OpenCode 1.18.6 fixes MCP refresh and branch caches

// 1h agoPRODUCT UPDATE

OpenCode 1.18.6 fixes MCP refresh and branch caches

OpenCode version 1.18.6 introduces key stability fixes and performance improvements across its desktop application and underlying client interfaces. This update resolves provider and Model Context Protocol (MCP) refresh issues in App v1, stabilizes v2 client compatibility by pinning the UI to a versioned `@opencode-ai/client` snapshot, and isolates remote reference caches by git branch to prevent cross-branch state collisions.

// ANALYSIS

Pinning client snapshots while isolating reference caches demonstrates maturity in maintaining stable execution environments for AI developer tools.

• Resolves provider and MCP refresh issues in App v1 to ensure persistent tool connections.

• Pins App and session UI to a versioned snapshot of `@opencode-ai/client` v2 for enhanced client compatibility.

• Implements branch isolation for remote reference caches to prevent context contamination across active git branches.

// TAGS

opencodeai-toolsdeveloper-toolsmcpopen-source

DISCOVERED

1h ago

2026-07-27

PUBLISHED

2h ago

2026-07-27

RELEVANCE

6/ 10

AUTHOR

OpenCodeLog

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

LAUNCH49m ago

Luma AI launches Luma Skills for workflows

Luma AI has launched Luma Skills, a feature designed to help creators and engineering teams package successful generative AI creation steps into reusable and shareable agent skills across image and video pipelines. By turning multi-step generation processes into modular templates, teams can streamline asset production, maintain visual consistency, and integrate automated creative workflows across projects.

OPEN SOURCE2h ago

ESP32 AI Runs 28.9M Model at 9.5 Tokens/Sec

ESP32 AI is an architectural experiment by slvDev that runs a 28.9-million-parameter TinyStories language model locally on an $8 ESP32-S3 microchip without relying on external cloud servers. By keeping a 25-million-parameter embedding table in memory-mapped SPI flash to fetch token rows on demand, the project successfully circumvents tight microcontroller RAM limitations while maintaining a generation throughput of approximately 9.5 tokens per second.

OPEN SOURCE2h ago

Open Science v0.7.2 boosts research workflow transparency

AIPOCH has released Open Science v0.7.2, an update to its open-source, model-agnostic AI workbench for scientific discovery. The new release prioritizes making AI research workflows more transparent, controllable, and easier to manage as researchers increasingly rely on autonomous agents for complex scientific tasks.