Useful as prompts grow longer and we benchmark alternate models — bare
PASS/FAIL hides regressions like a prompt that doubles latency without
changing correctness.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Initial skeleton for the deterministic compound-AI pipeline that turns
`tolkien deploy <name>` into a valinor scaffold. v0 wires one classifier
(`db_kind`) end-to-end against the Ollama-on-radagast backend so we can
iterate prompts with confidence before adding the rest.
- pyproject.toml: uv project, Python 3.13, httpx/pydantic/typer/pyyaml.
- src/tolkien/llm.py: single-turn /api/chat wrapper. JSON-mode + temp 0 +
30m keep-alive. Pydantic schema validation on parse.
- src/tolkien/cli.py: `tolkien classify db-kind --doc <file>` runs the
classifier and prints JSON. `tolkien deploy <name>` is stubbed.
- src/tolkien/prompts/db_kind.md: tight system prompt with 1-shot example
and explicit "return ONLY JSON" guard.
- src/tolkien/schemas.py: DbKindResult pydantic model.
- eval/cases/mealie.yml + run_eval.py: regression harness. Currently
one case (mealie); failures print field-level diffs.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
