This release includes breaking changes for platform teams planning a safe upgrade.
Published 4mo
AI Agents & Assistants
✓ No known CVEs patched
✓ No known CVEs patched in this version
Topics
ai-coding-agent
claude
cli
coding-assistant
developer-tools
ollama
+2 more
openai
python
Summary
AI summaryUnlimited iterations remove the 15‑iteration cap, allowing AI to work until completion.
Full changelog
What's New
- Arrow selector fixed — uses
tty.setcbreak+os.writeto fd directly; menus redraw in place instead of duplicating - Live API model routing — models discovered from Claude/Qwen API endpoints now route to the correct provider (previously fell through to Ollama)
- Unlimited iterations — removed the 15-iteration cap; AI keeps working until the task is done
- Provider-aware model pickers —
/modeland/modelstrack which provider each model belongs to
Fixes
- Arrow-key selector no longer shows literal
[s/[u/[3Aescape codes - Picking a live Qwen API model (e.g.
qwen3.5-122b-a10b) no longer shows "not installed" - Switching models no longer triggers full update check on all installed models
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About Kodiqa Agent
All releases →Related context
Related tools
Beta — feedback welcome: [email protected]