Gemini CLI Release v0.64.0

UpdateOct 13, 202612 days agoUnverifiedAdded Oct 25, 2026

- refactor(a2a-server): implement V1 to V2 settings migration logic fix(acp): bridge PromptResponse.usage and emit usage_update notifications Changelog for v0.63.0-preview.0 fix(cli): propagate resolved folder trust state in headless mode chore(release): bump version to 0.64.0-nightly.20260929.gd75234cae fix(cli): prevent CPU hang and quote swallowing on @...

Topics: LLMs, Observability, Developer tools, Coding agents

Google Cloud's release notes

More Gemini CLI releases

Every Gemini CLI release

UpdateOct 20unverified

Gemini CLI Release v0.65.0

- fix(cli): enforce read-only workspace settings in untrusted folders fix(core): avoid duplicate tool response turns when resuming sessions fix(core): prevent deletion of resumed session history on quick exit Changelog for v0.64.0-preview.0 Changelog for v0.63.0 fix(core): align OAuth callback iss parameter validation with RFC 9207 metadata fix(cli)...

Source ↗

UpdateSep 23unverified

Gemini CLI Release v0.61.0

- Changelog for v0.60.0-preview.0 chore(release): bump version to 0.61.0-nightly.20260908.gc647533d6 Changelog for v0.59.0 fix(core): preserve explicit versioned Flash model IDs fix(core): prevent indirect prompt injection via build file modifications and untrusted flags fix(sandbox): harden filesystem boundaries and isolate runtime state fix(core): ensure...

Source ↗

Also shipped on Oct 13, 2026

Google Cloud in October 2026

BetaOct 13unverified

What's included:

- Three training methods: Supervised fine-tuning (SFT) , direct preference optimization (DPO) , and reinforcement learning with group relative policy optimization (GRPO) . Each method trains a low-rank adapter (LoRA) or the full model weights. Custom loss functions : Train with any objective you compute in PyTorch from the model's log-probabilities.

Together AI Together AI platform Source ↗

GAOct 13unverified

On-demand state repartitioning is now generally available

On-demand state repartitioning is now generally available. You can resize the number of shuffle partitions for a stateful Structured Streaming query or Lakeflow pipeline without losing checkpoint state. See On-demand state repartitioning for stateful streaming queries .