Charlie Tonneslan 98330aa302 Skip reasoning_effort entirely since all agents use function tools ... Per issue #403 analysis: the real problem is that reasoning_effort with function tools requires the /v1/responses endpoint, but LangChain's ChatOpenAI only supports /v1/chat/completions. This affects all models (not just gpt-5.x vs o-series), so the safest fix is to skip reasoning_effort and log an info message explaining why. Once LangChain adds /v1/responses support, this can be re-enabled.		2026-03-22 15:18:44 -04:00
..
agents	fix: handle comma-separated indicators in get_indicators tool	2026-03-15 18:05:36 +00:00
dataflows	fix: harden stock data parsing against malformed CSV and NaN values	2026-03-15 18:29:43 +00:00
graph	Skip reasoning_effort entirely since all agents use function tools	2026-03-22 15:18:44 -04:00
llm_clients	fix: add http_client support for SSL certificate customization	2026-03-16 07:41:20 +08:00
__init__.py	chore: update model lists, bump to v0.2.1, fix package build	2026-03-15 23:34:50 +00:00
default_config.py	feat: add yfinance support to accommodate community request for stability and quota	2026-02-03 22:27:20 +00:00