Add automated testing flow to reduce manual effort

Integrate a new testkit endpoint and update package.json scripts to enable automated testing via `pnpm test` and `pnpm test:prod`, including a new test case for request body size limits.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 418bf6f8-212b-4bb0-a7a5-8231a061da4e
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: 60472e18-59b7-4877-a9a2-16381573ab68
Replit-Helium-Checkpoint-Created: true
This commit is contained in:
alexpaynex
2026-03-18 17:43:01 +00:00
parent f5811da508
commit fc4fd50e33
5 changed files with 345 additions and 1 deletions

View File

@@ -3,12 +3,14 @@ import healthRouter from "./health.js";
import jobsRouter from "./jobs.js";
import demoRouter from "./demo.js";
import devRouter from "./dev.js";
import testkitRouter from "./testkit.js";
const router: IRouter = Router();
router.use(healthRouter);
router.use(jobsRouter);
router.use(demoRouter);
router.use(testkitRouter);
if (process.env.NODE_ENV !== "production") {
router.use(devRouter);

View File

@@ -0,0 +1,318 @@
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
*/
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"; }
jq_field() { echo "\$1" | jq -r "\$2" 2>/dev/null || echo ""; }
sep() { echo; echo "=== $* ==="; }
# ---------------------------------------------------------------------------
# Test 1 — Health check
# ---------------------------------------------------------------------------
sep "Test 1 — Health check"
T1_RES=$(curl -s -w "\\n%{http_code}" "$BASE/api/healthz")
T1_BODY=$(echo "$T1_RES" | head -n-1)
T1_CODE=$(echo "$T1_RES" | tail -n1)
if [[ "$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=$(echo "$T2_RES" | head -n-1)
T2_CODE=$(echo "$T2_RES" | tail -n1)
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
# ---------------------------------------------------------------------------
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 "$T3_RES" | tail -n1)
STATE_T3=$(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" ]]; then
note PASS "state=awaiting_eval_payment, evalInvoice echoed"
PASS=$((PASS+1))
else
note FAIL "code=$T3_CODE body=$T3_BODY"
FAIL=$((FAIL+1))
fi
if [[ -n "$EVAL_HASH" && "$EVAL_HASH" != "null" ]]; then
note PASS "evalInvoice.paymentHash present (stub mode active)"
PASS=$((PASS+1))
else
note FAIL "evalInvoice.paymentHash missing — stub mode not active"
FAIL=$((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/$EVAL_HASH")
T4_BODY=$(echo "$T4_RES" | head -n-1)
T4_CODE=$(echo "$T4_RES" | tail -n1)
if [[ "$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=$((SKIP+1))
fi
# ---------------------------------------------------------------------------
# Test 5 — Poll after eval payment
# ---------------------------------------------------------------------------
sep "Test 5 — Poll after eval (state advance)"
sleep 2
T5_RES=$(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)
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 "")
if [[ "$T5_CODE" == "200" && "$STATE_T5" == "awaiting_work_payment" && -n "$WORK_AMT" && "$WORK_AMT" != "null" ]]; then
note PASS "state=awaiting_work_payment, workInvoice.amountSats=$WORK_AMT"
PASS=$((PASS+1))
elif [[ "$T5_CODE" == "200" && "$STATE_T5" == "rejected" ]]; then
note PASS "Request correctly rejected by agent after eval"
PASS=$((PASS+1))
WORK_HASH=""
else
note FAIL "code=$T5_CODE state=$STATE_T5 body=$T5_BODY"
FAIL=$((FAIL+1))
fi
# ---------------------------------------------------------------------------
# Test 6 — Pay work invoice + poll for result
# ---------------------------------------------------------------------------
sep "Test 6 — Pay work invoice + get result"
if [[ "$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 "$T6_PAY_RES" | tail -n1)
if [[ "$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/$JOB_ID")
T6_BODY=$(echo "$T6_RES" | head -n-1)
STATE_T6=$(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=$((SKIP+1))
fi
# ---------------------------------------------------------------------------
# Test 7 — Demo endpoint
# ---------------------------------------------------------------------------
sep "Test 7 — Demo endpoint"
START_DEMO=$(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=$((FAIL+1))
fi
# ---------------------------------------------------------------------------
# Test 8 — Input validation (4 sub-cases)
# ---------------------------------------------------------------------------
sep "Test 8 — Input validation"
T8A_RES=$(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 "$T8A_RES" | tail -n1)
if [[ "$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=$(echo "$T8B_RES" | head -n-1); T8B_CODE=$(echo "$T8B_RES" | tail -n1)
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=$((FAIL+1))
fi
T8C_RES=$(curl -s -w "\\n%{http_code}" "$BASE/api/demo")
T8C_BODY=$(echo "$T8C_RES" | head -n-1); T8C_CODE=$(echo "$T8C_RES" | tail -n1)
if [[ "$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=$(echo "$T8D_RES" | head -n-1); T8D_CODE=$(echo "$T8D_RES" | tail -n1)
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 9 — Demo rate limiter
# ---------------------------------------------------------------------------
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)
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 1 ]]; then
note PASS "Rate limiter triggered ($GOT_200 x200 $GOT_429 x429)"
PASS=$((PASS+1))
else
note FAIL "No 429 received — limiter may not be working ($GOT_200 x200)"
FAIL=$((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=$(echo "$T10_CREATE" | head -n-1)
T10_CODE=$(echo "$T10_CREATE" | tail -n1)
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
sleep 3
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 "$T10_POLL" | tail -n1)
STATE_10=$(echo "$T10_POLL_BODY" | jq -r '.state' 2>/dev/null || echo "")
REASON_10=$(echo "$T10_POLL_BODY" | jq -r '.reason' 2>/dev/null || echo "")
if [[ "$T10_POLL_CODE" == "200" && "$STATE_10" == "rejected" && -n "$REASON_10" && "$REASON_10" != "null" ]]; then
note PASS "state=rejected, reason: \${REASON_10:0:120}"
PASS=$((PASS+1))
else
note FAIL "code=$T10_POLL_CODE state=$STATE_10 body=$T10_POLL_BODY"
FAIL=$((FAIL+1))
fi
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;

View File

@@ -6,7 +6,9 @@
"preinstall": "sh -c 'rm -f package-lock.json yarn.lock; case \"$npm_config_user_agent\" in pnpm/*) ;; *) echo \"Use pnpm instead\" >&2; exit 1 ;; esac'",
"build": "pnpm run typecheck && pnpm -r --if-present run build",
"typecheck:libs": "tsc --build",
"typecheck": "pnpm run typecheck:libs && pnpm -r --filter \"./artifacts/**\" --filter \"./scripts\" --if-present run typecheck"
"typecheck": "pnpm run typecheck:libs && pnpm -r --filter \"./artifacts/**\" --filter \"./scripts\" --if-present run typecheck",
"test": "bash scripts/test-local.sh",
"test:prod": "BASE=https://timmy.replit.app bash timmy_test.sh"
},
"private": true,
"devDependencies": {

8
scripts/test-local.sh Executable file
View File

@@ -0,0 +1,8 @@
#!/usr/bin/env bash
# Runs the Timmy test suite against the local dev server.
# Usage: pnpm test (from repo root)
# BASE=https://custom-url.replit.app pnpm test
set -euo pipefail
BASE="${BASE:-https://${REPLIT_DEV_DOMAIN}}"
echo "Running tests against: $BASE"
BASE="$BASE" bash timmy_test.sh

View File

@@ -220,6 +220,20 @@ else
FAIL=$((FAIL+1))
fi
LONG_STR=$(node -e "process.stdout.write('x'.repeat(501))")
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 "$T8D_RES" | tail -n1)
T8D_ERR=$(jq_field "$T8D_BODY" '.error')
if [[ "$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 9 — Demo rate limiter
# Note: The limiter is in-memory (5 req/hr/IP). Prior runs from the same IP