add log

README.md

@@ -107,7 +107,7 @@ After you have Python and (optionally) PostgreSQL installed, follow these steps:
 
 1. `git clone https://github.com/Pythagora-io/gpt-pilot.git` (clone the repo)
 2. `cd gpt-pilot` (go to the repo folder)
-3. `python -m venv venv` (create a virtual environment)
+3. `python3 -m venv venv` (create a virtual environment)
 4. `source venv/bin/activate` (or on Windows `venv\Scripts\activate`) (activate the virtual environment)
 5. `pip install -r requirements.txt` (install the dependencies)
 6. `cp example-config.json config.json` (create `config.json` file)

core/llm/base.py

@@ -243,6 +243,7 @@ async def __call__(
                 # us confirm that we've breached the token limit, but Anthropic doesn't,
                 # so we can't be certain that's the problem in Anthropic case.
                 # Here we try to detect that and tell the user what happened.
+                log.info(f"API status error: {err}")
                 err_code = err.response.json().get("error", {}).get("code", "")
                 if err_code in ("request_too_large", "context_length_exceeded", "string_above_max_length"):
                     # Handle OpenAI and Groq token limit exceeded