feat(readme,skill,cli): the first screen an agent reads, three modes, and one flag that made two builds

`okf project` built a bundle two rules behind `okf build`. `cli.build`'s
signature defaulted `keep_table_heading` and `sheet_section_rows` to `False`
while argparse defaulted both to `True`, and `project.create` calls `build()`
as a function. Measured on a five-document folder: 15 concepts / 30 files
where `okf build` wrote 26 / 52, the whole difference in the priced sheet --
the document a question about price has to reach. The invariant test could not
see it: it compared `project.create` against the same function, and its two
fixture documents had neither a table nor a sheet. Both gaps are tests now,
and the two paths are byte-equal on that folder (`diff -rq`, 0 differences).

README opens with what / one install line / two commands / the three shapes of
request; the phase-status paragraph moved down, nothing deleted. One tag is
pinned everywhere: README pinned v0.4.0 on its install lines and v0.6.0 below,
llms.txt pinned v0.4.0, so an agent reading from the top installed a tag
without `okf project`.

The skill states three modes -- question, hypothesis (per premise, `confirmed`
/ `refuted` / `undecidable-from-bundle`), and a task producing a document
(source per claim in the artefact, an ungrounded paragraph written and marked
rather than dropped, the cut declared inside the document). The five markings
are untouched.

Generated skills state relative paths in the project layout: `okf consume
.okf/<id>` and `okf check --skill .claude/skills/<id>-consume/SKILL.md`,
runnable from where `okf project` tells the reader to start `claude`. Two
absolute paths to zero, measured with a query shown capable of finding first --
O5's published "4 -> 0" used `grep -c "^/"` against paths indented by two
spaces.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
Kjell Tore Guttormsen 2026-09-09 18:12:02 +02:00
commit 1260fac154
12 changed files with 532 additions and 43 deletions

View file

@ -1,15 +1,34 @@
# llm-ingestion-okf
> Shared OKF (Open Knowledge Format) ingestion library: spec-based connectors, bundle inbox, and external-bundle import. Security delegated to llm-ingestion-guard.
> Turn a folder of documents (PDF, DOCX, XLSX, PPTX, MD) into a bundle a model can answer from with a source on every claim. Offline and deterministic: no model call anywhere in the run path. Security is delegated to llm-ingestion-guard.
Requires Python 3.10+ and [uv](https://docs.astral.sh/uv/). Neither this package
nor the guard it depends on is on a package index yet; with uv, one command
resolves both:
nor the guard it depends on is on a package index yet; one command resolves both:
```
uv pip install "llm-ingestion-okf @ git+https://git.fromaitochitta.com/open/llm-ingestion-okf.git@v0.4.0"
```sh
uv tool install "llm-ingestion-okf[extract] @ git+https://git.fromaitochitta.com/open/llm-ingestion-okf.git@v0.7.0"
```
## Optional
Then, in the folder you want to work from:
- [README](README.md): the pip-only fallback if uv is unavailable, phase status, requirements, and the upstream OKF version policy.
```sh
okf project ~/my-documents
claude
```
`okf project` writes the bundle to `.okf/<id>/` and a Claude Code skill to
`.claude/skills/<id>-consume/` in the current directory. Start `claude` there
and ask in plain language. Three shapes of request are supported and the
generated skill states the rules for each: a **question**, a **hypothesis**
(answered per premise as `confirmed` / `refuted` / `undecidable-from-bundle`),
and a **task whose answer is a document** (every claim in the written file
carries its source; an ungrounded paragraph is written and marked, never
dropped).
## Docs
- [Consume in Claude Code](README.md#consume-in-claude-code): the same thing in
steps, several bundles in one project, and what was measured.
- [README](README.md): the pip-only fallback if uv is unavailable, the guard
pairing per tag, the build flags, phase status, and the upstream OKF version
policy.