v0.10.1

What's Changed

⚡️ CLI Super‑charge

Your command line interactions just got a turbo‑boost!
We polished the input flows, added an optional agent description, and hid your API key echo so your secrets stay secret. Managed to fix the streaming pipeline on the single‑pending‑buffer model—so longer chats flow smoother than ever. On the down‑pocket, the workspace path for the PR assistant is now spot‑on, reducing the frantic “It’s a broken build!” moments.

🤖 Llama‑cpp Ready & Smart Reasoning

Hit the large‑language‑model fan‑club: Llama.cpp is officially in the house, with fully configurable base URLs and an optional provider. We also peeled back the curtain on client‑side reasoning‑tags for local models—give your agents edgy, on‑device reasoning without a server lag. Paired with the new SDK, your agents are a high‑octane, low‑noise performance machine.

🚀 CI & PR Wizards

The PR context wizard has arrived. PR tasks now give jets to the jazz agents, finish workspace fixes, and use fully‑namespaced model‑ids for OpenRouter agents. The PR assistant itself has been cleaned up to stop spitting raw failures—clean diffs, cleaner fireworks. Together this means continuous integration that won’t break your pipeline, and PRs that ship with minimal friction.

📚 Documentation Leap

Strategic design and implementation plans for the Llama.cpp provider now live in the docs. We’ve omitted the “AI agents docs” bit that was no longer needed to keep the docs lean. Now you can dive straight into the specs and horizons of the new provider with minimal scroll‑and‑click effort.

---

Commits

• 229cc10 chore(release): OPENROUTER_API_KEY by @lvndry
• 63a7bb3 feat(ci): give jazz agents PR context and finish the workspace fix (#207) by @Landry Monga
• 000c8b6 fix(ci): give pr-assistant the workspace path and stop dumping raw failures (#205) by @Landry Monga
• 0d9ba9f fix(ci): use full namespaced model id for openrouter agents (#202) by @Landry Monga
• c8fedc6 feat(llm): add llama.cpp provider and configurable base URLs (#199) by @Landry Monga
• 855c0af feat(llm): client‑side reasoning‑tag parsing for local models (#208) by @Landry Monga
• da1f4cc fix(cli): rebuild streaming pipeline on single‑pending‑buffer model (#209) by @Landry Monga
• e480f06 fix(cli): polish input flows — optional agent description + mask API key echo (#210) by @Landry Monga
• ac686d0 chore(docs): ignore AI agents docs by @lvndry
• bf4d2b2 docs(plan): implementation plan for llama.cpp provider support by @lvndry
• 7c0050f docs(spec): design for llama.cpp provider support by @lvndry

---

Full diff

v0.10.0...v0.10.1