Yijia-Xiao 4016fd4efa fix: stop leaking OpenAI base_url into non-OpenAI provider clients ...

Default config had backend_url='https://api.openai.com/v1' which was
forwarded to every provider client, including Google. ChatGoogleGenerativeAI
constructed requests against that base, producing malformed URLs like
https://api.openai.com/v1/v1beta/models/gemini-2.5-flash:generateContent
that 404 with empty body.

Discovered while running propagate() against Gemini end-to-end. The
structured-output smoke worked because that path constructed the LLM
without going through the factory and without forwarding backend_url;
propagate() goes through TradingAgentsGraph.__init__ which forwards
config['backend_url'] to every provider.

Fix: default to None. Each provider client falls back to its own
endpoint (api.openai.com for OpenAI via _PROVIDER_CONFIG, Gemini's
default for Google, and so on). The CLI flow already sets backend_url
explicitly per provider when the user picks one, so that path is
unchanged.

Verified: full propagate() now passes end-to-end on both
OpenAI gpt-5.4-mini and Gemini gemini-3-flash-preview, with all nine
structure/log/signal checks green for each.

2026-04-25 20:54:19 +00:00

..

agents

feat: structured-output Trader and Research Manager (#434, finishes the trio)

2026-04-25 20:27:23 +00:00

dataflows

fix: use explicit encoding="utf-8" for all file I/O so Windows users avoid cp1252 crashes (#543, #550, #576)

2026-04-25 07:25:32 +00:00

graph

feat: structured-output Portfolio Manager + 5-tier rating consistency (#434)

2026-04-25 19:57:26 +00:00

llm_clients

test: lazy-load LLM provider clients and add API-key fixtures so the test suite runs cleanly without credentials (#588)

2026-04-25 07:41:36 +00:00

__init__.py

fix: use explicit encoding="utf-8" for all file I/O so Windows users avoid cp1252 crashes (#543, #550, #576)

2026-04-25 07:25:32 +00:00

default_config.py

fix: stop leaking OpenAI base_url into non-OpenAI provider clients

2026-04-25 20:54:19 +00:00