TradingAgents/tradingagents/llm_clients
KK 00815a5ade fix: do not pass base_url to ChatGoogleGenerativeAI
The CLI hardcodes backend_url as https://generativelanguage.googleapis.com/v1
for the Google provider and passes it as base_url to ChatGoogleGenerativeAI.
However, the google-genai SDK manages its own endpoint and API versioning
internally — passing an external base_url causes the SDK to construct
incorrect request paths, resulting in 404 Not Found errors for all Gemini
models including stable ones like gemini-2.5-flash.

Remove the base_url forwarding for Google clients so the SDK uses its
default endpoint logic.

Reproducer:
    ChatGoogleGenerativeAI(model="gemini-2.5-flash",
        base_url="https://generativelanguage.googleapis.com/v1").invoke("hi")
    # → ChatGoogleGenerativeAIError: 404 Not Found
2026-03-31 16:16:10 +08:00
..
TODO.md fix: pass base_url to Google and Anthropic clients for proxy support (#427) 2026-03-29 17:59:52 +00:00
__init__.py feat: add multi-provider LLM support with factory pattern 2026-02-03 22:27:20 +00:00
anthropic_client.py Merge pull request #464 from CadeYu/sync-validator-models 2026-03-29 11:07:51 -07:00
base_client.py Merge pull request #464 from CadeYu/sync-validator-models 2026-03-29 11:07:51 -07:00
factory.py fix: add http_client support for SSL certificate customization 2026-03-16 07:41:20 +08:00
google_client.py fix: do not pass base_url to ChatGoogleGenerativeAI 2026-03-31 16:16:10 +08:00
model_catalog.py chore: update model lists and defaults to GPT-5.4 family 2026-03-29 19:45:36 +00:00
openai_client.py Merge pull request #464 from CadeYu/sync-validator-models 2026-03-29 11:07:51 -07:00
validators.py sync model validation with cli catalog 2026-03-25 21:23:02 +08:00