gemini-cli PR adds model.requestTimeoutMs to fix 60s header timeout aborting long-thinking requests
prath47 · ghdev · 2026-11-01
- PR #30082 in google-gemini/gemini-cli adds a model.requestTimeoutMs setting to raise the hardcoded 60s API headers timeout.
- Root cause: the timeout was only tunable via the DEFAULTREQUESTTIMEOUT experiment flag, which is never fetched under Vertex AI / API key auth, so long-thinking requests get aborted at 60s and replayed from scratch (fixes #29693).
- Implementation: positive finite values win over the flag, otherwise it falls back as before; refreshAuth already calls updateGlobalFetchTimeouts() for every auth type, so Vertex AI picks it up automatically; 0/negative/NaN are ignored; unset means no behavior change.
- Adds 3 behavior tests that fail on main and pass on the branch; full test suites (255 + 385), typecheck, eslint and prettier all green.
More from coding & agent
- From chatbot to agent: how tools, planning and memory were added step by step — _jaydeepkarale · 2026-11-04
- Binance's $7B hack reportedly started with a tampered Homebrew install during vibe coding — xuanalogue · 2026-11-04
- $100 of GPU time edits model weights to cut thinking tokens by 40% — jarrodwatts · 2026-11-04
- Cua Driver integrates with Google Antigravity for background cross-app computer agents — m4rkmc · 2026-11-04
- Sentdex: OpenHands was the first reasonably useful agent to abstract away the code editor — rajistics · 2026-11-04
- Security advisory: run AI agents in managed cloud environments, not employee endpoints — amasad · 2026-11-04