OpenCode 1.18.12 eliminates composer lag, sharpens diff reviews

// 1h agoPRODUCT UPDATE

OpenCode 1.18.12 eliminates composer lag, sharpens diff reviews

OpenCode version 1.18.12 brings targeted performance and stability improvements to AI-assisted coding workflows by migrating prompt drafts to async IndexedDB with buffering to eliminate composer lag. The release also sharpens diff review precision, resolves Azure GPT-5.5+ completion failures, and fixes Gemini reasoning token tracking.

// ANALYSIS

Shifting draft history to asynchronous browser storage solves a major pain point for users experiencing input latency during fast AI prompting sessions.

• Async IndexedDB and buffered blob drafts prevent composer stutter during high-frequency prompt editing.

• Improved diff review clarity makes verifying complex multi-file code modifications easier.

• Stability fixes address failing Azure GPT-5.5+ API calls and ensure proper token usage accounting for Gemini reasoning models.

// TAGS

opencodeai-codingdevtoolreleaseindexeddbazure-gpt-5.5gemini

DISCOVERED

1h ago

2026-08-04

PUBLISHED

2h ago

2026-08-04

RELEVANCE

7/ 10

AUTHOR

OpenCodeLog

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE1h ago

Claude Code v2.1.221 adds sandbox mask mode

The v2.1.221 release of Claude Code adds support for mask mode within its sandbox environment on Linux and WSL2. By adding .env files to the sandbox credentials configuration, executing commands and tools automatically read fake values instead of real sensitive secrets.

UPDATE2h ago

Google deprecates temperature, top_p, top_k in Gemini

Google is moving away from traditional developer-tuned LLM hyperparameters—specifically temperature, top_p, and top_k—which will be ignored and rejected by future Gemini models in favor of new control mechanisms.

UPDATE2h ago

Browser Use launches GPT 5.6 Luna web agent

Browser Use announced a new browser automation agent integration featuring the GPT 5.6 Luna model. The update invites users to test out enhanced web agent capabilities designed to improve autonomous web navigation, complex task execution, and site interaction.