GPT-4o returns JSON with trailing comma in tool call Apr 15, 2025

GPT-4o returns JSON with trailing comma in tool call

While parsing function‑call output from GPT‑4o the JSON loader threw:

...
Anthropic Messages API truncates tools array Feb 15, 2025

Anthropic Messages API truncates tools array

Today a Claude 3 call with tool definitions started ignoring the last tool in the list. No errors, just missing.

...
Gemini 1.5 Flash API payload exceeds 32k window silently Dec 16, 2024

Gemini 1.5 Flash API payload exceeds 32k window silently

Pushed a long system prompt and history to the beta Flash model last night. Response came back with the choices array empty and no error.

...
LangGraph raises TypeError on function node output Oct 15, 2024

LangGraph raises TypeError on function node output

This morning my LangGraph flow crashed after a new tool node.

...
HuggingFace pipeline returns empty string with Gemini 1.5 Pro Aug 15, 2024

HuggingFace pipeline returns empty string with Gemini 1.5 Pro

Last week a quick text‑generation pipeline came back blank every call.

...
vLLM tokenizer mismatch on finetuned Mistral model Jun 15, 2024

vLLM tokenizer mismatch on finetuned Mistral model

Spent the afternoon benchmarking a Mistral‑7B finetune with vLLM. First prompt returned gibberish tokens.

...
OpenRouter API response missing text in JSON payload May 15, 2024

OpenRouter API response missing ’text’ in JSON payload

Testing OpenRouter with gpt‑4 turbo. Request looked fine but the completion field came back empty:

...
langchain.tools.SerpAPIWrapper throws Invalid API Key despite valid key Mar 15, 2024

langchain.tools.SerpAPIWrapper throws Invalid API Key despite valid key

Spotted this today while wiring a quick search tool.

...
Gemini Pro API throws 403 in Postman with valid key Feb 15, 2024

Gemini Pro API throws 403 in Postman with valid key

Tried hitting the Gemini Pro v1/models/gemini-pro:generateContent endpoint in Postman.

...
Mistral inference on local GPU hits OOM with 13B model Jan 15, 2024

Mistral inference on local GPU hits OOM with 13B model

Last week I tried the 13B Mistral model on a single RTX 3060 (12 GB). python main.py crashed instantly:

...