docling-studio/document-parser/persistence/analysis_repo.py
Pier-Jean Malandrino 1f02274ac4 feat(reasoning): reasoning-trace viewer v1 with SQLite-backed graph
Adds the `docling-agent` reasoning-trace viewer as a Studio tunnel, per
`docs/design/reasoning-trace.md`. Users pick an analyzed document, import
a RAGResult JSON, and the iterations are overlaid on the document graph.

Graph source is decoupled from Neo4j: a new pure builder
(`infra/docling_graph.build_graph_payload`) reads `document_json` from
SQLite and emits the same Cytoscape-shaped payload that `fetch_graph`
returns from Neo4j. Neo4j stays exclusive to the Maintain ingestion
pipeline. Shared DoclingDocument helpers live in `infra/docling_tree.py`
so TreeWriter and the builder can't drift on label taxonomy or tree walks.

Also removes the Cytoscape minimap (cytoscape-navigator) from GraphView:
second render instance hurt perf on large documents for no UX win.

Backend
- new `GET /api/documents/:id/reasoning-graph` (SQLite-only)
- new `infra/docling_tree.py`, `infra/docling_graph.py`
- `analysis_repo.find_latest_completed_by_document`
- tests: `test_docling_graph.py` (builder), `test_graph_api.py` (endpoint)

Frontend
- `features/reasoning/` — store, overlay, types, panel, import dialog,
  workspace, doc picker
- new `ReasoningPage` + `/reasoning` and `/reasoning/:docId` routes
- `GraphView` gains a `fetcher` prop so reasoning can inject the
  SQLite-backed fetcher while Maintain keeps using the Neo4j one
- drops minimap (nav container, dep, CSS)
- legend filters + section parenting extracted for reuse
- i18n base strings (FR + EN)
2026-04-21 11:30:47 +02:00

153 lines
6.3 KiB
Python

"""Analysis job repository — SQLite CRUD for analysis_jobs table."""
from __future__ import annotations
from datetime import UTC, datetime
from domain.models import AnalysisJob, AnalysisStatus
from persistence.database import get_connection
def _parse_dt(value: str | None) -> datetime | None:
"""Parse an ISO-format datetime string back into a datetime object."""
if not value:
return None
return datetime.fromisoformat(value)
def _row_to_job(row) -> AnalysisJob:
keys = row.keys()
return AnalysisJob(
id=row["id"],
document_id=row["document_id"],
status=AnalysisStatus(row["status"]),
content_markdown=row["content_markdown"],
content_html=row["content_html"],
pages_json=row["pages_json"],
document_json=row["document_json"] if "document_json" in keys else None,
chunks_json=row["chunks_json"] if "chunks_json" in keys else None,
error_message=row["error_message"],
progress_current=row["progress_current"] if "progress_current" in keys else None,
progress_total=row["progress_total"] if "progress_total" in keys else None,
started_at=_parse_dt(row["started_at"]),
completed_at=_parse_dt(row["completed_at"]),
created_at=_parse_dt(row["created_at"]) or datetime.now(UTC),
document_filename=row["filename"] if "filename" in keys else None,
)
_SELECT_WITH_DOC = """
SELECT aj.*, d.filename
FROM analysis_jobs aj
JOIN documents d ON d.id = aj.document_id
"""
class SqliteAnalysisRepository:
"""SQLite implementation of the AnalysisRepository port."""
async def insert(self, job: AnalysisJob) -> None:
"""Persist a new analysis job record."""
async with get_connection() as db:
await db.execute(
"""INSERT INTO analysis_jobs (id, document_id, status, created_at)
VALUES (?, ?, ?, ?)""",
(job.id, job.document_id, job.status.value, str(job.created_at)),
)
await db.commit()
async def find_all(self, *, limit: int = 200, offset: int = 0) -> list[AnalysisJob]:
"""Return analysis jobs with document info, newest first."""
async with get_connection() as db:
cursor = await db.execute(
f"{_SELECT_WITH_DOC} ORDER BY aj.created_at DESC LIMIT ? OFFSET ?",
(limit, offset),
)
rows = await cursor.fetchall()
return [_row_to_job(r) for r in rows]
async def find_by_id(self, job_id: str) -> AnalysisJob | None:
"""Find an analysis job by ID (with document filename), or return None."""
async with get_connection() as db:
cursor = await db.execute(f"{_SELECT_WITH_DOC} WHERE aj.id = ?", (job_id,))
row = await cursor.fetchone()
return _row_to_job(row) if row else None
async def find_latest_completed_by_document(self, document_id: str) -> AnalysisJob | None:
"""Latest COMPLETED analysis with a non-null `document_json` for a doc.
Used by the reasoning-trace tunnel to prime Neo4j from an existing
analysis when the graph doesn't yet exist (e.g. analysis ran before
Neo4j was wired in).
"""
async with get_connection() as db:
cursor = await db.execute(
f"{_SELECT_WITH_DOC} WHERE aj.document_id = ? "
"AND aj.status = 'COMPLETED' AND aj.document_json IS NOT NULL "
"ORDER BY aj.completed_at DESC LIMIT 1",
(document_id,),
)
row = await cursor.fetchone()
return _row_to_job(row) if row else None
async def update_status(self, job: AnalysisJob) -> None:
"""Persist all mutable fields of an analysis job (status, results, timestamps)."""
async with get_connection() as db:
await db.execute(
"""UPDATE analysis_jobs
SET status = ?, content_markdown = ?, content_html = ?,
pages_json = ?, document_json = ?, chunks_json = ?,
error_message = ?, progress_current = ?, progress_total = ?,
started_at = ?, completed_at = ?
WHERE id = ?""",
(
job.status.value,
job.content_markdown,
job.content_html,
job.pages_json,
job.document_json,
job.chunks_json,
job.error_message,
job.progress_current,
job.progress_total,
str(job.started_at) if job.started_at else None,
str(job.completed_at) if job.completed_at else None,
job.id,
),
)
await db.commit()
async def update_progress(self, job_id: str, current: int, total: int) -> None:
"""Update only the progress columns for a running analysis."""
async with get_connection() as db:
await db.execute(
"UPDATE analysis_jobs SET progress_current = ?, progress_total = ? WHERE id = ?",
(current, total, job_id),
)
await db.commit()
async def update_chunks(self, job_id: str, chunks_json: str) -> bool:
"""Update only the chunks_json column for a completed analysis."""
async with get_connection() as db:
cursor = await db.execute(
"UPDATE analysis_jobs SET chunks_json = ? WHERE id = ?",
(chunks_json, job_id),
)
await db.commit()
return cursor.rowcount > 0
async def delete(self, job_id: str) -> bool:
"""Delete an analysis job by ID. Returns True if a row was removed."""
async with get_connection() as db:
cursor = await db.execute("DELETE FROM analysis_jobs WHERE id = ?", (job_id,))
await db.commit()
return cursor.rowcount > 0
async def delete_by_document(self, document_id: str) -> int:
"""Delete all analysis jobs for a given document. Returns count deleted."""
async with get_connection() as db:
cursor = await db.execute(
"DELETE FROM analysis_jobs WHERE document_id = ?", (document_id,)
)
await db.commit()
return cursor.rowcount