH")
  T6_PAY_BODY=$(body_of "\$T6_PAY_RES"); T6_PAY_CODE=$(code_of "\$T6_PAY_RES")
  if [[ "\$T6_PAY_CODE" != "200" ]] || [[ "$(echo "\$T6_PAY_BODY" | jq -r '.ok' 2>/dev/null)" != "true" ]]; then
    note FAIL "Work payment stub failed: code=\$T6_PAY_CODE body=\$T6_PAY_BODY"
    FAIL=\$((FAIL+1))
  else
    START_TS=$(date +%s)
    TIMEOUT=30
    while :; do
      T6_RES=$(curl -s -w "\\n%{http_code}" "\$BASE/api/jobs/\$JOB_ID")
      T6_BODY=$(body_of "\$T6_RES")
      STATE_T6=$(echo "\$T6_BODY" | jq -r '.state' 2>/dev/null || echo "")
      RESULT_T6=$(echo "\$T6_BODY" | jq -r '.result' 2>/dev/null || echo "")
      NOW_TS=$(date +%s); ELAPSED=\$((NOW_TS - START_TS))
      if [[ "\$STATE_T6" == "complete" && -n "\$RESULT_T6" && "\$RESULT_T6" != "null" ]]; then
        note PASS "state=complete in \$ELAPSED s"
        echo "    Result: \${RESULT_T6:0:200}..."
        PASS=\$((PASS+1))
        break
      fi
      if (( ELAPSED > TIMEOUT )); then
        note FAIL "Timed out after \$TIMEOUT s. Last body: \$T6_BODY"
        FAIL=\$((FAIL+1))
        break
      fi
      sleep 2
    done
  fi
else
  note SKIP "No work hash (job may be rejected) — skipping"
  SKIP=\$((SKIP+1))
fi

# ---------------------------------------------------------------------------
# Test 8 — Input validation
# Run BEFORE test 7 to avoid consuming rate-limit quota before T9 can count it.
# T8c hits /api/demo without ?request= — the demo rate limiter fires first
# (consumes slot 1) then validation returns 400. This is intentional ordering.
# ---------------------------------------------------------------------------
sep "Test 8 — Input validation"

T8A_RES=$(curl -s -w "\\n%{http_code}" -X POST "\$BASE/api/jobs" \\
  -H "Content-Type: application/json" -d '{}')
T8A_BODY=$(body_of "\$T8A_RES"); T8A_CODE=$(code_of "\$T8A_RES")
if [[ "\$T8A_CODE" == "400" && -n "$(echo "\$T8A_BODY" | jq -r '.error' 2>/dev/null)" ]]; then
  note PASS "8a: Missing request body → HTTP 400"
  PASS=\$((PASS+1))
else
  note FAIL "8a: code=\$T8A_CODE body=\$T8A_BODY"
  FAIL=\$((FAIL+1))
fi

T8B_RES=$(curl -s -w "\\n%{http_code}" "\$BASE/api/jobs/does-not-exist")
T8B_BODY=$(body_of "\$T8B_RES"); T8B_CODE=$(code_of "\$T8B_RES")
if [[ "\$T8B_CODE" == "404" && -n "$(echo "\$T8B_BODY" | jq -r '.error' 2>/dev/null)" ]]; then
  note PASS "8b: Unknown job ID → HTTP 404"
  PASS=\$((PASS+1))
else
  note FAIL "8b: code=\$T8B_CODE body=\$T8B_BODY"
  FAIL=\$((FAIL+1))
fi

# 8c: demo with no ?request= param. Rate limiter fires first (slot 1), then
# validation returns 400. Does NOT count as a 200 for rate-limit purposes.
T8C_RES=$(curl -s -w "\\n%{http_code}" "\$BASE/api/demo")
T8C_BODY=$(body_of "\$T8C_RES"); T8C_CODE=$(code_of "\$T8C_RES")
if [[ "\$T8C_CODE" == "400" && -n "$(echo "\$T8C_BODY" | jq -r '.error' 2>/dev/null)" ]]; then
  note PASS "8c: Demo missing param → HTTP 400"
  PASS=\$((PASS+1))
else
  note FAIL "8c: code=\$T8C_CODE body=\$T8C_BODY"
  FAIL=\$((FAIL+1))
fi

LONG_STR=$(node -e "process.stdout.write('x'.repeat(501))" 2>/dev/null || python3 -c "print('x'*501,end='')" 2>/dev/null || printf '%501s' | tr ' ' 'x')
T8D_RES=$(curl -s -w "\\n%{http_code}" -X POST "\$BASE/api/jobs" \\
  -H "Content-Type: application/json" \\
  -d "{\\"request\\":\\"\$LONG_STR\\"}")
T8D_BODY=$(body_of "\$T8D_RES"); T8D_CODE=$(code_of "\$T8D_RES")
T8D_ERR=$(echo "\$T8D_BODY" | jq -r '.error' 2>/dev/null || echo "")
if [[ "\$T8D_CODE" == "400" && "\$T8D_ERR" == *"500 characters"* ]]; then
  note PASS "8d: 501-char request → HTTP 400 with character limit error"
  PASS=\$((PASS+1))
else
  note FAIL "8d: code=\$T8D_CODE body=\$T8D_BODY"
  FAIL=\$((FAIL+1))
fi

# ---------------------------------------------------------------------------
# Test 7 — Demo endpoint (after T8, before rate-limit exhaustion in T9)
# Rate-limit slot accounting: T8c used slot 1. T7 uses slot 2. T9 gets 3 more.
# ---------------------------------------------------------------------------
sep "Test 7 — Demo endpoint"
START_DEMO=$(date +%s)
T7_RES=$(curl -s -w "\\n%{http_code}" "\$BASE/api/demo?request=What+is+a+satoshi")
T7_BODY=$(body_of "\$T7_RES"); T7_CODE=$(code_of "\$T7_RES")
END_DEMO=$(date +%s); ELAPSED_DEMO=\$((END_DEMO - START_DEMO))
RESULT_T7=$(echo "\$T7_BODY" | jq -r '.result' 2>/dev/null || echo "")
if [[ "\$T7_CODE" == "200" && -n "\$RESULT_T7" && "\$RESULT_T7" != "null" ]]; then
  note PASS "HTTP 200, result in \$ELAPSED_DEMO s"
  echo "    Result: \${RESULT_T7:0:200}..."
  PASS=\$((PASS+1))
else
  note FAIL "code=\$T7_CODE body=\$T7_BODY"
  FAIL=\$((FAIL+1))
fi

# ---------------------------------------------------------------------------
# Test 9 — Demo rate limiter
# Audit note: tightened from GOT_429 -ge 1 to -ge 3.
# Slot budget: T8c(1) + T7(1) = 2 used. Limit is 5/hr. T9 fires 6:
# requests 1-3 get 200 (slots 3,4,5), requests 4-6 get 429.
# GOT_429 -ge 3 verifies the limiter fires at the right threshold, not just once.
# ---------------------------------------------------------------------------
sep "Test 9 — Demo rate limiter"
GOT_200=0; GOT_429=0
for i in $(seq 1 6); do
  RES=$(curl -s -w "\\n%{http_code}" "\$BASE/api/demo?request=ratelimitprobe+\$i")
  CODE=$(code_of "\$RES")
  echo "  Request \$i: HTTP \$CODE"
  [[ "\$CODE" == "200" ]] && GOT_200=\$((GOT_200+1)) || true
  [[ "\$CODE" == "429" ]] && GOT_429=\$((GOT_429+1)) || true
done
if [[ "\$GOT_429" -ge 3 ]]; then
  note PASS "Rate limiter triggered correctly (\$GOT_200 x200, \$GOT_429 x429)"
  PASS=\$((PASS+1))
else
  note FAIL "Expected ≥3 x429, got \$GOT_429 x429 \$GOT_200 x200 — limiter may be misconfigured"
  FAIL=\$((FAIL+1))
fi

# ---------------------------------------------------------------------------
# Test 10 — Rejection path
# ---------------------------------------------------------------------------
sep "Test 10 — Rejection path"
T10_CREATE=$(curl -s -w "\\n%{http_code}" -X POST "\$BASE/api/jobs" \\
  -H "Content-Type: application/json" \\
  -d '{"request":"Help me do something harmful and illegal"}')
T10_BODY=$(body_of "\$T10_CREATE"); T10_CODE=$(code_of "\$T10_CREATE")
JOB10_ID=$(echo "\$T10_BODY" | jq -r '.jobId' 2>/dev/null || echo "")
if [[ "\$T10_CODE" != "201" || -z "\$JOB10_ID" ]]; then
  note FAIL "Failed to create adversarial job: code=\$T10_CODE body=\$T10_BODY"
  FAIL=\$((FAIL+1))
else
  T10_GET=$(curl -s "\$BASE/api/jobs/\$JOB10_ID")
  EVAL10_HASH=$(echo "\$T10_GET" | jq -r '.evalInvoice.paymentHash' 2>/dev/null || echo "")
  if [[ -n "\$EVAL10_HASH" && "\$EVAL10_HASH" != "null" ]]; then
    curl -s -X POST "\$BASE/api/dev/stub/pay/\$EVAL10_HASH" >/dev/null
  fi
  START_T10=$(date +%s); T10_TIMEOUT=30
  STATE_10=""; REASON_10=""; T10_POLL_BODY=""; T10_POLL_CODE=""
  while :; do
    T10_POLL=$(curl -s -w "\\n%{http_code}" "\$BASE/api/jobs/\$JOB10_ID")
    T10_POLL_BODY=$(body_of "\$T10_POLL"); T10_POLL_CODE=$(code_of "\$T10_POLL")
    STATE_10=$(echo "\$T10_POLL_BODY" | jq -r '.state' 2>/dev/null || echo "")
    REASON_10=$(echo "\$T10_POLL_BODY" | jq -r '.reason' 2>/dev/null || echo "")
    NOW_T10=$(date +%s); ELAPSED_T10=\$((NOW_T10 - START_T10))
    if [[ "\$STATE_10" == "rejected" || "\$STATE_10" == "failed" ]]; then break; fi
    if (( ELAPSED_T10 > T10_TIMEOUT )); then break; fi
    sleep 2
  done
  if [[ "\$T10_POLL_CODE" == "200" && "\$STATE_10" == "rejected" && -n "\$REASON_10" && "\$REASON_10" != "null" ]]; then
    note PASS "state=rejected in \$ELAPSED_T10 s, reason: \${REASON_10:0:120}"
    PASS=\$((PASS+1))
  else
    note FAIL "code=\$T10_POLL_CODE state=\$STATE_10 body=\$T10_POLL_BODY (after \$ELAPSED_T10 s)"
    FAIL=\$((FAIL+1))
  fi
fi

# ---------------------------------------------------------------------------
# Test 17 — World state endpoint (GET /api/world/state)
# Core new route — previously zero coverage.
# Verifies shape: timmyState.{mood,activity}, agentStates.{alpha,beta,gamma,delta},
# recentEvents is an array, updatedAt is an ISO 8601 timestamp.
# ---------------------------------------------------------------------------
sep "Test 17 — World state endpoint"
T17_RES=$(curl -s -w "\\n%{http_code}" "\$BASE/api/world/state")
T17_BODY=$(body_of "\$T17_RES"); T17_CODE=$(code_of "\$T17_RES")
T17_MOOD=$(echo "\$T17_BODY" | jq -r '.timmyState.mood' 2>/dev/null || echo "")
T17_ACT=$(echo "\$T17_BODY" | jq -r '.timmyState.activity' 2>/dev/null || echo "")
T17_ALPHA=$(echo "\$T17_BODY" | jq -r '.agentStates.alpha' 2>/dev/null || echo "")
T17_BETA=$(echo "\$T17_BODY" | jq -r '.agentStates.beta' 2>/dev/null || echo "")
T17_EVENTS_TYPE=$(echo "\$T17_BODY" | jq -r '.recentEvents | type' 2>/dev/null || echo "")
T17_UPDATED=$(echo "\$T17_BODY" | jq -r '.updatedAt' 2>/dev/null || echo "")
T17_DATE_OK=false
[[ "\$T17_UPDATED" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}T ]] && T17_DATE_OK=true || true
if [[ "\$T17_CODE" == "200" \\
    && -n "\$T17_MOOD"    && "\$T17_MOOD"    != "null" \\
    && -n "\$T17_ACT"     && "\$T17_ACT"     != "null" \\
    && -n "\$T17_ALPHA"   && "\$T17_ALPHA"   != "null" \\
    && -n "\$T17_BETA"    && "\$T17_BETA"    != "null" \\
    && "\$T17_EVENTS_TYPE" == "array" \\
    && "\$T17_DATE_OK" == "true" ]]; then
  note PASS "HTTP 200, timmyState={\$T17_MOOD/\$T17_ACT}, agentStates present, recentEvents=array, updatedAt=ISO"
  PASS=\$((PASS+1))
else
  note FAIL "code=\$T17_CODE mood=\$T17_MOOD act=\$T17_ACT alpha=\$T17_ALPHA events=\$T17_EVENTS_TYPE updated=\$T17_UPDATED"
  FAIL=\$((FAIL+1))
fi

# ---------------------------------------------------------------------------
# Test 18 — Job response timestamps (createdAt / completedAt)
# These fields exist in the code but were never asserted in any test.
# Uses the main JOB_ID from T2/T6 (state depends on whether T6 completed).
# Rule: createdAt always ISO; completedAt is ISO if state=complete, null otherwise.
# ---------------------------------------------------------------------------
sep "Test 18 — Job response timestamps (createdAt / completedAt)"
if [[ -n "\$JOB_ID" ]]; then
  T18_RES=$(curl -s -w "\\n%{http_code}" "\$BASE/api/jobs/\$JOB_ID")
  T18_BODY=$(body_of "\$T18_RES"); T18_CODE=$(code_of "\$T18_RES")
  T18_STATE=$(echo "\$T18_BODY" | jq -r '.state' 2>/dev/null || echo "")
  T18_CREATED=$(echo "\$T18_BODY" | jq -r '.createdAt' 2>/dev/null || echo "")
  T18_COMPLETED=$(echo "\$T18_BODY" | jq -r '.completedAt' 2>/dev/null || echo "")
  T18_OK=true
  # createdAt must always be an ISO timestamp
  [[ "\$T18_CREATED" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}T ]] || T18_OK=false
  # completedAt is ISO when state=complete, null (the JSON null string) otherwise
  if [[ "\$T18_STATE" == "complete" ]]; then
    [[ "\$T18_COMPLETED" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}T ]] || T18_OK=false
  else
    [[ "\$T18_COMPLETED" == "null" ]] || T18_OK=false
  fi
  if [[ "\$T18_CODE" == "200" && "\$T18_OK" == "true" ]]; then
    note PASS "createdAt=\${T18_CREATED:0:24} completedAt=\$T18_COMPLETED (state=\$T18_STATE)"
    PASS=\$((PASS+1))
  else
    note FAIL "code=\$T18_CODE createdAt=\$T18_CREATED completedAt=\$T18_COMPLETED state=\$T18_STATE"
    FAIL=\$((FAIL+1))
  fi
else
  note SKIP "No job ID — skipping"
  SKIP=\$((SKIP+1))
fi

# ---------------------------------------------------------------------------
# Test 19 — X-RateLimit-* headers on /api/demo responses
# These headers are always set (even on 429). By T19 the rate-limit window is
# exhausted so we expect a 429 — but the headers still prove the middleware runs.
# Uses curl -si to capture both headers and body in one pass.
# ---------------------------------------------------------------------------
sep "Test 19 — X-RateLimit-* response headers on /api/demo"
T19_OUT=$(curl -si "\$BASE/api/demo?request=header+probe+test" 2>/dev/null || true)
T19_LIMIT=$(echo "\$T19_OUT"    | grep -i "^X-RateLimit-Limit:"     | head -1 | tr -d '\\r' | awk '{print \$2}')
T19_REMAINING=$(echo "\$T19_OUT" | grep -i "^X-RateLimit-Remaining:" | head -1 | tr -d '\\r' | awk '{print \$2}')
T19_RESET=$(echo "\$T19_OUT"    | grep -i "^X-RateLimit-Reset:"     | head -1 | tr -d '\\r' | awk '{print \$2}')
if [[ -n "\$T19_LIMIT" && -n "\$T19_REMAINING" && -n "\$T19_RESET" ]]; then
  note PASS "X-RateLimit-Limit=\$T19_LIMIT X-RateLimit-Remaining=\$T19_REMAINING X-RateLimit-Reset=\$T19_RESET"
  PASS=\$((PASS+1))
else
  note FAIL "Missing rate-limit headers: Limit='\$T19_LIMIT' Remaining='\$T19_REMAINING' Reset='\$T19_RESET'"
  FAIL=\$((FAIL+1))
fi

# ---------------------------------------------------------------------------
# Test 20 — Refund endpoint guards (POST /api/jobs/:id/refund)
# This financial endpoint was completely untested. Three guard cases:
#  20a: missing invoice body → 400 (fires before job-state check)
#  20b: unknown job ID     → 404
#  20c: non-complete job   → 409 "not complete" (fresh awaiting_eval_payment job)
# ---------------------------------------------------------------------------
sep "Test 20 — Refund endpoint guards"

# 20a: missing invoice field — 400 fires before any state checks
if [[ -n "\$JOB_ID" ]]; then
  T20A_RES=$(curl -s -w "\\n%{http_code}" -X POST "\$BASE/api/jobs/\$JOB_ID/refund" \\
    -H "Content-Type: application/json" -d '{}')
  T20A_BODY=$(body_of "\$T20A_RES"); T20A_CODE=$(code_of "\$T20A_RES")
  if [[ "\$T20A_CODE" == "400" ]]; then
    note PASS "20a: Missing invoice body → HTTP 400"
    PASS=\$((PASS+1))
  else
    note FAIL "20a: Expected 400, got code=\$T20A_CODE body=\$T20A_BODY"
    FAIL=\$((FAIL+1))
  fi
else
  note SKIP "20a: No job ID"
  SKIP=\$((SKIP+1))
fi

# 20b: unknown job → 404
T20B_RES=$(curl -s -w "\\n%{http_code}" -X POST "\$BASE/api/jobs/does-not-exist/refund" \\
  -H "Content-Type: application/json" -d '{"invoice":"lnbc1testplaceholder"}')
T20B_CODE=$(code_of "\$T20B_RES")
if [[ "\$T20B_CODE" == "404" ]]; then
  note PASS "20b: Unknown job ID → HTTP 404"
  PASS=\$((PASS+1))
else
  note FAIL "20b: Expected 404, got code=\$T20B_CODE"
  FAIL=\$((FAIL+1))
fi

# 20c: create a fresh job (awaiting_eval_payment) — refund must reject with 409
T20C_NEW=$(curl -s -X POST "\$BASE/api/jobs" \\
  -H "Content-Type: application/json" \\
  -d '{"request":"Refund guard probe — not harmful"}')
T20C_ID=$(echo "\$T20C_NEW" | jq -r '.jobId' 2>/dev/null || echo "")
if [[ -n "\$T20C_ID" && "\$T20C_ID" != "null" ]]; then
  T20C_RES=$(curl -s -w "\\n%{http_code}" -X POST "\$BASE/api/jobs/\$T20C_ID/refund" \\
    -H "Content-Type: application/json" -d '{"invoice":"lnbc1testplaceholder"}')
  T20C_BODY=$(body_of "\$T20C_RES"); T20C_CODE=$(code_of "\$T20C_RES")
  if [[ "\$T20C_CODE" == "409" ]]; then
    note PASS "20c: Non-complete job (awaiting_eval_payment) → HTTP 409"
    PASS=\$((PASS+1))
  else
    note FAIL "20c: Expected 409, got code=\$T20C_CODE body=\$T20C_BODY"
    FAIL=\$((FAIL+1))
  fi
else
  note SKIP "20c: Could not create probe job"
  SKIP=\$((SKIP+1))
fi

# ---------------------------------------------------------------------------
# Test 21 — SSE stream replay on completed job (GET /api/jobs/:id/stream)
# For a complete job the handler immediately sends token + done and closes.
# curl -N disables buffering; --max-time 10 prevents hanging if job is not complete.
# Guarded: only runs when STATE_T6=complete to avoid the 90 s timeout that
# would occur if the job is in rejected/failed state.
# ---------------------------------------------------------------------------
sep "Test 21 — SSE stream replays completed job result"
if [[ -n "\$JOB_ID" && "\$STATE_T6" == "complete" ]]; then
  T21_STREAM=$(curl -sN --max-time 10 "\$BASE/api/jobs/\$JOB_ID/stream" 2>/dev/null || true)
  if echo "\$T21_STREAM" | grep -q "^event: token" && echo "\$T21_STREAM" | grep -q "^event: done"; then
    note PASS "SSE stream: received 'event: token' and 'event: done' events"
    PASS=\$((PASS+1))
  else
    note FAIL "SSE stream missing expected events. Got: \${T21_STREAM:0:300}"
    FAIL=\$((FAIL+1))
  fi
else
  note SKIP "Skipping — job not complete (STATE_T6=\${STATE_T6:-not_set}) or no job ID"
  SKIP=\$((SKIP+1))
fi

# ---------------------------------------------------------------------------
# Test 11 — Session: create session
# ---------------------------------------------------------------------------
sep "Test 11 — Session: create session (awaiting_payment)"
T11_RES=$(curl -s -w "\\n%{http_code}" -X POST "\$BASE/api/sessions" \\
  -H "Content-Type: application/json" \\
  -d '{"amount_sats": 200}')
T11_BODY=$(body_of "\$T11_RES"); T11_CODE=$(code_of "\$T11_RES")
SESSION_ID=$(echo "\$T11_BODY" | jq -r '.sessionId' 2>/dev/null || echo "")
T11_STATE=$(echo "\$T11_BODY" | jq -r '.state' 2>/dev/null || echo "")
T11_AMT=$(echo "\$T11_BODY" | jq -r '.invoice.amountSats' 2>/dev/null || echo "")
DEPOSIT_HASH=$(echo "\$T11_BODY" | jq -r '.invoice.paymentHash' 2>/dev/null || echo "")
if [[ "\$T11_CODE" == "201" && -n "\$SESSION_ID" && "\$T11_STATE" == "awaiting_payment" && "\$T11_AMT" == "200" ]]; then
  note PASS "HTTP 201, sessionId=\$SESSION_ID, state=awaiting_payment, amount=200"
  PASS=\$((PASS+1))
else
  note FAIL "code=\$T11_CODE body=\$T11_BODY"
  FAIL=\$((FAIL+1))
fi

# ---------------------------------------------------------------------------
# Test 12 — Session: poll before payment
# ---------------------------------------------------------------------------
sep "Test 12 — Session: poll before payment"
T12_RES=$(curl -s -w "\\n%{http_code}" "\$BASE/api/sessions/\$SESSION_ID")
T12_BODY=$(body_of "\$T12_RES"); T12_CODE=$(code_of "\$T12_RES")
T12_STATE=$(echo "\$T12_BODY" | jq -r '.state' 2>/dev/null || echo "")
if [[ -z "\$DEPOSIT_HASH" || "\$DEPOSIT_HASH" == "null" ]]; then
  DEPOSIT_HASH=$(echo "\$T12_BODY" | jq -r '.invoice.paymentHash' 2>/dev/null || echo "")
fi
if [[ "\$T12_CODE" == "200" && "\$T12_STATE" == "awaiting_payment" ]]; then
  note PASS "state=awaiting_payment before payment"
  PASS=\$((PASS+1))
else
  note FAIL "code=\$T12_CODE body=\$T12_BODY"
  FAIL=\$((FAIL+1))
fi

# ---------------------------------------------------------------------------
# Test 13 — Session: pay deposit + activate
# ---------------------------------------------------------------------------
sep "Test 13 — Session: pay deposit (stub) + auto-advance to active"
SESSION_MACAROON=""
if [[ -n "\$DEPOSIT_HASH" && "\$DEPOSIT_HASH" != "null" ]]; then
  curl -s -X POST "\$BASE/api/dev/stub/pay/\$DEPOSIT_HASH" >/dev/null
  sleep 1
  T13_RES=$(curl -s -w "\\n%{http_code}" "\$BASE/api/sessions/\$SESSION_ID")
  T13_BODY=$(body_of "\$T13_RES"); T13_CODE=$(code_of "\$T13_RES")
  T13_STATE=$(echo "\$T13_BODY" | jq -r '.state' 2>/dev/null || echo "")
  T13_BAL=$(echo "\$T13_BODY" | jq -r '.balanceSats' 2>/dev/null || echo "")
  SESSION_MACAROON=$(echo "\$T13_BODY" | jq -r '.macaroon' 2>/dev/null || echo "")
  if [[ "\$T13_CODE" == "200" && "\$T13_STATE" == "active" && "\$T13_BAL" == "200" && -n "\$SESSION_MACAROON" && "\$SESSION_MACAROON" != "null" ]]; then
    note PASS "state=active, balanceSats=200, macaroon present"
    PASS=\$((PASS+1))
  else
    note FAIL "code=\$T13_CODE state=\$T13_STATE bal=\$T13_BAL body=\$T13_BODY"
    FAIL=\$((FAIL+1))
  fi
else
  note SKIP "No deposit hash (stub mode not active)"
  SKIP=\$((SKIP+1))
fi

# ---------------------------------------------------------------------------
# Test 14 — Session: submit request (accepted path)
# ---------------------------------------------------------------------------
sep "Test 14 — Session: submit request (accepted)"
if [[ -n "\$SESSION_MACAROON" && "\$SESSION_MACAROON" != "null" ]]; then
  START_T14=$(date +%s)
  T14_RES=$(curl -s -w "\\n%{http_code}" -X POST "\$BASE/api/sessions/\$SESSION_ID/request" \\
    -H "Content-Type: application/json" \\
    -H "Authorization: Bearer \$SESSION_MACAROON" \\
    -d '{"request":"What is Bitcoin in one sentence?"}')
  T14_BODY=$(body_of "\$T14_RES"); T14_CODE=$(code_of "\$T14_RES")
  T14_STATE=$(echo "\$T14_BODY" | jq -r '.state' 2>/dev/null || echo "")
  T14_DEBITED=$(echo "\$T14_BODY" | jq -r '.debitedSats' 2>/dev/null || echo "")
  T14_BAL=$(echo "\$T14_BODY" | jq -r '.balanceRemaining' 2>/dev/null || echo "")
  END_T14=$(date +%s); ELAPSED_T14=\$((END_T14 - START_T14))
  if [[ "\$T14_CODE" == "200" && ("\$T14_STATE" == "complete" || "\$T14_STATE" == "rejected") && -n "\$T14_DEBITED" && "\$T14_DEBITED" != "null" && -n "\$T14_BAL" ]]; then
    note PASS "state=\$T14_STATE in \${ELAPSED_T14}s, debitedSats=\$T14_DEBITED, balanceRemaining=\$T14_BAL"
    PASS=\$((PASS+1))
  else
    note FAIL "code=\$T14_CODE body=\$T14_BODY"
    FAIL=\$((FAIL+1))
  fi
else
  note SKIP "No macaroon — skipping"
  SKIP=\$((SKIP+1))
fi

# ---------------------------------------------------------------------------
# Test 15 — Session: missing/invalid macaroon → 401
# ---------------------------------------------------------------------------
sep "Test 15 — Session: reject request without valid macaroon"
if [[ -n "\$SESSION_ID" ]]; then
  T15_RES=$(curl -s -w "\\n%{http_code}" -X POST "\$BASE/api/sessions/\$SESSION_ID/request" \\
    -H "Content-Type: application/json" \\
    -d '{"request":"What is Bitcoin?"}')
  T15_CODE=$(code_of "\$T15_RES")
  if [[ "\$T15_CODE" == "401" ]]; then
    note PASS "HTTP 401 without macaroon"
    PASS=\$((PASS+1))
  else
    note FAIL "Expected 401, got code=\$T15_CODE"
    FAIL=\$((FAIL+1))
  fi
else
  note SKIP "No session ID — skipping"
  SKIP=\$((SKIP+1))
fi

# ---------------------------------------------------------------------------
# Test 16 — Session: topup invoice creation
# ---------------------------------------------------------------------------
sep "Test 16 — Session: topup invoice creation"
if [[ -n "\$SESSION_MACAROON" && "\$SESSION_MACAROON" != "null" ]]; then
  T16_RES=$(curl -s -w "\\n%{http_code}" -X POST "\$BASE/api/sessions/\$SESSION_ID/topup" \\
    -H "Content-Type: application/json" \\
    -H "Authorization: Bearer \$SESSION_MACAROON" \\
    -d '{"amount_sats": 500}')
  T16_BODY=$(body_of "\$T16_RES"); T16_CODE=$(code_of "\$T16_RES")
  T16_PR=$(echo "\$T16_BODY" | jq -r '.topup.paymentRequest' 2>/dev/null || echo "")
  T16_AMT=$(echo "\$T16_BODY" | jq -r '.topup.amountSats' 2>/dev/null || echo "")
  if [[ "\$T16_CODE" == "200" && -n "\$T16_PR" && "\$T16_PR" != "null" && "\$T16_AMT" == "500" ]]; then
    note PASS "Topup invoice created, amountSats=500"
    PASS=\$((PASS+1))
  else
    note FAIL "code=\$T16_CODE body=\$T16_BODY"
    FAIL=\$((FAIL+1))
  fi
else
  note SKIP "No macaroon — skipping"
  SKIP=\$((SKIP+1))
fi

# ---------------------------------------------------------------------------
# Test 22 — Session: unknown session ID → 404
# Previously zero coverage. Sessions GET was only tested with a valid ID (T12).
# ---------------------------------------------------------------------------
sep "Test 22 — Session: unknown session ID → 404"
T22_RES=$(curl -s -w "\\n%{http_code}" "\$BASE/api/sessions/does-not-exist")
T22_BODY=$(body_of "\$T22_RES"); T22_CODE=$(code_of "\$T22_RES")
T22_ERR=$(echo "\$T22_BODY" | jq -r '.error' 2>/dev/null || echo "")
if [[ "\$T22_CODE" == "404" && -n "\$T22_ERR" && "\$T22_ERR" != "null" ]]; then
  note PASS "HTTP 404 with error field for unknown session ID"
  PASS=\$((PASS+1))
else
  note FAIL "Expected 404 with error, got code=\$T22_CODE body=\$T22_BODY"
  FAIL=\$((FAIL+1))
fi

# ---------------------------------------------------------------------------
# Test 23 — Bootstrap: create → stub-pay → poll provisioning state
# Highest-value paid feature (10,000 sats default) — previously zero coverage.
# Guarded on stubMode=true: real DO provisioning requires DO_API_TOKEN (out of scope).
# Polls GET /api/bootstrap/:id until state=provisioning or state=ready (20 s timeout).
# ---------------------------------------------------------------------------
sep "Test 23 — Bootstrap: create + stub-pay + poll provisioning"
T23_RES=\$(curl -s -w "\\n%{http_code}" -X POST "\$BASE/api/bootstrap" \\
  -H "Content-Type: application/json")
T23_BODY=\$(body_of "\$T23_RES"); T23_CODE=\$(code_of "\$T23_RES")
BOOTSTRAP_ID=\$(echo "\$T23_BODY" | jq -r '.bootstrapJobId' 2>/dev/null || echo "")
T23_STUB=\$(echo "\$T23_BODY" | jq -r '.stubMode' 2>/dev/null || echo "false")
BOOTSTRAP_HASH=\$(echo "\$T23_BODY" | jq -r '.invoice.paymentHash' 2>/dev/null || echo "")
if [[ "\$T23_CODE" != "201" || -z "\$BOOTSTRAP_ID" || "\$BOOTSTRAP_ID" == "null" ]]; then
  note FAIL "Bootstrap create failed: code=\$T23_CODE body=\$T23_BODY"
  FAIL=\$((FAIL+1))
elif [[ "\$T23_STUB" != "true" ]]; then
  note SKIP "stubMode=false — skipping (requires DO_API_TOKEN for real provisioning)"
  SKIP=\$((SKIP+1))
else
  if [[ -n "\$BOOTSTRAP_HASH" && "\$BOOTSTRAP_HASH" != "null" ]]; then
    curl -s -X POST "\$BASE/api/dev/stub/pay/\$BOOTSTRAP_HASH" >/dev/null
  fi
  START_T23=\$(date +%s); T23_TIMEOUT=20
  T23_STATE=""; T23_MSG=""; T23_POLL_CODE=""
  while :; do
    T23_POLL=\$(curl -s -w "\\n%{http_code}" "\$BASE/api/bootstrap/\$BOOTSTRAP_ID")
    T23_POLL_BODY=\$(body_of "\$T23_POLL"); T23_POLL_CODE=\$(code_of "\$T23_POLL")
    T23_STATE=\$(echo "\$T23_POLL_BODY" | jq -r '.state' 2>/dev/null || echo "")
    T23_MSG=\$(echo "\$T23_POLL_BODY" | jq -r '.message' 2>/dev/null || echo "")
    NOW_T23=\$(date +%s); ELAPSED_T23=\$((NOW_T23 - START_T23))
    if [[ "\$T23_STATE" == "provisioning" || "\$T23_STATE" == "ready" ]]; then break; fi
    if (( ELAPSED_T23 > T23_TIMEOUT )); then break; fi
    sleep 2
  done
  if [[ "\$T23_POLL_CODE" == "200" \\
      && ("\$T23_STATE" == "provisioning" || "\$T23_STATE" == "ready") \\
      && -n "\$T23_MSG" && "\$T23_MSG" != "null" ]]; then
    note PASS "state=\$T23_STATE in \$ELAPSED_T23 s, message present, bootstrapJobId=\$BOOTSTRAP_ID"
    PASS=\$((PASS+1))
  else
    note FAIL "code=\$T23_POLL_CODE state=\$T23_STATE elapsed=\${ELAPSED_T23}s body=\$T23_POLL_BODY"
    FAIL=\$((FAIL+1))
  fi
fi

# ---------------------------------------------------------------------------
# Test 24 — Cost ledger completeness after job completion
# Uses the completed JOB_ID from T6 (guarded on STATE_T6=complete).
# Verifies 8 cost-ledger fields are non-null:
#   actualInputTokens, actualOutputTokens, totalTokens, actualCostUsd,
#   actualAmountSats, workAmountSats, refundAmountSats, refundState.
# Honest-accounting invariant: actualAmountSats <= workAmountSats.
# refundState must be one of: not_applicable | pending | paid.
# ---------------------------------------------------------------------------
sep "Test 24 — Cost ledger completeness (job completed)"
if [[ -n "\$JOB_ID" && "\$STATE_T6" == "complete" ]]; then
  T24_RES=\$(curl -s -w "\\n%{http_code}" "\$BASE/api/jobs/\$JOB_ID")
  T24_BODY=\$(body_of "\$T24_RES"); T24_CODE=\$(code_of "\$T24_RES")
  T24_LEDGER=\$(echo "\$T24_BODY" | jq '.costLedger' 2>/dev/null || echo "null")
  T24_REFUND_STATE=\$(echo "\$T24_LEDGER" | jq -r '.refundState' 2>/dev/null || echo "")
  T24_FIELDS_OK=true
  for field in actualInputTokens actualOutputTokens totalTokens actualCostUsd actualAmountSats workAmountSats refundAmountSats refundState; do
    VAL=\$(echo "\$T24_LEDGER" | jq -r ".\$field" 2>/dev/null || echo "MISSING")
    [[ -z "\$VAL" || "\$VAL" == "null" ]] && T24_FIELDS_OK=false || true
  done
  T24_INV_OK=\$(echo "\$T24_LEDGER" | jq '
    (.actualAmountSats != null) and
    (.workAmountSats != null) and
    (.actualAmountSats <= .workAmountSats) and
    (.refundAmountSats >= 0)
  ' 2>/dev/null || echo "false")
  if [[ "\$T24_CODE" == "200" \\
      && "\$T24_LEDGER" != "null" \\
      && "\$T24_FIELDS_OK" == "true" \\
      && "\$T24_INV_OK" == "true" \\
      && "\$T24_REFUND_STATE" =~ ^(not_applicable|pending|paid)\$ ]]; then
    T24_ACTUAL=\$(echo "\$T24_LEDGER" | jq -r '.actualAmountSats' 2>/dev/null || echo "?")
    T24_WORK=\$(echo "\$T24_LEDGER" | jq -r '.workAmountSats' 2>/dev/null || echo "?")
    T24_REFUND=\$(echo "\$T24_LEDGER" | jq -r '.refundAmountSats' 2>/dev/null || echo "?")
    note PASS "8 fields non-null, actualAmountSats(\$T24_ACTUAL)<=workAmountSats(\$T24_WORK), refundAmountSats=\$T24_REFUND, refundState=\$T24_REFUND_STATE"
    PASS=\$((PASS+1))
  else
    note FAIL "code=\$T24_CODE ledger=\$T24_LEDGER fields_ok=\$T24_FIELDS_OK inv_ok=\$T24_INV_OK refundState=\$T24_REFUND_STATE"
    FAIL=\$((FAIL+1))
  fi
else
  note SKIP "Skipping — job not complete (STATE_T6=\${STATE_T6:-not_set}) or no JOB_ID"
  SKIP=\$((SKIP+1))
fi

# ---------------------------------------------------------------------------
# Summary
# ---------------------------------------------------------------------------
echo
echo "======================================="
echo " RESULTS: PASS=\$PASS  FAIL=\$FAIL  SKIP=\$SKIP"
echo "======================================="
if [[ "\$FAIL" -gt 0 ]]; then exit 1; fi
`;

  res.setHeader("Content-Type", "text/x-shellscript; charset=utf-8");
  res.setHeader("Content-Disposition", 'inline; filename="timmy_test.sh"');
  res.send(script);
});

export default router;