Create server/src/lib/validators.ts with reusable schemas for all API
inputs (auth, fights, bets, payments, tournaments, queue, docs).
Import and use in all route handlers, replacing inline validation.
Add formatZodError helper for user-friendly error messages.
77 test cases in validators.test.ts cover valid, invalid, boundary,
and attack inputs (SQL injection, XSS, prototype pollution).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove ^ prefix from all 33 dependencies across root, server, and
frontend package.json files. Lockfile regenerated and verified with
pnpm install --frozen-lockfile.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Human morph sprites were generated without archetype and customization
params, causing fallback to generic sprites instead of the bot's actual
appearance.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Added isVerifyingWebhook state with spinner and disabled button during
webhook test. Improved error message to guide user on retry.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Changed from fixed 1.5s setInterval to recursive setTimeout with
exponential backoff on consecutive errors. Resets to 1.5s on success.
Added 2 tests verifying backoff escalation and reset behavior.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Bot registration (3 tests), human registration (1 test), fight replay
(2 tests for JS error checking), and leaderboard (3 tests for rendering).
All use Playwright with text-based selectors.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Set up Playwright with Chromium, dev server auto-start, test helpers
for seeding bots and programmatic auth. Added smoke spec that verifies
homepage and leaderboard load without crashes.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
14 integration tests covering full fight lifecycle with real in-memory
DB: SSE event ordering, polling bot challenge/response flow, human
player response submission, and 3 concurrent fights without interference.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
8 tests covering: complete fight lifecycle, HP progression, ELO
updates, concurrent fight prevention, round data validity, ELO
conservation, status transitions, and win streak tracking.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Critical finding: when all bots answer correctly, even a 50ms speed
advantage wins 95.4% of fights. At 100ms+ gap it's 100% deterministic.
ELO separation reaches 450+ after just 50 fights. Speed completely
dominates the "all correct" meta.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Simulated 1000 fights with 80% accuracy and equal speed. First-to-lead
wins 60.4% of decided fights, confirming combo system is balanced.
No decay or comeback mechanics needed.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When both bots answer wrong, the one with higher checkAnswer confidence
(closer to correct) gets +1 point advantage. Rewards trying over
timing out. Equally wrong remains a pure draw.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When both bots are correct, the one with higher checkAnswer confidence
(exact match 1.0 vs fuzzy match 0.8) gets up to +1.0 bonus points.
This rewards precise answers over approximate ones, adding another
competitive dimension beyond pure speed.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Both-correct fights could almost never produce critical hits because
max margin at typical speed differences was ~2.2, far below threshold
of 4. Lowering to 3 yields ~15% critical hit rate (target 10-20%),
making speed differences produce more exciting fight dynamics.
Research findings: simulated 1000 fights with both bots answering
correctly. Critical rate went from 0% to 15.3% with new threshold.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Multi-turn simulation, authority impersonation, encoding tricks
(Base64, ROT13), fake JSON system prompts, red team framing,
reward manipulation, inverted instruction logic. All difficulty: hard.
Zero audit failures after addition.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Test roundToDifficulty: rounds 1-2 easy, 3-4 medium, 5+ hard
- Test pickChallenge difficulty filtering works with round numbers
- Audit prompt difficulty tags across all 16 challenge types
- 8 types lack hard prompts, 3 lack medium prompts
- 82.7% of prompts are untagged (no difficulty attribute)
- Report written to loop/difficulty-distribution.md
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- checkAnswer now returns highest score across all accepted answers
instead of first match, fixing 95 false-low-confidence results
- Skip string containment for purely numeric strings to prevent
false positives like "1000" matching inside "10000"
- Preserve decimal points in normalize() (42.0 no longer becomes 420)
- Use word-boundary regex for number matching in responses
- Fix 47 wrong choices scoring too high (comma-formatted numbers,
verbose choices matching terse answers)
- Fix 17 prompts where no choice matched any accepted answer
- Challenge audit now reports zero failures across all 1472 prompts
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
fetchNostrProfile now uses Promise.allSettled to query all relays
concurrently. Aggregates results with latest-created_at-wins strategy
instead of stopping at the first relay that responds.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Module re-evaluation during HMR reset autoRestoreRan to false, causing
duplicate auth-restore API calls. Now persists flag on globalThis.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
useNostr (9), useFightCache (5), useOnlineStatus (4) composable tests.
Added fake-indexeddb dev dependency for IDB tests.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Only invalidates __alltime__ and current season cache keys on fight completion,
preserving historical season caches. Test verifies selective behavior.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Global app.onError handler already in app.ts catches all unhandled route
exceptions. Production mode returns "Internal server error" only.
Tests verify no stack traces or file paths leak in responses.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Both bots timing out every round: verified draw with zero damage
- Perfect victory (10-0): verified correct ELO calculation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
blacklistJwt() adds token to in-memory blacklist until its natural expiry.
verifyJwt() checks blacklist before signature verification.
Cleanup interval removes expired entries every 10 minutes.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Documents finding: no replay protection in NIP-98 verification.
Token replay within 120s window succeeds (mitigated by JWT issuance being idempotent).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Tests the actual rateLimit middleware with production mode via dynamic import.
Covers: under-limit allows, over-limit returns 429, window reset, per-IP
isolation, and poll endpoint config (30 req/1s window).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Catches runtime errors in child components, displays user-friendly
error message with reload button. Wired into App.vue wrapping
router-view. Tests verify error capture and button rendering.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Timeout and WebSocket errors reject with proper Error objects
- Caller catches and falls through to poll-based confirmation
- Preimage undefined check prevents calling confirm with no preimage
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
feedbackTimer, timerHandle, and pollHandle are all cleared in
onUnmounted. Test confirms cleanup pattern works correctly.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
13 silent catch handlers replaced with descriptive console.warn logging
across 6 frontend files. No silent error swallowing remains.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
SSE now always attempts reconnection when fight isn't finished,
regardless of isLive.value. Uses exponential backoff (1s, 2s, 4s,
max 8s). Moved sseRetries to outer scope to persist across reconnects.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Validates challenge type against the full CHALLENGE_TYPES enum before
processing. Invalid types now return 400 instead of silently falling
back to speed_blitz.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Production now requires JWT_SECRET env var. Added comprehensive JWT
tests: creation, verification, expiry, tampered payload, tampered
signature, and malformed token rejection.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Added getDecodedToken validation that rejects malformed tokens with
400 before any DB lookups. Tests cover empty, non-base64, truncated,
and random base64 tokens.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add rateLimit(1_000, 30) middleware to GET /poll endpoint
- Fix Challenge type errors in human-responses test files (missing baseDamage)
- Add rate-limit unit test verifying 429 after exceeding limit
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
better-sqlite3 driver is synchronous — .get() does NOT need await.
Added tests for unknown pubkey (404) and missing pubkey (400) on join.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Frontend: vitest.config.ts with vue plugin + jsdom, dummy component test
- Server: in-memory SQLite test DB factory + Hono testClient helper + smoke test
- CI: add pnpm audit and server coverage threshold steps
- Root: vitest workspace config for multi-project test discovery
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Scoring: both-wrong is now a DRAW — equal scores (3/3), no winner,
symmetric minimal damage. Garbage answers no longer beat reasonable
ones just by being faster. Both-wrong narrations reflect the draw.
Entrance: removed duplicate announceDeepIntro() call from FightViewer
(was already called inside playEntrance). Removed _resetPositions()
after entrance (entrance already places fighters at home positions,
the extra reset caused a visible snap/reset).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Merged bot-setup and choose-connection into one actionable step.
Users now see mode picker, download button for the correct guide
(BOTFIGHTS-WEBHOOK.md or BOTFIGHTS-POLLING.md), and safety info
all on one screen instead of two filler steps with no actions.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
buildNip98Token checked window.nostr before secretKeyHex, so
"Generate New Identity" would sign with the browser extension's key
after saving. Now explicit keys always take priority over extensions.
Also made setup flow mode-aware: webhook users get BOTFIGHTS-WEBHOOK.md,
polling users get BOTFIGHTS-POLLING.md with matching copy prompts.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Polling bots have no external script running during practice mode,
so the poll would time out giving empty answers. Now overrides the
webhook URL to human.local so the browser UI handles challenges.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Allow huggingface.co in CSP connect-src (fixes Kokoro TTS model download)
- Add registerSW.js route (fixes PWA service worker 404)
- Add _resetPositions() safety after entrance (fixes invisible fighters)
- Fight end sequence works without canvas scene (KO/overlays/log always play)
- Pre-fight instructions in battle log for human players
- NIP-55 visibility sync and cleanup handlers
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When window.nostr isn't available (common on mobile Chrome where
extensions can't inject), fall back to NIP-55 nostrsigner: intent
URIs. This opens Amber/Primal directly to sign a NIP-98 event,
then redirects back with the signed event for JWT authentication.
- Build nostrsigner: URI with unsigned NIP-98 event + callback URL
- Process NIP-55 callback on page mount (extract signed event from URL)
- Auto-detect Android to show "SIGN IN WITH AMBER / PRIMAL" label
- Reduced window.nostr polling from 3s to 2s before NIP-55 fallback
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Security:
- Move CREATOR_PUBKEY from hardcoded constant to BOTFIGHTS_CREATOR_PUBKEYS
env var. Shared isCreatorPubkey() in constants.ts used by auth, admin,
tournaments. Frontend checks authorization via API, not client-side.
Mobile fixes:
- Nostr signer: poll for window.nostr up to 3s (Amber injects late).
- TTS: auto-unlock AudioContext on first user interaction via
installAutoUnlock() on fight page mount.
UX:
- Add loading spinners to "I BUILD BOTS" and "I FIGHT MYSELF" buttons.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Nostr signer: poll for window.nostr up to 3s on mobile (Amber injects
late). Both login() and handleSignerLogin() now wait before failing.
- Mobile TTS: install global one-time click/touch/keydown handler to
auto-unlock AudioContext when fight pages mount. Previously only
triggered by explicit sound toggle, so mobile TTS silently failed.
- Add loading spinners to "I BUILD BOTS" and "I FIGHT MYSELF" buttons.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add sfxModem() — synthesized 56k handshake sound with carrier tones,
data burst, and chirps. Plays instead of TTS for code_golf/hack_battle
rounds and code-detected answers.
- Fix entrance voice overlap: remove duplicate announceDeepIntro() from
robe entrance, add cancelPrevious to entrance-specific voice calls
(girlfriend, bouncer, shopping cart, spotlight, creator) so they
cleanly replace the global intro instead of overlapping.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Expand all 5 creative answer pools from 5-10 to 25-30 entries each
- Fix factual wrong answers to pick from challenge's own wrong choices
instead of random non-sequiturs like "banana" and "purple?"
- Reduce bad answer rate: 25% → 2.5% at elo 1200, 0% at elo 1300+
- Improve BAD_ANSWERS and WRONG_FACTUAL to be funny when they do appear
- 90%+ of all mock answers are now good attempts that make sense
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove .slice(0, 120) truncation from battle log entries and
.slice(0, 60) from speech bubble calls. Increase bubble limits
to 200 chars, 24 chars/line, 8 lines so responses display fully.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
On narrow viewports (<600px), fighters were oversized due to the
desktop scale formula. Use reduced base (1.1) and tier (0.2) scale
factors on mobile while keeping desktop unchanged.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fix invisible characters in human mode: init live scene BEFORE starting
challenge polling so entrance plays before first question appears
- Cap creative writing timer to 10s for multiple choice (just tapping buttons)
- Fix TTS reliability: precache priority phrases (Round 1-7, Fight!, K.O.)
all at once instead of in slow batches; prevent duplicate precache runs
- Add 10 vibe-coded narrations (~20% chance): "I was vibe coded into existence"
- Add 15 sweary narrations (~30% chance): raw unhinged fight commentary
- Add sweary draw and retro narrations
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace insecure raw-pubkey auth with cryptographic NIP-98 signed
requests and server-issued JWT sessions. Logout now fully clears
all state including nsec. Add yellow "Use Nostr Signer" button
for Amber/NIP-07 remote signers.
- Server: JWT middleware (HMAC-SHA256, 24h expiry), NIP-98 verification
- Server: POST /api/auth/nostr/session endpoint
- Frontend: NIP-98 token builder + authFetch wrapper with JWT Bearer
- Frontend: All authenticated API calls use authFetch
- Security: logout clears JWT, pubkey, bot, nsec, and profile pic
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add Practice button to BotProfilePage for quick sparring
- Fix rate limiter bug: all rateLimit() instances shared one counter map,
causing global and per-route limits to corrupt each other. Each limiter
now gets its own isolated map.
- Replace 8-digit hex colors (#ffd70066) with rgba() in sprite rendering
for mobile browser compatibility (iOS Safari renders them as black boxes)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Shows a one-time warning when users first click "Fight For Sats" letting
them know it's vibe coded and to only use small sats amounts. Acknowledged
state persists in localStorage.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Mobile nav menu now overlays content (absolute positioning) instead of
pushing it down
- Speech bubbles stay visible for minimum 400ms even when TTS resolves
instantly or fails
- kokoroPlayCached checks audio cache and loads static files even when
Kokoro worker hasn't loaded — fixes TTS not playing on production
- CORS_ORIGIN env now supports comma-separated origins
- Rename "VIDEO REPLAY" to play icon + "REPLAY"
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Guard initScene() with initializingScene flag to prevent concurrent calls
- Don't auto-reinit scene on WebGL context restore during active replay
- Block initScene() after component is destroyed
- Static audio files now play even before Kokoro worker loads
- kokoroSpeak/kokoroSpeakAsync check cache before requiring worker ready
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
71 static voice files (9.6MB) for round calls, intros, hype lines,
and challenge announces. These play instantly from file instead of
running Kokoro TTS generation in the browser. Dynamic content
(questions, answers, narrations) still uses Kokoro.
Includes Node.js generation script (scripts/generate-voice-files.mjs)
and modified tts.ts to check static file cache before worker generation.
Static audio works even before Kokoro model finishes loading.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Reduces worker generation timeout from 10s to 4s and adds 2s race on
awaitReady so slow Kokoro generation falls back to Web Speech API
quickly instead of stalling the fight.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds await-then-play pattern: audio is pre-generated and cached before
visuals appear, so log text + speech bubble + mouth animation + voice
all fire in the same frame. Prefetches both answers during question
playback for instant transitions. Adds hideSpeechBubble() to dismiss
bubbles when voice ends instead of fixed 5s timer.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Track active fight IDs per bot in orchestrator (Set → Map)
- Return fightId in "already in fight" error responses (409)
- Frontend shows "REJOIN FIGHT" link instead of generic error
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Benchmarks the scoring pipeline (challenge → response → score → elo → tier)
without I/O. Currently achieves ~8500 fights/sec.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Listen for webglcontextlost/restored events on the fight canvas.
Show "recovering" overlay on context loss, re-init scene on restore.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
