A content-addressed, Merkle-committed document store implementing the runtime spec from Merkle Providence Reverse RAG (April 2026 whitepaper) and Merkle-AGI v9.8 admissibility ledger. Ports proxy.unturf.com Go merkle conventions to Python: non-commutative HashCombine with 0x03 prefix, explicit IsLeft per sibling, self-duplicate odd elements. What's in: - merkle.py — proof generation/verification, JSON serialization - store.py — v9.8 SQLite schema: 8-dim providence_cache key, falsification_state, append-only audit chain, surface/core kind, hot/warm/cold tier, derivations, edges - ingest.py — Source -> normalize -> chunk -> merkle -> upsert, idempotent on document_root collision - search/ — SearchBackend ABC with explicit AuditMode (STRICT/HYBRID/ VISUAL), FTS5 backend returning VISUAL hits - sources/ — wikipedia.py (streaming bz2/MySQL extended-INSERT parser for 2003-era cur dumps); html_page.py (selectolax + httpx, robots.txt honored automatically) - distill/ — Distiller ABC + first-sentence-v1 stub. Runner generates per-contributing-chunk Merkle proofs binding cores back to source document_root. - evict.py — hot->cold demote (NULLs content, drops FTS row, retains leaf_hash). rehydrate() refetches via source pipeline; matching root restores content, mismatching root marks providence stale and writes rehydrate_drift event. Cores never evict. - cli.py — ingest / search / verify / stats / distill / evict / rehydrate - 31 tests covering merkle round-trip, ingest+audit, chunker version binding, html parse, distillation proof verification, evict+ rehydrate including drift detection. Smoke: 503 Wikipedia 2003-05-16 + 3 fox-owned HTML pages ingested, 478 cores produced (24 surface->core merkle dedups), 7 chunks evicted to cold and round-tripped via rehydrate, 987 audit events chained 0 breaks.
132 lines
4.6 KiB
Python
132 lines
4.6 KiB
Python
"""Distillation: cores must Merkle-bind back to their source surface roots."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
from typing import Iterator
|
|
|
|
from aborist.distill import FirstSentenceDistiller
|
|
from aborist.distill.runner import distill_existing
|
|
from aborist.document import Document
|
|
from aborist.ingest import ingest_source
|
|
from aborist.merkle import proof_from_dict, verify_proof
|
|
from aborist.source import Source
|
|
from aborist.store import connect
|
|
|
|
|
|
class FakeSource(Source):
|
|
source_type = "test"
|
|
|
|
def __init__(self, docs: list[Document]):
|
|
self.docs = docs
|
|
|
|
def iter_documents(self) -> Iterator[Document]:
|
|
yield from self.docs
|
|
|
|
|
|
def _doc(uri: str, content: str) -> Document:
|
|
return Document(uri=uri, content=content, source_type="test", title=uri)
|
|
|
|
|
|
# A long, multi-paragraph source so the chunker produces multiple chunks.
|
|
LONG_TEXT = (
|
|
"The quick brown fox jumps over the lazy dog. " * 30
|
|
+ "\n\n"
|
|
+ "Merkle providence proves answer derives from a specific source. " * 30
|
|
+ "\n\n"
|
|
+ "The eight forms of capital include living, social, and intellectual. " * 30
|
|
)
|
|
|
|
|
|
def test_distillation_produces_core_with_verifiable_proofs(tmp_path):
|
|
db = tmp_path / "distill.db"
|
|
src_doc = _doc("test://long", LONG_TEXT)
|
|
conn = connect(db)
|
|
try:
|
|
ingest_source(conn, FakeSource([src_doc]))
|
|
result = distill_existing(conn, FirstSentenceDistiller())
|
|
|
|
assert result["distilled"] == 1
|
|
assert result["skipped_existing"] == 0
|
|
|
|
# Core document exists and is marked correctly.
|
|
cores = conn.execute(
|
|
"SELECT * FROM documents WHERE kind = 'core'"
|
|
).fetchall()
|
|
assert len(cores) == 1
|
|
core = cores[0]
|
|
assert core["compression_depth"] == 1
|
|
assert core["source_type"] == "core:first-sentence-v1"
|
|
|
|
# Derivation row binds core to source.
|
|
derivs = conn.execute("SELECT * FROM derivations").fetchall()
|
|
assert len(derivs) == 1
|
|
d = derivs[0]
|
|
assert d["core_root"] == core["document_root"]
|
|
assert d["process_id"] == "first-sentence-v1"
|
|
|
|
# CRITICAL: every contributing-chunk Merkle proof in proof_blob must
|
|
# reconstruct the source's document_root. This is the cryptographic
|
|
# binding of compressed core back to surface.
|
|
proof_data = json.loads(d["proof_blob"])
|
|
assert proof_data["core_root"] == core["document_root"]
|
|
src_root = proof_data["src_root"]
|
|
assert len(proof_data["contributing"]) >= 1
|
|
for entry in proof_data["contributing"]:
|
|
proof = proof_from_dict(entry["proof"])
|
|
assert verify_proof(proof), f"proof invalid for chunk {entry['src_chunk_idx']}"
|
|
assert proof.root.hex() == src_root, (
|
|
"contributing-chunk proof must reconstruct source root"
|
|
)
|
|
|
|
# derived_from edge in the forest.
|
|
edges = conn.execute(
|
|
"SELECT * FROM edges WHERE edge_type = 'derived_from'"
|
|
).fetchall()
|
|
assert len(edges) == 1
|
|
assert edges[0]["src_root"] == core["document_root"]
|
|
assert edges[0]["dst_root"] == src_root
|
|
|
|
# Audit chain has both ingest and derive events.
|
|
events = conn.execute(
|
|
"SELECT event_type FROM audit_events ORDER BY seq ASC"
|
|
).fetchall()
|
|
types = [r["event_type"] for r in events]
|
|
assert "ingest" in types and "derive" in types
|
|
finally:
|
|
conn.close()
|
|
|
|
|
|
def test_distill_idempotent(tmp_path):
|
|
db = tmp_path / "idempotent.db"
|
|
conn = connect(db)
|
|
try:
|
|
ingest_source(conn, FakeSource([_doc("test://x", LONG_TEXT)]))
|
|
d = FirstSentenceDistiller()
|
|
first = distill_existing(conn, d)
|
|
second = distill_existing(conn, d)
|
|
assert first["distilled"] == 1
|
|
assert second["distilled"] == 0
|
|
assert second["skipped_existing"] == 1
|
|
# Still only one core document.
|
|
n_cores = conn.execute(
|
|
"SELECT COUNT(*) FROM documents WHERE kind='core'"
|
|
).fetchone()[0]
|
|
assert n_cores == 1
|
|
finally:
|
|
conn.close()
|
|
|
|
|
|
def test_distill_skips_cold_chunks(tmp_path):
|
|
"""If any source chunk has been evicted (content NULL), we must skip."""
|
|
db = tmp_path / "cold.db"
|
|
conn = connect(db)
|
|
try:
|
|
ingest_source(conn, FakeSource([_doc("test://cold", LONG_TEXT)]))
|
|
# Manually evict one chunk to cold tier.
|
|
conn.execute("UPDATE chunks SET content=NULL, tier='cold' WHERE idx=0")
|
|
result = distill_existing(conn, FirstSentenceDistiller())
|
|
assert result["distilled"] == 0
|
|
assert result["skipped_cold"] == 1
|
|
finally:
|
|
conn.close()
|