llm-ingestion-okf/README.md

# 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.

Status: phases 1–3 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). Phase 3 makes the bundle contract configurable, so types,
layers, frontmatter sets, index shape, and reserved-file policy are carried by
a profile rather than by constants (see [Upstream OKF
versions](#upstream-okf-versions)). Binary extraction runs behind the
optional `[extract]` extra: `pdf` through a PDF parser, and five office
formats through a vendored document converter. Three of those five office
rows are **unmeasured** — see [Binary extraction](#binary-extraction). Phase 4
(the Node half) is planned (see `docs/plan/`).

## Install

Python 3.10+. Neither this package nor the guard it depends on is on a package
index yet. With uv, one command is enough:

```
uv pip install "llm-ingestion-okf @ git+https://git.fromaitochitta.com/open/llm-ingestion-okf.git@v0.4.0"
```

uv resolves the guard on its own, because it reads the `[tool.uv.sources]`
entry in the `pyproject.toml` **of the tag it is installing**, and `v0.4.0`
points that entry at the guard tag below. Measured 2026-07-25 and re-measured
2026-08-20 with an empty `uv` cache; both runs installed
`llm-ingestion-guard==0.2.0` + `llm-ingestion-okf==0.4.0` and imported clean.

With plain pip, the transitive git dependency does not resolve on its own —
**install the guard first**, or 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"
```

The guard tag is paired to the okf tag, not to this branch: `v0.4.0` declares
`llm-ingestion-guard>=0.2,<0.3`, which `v0.2.0` satisfies and later guard tags
do not. `main` has since moved its own pin to `>=1.2,<2.0` (see
[Requirements](#requirements)); that pin reaches you in the next stable tag,
not in the commands above. Reading a pin off this branch and installing it
against `v0.4.0` is the one combination that fails.

`v0.4.0` is the current stable tag. `v0.5.0a2` is a pre-release for the named
OKF v0.2 pilot set only; pin it only if you are one of them (see
[Upstream OKF versions](#upstream-okf-versions)).

## Build

Installing the package installs one command. A folder of documents in, an OKF
bundle out:

```
okf build ./documents --bundle ./bundle --bundle-id my-bundle --okf-version 0.2
```

It walks the folder recursively, proposes a segmentation for each document with
the mechanical rules, replays those proposals through the bundle inbox, writes
the bundle and its `log.md`, and prints the run's numbers. Every proposal is
marked `PROPOSED` and `adjudicated: false` — the command segments nothing a
human has approved, and says so in the artifact.

The last line that matters is the conservation identity: `merged + coded
rejections == N`, where `N` is the folder's file count read at run time. **The
run exits non-zero when it does not hold**, and names the unaccounted files, so
a pipeline cannot mistake a partial bundle for a complete one.

Flags worth knowing: `--segments off` ingests each document as one concept and
asks for no root values; `--plans-dir` keeps the proposals instead of
discarding them; `--report` writes the full report to a file as well as stdout.
`--ingested-at` and `--proposed-at` default to `1970-01-01T00:00:00Z` rather
than the clock, so two builds of the same folder are byte-identical — a
wall-clock default would break rebuild-equals-incremental for every caller who
did not pass them.

Measured 2026-09-07 on a 43-file corpus (33 `pdf`, 5 `docx`, 2 `xlsx`, and
three files no reader accepts), one
`okf build` invocation replacing the shell loop over `tools/` that produced the
same corpus's bundle on 2026-09-03:

| figure | value |
|---|---|
| `N` (folder file count, computed) | 43 |
| merged | 39/43 |
| coded rejections | 4/43 (`extractor_unknown` 3, `extractor_empty_pdf` 1) |
| K1b | `39 + 4 = 43 = N`, exit `0` |
| files written | 1108 |
| identical to the 2026-09-03 bundle | 1107/1108 |
| wall time | 779.43 s total, 18.126 s per file |

The one file that differs is the root `index.md`, by exactly one line: the link
to the bundle's own `log.md`, added by a commit that postdates the stored
artifact by fifteen hours. Appending that line to the stored `index.md`
reproduces the new one byte for byte. The command's own byte-identity test
compares it against the two scripts at the current commit, where the two agree
over the whole tree.

## Implemented 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` and the five office formats (`docx`, `xlsx`, `pptx`, `odt`, `rtf`)
   require the optional `[extract]` extra and are rejected fail-fast without
   it. Extracted text passes the security gate before anything is persisted.
   The drop directory is walked **recursively**, in sorted relative-path order:
   a file at any depth is ingested and records its path relative to the inbox
   root as its `source_file`, while dot-directories and a bundle directory
   sitting inside the inbox are skipped with a reported code.

<!-- extract-formats: .md, .txt, .csv, .json, .html, .htm, .pdf, .docx, .xlsx, .pptx, .odt, .rtf -->
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`](https://git.fromaitochitta.com/open/llm-ingestion-pipeline-security)
(pinned `>=1.2,<2.0`). 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:

```python
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](docs/plan/phase-1-door-a.md).
2. Bundle inbox and external-bundle import (Python), guard-gated —
   [plan](docs/plan/phase-2-doors-b-c.md).
3. Configurable bundle contract (types, layers, frontmatter sets, index
   shape, and reserved-file policy as configuration), enabling stricter
   bundle profiles such as `strict-v1` —
   [plan](docs/plan/phase-3-configurable-contract.md).
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](docs/plan/phase-4-node-half.md).

## Upstream OKF versions

The library targets the current latest version of Google's OKF. Support is
**additive** — a new upstream version arrives as a new profile, never as a
migration of an existing one — so an *upstream* release does not change the
bytes an existing profile emits.

That guarantee is about upstream, and one profile tracks a second contract as
well. `DEFAULT` states the ingest-spec owned by `portfolio-optimiser-commons`,
so when they change that spec, `DEFAULT` follows them. It happened on
2026-08-09: `generated` moved from `true` to
`{ by: process:okf-ingest, at: <ingested_at> }`, one changed line per generated
file. Upgrading across it costs a re-run and nothing more — a profile still
recognises bundles stamped by earlier versions, so re-running writes in place
instead of refusing. `DEFAULT` remains OKF v0.1 on every axis upstream owns.

| Profile | Contract | Status |
|---|---|---|
| `DEFAULT` | commons' ingest-spec layer (OKF v0.1 semantics) | stable |
| `STRICT_V1` | a consumer's ratified v0.1 contract | stable |
| `OKF_V0_2` | OKF v0.2 | **provisional**, pre-release only |
| `STRUCTURED_V1` | `DEFAULT` plus a faceted, derived index | stable |
| `OKF_LATEST` | alias for the latest version supported as *stable* | currently `DEFAULT` |

`STRUCTURED_V1` is `DEFAULT` in every respect but the index. Under it, Door B
derives each dropped document's title, number, hierarchy and cross-references,
writes them into the concept's own frontmatter, and carries them into the index
entry — so a consumer can reason over the bundle rather than only look things
up in it. Every inferred field is named in a `derived` list, because an
unmarked heuristic is worse than no heuristic: the consumer cannot know when to
doubt it. A pointer to a document not dropped yet is rendered `N200?` rather
than omitted, since a bundle is built up over several drops and an absence that
leaves no trace is the dangerous kind. Carrying the metadata costs index
characters — roughly 3x to 6x the flat index, depending on how many facets the
profile names — and the facet key set is the dial. Design record and
measurements: [`docs/plan/structure-derivation.md`](docs/plan/structure-derivation.md).

`OKF_V0_2` ships first as a pre-release to a named pilot set and may change on
their feedback without a deprecation cycle. Pin the versioned constant rather
than `OKF_LATEST` unless you have explicitly opted into tracking; `OKF_LATEST`
moves at general availability, which is a deliberate release event rather than
a side effect of an upgrade.

Selecting a profile is keyword-only, so existing call sites are unaffected:

```python
materialize_bundle(manifest, bundle_dir, ingested_at, profile=OKF_V0_2)
```

A bundle may declare the version it targets. OKF v0.2 §12 makes this a MAY, and
puts the declaration in the bundle-root `index.md`'s frontmatter block. The
profile names the key; the **caller supplies the value**, because that value
tracks the upstream version and is not this library's to decide:

```python
materialize_bundle(
    manifest, bundle_dir, ingested_at,
    profile=OKF_V0_2,
    root_frontmatter_values={"okf_version": "0.2"},
)
```

Omit the argument and no frontmatter block is written. Offering a key the
profile does not name is refused before anything is written to disk.

### Attested computations (v0.2 §10)

`OKF_V0_2` supports the `Attested Computation` type as a **format**: its five
contract fields — `runtime`, `parameters`, `computation`, `executor`,
`attester` — are emitted in canonical position, judged, and round-tripped.
`runtime` is required for that type and for no other, which the profile
expresses through `FrontmatterSchema.required_by_type`; a type the mapping does
not name carries no extra requirement, because §14 forbids a consumer to reject
on an unknown `type`.

Nothing here executes a computation or checks an attestation. Upstream defers
the receipt and verdict wire formats, so there is no contract to implement, and
the question an attestation answers — was this value produced the sanctioned
way — is not this library's. It re-enters scope when upstream specifies the
protocol.

On the import side, a third-party concept may name an `executor` or `attester`
resource pointing at executable code. Door C imports the **pointer** and never
the code — it writes concepts verbatim and skips every non-`.md` file — so such
a reference may not resolve, or may resolve to a file the destination tree
already holds under that path. Each one is reported in
`ImportResult.unverified_references`; the concept still merges, because §14
forbids rejecting a bundle over a broken cross-link while §10.5 asks a consumer
to surface rather than silently drop. The report names the pointer key, not the
resource it points at: recovering the resource needs the structured reader.

One limit worth knowing before you write such a concept: §10.2 presents
`executor` and `attester` as nested block mappings, and this library's
frontmatter parser is line-oriented. It reads inline **flow** mappings
(`executor: { resource: …, receipt: [ … ] }`) as opaque values that round-trip
unchanged, but it cannot read the block form — two block mappings that both
carry a `resource` collapse into one namespace and the first is lost. Write the
flow form; both are valid YAML, and a real YAML consumer recovers the same
structure from either.

## 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>=1.2,<2.0`. Everything else is stdlib. The commands are
under [Install](#install); what follows is why they look the way they do.

From a checkout, the test suite runs with:

```
.venv/bin/python -m pytest
```

The suite is the verification surface for everything above: 596 tests, run on
2026-08-21 against this branch with the `[extract]` extra installed. Without
the extra the same suite is 589 passed and 7 skipped, measured the same day:
the seven cover the parser path, and the tests holding the fail-fast rejection
for an uninstalled extra run in both. It is not shipped in an installed
distribution — `tests/` lives at the repository root, so this command needs a
clone rather than a `pip install`.

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 — a wheel built from this branch carries `Requires-Dist:
llm-ingestion-guard<2.0,>=1.2`, measured 2026-08-23 — and resolves normally
once the package index exists. A wheel built from a *tag* carries that tag's
range instead, which is why the install commands pair tag with tag.

### Binary extraction

The optional `[extract]` extra ships two things: `pdfplumber` (MIT) for `pdf`,
and `pypandoc-binary` for five office formats. It is opt-in because it pulls
binary wheels, which the default install must never do — the single runtime
dependency rule covers the default install and this extra sits outside it.

The converter **binary travels inside the wheel** and is resolved by path
rather than found on `PATH`, with its version asserted against a pin. A host
carrying a different converter is refused, not silently used: extraction is
deterministic within a converter version and not across one.

| Format | Reader | Evidence |
|---|---|---|
| `pdf` | `pdfplumber` | measured |
| `docx` | converter | measured |
| `xlsx` | converter | measured |
| `pptx` | converter | **unmeasured** |
| `odt` | converter | **unmeasured** |
| `rtf` | converter | **unmeasured** |

**`unmeasured` means what it says.** The corpus this work was measured on
contains **zero** `pptx`, `odt` and `rtf` files, so those three rows work by
construction and have never been checked against a document anyone wrote.
They are not known to be broken; they are not known to be right either, and
the distinction is the point.

**What stays out.** `.doc` (Word 97) is not supported — the converter does not
read it. Rastered or scanned PDFs are refused rather than persisted as empty
concepts, because this library does not do OCR. Drawn content — figures,
diagrams, shapes — does not survive extraction in any format here, and every
extraction says so with a warning. Structured table recovery is out of scope.

Request it by appending `[extract]` to the package name in whichever install
command from [Install](#install) you are using — this package is not on an
index, so a bare `pip install 'llm-ingestion-okf[extract]'` does **not** work
today, and the error message naming that command is written for the day it
does. The extra is unreleased: it reaches a consumer through a tag that
contains it, and no such tag exists yet.

Two properties of the extra are worth knowing before depending on its output:

- **Extracted text is pinned to an exact parser version.** `pdfplumber` pins
  `pdfminer.six==20260107` exactly, and `pdfminer.six` ships date-stamped
  releases with no stability contract. Extraction is deterministic within a
  parser version and not guaranteed across one, so a golden fixture built on
  extracted PDF text is a fixture migration away from any parser upgrade.
- **Text extraction recovers text, and nothing that is drawn.** Figures,
  diagrams and images have no text to recover — only their captions survive —
  so a bundle built from drawn documents is incomplete by construction. The
  library says so itself: every `pdf` extraction emits an `ExtractionWarning`.
  Structured table recovery is separately out of scope; PDFs enter as prose.

The planned Node half targets Node/ESM with zero npm dependencies.

## License

MIT — see [LICENSE](LICENSE).