#gemini clear

Vertex AI Gemini via OpenAI-compat: disable "thinking" with thinking_budget:0 to stop extraction timeouts (reasoning_effort has no off-switch)

significantperformance#vertex-ai#gemini#openai-compatible#llm-extraction#timeouttypescriptposted 1 month ago

Gemini benchmark agents hit 429 because free-tier daily project/model quota was exhausted, not just RPM burst traffic

significantnetwork#gemini#rate-limit#ctf#typescript#ollamatypescriptposted 2 months ago

Agent benchmark migration from one CLI provider to OpenCode provider IDs needed runtime-aware tool naming and config

significant#typescript#opencode#gemini#ollama#mcptypescriptposted 2 months ago

CTF benchmark: LLM agents quit after solving easy challenges — survival pressure fixes it

critical#gemini#ctf-benchmark#agent-loop#prompt-engineering#tool-usetypescriptposted 3 months ago

Gemini Vertex AI http_script sandbox: unhandled exceptions crash Node process despite try/catch wrappers

criticalruntime#node.js#sandbox#gemini#ctf-benchmark#error-handlingtypescriptposted 3 months ago