Bryan Helmkamp 9768651b52 feat(model): add opt-in Ollama catalog provider (#268) ... ## Summary Adds Ollama as a disabled-by-default built-in catalog provider backed entirely by provider TOML. Enabling `[llm.providers.ollama] enabled = true` exposes the bundled `qwen3-coder` sample model through the existing OpenAI-compatible adapter, while other local Ollama models still require explicit model blocks until fabro-sh/fabro#267 adds discovery. The docs now show the opt-in setting and note that local users can set `OLLAMA_API_KEY=ollama` for Ollama's OpenAI-compatible endpoint. ## Verification - `cargo nextest run -p fabro-model` - `cargo nextest run -p fabro-cli cmd::model` - `cargo +nightly-2026-04-14 fmt --check --all` --- [](https://github.com/EveryInc/compound-engineering-plugin) 🤖 Generated with GPT-5 via [Codex](https://openai.com/codex) --------- Co-authored-by: roALAB1 <233429779+roALAB1@users.noreply.github.com> Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>		2026-05-16 08:18:21 -04:00
..
brainstorms	refactor(integrations): make chat integrations Slack-only	2026-05-09 11:43:16 -04:00
ideation	docs	2026-04-09 17:24:30 -04:00
internal	docs(llm): finish configurable provider cleanup (#260)	2026-05-13 17:17:54 -04:00
plans	refactor(run): add rich failure contract (#256)	2026-05-13 12:32:28 -04:00
public	feat(model): add opt-in Ollama catalog provider (#268)	2026-05-16 08:18:21 -04:00
superpowers	feat(install): make LLM setup optional in web installer and CLI (#265)	2026-05-14 22:34:39 -04:00