Shared OKF (Open Knowledge Format) ingestion library: spec-based connectors, bundle inbox, and external-bundle import. Security delegated to llm-ingestion-guard.
Find a file
Kjell Tore Guttormsen 5de590ebdf docs(okf-v0.2): the pilot tests state their expected results up front
The pilot invitations asked for feedback without specifying what to run or
what we expect to see. That returns a description, not a measurement: only a
stated expectation lets someone else's run falsify our model instead of
merely confirming it.

Each of the three tests now carries a numbered procedure, numbered expected
outcomes, and an explicit list of what would surprise us. Naming the
surprises is the load-bearing part -- a consumer who sees something odd but
passing otherwise has no reason to mention it.

Test A (producer, portfolio-optimiser-claude) runs one already-working
manifest twice with the same explicit ingested_at, once under DEFAULT as
baseline and once under OKF_V0_2, and diffs. A-E1 is the stop condition: if
the DEFAULT run is not byte-identical to their current pinned output, we have
broken a v0.1 consumer and the pilot ends there. The named surprises include
`at` differing from the ingested_at they passed, which would mean a
wall-clock crept in, and a collision refusal on a file that IS theirs, which
is the inverse of the fail-safe we predicted -- we expect foreign files to be
refused, so a false refusal of their own is the defect.

Test B (gate, catalog) runs their unmodified gate on the v0.2 fixture and on
a 0.1 control. B-E3 -- that no gate other than the version gate behaves
differently between the two -- is what converts our reading of their form
regex into a measurement. A membership list or equality comparison anywhere
in their chain is exactly what this is paid for.

Test C (expressiveness, wiki) is run by us, read-only at a recorded commit,
and the report goes to them. What we ask them to check is the part we cannot
measure from outside: whether a field we called an optional addition is in
fact load-bearing in their pipeline, and whether "no change required" holds
operationally rather than only formally.

Feedback gains a per-expectation verdict line so three independent runs are
comparable and a disagreement is located rather than merely reported. The
request also says outright that a wrong expectation is a better result than a
clean run, since a clean run only confirms what we already believed.

Inputs come from this repo at the pre-release tag; nothing is transported
through the mailbox except the specification.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01A2aKJxLejT9S8jYwoZ9fut
2026-07-26 14:10:40 +02:00
docs docs(okf-v0.2): the pilot tests state their expected results up front 2026-07-26 14:10:40 +02:00
examples feat(examples): ship the §11 golden fixtures with byte-exact conformance 2026-07-16 20:09:03 +02:00
src/llm_ingestion_okf feat(phase-3): the index policy becomes configurable, with the reader that judges it 2026-07-25 20:30:54 +02:00
tests feat(phase-3): the index policy becomes configurable, with the reader that judges it 2026-07-25 20:30:54 +02:00
.gitignore feat: initial commit — repo scaffold and v1 scope 2026-07-16 10:12:59 +02:00
CHANGELOG.md docs: two corrections from the convention owner and the spec owner 2026-07-25 12:32:21 +02:00
CLAUDE.md docs(okf-v0.2): ship to a pilot set before general availability 2026-07-26 13:50:28 +02:00
LICENSE feat: initial commit — repo scaffold and v1 scope 2026-07-16 10:12:59 +02:00
pyproject.toml docs(install): correct how the guard reaches a consumer, measured both ways 2026-07-25 12:24:54 +02:00
README.md feat(phase-3): the index policy becomes configurable, with the reader that judges it 2026-07-25 20:30:54 +02:00
uv.lock chore(release): v0.4.0 2026-07-25 12:08:48 +02:00

llm-ingestion-okf

Shared ingestion library for OKF (Open Knowledge Format) bundles.

Status: phases 1 and 2 are implemented. Phase 1 (spec-based ingestion) covers manifest validation, the file/sql/http connectors, deterministic materialization, index generation, and the golden fixture suite under examples/. Phase 2 adds the bundle inbox (process_inbox) and external-bundle import (import_bundle), both against an injected persist gate, with llm_ingestion_okf.guard_adapter wiring that gate to the real guard (see below). One phase-2 item is deliberately outstanding: binary extraction (pdf/docx/xlsx behind the [extract] extra) is unimplemented, so those types are rejected fail-fast. Phases 34 are planned (see docs/plan/).

Planned scope (v1)

The library provides three entry points for getting content into an OKF bundle:

  1. Spec-based ingestion. An implementation of the normative ingest specification owned by portfolio-optimiser-commons: manifest → file/sql/http connector → deterministic materialization of ingest-{id}.md concept files → index generation. Zero model calls in the run path; output is reproducible byte-for-byte against golden fixtures.
  2. Bundle inbox. A drop directory where common file types are converted to OKF concept files. All file-type→text extraction lives in this library: md, txt, csv, json, and html are handled by the stdlib core; pdf, docx, and xlsx require the optional [extract] extra and are rejected fail-fast without it. Extracted text passes the security gate before anything is persisted.
  3. External bundle import. Import and merge of third-party OKF bundles: each concept is assessed via the security gate, and only concepts that pass are merged, materialized, and linked into the index.

Boundary: security is delegated

Security is owned by the sibling package llm-ingestion-guard (pinned >=0.2,<0.3). The division is strict:

  • guard answers "is this content safe to persist?" — scan, sanitize, quarantine, fail-secure, provenance stamping.
  • this library does the plumbing — connect a source, materialize a deterministic OKF bundle, generate the index.

No security functionality is reimplemented here.

What is gated today: read this before trusting a door

  • Door A (materialize_bundle) is ungated. It calls nothing before writing to disk and writes what it is given. A caller materializing untrusted content is responsible for gating it.
  • Doors B and C (process_inbox, import_bundle) gate through an adapter you pass in. Each takes a gate argument; the flow hands it the content and obeys the verdict, refusing to persist anything that does not clear the guard's non-blocking floor — including a disposition it does not recognise, and (at Door C) a concept the gate returned no verdict for. What it cannot do is check that your adapter is a real guard: a permissive stub approves everything, and the flow will believe it.

llm_ingestion_okf.guard_adapter is the adapter over the real guard, and the only module here that imports it — importing the package itself does not:

from llm_ingestion_okf import process_inbox
from llm_ingestion_okf.guard_adapter import inbox_gate

result = process_inbox(inbox_dir, bundle_dir, "2026-07-25T12:00:00Z",
                       okf_type="reference", gate=inbox_gate)

Two properties of that adapter are worth knowing before you rely on it. It screens the exact bytes it persists — the guard's prepare_input bookend prepares text for a model call, which this library never makes, so only screen_output is used and the screened string is the written string. And it refuses rather than repairs: a file carrying an invisible zero-width or bidi character is rejected, not silently stripped and written. Door B screens under the untrusted-upload policy, so any finding at all is held back rather than persisted.

This section is stated plainly because earlier wording ("calls the guard at every persist gate") described the intended end state in the present tense, and a consumer reasonably read it as safe-by-default.

Roadmap

The library is built in four phases so that every known OKF surface in the ecosystem is eventually covered. Each phase has a detailed plan with verification criteria:

  1. Spec-based ingestion (Python) with byte-exact golden fixtures — plan.
  2. Bundle inbox and external-bundle import (Python), guard-gated — plan.
  3. Configurable bundle contract (types, layers, frontmatter sets, index shape, and reserved-file policy as configuration), enabling stricter bundle profiles such as strict-v1plan.
  4. A node/ half: a zero-dependency Node/ESM package (importable and CLI-invokable, vendored per consumer) providing bundle checking, index generation, inbox processing, and document conversion for the OKF second-brain plugin ecosystem. The Python and Node halves share the OKF contract and fixture suite, not code — plan.

Non-goals

  • Verdict/feedback machinery from the method specification (stays in the consuming repositories).
  • Embedding- or retrieval-layer functionality.
  • Security functionality, in either runtime — that is always llm-ingestion-guard's domain.

Requirements

Python 3.10+, and exactly one runtime dependency — the security boundary, llm-ingestion-guard>=0.2,<0.3. Everything else is stdlib.

That guard is not on a package index yet, so with pip, install it first — otherwise installing this package fails with No matching distribution found for llm-ingestion-guard:

pip install "llm-ingestion-guard @ git+https://git.fromaitochitta.com/open/llm-ingestion-pipeline-security.git@v0.2.0"
pip install "llm-ingestion-okf @ git+https://git.fromaitochitta.com/open/llm-ingestion-okf.git@v0.4.0"

With uv, one command is enough — uv pip install "llm-ingestion-okf @ git+…@v0.4.0" resolves the guard from the tag on its own, because uv reads the [tool.uv.sources] entry in this project's pyproject.toml when it builds from the source tree. Both paths were measured on 2026-07-25.

A git URL is a PEP 508 direct reference and pins one exact tag, so it is an install-time channel, not the pin: the range above stays the declared dependency — the built wheel carries Requires-Dist: llm-ingestion-guard<0.3,>=0.2 — and resolves normally once the package index exists. The optional [extract] extra (pdf/docx/xlsx parsers) is not populated yet. The planned Node half targets Node/ESM with zero npm dependencies.

License

MIT — see LICENSE.