token-guard
edmonddantesj tarafından
AI & LLMsÖzet
<!-- 🌌 Aoineco-Verified | S-DNA: AOI-2026-0213-SDNA-TG01 -->.
Açıklama
Bu Beceri Ne Yapar
Intercepts LLM API requests before they're sent to prevent 429 rate limit errors. Tracks per-model token usage with a sliding window and automatically waits, falls back to another model, or blocks runaway duplicate requests. Works with Gemini, Claude, GPT-4o, and DeepSeek with pre-configured quotas.
Unlike post-hoc retry wrappers, it estimates token count before the call so failed requests never consume quota.
Ne Zaman Kullanılır
- Processing large PDFs without hitting Gemini's 1M TPM limit
- Detecting and stopping retry loops that spiral into quota exhaustion
- Switching to a cheaper model automatically when primary quota runs low
- Caching repeated prompts to avoid redundant API calls
- Monitoring token spend across multiple models in a single agent run
Örnek İş Akışı
User asks: process this 200-page PDF using Gemini Flash
- 1
Call guard.check(prompt_text, model='gemini-3-flash') to estimate token count
- 2
Receive decision.action == 'wait' because usage is above 80% of 1M TPM limit
- 3
Sleep for decision.wait_seconds, then re-check
- 4
Receive decision.action == 'proceed', call the LLM API
- 5
Call guard.record_usage() and guard.cache_response() to update quota tracking
PDF processed without a 429 error; quota state updated for subsequent calls
Kurulum
clawhub install edmonddantesj/token-guardCLI komutunu çalıştırın ya da istemi Claude Code, Cursor, Codex veya kullandığınız kodlama ajanına yapıştırın.