Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.
Commits on main
fix(core): handle ResponseIncompleteEvent in OpenAI Responses API streaming (#9535)
e8d5922 jnjpng committed 9 months ago
fix(core): add OpenAI 24h prompt cache retention for supported models (#9509)
21765d1 Ari Webb committed 9 months ago
fix(core): add warning log for streaming chunks missing id or otid (#9513)
042c9c3 jnjpng committed 9 months ago
chore: add ty + pre-commit hook and repeal even more ruff rules (#9504)
f5c4ab5 Kian Jones committed 9 months ago
Revert "fix(core): add OpenAI prompt cache key and model-gated 24h retention" (#9502)
fa70e09 Ari Webb committed 9 months ago
fix(core): add OpenAI prompt cache key and model-gated 24h retention (#9492)
619e81e Charles Packer committed 9 months ago
fix: retry ChatGPT 502 and upstream connection errors with exponential backoff (#9495)
fbc0bb6 jnjpng committed 9 months ago
fix(core): skip malformed send_message entries in message conversion (#9494)
26cbdb7 Sarah Wooders committed 9 months ago
fix(core): remove old static landing page from Docker image (#9369)
c32d53f Charles Packer committed 9 months ago
fix: re-raise LLMError before wrapping with handle_llm_error (#9482)
e3eafb1 jnjpng committed 9 months ago
debug: log statement_timeout + connection pid on session checkout (#9472)
2f02941 Kian Jones committed 9 months ago
feat: add credit verification before agent message endpoints [LET-XXXX] (#9433)
0a8a8fd Ari Webb committed 9 months ago
New prompts/defaults for `sliding_window` and `all` compaction (#9444)
9bec8c6 amysguan committed 9 months ago
fix: update system prompt metadata label to "System prompt last recompiled" (#9477)
0b08164 github-actions[bot] committed 9 months ago
fix(core): descriptive error for empty message_ids instead of IndexError (#9464)
f55ff3a Kian Jones committed 9 months ago
fix(core): catch bare openai.APIError in handle_llm_error (#9468)
80f34f1 Kian Jones committed 9 months ago