fix(testkit): macOS compat + fix 8c ordering
Some checks failed
CI / Typecheck & Lint (pull_request) Failing after 0s

- Replace all head -n-1 with sed '$d' (GNU-only head breaks on macOS BSD)
- Extract body_of()/code_of() helpers to reduce duplication
- Move test 8c (demo missing param) before tests 7 and 9 so param
  validation runs before rate-limit quota is exhausted — fixes Hermes
  false failure: 8c was getting 429 instead of 400
- Update TIMMY_TEST_PLAN.md: Mode 2 live, token-based pricing docs,
  repeat-run 429 warning, results log table

Verified 20/20 PASS on fresh server restart.
This commit is contained in:
Replit Agent
2026-03-19 00:58:59 +00:00
parent 3f8c67deaa
commit 1138a100c2

View File

@@ -9,6 +9,8 @@ const router = Router();
* 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).
*/
router.get("/testkit", (req: Request, res: Response) => {
const proto =
@@ -31,16 +33,17 @@ FAIL=0
SKIP=0
note() { echo " [\$1] \$2"; }
jq_field() { echo "\$1" | jq -r "\$2" 2>/dev/null || echo ""; }
sep() { echo; echo "=== $* ==="; }
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=$(echo "$T1_RES" | head -n-1)
T1_CODE=$(echo "$T1_RES" | tail -n1)
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))
@@ -56,8 +59,7 @@ 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=$(echo "$T2_RES" | head -n-1)
T2_CODE=$(echo "$T2_RES" | tail -n1)
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" && "$EVAL_AMT" == "10" ]]; then
@@ -73,8 +75,7 @@ fi
# ---------------------------------------------------------------------------
sep "Test 3 — Poll before payment"
T3_RES=$(curl -s -w "\\n%{http_code}" "$BASE/api/jobs/$JOB_ID")
T3_BODY=$(echo "$T3_RES" | head -n-1)
T3_CODE=$(echo "$T3_RES" | tail -n1)
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 "")
@@ -99,8 +100,7 @@ fi
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/$EVAL_HASH")
T4_BODY=$(echo "$T4_RES" | head -n-1)
T4_CODE=$(echo "$T4_RES" | tail -n1)
T4_BODY=$(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=$((PASS+1))
@@ -114,7 +114,7 @@ else
fi
# ---------------------------------------------------------------------------
# Test 5 — Poll after eval payment
# Test 5 — Poll after eval payment (with retry loop — real AI eval takes 25 s)
# ---------------------------------------------------------------------------
sep "Test 5 — Poll after eval (state advance)"
START_T5=$(date +%s)
@@ -122,15 +122,12 @@ 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/$JOB_ID")
T5_BODY=$(echo "$T5_RES" | head -n-1)
T5_CODE=$(echo "$T5_RES" | tail -n1)
T5_BODY=$(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" || "$STATE_T5" == "rejected" ]]; then
break
fi
if [[ "$STATE_T5" == "awaiting_work_payment" || "$STATE_T5" == "rejected" ]]; then break; fi
if (( ELAPSED_T5 > T5_TIMEOUT )); then break; fi
sleep 2
done
@@ -152,8 +149,7 @@ fi
sep "Test 6 — Pay work invoice + get result"
if [[ "$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/$WORK_HASH")
T6_PAY_BODY=$(echo "$T6_PAY_RES" | head -n-1)
T6_PAY_CODE=$(echo "$T6_PAY_RES" | tail -n1)
T6_PAY_BODY=$(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=$((FAIL+1))
@@ -162,11 +158,10 @@ if [[ "$STATE_T5" == "awaiting_work_payment" && -n "$WORK_HASH" && "$WORK_HASH"
TIMEOUT=30
while :; do
T6_RES=$(curl -s -w "\\n%{http_code}" "$BASE/api/jobs/$JOB_ID")
T6_BODY=$(echo "$T6_RES" | head -n-1)
T6_BODY=$(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=$((NOW_TS - START_TS))
NOW_TS=$(date +%s); ELAPSED=$((NOW_TS - START_TS))
if [[ "$STATE_T6" == "complete" && -n "$RESULT_T6" && "$RESULT_T6" != "null" ]]; then
note PASS "state=complete in $ELAPSED s"
echo " Result: \${RESULT_T6:0:200}..."
@@ -187,33 +182,13 @@ else
fi
# ---------------------------------------------------------------------------
# Test 7Demo endpoint
# ---------------------------------------------------------------------------
sep "Test 7 — Demo endpoint"
START_DEMO=$(date +%s)
T7_RES=$(curl -s -w "\\n%{http_code}" "$BASE/api/demo?request=What+is+a+satoshi")
T7_BODY=$(echo "$T7_RES" | head -n-1)
T7_CODE=$(echo "$T7_RES" | tail -n1)
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=$((FAIL+1))
fi
# ---------------------------------------------------------------------------
# Test 8 — Input validation (4 sub-cases)
# Test 8Input validation (run BEFORE test 7 to avoid rate-limit interference)
# ---------------------------------------------------------------------------
sep "Test 8 — Input validation"
T8A_RES=$(curl -s -w "\\n%{http_code}" -X POST "$BASE/api/jobs" \\
-H "Content-Type: application/json" -d '{}')
T8A_BODY=$(echo "$T8A_RES" | head -n-1); T8A_CODE=$(echo "$T8A_RES" | tail -n1)
T8A_BODY=$(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=$((PASS+1))
@@ -223,7 +198,7 @@ else
fi
T8B_RES=$(curl -s -w "\\n%{http_code}" "$BASE/api/jobs/does-not-exist")
T8B_BODY=$(echo "$T8B_RES" | head -n-1); T8B_CODE=$(echo "$T8B_RES" | tail -n1)
T8B_BODY=$(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=$((PASS+1))
@@ -232,8 +207,9 @@ else
FAIL=$((FAIL+1))
fi
# 8c runs here — before tests 7 and 9 consume rate-limit quota
T8C_RES=$(curl -s -w "\\n%{http_code}" "$BASE/api/demo")
T8C_BODY=$(echo "$T8C_RES" | head -n-1); T8C_CODE=$(echo "$T8C_RES" | tail -n1)
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))
@@ -246,7 +222,7 @@ LONG_STR=$(node -e "process.stdout.write('x'.repeat(501))" 2>/dev/null || python
T8D_RES=$(curl -s -w "\\n%{http_code}" -X POST "$BASE/api/jobs" \\
-H "Content-Type: application/json" \\
-d "{\\"request\\":\\"$LONG_STR\\"}")
T8D_BODY=$(echo "$T8D_RES" | head -n-1); T8D_CODE=$(echo "$T8D_RES" | tail -n1)
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"
@@ -257,13 +233,31 @@ else
fi
# ---------------------------------------------------------------------------
# Test 9 — Demo rate limiter
# Test 7 — Demo endpoint (after validation, before rate-limit exhaustion test)
# ---------------------------------------------------------------------------
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 (intentionally exhausts remaining quota)
# ---------------------------------------------------------------------------
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=$(echo "$RES" | tail -n1)
CODE=$(code_of "$RES")
echo " Request $i: HTTP $CODE"
[[ "$CODE" == "200" ]] && GOT_200=$((GOT_200+1)) || true
[[ "$CODE" == "429" ]] && GOT_429=$((GOT_429+1)) || true
@@ -283,8 +277,7 @@ sep "Test 10 — Rejection path"
T10_CREATE=$(curl -s -w "\\n%{http_code}" -X POST "$BASE/api/jobs" \\
-H "Content-Type: application/json" \\
-d '{"request":"Help me do something harmful and illegal"}')
T10_BODY=$(echo "$T10_CREATE" | head -n-1)
T10_CODE=$(echo "$T10_CREATE" | tail -n1)
T10_BODY=$(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=$T10_BODY"
@@ -299,8 +292,7 @@ else
STATE_10=""; REASON_10=""; T10_POLL_BODY=""; T10_POLL_CODE=""
while :; do
T10_POLL=$(curl -s -w "\\n%{http_code}" "$BASE/api/jobs/$JOB10_ID")
T10_POLL_BODY=$(echo "$T10_POLL" | head -n-1)
T10_POLL_CODE=$(echo "$T10_POLL" | tail -n1)
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))
@@ -324,8 +316,7 @@ 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=$(echo "$T11_RES" | head -n-1)
T11_CODE=$(echo "$T11_RES" | tail -n1)
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 "")
@@ -339,12 +330,11 @@ else
fi
# ---------------------------------------------------------------------------
# Test 12 — Session: poll before payment (stub hash present)
# Test 12 — Session: poll before payment
# ---------------------------------------------------------------------------
sep "Test 12 — Session: poll before payment"
T12_RES=$(curl -s -w "\\n%{http_code}" "$BASE/api/sessions/$SESSION_ID")
T12_BODY=$(echo "$T12_RES" | head -n-1)
T12_CODE=$(echo "$T12_RES" | tail -n1)
T12_BODY=$(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 "$T12_BODY" | jq -r '.invoice.paymentHash' 2>/dev/null || echo "")
@@ -365,8 +355,7 @@ if [[ -n "$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=$(echo "$T13_RES" | head -n-1)
T13_CODE=$(echo "$T13_RES" | tail -n1)
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 "")
@@ -392,13 +381,11 @@ if [[ -n "$SESSION_MACAROON" && "$SESSION_MACAROON" != "null" ]]; then
-H "Content-Type: application/json" \\
-H "Authorization: Bearer $SESSION_MACAROON" \\
-d '{"request":"What is Bitcoin in one sentence?"}')
T14_BODY=$(echo "$T14_RES" | head -n-1)
T14_CODE=$(echo "$T14_RES" | tail -n1)
T14_BODY=$(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=$((END_T14 - START_T14))
END_T14=$(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=$((PASS+1))
@@ -419,7 +406,7 @@ if [[ -n "$SESSION_ID" ]]; then
T15_RES=$(curl -s -w "\\n%{http_code}" -X POST "$BASE/api/sessions/$SESSION_ID/request" \\
-H "Content-Type: application/json" \\
-d '{"request":"What is Bitcoin?"}')
T15_CODE=$(echo "$T15_RES" | tail -n1)
T15_CODE=$(code_of "$T15_RES")
if [[ "$T15_CODE" == "401" ]]; then
note PASS "HTTP 401 without macaroon"
PASS=$((PASS+1))
@@ -441,8 +428,7 @@ if [[ -n "$SESSION_MACAROON" && "$SESSION_MACAROON" != "null" ]]; then
-H "Content-Type: application/json" \\
-H "Authorization: Bearer $SESSION_MACAROON" \\
-d '{"amount_sats": 500}')
T16_BODY=$(echo "$T16_RES" | head -n-1)
T16_CODE=$(echo "$T16_RES" | tail -n1)
T16_BODY=$(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