0xallamandAhmed Allam afec29c0ef fix(llm): add streaming retry with exponential backoff ...

- Retry failed streams up to 3 times with exp backoff (8s min, 64s max)
- Reset chunks on failure and retry full request
- Use litellm._should_retry() for retryable error detection
- Switch to async acompletion() for streaming
- Refactor generate() into smaller focused methods

2026-01-06 16:44:22 -08:00

..

__init__.py

fix: pass api_key directly to litellm completion calls

2025-12-07 01:38:21 +04:00

config.py

feat: add --scan-mode CLI option with quick/standard/deep modes

2025-12-14 19:13:08 -08:00

llm.py

fix(llm): add streaming retry with exponential backoff

2026-01-06 16:44:22 -08:00

memory_compressor.py

feat: add configurable timeout for LLM requests

2025-11-12 18:58:03 +04:00

request_queue.py

fix(llm): add streaming retry with exponential backoff

2026-01-06 16:44:22 -08:00

utils.py

feat(tui): add real-time streaming LLM output with full content display

2026-01-06 16:44:22 -08:00