🇨🇳 SuperQode v0.2.22: Kimi K3 Support
SuperQode v0.2.22
This release adds first-class support for Moonshot AI’s Kimi K3, including a dedicated long-horizonvcoding harness, provider integration, model metadata, reasoning support, and comprehensivevdocumentation.
Highlights
- Added Kimi K3 through Moonshot’s first-party global API:
- Provider:
moonshot - Model:
kimi-k3 - Endpoint:
https://api.moonshot.ai/v1
- Provider:
- Added
MOONSHOT_API_KEYandKIMI_API_KEYcredential support. - Added current Kimi models to the SuperQode catalog:
kimi-k3kimi-k2.7-code-highspeedkimi-k2.7-codekimi-k2.6
- Added the
kimi-k3-codingharness preset with:- 1M-token context window
- Maximum reasoning
- Parallel tool execution
- Cache-friendly extended session history
- Kimi coding-model fallbacks
- Preserved K3
reasoning_contentacross multi-turn tool calls. - Added K3-specific request shaping:
- Maps reasoning to the currently supported
maxlevel - Removes incompatible sampling overrides
- Converts
max_tokenstomax_completion_tokens - Supports streaming and non-streaming requests
- Maps reasoning to the currently supported
- Added comprehensive Kimi documentation covering API routes, Kimi Code subscriptions, ACP, pricing,
vision, tools, caching, structured output, limitations, and troubleshooting.
Getting started
export MOONSHOT_API_KEY=your-api-key
superqode --harness kimi-k3-coding \
-p "Review this repository and fix the failing tests"
To create a project-owned harness:
superqode harness init kimi-project \
--template kimi-k3-coding \
--output harness.yaml
superqode --harness harness.yaml \
-p "Implement the requested feature"
You can also connect directly:
superqode connect byok moonshot kimi-k3