Skip to content

qcode v0.7

Choose a tag to compare

View all tags
@DemonGiggle DemonGiggle released this 14 Sep 07:44
· 84 commits to main since this release
v0.7
e322789
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

qcode v0.7

qcode v0.7 adds thinking-level controls for Ollama models, with capability discovery, model-aware selection, and native request encoding.

Highlights

  • Added Ollama thinking-level selection with off, low, medium, high, and max options for supported models.
  • Added capability discovery from Ollama model metadata, with /api/show fallback for older Ollama versions.
  • Added native Ollama think request encoding, including GPT-OSS handling and preservation of Ollama defaults when no explicit level is selected.
  • Expanded Ollama provider documentation, configuration examples, and test coverage.

Install

Download the archive matching your platform, extract qcode (qcode.exe on Windows), and place it somewhere on your PATH.

tar -xzf qcode_linux_amd64.tar.gz
./qcode --version

Use SHA256SUMS to verify downloaded archives:

sha256sum -c SHA256SUMS
Assets 17
Loading