b9972

ggml-org/llama.cppb9972Jul 12, 2026by github-actions[bot]same day as b9971

What changed since b9971

medium risk

b9972 adds streaming output support to the server's exec_shell_command tool, building on b9971's stream refactor.

New features

  • The exec_shell_command server tool can now stream shell output incrementally instead of returning only the final result.

Improvements

  • Server tool execution path extended to reuse the streaming infrastructure refactored in the previous build.
  • Developer documentation updated to describe streaming for shell tool invocations.

Upgrade notes

This is a purely additive change on top of b9971's stream refactor; no config or API migrations are required. Clients that consume shell tool output should be prepared to handle chunked/streamed responses if they opt into streaming, while non-streaming callers keep working unchanged.

Analyzed Oct 24, 2026

Upgrading?

Release notes summary

Enhances the server API by enabling streaming for the `exec_shell_command` tool, allowing real-time output from shell executions.

Key Highlights

  • Added streaming capability to `exec_shell_command`
  • Enables real-time output from shell commands
  • Includes tests and documentation updates

Release Notes (excerpt)

<details open> server: allow stream for exec_shell_command (#25526) * init stream * add stream for shell tool * add test * nits * update docs </details> **macOS/iOS:** - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) - iOS XCFramework **Linux:** - Ubuntu x64 (CPU) - Ubuntu arm64 (CPU) - Ubuntu s390x (CPU) - Ubuntu x64 (Vulkan) - Ubuntu arm64 (Vulkan) - Ubuntu x64 (ROCm 7.2) - Ubuntu x64 (OpenVINO) - Ubuntu x64 (SYCL FP32)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories