Commit Graph
10 Commits
Author SHA1 Message Date
173fa68025 perf: optimasi 7 hot-path bottleneck (buildKey, SSE, cooldowns, encode) (#6)
1. ResponseCache: short-circuit buildKey() via shouldCacheModel() check
   + WeakMap memoization untuk stableStringify (skip recursive sort
   kalau object reference sudah pernah di-stringify).

2. extractTextFromSSEEvent: ganti regex greedy \{.*\} dengan manual
   indexOf untuk JSON bounds (hindari backtracking per SSE chunk).

3. ProxyPool: bound cooldowns Map ke MAX_COOLDOWNS=10_000 dengan
   insertion-order LRU eviction — mencegah memory growth kalau
   banyak unique (proxy, model) pairs kena 429.

4. Single JSON.stringify: hitung responseBody sekali, pakai untuk
   cache.set dan Response constructor (sebelumnya stringified 2x).

5. Shared SHARED_ENCODER singleton: TextEncoder stateless, share
   module-level. Decoder tetap per-stream (stateful).

6. Branch DSML early: skip extractTextFromSSEEvent + JSON.parse
   kalau isDSMLDetectionEnabled() === false (untuk non-DeepSeek model).

7. safeReleaseReader() idempotent guard: gunakan readerReleased flag
   untuk mencegah double-delete di ACTIVE_READERS kalau exception
   terjadi di tengah stream cleanup.

274 tests pass, no regression. Estimated total saving: 5-15ms/req
untuk model non-cached + 30-150ms per streaming response.

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-27 17:46:51 +07:00
MythEclipse ac19f8f30d perf: stability and performance improvements across proxy
- Add exponential backoff (200ms-2s) between retry attempts
- Fix session retry bug: rotate proxy before retry to avoid same proxy
- Fix ACTIVE_READERS memory leak: release reader on stream done/error
- Make closeAllActiveReaders async with proper await
- WebSocket backpressure: pause upstream forwarding at 512KB buffer
- Optimize rate-limiter pruneTimestamps: avoid array reallocation
- Batch stream chunks (8 per yield) to reduce event loop overhead
- Add periodic cooldown cleanup in ProxyPool (30s interval)
- Extract shared wrapStreamWithCleanup utility to reduce duplication
- Fix fetchViaCurl temp file cleanup with proper unlink()
- Add missing ipv6Source overload to AI proxy handlers
2026-06-20 19:32:23 +07:00
MythEclipse cb6191902e fix: critical bugs, serverless stability, and security hardening
Bug Fixes:
- Fix rate limiter API mismatch: check() -> checkAsync() in index.ts, worker.ts, api/relay.ts
- Fix WebSocket SSRF silent drop: return error Response instead of undefined
- Fix isDevMode() default: changed from true to false (production-safe)
- Fix process.env -> env bindings in worker.ts requireAuth for Cloudflare Workers
- Fix Bun.file() crash in Workers: add try/catch with fallback
- Fix Bun.CryptoHasher -> Web Crypto API in mimo-auth.ts for Workers compat

Architecture:
- Add public methods to ProxyPool (getEntryAtIndex, getProxyUrlAtIndex, getCurrentIndex, setCurrentIndex) to remove all 'as any' casts in SessionProxyPool
- Add addProxy() method for manual proxy management
- Add loadAsync(), tryLoadAsync(), loadFromString() to ProxyPool

Serverless Stability:
- Add optional DNS rebinding protection via SSRF_DNS_CHECK env flag
- CORS cache now auto-invalidates when CORS_ORIGIN env changes
- Rate limiter max-size eviction (10k keys) prevents unbounded memory growth

Tests:
- Fix type assertions in test files (body as Record<string, unknown>)
- All 153 tests pass, typecheck clean
2026-06-19 18:10:49 +07:00
MythEclipseandClaude 7cbf6fd817 feat: add per-model proxy cooldown for rate-limit handling
ProxyPool:
- Add cooldowns map (host:port::model -> expiry) and cooldownDuration (60s default)
- Add markRateLimited(model) — puts current proxy in cooldown for a model
- Add isProxyInCooldown, isIndexInCooldown, isCurrentInCooldown checks
- Modify rotate(model?) — skip proxies in cooldown for the given model
- Add setCooldownDuration(ms) for configuration

SessionProxyPool:
- Add markRateLimited(sessionId, model) — delegates to underlying pool
- Modify rotateNow(sessionId, model?) — skip cooldown proxies
- Modify acquire(sessionId, model?) — skip cooldown when picking least-loaded
- Modify pickLeastUsedIndex(model?) — skip cooldown proxies in scan

fetch-utils.ts:
- Add extractModel helper — extracts model from context string
- On HTTP 429: call markRateLimited(model) before markFailed
- Pass model to rotate() / rotateNow() / acquire() throughout

Co-Authored-By: Claude <noreply@anthropic.com>
2026-06-17 04:59:16 +07:00
MythEclipseandClaude 283ed26231 fix: exhaust all proxies then direct fallback before giving up
fetchWithRetry:
- Dynamically calculate maxAttempts = pool.size + 1 (direct fallback)
- Try every proxy in pool via rotation, then direct as last resort
- Only classify as error when even direct produces no response

fetchWithSessionRetry:
- Default maxRetries = sessionPool.size + 1 instead of hardcoded 3
- Try pool.size proxy attempts (each on a different proxy via rotateNow),
  then 1 direct attempt (no proxy) before giving up
- Only classify as error if direct also returns no response

ProxyPool.rotate():
- Skip proxies that have exceeded the failure threshold (isFailed)

Co-Authored-By: Claude <noreply@anthropic.com>
2026-06-17 04:45:30 +07:00
MythEclipseandClaude f1943353ef fix: rotate proxy on every failure, return proper HTTP status
- Add rotateNow() to SessionProxyPool — force-rotate session to a
  different proxy immediately (excludes current index to ensure real
  rotation). Uses round-robin scan from oldIndex+1 so all proxies
  get used, not just bouncing between two.

- fetchWithSessionRetry: call rotateNow() on every failure instead of
  markFailed() which only rotated after threshold. Return last HTTP
  response (e.g. 429) instead of classifying as 502 when we have one.

- fetchWithRetry: rotate pool on every failure for consistency.

Co-Authored-By: Claude <noreply@anthropic.com>
2026-06-17 04:40:45 +07:00
MythEclipseandClaude 45f1b33fb6 feat: add structured logging across proxy pool and fetch utils
- fetch-utils.ts: logProxy() — logs every attempt, proxy used, success/failure
  with sessionId prefix for traceability
- proxy-pool.ts: logPool() — logs acquire/release/rotate/markFailed/markSuccess
  with active session count and proxy host info
- Both use consistent [prefix] HH:MM:SS.mmm key=value format

Co-Authored-By: Claude <noreply@anthropic.com>
2026-06-17 04:29:31 +07:00
MythEclipseandClaude 9bd6acddc5 feat: implement session-based sticky proxy pool with auto-failover
Add SessionProxyPool for per-session sticky proxy allocation with
load-balanced least-used selection and auto-rotation on failure.
Introduce fetchWithSessionRetry for transparent retry with proxy
rotation. Wire into AI proxy handlers (OpenAI + Anthropic) with
stream lifecycle cleanup.

Co-Authored-By: Claude <noreply@anthropic.com>
2026-06-16 23:50:47 +07:00
MythEclipse b09bca8def feat(core): implement robust fetch utilities and stream management
Introduce a centralized `fetch-utils.ts` to handle retry logic with proxy fallback, SSE line buffering to prevent chunk-boundary corruption, and graceful shutdown via active reader tracking.

Key changes:
- Add `fetchWithRetry` for automatic direct-to-proxy failover.
- Implement `SSELineBuffer` to ensure reliable parsing of split SSE chunks.
- Add `createStreamBodyLimiter` to enforce payload limits on streaming requests.
- Refactor `ProxyPool` to decouple failure marking from rotation.
- Standardize CORS handling and environment variable configuration.
- Clean up documentation and remove obsolete skill files.
2026-06-11 03:56:26 +07:00
MythEclipseandClaude Fable 5 03427cae8c feat: auto-rotate proxy pool with retry on network failure
- Add src/lib/proxy-pool.ts: round-robin proxy pool that reads
  proxy.txt (host:port:user:pass), tracks consecutive failures,
  and rotates on threshold
- Integrate into src/index.ts: on fetch network error, mark proxy
  as failed, rotate to next, and retry the request once
- proxy.txt loaded from PROXY_FILE/PROXY_LIST env var or ./proxy.txt
- Graceful no-op when proxy.txt doesn't exist (Vercel/Workers)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-06-10 22:12:59 +07:00