feat(antigravity): ✨ add TransientQuotaError for bare 429 responses

fix(retry): 🐛 parse millisecond durations and avoid immediate retry loops

feat(antigravity): ✨ add automatic retry logic for empty API responses

fix(oauth): 🐛 prevent deadlock and token desync for rotating refresh tokens

feat(usage): ✨ implement per-model quota tracking with authoritative reset timestamps

feat(rotation): ✨ add sequential rotation mode with provider-specific quota parsing

fix(error-handler): 🔨 extract JSON retry parsing into dedicated function

fix(error-handler): 🐛 handle compound duration formats in retry-after parsing

Merge branch 'Antigravity' of https://github.com/Mirrowel/LLM-API-Key-Proxy into fix/quota-exceeded-global-cooldown

fix(rotator): prevent quota errors from global cooldown

fix(logging): preserve full credential filenames in logs

fix: improve error handling implementation based on code review

feat(core): ✨ add structured error accumulator and consistent error handling/reporting

fix(gemini): 🐛 consolidate parallel tool responses and improve rate limit handling

fix(core): improve error classification and prevent false key penalization

feat(core): enable static model configuration and LiteLLM compatibility for custom providers

feat(providers): ✨ enable dynamic support for custom openai-compatible providers

feat(provider): introduce OAuth credential management and custom provider handling

feat(client): add pre-request callback support to API client

perf(rotator): prevent indefinite waits for API key acquisition

refactor: Enhance error handling and retry logic

feat: enhance changelog generation and error handling in build process

feat: Enhance error classification and handling in UsageManager and error_handler for improved retry logic and cooldown management

feat: Enhance asynchronous handling in RotatingClient and UsageManager for improved error management and usage tracking

Inital commit