memoria/tests/test_compile_chunking.py
agent-admin 347d191935 fork: tests (29 green) + fork README + pytest config
Acceptance test suite under tests/ covers 8 of the 10 audit-defined
assertions directly (the 2 that require integration-level fixtures —
flush-subprocess-survives-hook-exit and whole-wiki-not-in-prompt
token-count — are documented as manual-test checks rather than
automated).

tests/test_fs_utils.py — 17 tests
  * Atomic write: roundtrip, overwrite, original-preserved-on-exception,
    parent-dir-creation.
  * Locked append: 4 concurrent workers × 25 entries each, asserts every
    entry appears exactly once and its body lines are contiguous. This
    is the acceptance criterion for "two concurrent flushes don't
    interleave writes."
  * JSON recovery: clean roundtrip, missing-file default, corruption
    produces timestamped .bak and returns default.
  * Wikilink parsing: bare / aliased / mixed; parse_wikilink strip.
  * Path safety: clean / traversal / absolute / empty / null-byte /
    aliased-but-safe.

tests/test_compile_chunking.py — 8 tests
  * Chunking: small log passthrough, byte-exact reconstruction,
    boundary respect, oversized-single-section, mixed-size packing.
  * State-on-failure: single-chunk SDK error does NOT update state;
    multi-chunk partial failure does NOT update state; all-chunks
    succeed DOES update state with hash + cost.

tests/test_lint_backlinks.py — 4 tests
  * Aliased wikilinks aren't flagged as broken links.
  * Aliased backlinks count as valid inbound references (the C9 fix).
  * QA articles referencing concepts don't trigger backlink suggestions.
  * Concept-to-concept asymmetry IS still reported (C9 scope is narrow).

FORK.md — fork-specific docs:
  * Summary of delta vs upstream (data-integrity, scaling, correctness,
    safety, configurability, hygiene categories)
  * Full env-var reference
  * Test invocation + coverage summary
  * Upstream sync guidance (cherry-pick, don't blind-pull)

Result: 29 passed in 0.07s. All patches in this fork verified via
automated test before any production use.
2026-04-24 17:54:00 -04:00

209 lines
7.6 KiB
Python

"""Tests for compile.py chunking + state-on-failure behavior.
Covers audit assertions #4 (failed SDK call doesn't mark log as compiled)
and the chunking correctness that underpins #5 (bounded prompt size).
"""
from __future__ import annotations
import asyncio
from pathlib import Path
from typing import Any
from unittest.mock import patch
import pytest
import compile as compile_mod
# ── Chunking correctness ────────────────────────────────────────────────
def test_chunk_small_log_single_chunk() -> None:
small = "### Section A\nbody\n\n### Section B\nbody\n"
chunks = compile_mod._split_log_into_chunks(small, max_chars=100_000)
assert chunks == [small]
def test_chunk_reconstructs_byte_exact() -> None:
sections = [f"### Section {i}\n" + "x" * 40_000 + "\n" for i in range(3)]
large = "".join(sections)
chunks = compile_mod._split_log_into_chunks(large, max_chars=100_000)
assert "".join(chunks) == large
def test_chunk_respects_section_boundaries() -> None:
# 4 sections of 30k each; max 70k → each chunk should be a clean
# boundary cut, never splitting a `### ` header from its body.
sections = [f"### S{i}\n" + "y" * 30_000 + "\n" for i in range(4)]
large = "".join(sections)
chunks = compile_mod._split_log_into_chunks(large, max_chars=70_000)
# Every chunk that isn't the first should start with `### `.
for chunk in chunks:
if chunk != chunks[0]:
assert chunk.startswith("### "), f"chunk boundary split mid-section: {chunk[:50]!r}"
def test_chunk_oversized_single_section_emits_alone() -> None:
# Section larger than max_chars should be emitted as its own oversized
# chunk rather than being split mid-thought.
huge = "### One big section\n" + "z" * 150_000 + "\n"
chunks = compile_mod._split_log_into_chunks(huge, max_chars=100_000)
assert len(chunks) == 1
assert chunks[0] == huge
def test_chunk_mixed_sizes() -> None:
# Section headers must anchor at line-start (regex is `(?m)(?=^### )`),
# so each section body must end with a newline.
parts = [
"### A\n" + "a" * 30_000 + "\n",
"### B\n" + "b" * 30_000 + "\n",
"### C\n" + "c" * 30_000 + "\n",
]
content = "".join(parts) # ~90K
chunks = compile_mod._split_log_into_chunks(content, max_chars=80_000)
# First chunk should contain A + B (~60K), second chunk C.
assert len(chunks) == 2
assert "### A" in chunks[0] and "### B" in chunks[0]
assert "### C" in chunks[1]
# Chunk 2 begins at a clean section boundary.
assert chunks[1].startswith("### C")
# ── State-on-failure (acceptance #4) ────────────────────────────────────
@pytest.mark.asyncio
async def test_failed_sdk_does_not_mark_compiled(tmp_path: Path, monkeypatch) -> None:
"""If the SDK raises, compile_daily_log must NOT update state.json.
Re-running should still see the log as uncompiled.
"""
import config
import utils
# Redirect state file + paths to tmp.
state_file = tmp_path / "state.json"
daily_dir = tmp_path / "daily"
daily_dir.mkdir()
knowledge_dir = tmp_path / "knowledge"
knowledge_dir.mkdir()
monkeypatch.setattr(utils, "STATE_FILE", state_file)
# Make a tiny fake daily log.
log_path = daily_dir / "2026-04-24-test.md"
log_path.write_text("### Test\nhello\n")
# Make AGENTS.md resolvable (compile.py reads it).
agents_file = tmp_path / "AGENTS.md"
agents_file.write_text("# Test Schema\n")
monkeypatch.setattr(config, "AGENTS_FILE", agents_file)
monkeypatch.setattr(compile_mod, "AGENTS_FILE", agents_file)
# Mock _invoke_llm to always fail.
async def failing_invoke(_prompt: str) -> tuple[float, bool]:
return (0.0, False)
monkeypatch.setattr(compile_mod, "_invoke_llm", failing_invoke)
state: dict[str, Any] = {"ingested": {}, "total_cost": 0.0}
cost = await compile_mod.compile_daily_log(log_path, state)
# Function returns 0.0 cost.
assert cost == 0.0
# State was NOT updated with this log's hash.
assert log_path.name not in state.get("ingested", {})
# state.json file was NOT written (save_state only runs on full success).
assert not state_file.exists()
@pytest.mark.asyncio
async def test_partial_chunk_failure_does_not_mark_compiled(tmp_path: Path, monkeypatch) -> None:
"""Multi-chunk log: if chunk 2 fails, log must NOT be marked compiled.
Verifies the `all_succeeded` gate holds across chunks.
"""
import config
import utils
state_file = tmp_path / "state.json"
daily_dir = tmp_path / "daily"
daily_dir.mkdir()
(tmp_path / "knowledge").mkdir()
(tmp_path / "knowledge" / "index.md").write_text("(empty)")
monkeypatch.setattr(utils, "STATE_FILE", state_file)
# Log large enough to chunk (>100K) via 3 sections.
sections = [f"### Section {i}\n" + "x" * 40_000 + "\n" for i in range(3)]
log_path = daily_dir / "2026-04-24-big.md"
log_path.write_text("".join(sections))
agents_file = tmp_path / "AGENTS.md"
agents_file.write_text("# Test Schema\n")
monkeypatch.setattr(config, "AGENTS_FILE", agents_file)
monkeypatch.setattr(compile_mod, "AGENTS_FILE", agents_file)
# Patch read_wiki_index to return a dummy value (avoid hitting the real
# knowledge dir).
monkeypatch.setattr(compile_mod, "read_wiki_index", lambda: "(test index)")
# _invoke_llm: succeed on 1st chunk, fail on 2nd. Track calls.
calls = {"n": 0}
async def flaky_invoke(_prompt: str) -> tuple[float, bool]:
calls["n"] += 1
if calls["n"] == 1:
return (0.25, True) # chunk 1 ok
return (0.0, False) # chunk 2 fails
monkeypatch.setattr(compile_mod, "_invoke_llm", flaky_invoke)
state: dict[str, Any] = {"ingested": {}, "total_cost": 0.0}
cost = await compile_mod.compile_daily_log(log_path, state)
# Returned partial cost (chunk 1 actually cost something).
assert cost == 0.25
# But state NOT updated — log is still "uncompiled" from the outside.
assert log_path.name not in state.get("ingested", {})
assert not state_file.exists()
# Exactly 2 chunk attempts (first success, second failure, then bail).
assert calls["n"] == 2
@pytest.mark.asyncio
async def test_all_chunks_succeed_updates_state(tmp_path: Path, monkeypatch) -> None:
"""When every chunk succeeds, state IS updated with the hash."""
import config
import utils
state_file = tmp_path / "state.json"
daily_dir = tmp_path / "daily"
daily_dir.mkdir()
(tmp_path / "knowledge").mkdir()
monkeypatch.setattr(utils, "STATE_FILE", state_file)
log_path = daily_dir / "2026-04-24-ok.md"
log_path.write_text("### Section\nhi\n")
agents_file = tmp_path / "AGENTS.md"
agents_file.write_text("# Schema\n")
monkeypatch.setattr(config, "AGENTS_FILE", agents_file)
monkeypatch.setattr(compile_mod, "AGENTS_FILE", agents_file)
monkeypatch.setattr(compile_mod, "read_wiki_index", lambda: "(index)")
async def good_invoke(_prompt: str) -> tuple[float, bool]:
return (0.10, True)
monkeypatch.setattr(compile_mod, "_invoke_llm", good_invoke)
state: dict[str, Any] = {"ingested": {}, "total_cost": 0.0}
cost = await compile_mod.compile_daily_log(log_path, state)
assert cost == 0.10
assert log_path.name in state["ingested"]
assert state["ingested"][log_path.name]["cost_usd"] == 0.10
assert state["total_cost"] == 0.10
# state.json now exists on disk.
assert state_file.exists()