Add semantic skill matching using all-MiniLM-L6-v2 sentence embeddings.
Skills are automatically injected into user turns based on relevance.
New packages:
- embedding: ONNX-based text embedding with MiniLM model
- skills: skill discovery, embedding cache, and semantic matching
Integration:
- InitSkillIndex called at startup in fs.NewRoot
- matchSkills called per-turn in executeTurn
- Matched skills injected in <context> block alongside user prompts
Makefile:
- install-models target downloads model and ONNX runtime
- Model files stored in ~/.local/share/ollie/models/
Config:
- Threshold: 0.2 cosine similarity
- Limit: 3 skills per turn
- Skill dirs: ~/.kiro/skills (user), ~/.config/ollie/skills (installed)
- Create fsedsl/ as embedded library with generic types:
- FsNodeDecl[Ctx], Binding[Ctx], NodeOption[Ctx]
- BuildTree[Ctx], GenerateHelp[Ctx]
- Tree, File, FileConfig, SyntheticFileInfo
- Update ollie/fs to use fsedsl via type aliases:
- type FsNodeDecl = fsedsl.FsNodeDecl[HandlerCtx]
- Wrapper functions for constructors and options
- Migrate binding functions to Applier pattern:
- Binding.Applier replaces direct field assignment
- Cleanly separates EDSL mechanics from domain types
- Add replace directive in go.mod for local module
The library can be extracted to a separate repo later by
changing the module path and removing the replace directive.
The FUSE-based 9P mount (mount/) was unused — all actual mounting
uses 9pfuse via ollie-remount. Remove the package, the olliesrv mount
subcommand, and the go-fuse dependency.
Levi Neely
Ollie Agent