mirror of
https://github.com/Stirling-Tools/Stirling-PDF.git
synced 2026-09-03 05:10:16 +03:00
## Overview Adds **AI document classification** and a **classification-aware Files sidebar**: uploaded documents are automatically tagged with document-type labels (Invoice, Contract, Lab report, …), and the sidebar groups files under editable parent categories so a large library stays navigable. > [!IMPORTANT] > **This feature only runs in the SaaS build.** Classification depends on the AI engine and team-scoped label storage, so it's gated to SaaS end-to-end: > - The sidebar grouping is a `saas/`-layer override of the `fileSidebarGrouping` seam; every other build (OSS core, self-hosted proprietary, desktop) gets the null stub and renders the **unchanged flat, recency-sorted list** — no categories, no "Other", no picker. > - The classify/labels backend endpoints are gated on `policies.enabled` (on in SaaS) and live in `app/proprietary`, so they're absent from pure OSS and dormant in self-hosted unless explicitly enabled. > - The Python classifier is reached only via that gated path. > > Shared-layer changes that do compile everywhere are inert without the engine (dormant schema/field additions) or intentional (`GetInfoOnPDF` surfacing custom metadata). ## What it does - **Classifier (engine):** reads the first/last two pages of a PDF and assigns document-type labels from an allowed vocabulary. Labels are deliberately document-*type* descriptors — no deep-content/PII detection, since only a page window is read. - **Team label vocabulary:** ~270 built-in defaults across ~15 families, seeded per team. Editable by team leaders/admins in the Classification policy settings (import/export/reset). Team-scoped and shared; **per-user personal labels are intentionally out of scope** — the vocabulary is team-level only. - **Sidebar categories:** files group under parent categories (Financial, Legal, Medical, …), busiest-first, collapsible, with a "Recent" group on top and an "Other" group for anything uncategorised. The category structure (names, icons, membership, custom categories) is **device-local and user-editable** via a "Customize" picker — the only per-user personalization; it never changes the team's label vocabulary. - Classification results are written to PDF metadata (`StirlingPDFClassification`), read back to keep files in their groups without re-parsing. ## Architecture Spans all three layers, mirroring the existing policy/source subsystem conventions: - **`frontend/editor`** — sidebar grouping seam + SaaS override, category manager, labels editor, icon palette, file grouping, tests, `en-US` i18n. - **`app/proprietary` + `app/common` + `app/core`** — `ClassifyLabelController`, team-scoped `ClassificationLabelStore` (Jpa + in-process impls, same shape as `PolicyStore`/`SourceStore`), metadata read/write. - **`engine`** — the document-classifier agent, contracts, routes, tests. ## Screenshots **Files sidebar — grouped by category (SaaS)** ### Loading view <img width="2056" height="1046" alt="Screenshot 2026-07-07 at 5 12 56 PM" src="https://github.com/user-attachments/assets/1d712da5-50ae-4349-b0cd-e62665c3ec0c" /> ### Organized in the sidebar <img width="2056" height="1045" alt="Screenshot 2026-07-07 at 5 14 05 PM" src="https://github.com/user-attachments/assets/3ea4fe21-da51-4cea-bc3a-18ce040d3d05" /> **Customize categories picker** ### Personal settings to change how labels are grouped in an individual users editor <img width="2056" height="1044" alt="Screenshot 2026-07-07 at 5 52 42 PM" src="https://github.com/user-attachments/assets/40be03ce-0f63-4d1e-b58b-cec045d01cb2" /> **Classification labels editor (team settings)** <img width="2056" height="1042" alt="Screenshot 2026-07-07 at 5 53 00 PM" src="https://github.com/user-attachments/assets/337b0739-15c9-4749-9c6b-22e3b20825b8" /> ## Testing - Frontend `task frontend:check` — green (editor + portal tests, typecheck across all flavors, lint, label-drift guard). - Backend `task backend:check` (proprietary) and `:saas:test` — green. - Engine `task engine:check` — green.
93 lines
3.0 KiB
Python
93 lines
3.0 KiB
Python
from __future__ import annotations
|
|
|
|
from collections.abc import Iterator
|
|
|
|
import pytest
|
|
from fastapi.testclient import TestClient
|
|
|
|
from stirling.api import app
|
|
from stirling.api.dependencies import get_document_classifier_agent
|
|
from stirling.contracts import (
|
|
ClassifyDocumentRequest,
|
|
ClassifyDocumentResponse,
|
|
DocumentClassificationResponse,
|
|
)
|
|
|
|
|
|
class StubClassifierAgent:
|
|
"""Stands in for DocumentClassifierAgent so route tests don't call a model."""
|
|
|
|
def __init__(self, response: ClassifyDocumentResponse) -> None:
|
|
self._response = response
|
|
|
|
async def classify(self, _request: ClassifyDocumentRequest) -> ClassifyDocumentResponse:
|
|
return self._response
|
|
|
|
|
|
@pytest.fixture
|
|
def classification_client() -> Iterator[TestClient]:
|
|
app.dependency_overrides[get_document_classifier_agent] = lambda: StubClassifierAgent(
|
|
# The result is label ids (the model's name answers, mapped to ids).
|
|
DocumentClassificationResponse(labels=["nda", "contract"])
|
|
)
|
|
try:
|
|
yield TestClient(app)
|
|
finally:
|
|
app.dependency_overrides.pop(get_document_classifier_agent, None)
|
|
|
|
|
|
_LABELS = [{"id": "nda", "name": "NDA"}, {"id": "contract", "name": "Contract"}]
|
|
|
|
|
|
def test_classify_returns_assigned_labels(classification_client: TestClient) -> None:
|
|
response = classification_client.post(
|
|
"/api/v1/documents/classify",
|
|
json={
|
|
"fileName": "nda.pdf",
|
|
"pages": [{"pageNumber": 1, "text": "Mutual NDA between A and B."}],
|
|
"labels": _LABELS,
|
|
},
|
|
)
|
|
assert response.status_code == 200
|
|
assert response.json() == {"labels": ["nda", "contract"]}
|
|
|
|
|
|
def test_classify_accepts_allowed_labels_on_the_request(classification_client: TestClient) -> None:
|
|
response = classification_client.post(
|
|
"/api/v1/documents/classify",
|
|
json={
|
|
"fileName": "nda.pdf",
|
|
"pages": [],
|
|
"labels": [
|
|
{"id": "contract", "name": "Contract"},
|
|
{"id": "invoice", "name": "Invoice"},
|
|
],
|
|
},
|
|
)
|
|
assert response.status_code == 200
|
|
|
|
|
|
def test_classify_accepts_empty_pages(classification_client: TestClient) -> None:
|
|
response = classification_client.post(
|
|
"/api/v1/documents/classify",
|
|
json={"fileName": "blank.pdf", "pages": [], "labels": _LABELS},
|
|
)
|
|
assert response.status_code == 200
|
|
|
|
|
|
def test_classify_rejects_empty_file_name(classification_client: TestClient) -> None:
|
|
response = classification_client.post(
|
|
"/api/v1/documents/classify",
|
|
json={"fileName": "", "pages": [], "labels": _LABELS},
|
|
)
|
|
assert response.status_code == 422
|
|
|
|
|
|
def test_classify_rejects_missing_labels(classification_client: TestClient) -> None:
|
|
# The backend always supplies the vocabulary; a request without one is invalid.
|
|
response = classification_client.post(
|
|
"/api/v1/documents/classify",
|
|
json={"fileName": "nda.pdf", "pages": []},
|
|
)
|
|
assert response.status_code == 422
|