mirror of
https://github.com/safishamsi/graphify.git
synced 2026-07-12 18:37:12 +00:00
safishamsi
89dd00f140
Adds the deterministic work-memory loop: `save-result --outcome useful|dead_end|corrected [--correction]` records how a saved Q&A turned out, and `graphify reflect` aggregates graphify-out/memory/ into a deterministic reflections/LESSONS.md an agent loads next session. Source nodes are scored, not counted: signed, recency-decayed (useful +, dead_end/corrected -, configurable --half-life-days, default 30), so a fresh dead end outweighs a stale useful. A node is "preferred" only once corroborated by >=--min-corroboration distinct results (default 2); others are "tentative", and mixed-signal nodes render once as "contested" (recency-wins). Source nodes are matched to the graph by label OR id, and citations whose node no longer exists are dropped, so a plain `graphify update` after deleting code clears stale lessons. Deterministic, no LLM; bare save-result and existing behavior unchanged. Rigorously verified end-to-end on real data: corroboration boundary, recency flip, contested verdict, foreign/malformed memory docs, cold start, 300-doc scale + byte-stable output, and the node-gate dropping deleted-code lessons after update. Full suite 2383 passed; skillgen --check clean; ruff clean. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
101 lines
3.4 KiB
Python
101 lines
3.4 KiB
Python
"""Tests for graphify.ingest.save_query_result"""
|
|
from __future__ import annotations
|
|
import re
|
|
from pathlib import Path
|
|
import pytest
|
|
from graphify.ingest import save_query_result
|
|
|
|
|
|
def test_file_created(tmp_path):
|
|
out = save_query_result("what is attention?", "Attention is...", tmp_path / "memory")
|
|
assert out.exists()
|
|
|
|
|
|
def test_filename_format(tmp_path):
|
|
mem = tmp_path / "memory"
|
|
out = save_query_result("what connects A to B?", "They share...", mem)
|
|
assert out.name.startswith("query_")
|
|
assert out.suffix == ".md"
|
|
|
|
|
|
def test_frontmatter_question(tmp_path):
|
|
mem = tmp_path / "memory"
|
|
question = "what is attention?"
|
|
out = save_query_result(question, "Attention is softmax.", mem)
|
|
content = out.read_text()
|
|
assert "question:" in content
|
|
assert "attention" in content.lower()
|
|
|
|
|
|
def test_frontmatter_type(tmp_path):
|
|
mem = tmp_path / "memory"
|
|
out = save_query_result("q", "a", mem, query_type="path_query")
|
|
content = out.read_text()
|
|
assert 'type: "path_query"' in content
|
|
|
|
|
|
def test_source_nodes_included(tmp_path):
|
|
mem = tmp_path / "memory"
|
|
nodes = ["AttentionLayer", "SoftmaxFunc"]
|
|
out = save_query_result("q", "a", mem, source_nodes=nodes)
|
|
content = out.read_text()
|
|
assert "AttentionLayer" in content
|
|
assert "SoftmaxFunc" in content
|
|
|
|
|
|
def test_source_nodes_capped_at_10(tmp_path):
|
|
mem = tmp_path / "memory"
|
|
nodes = [f"Node{i}" for i in range(20)]
|
|
out = save_query_result("q", "a", mem, source_nodes=nodes)
|
|
content = out.read_text()
|
|
# Only first 10 should appear in frontmatter source_nodes line
|
|
fm_line = [l for l in content.splitlines() if l.startswith("source_nodes:")][0]
|
|
assert fm_line.count('"Node') == 10
|
|
|
|
|
|
def test_memory_dir_created(tmp_path):
|
|
mem = tmp_path / "deep" / "memory"
|
|
assert not mem.exists()
|
|
save_query_result("q", "a", mem)
|
|
assert mem.exists()
|
|
|
|
|
|
def test_answer_in_body(tmp_path):
|
|
mem = tmp_path / "memory"
|
|
answer = "The answer is forty-two."
|
|
out = save_query_result("what is the answer?", answer, mem)
|
|
content = out.read_text()
|
|
assert answer in content
|
|
|
|
def test_outcome_in_frontmatter_and_body(tmp_path):
|
|
"""An outcome signal is written to both frontmatter (for `reflect`) and an
|
|
## Outcome body section (so it round-trips into the graph on re-extraction)."""
|
|
out = save_query_result("q", "a", tmp_path / "memory", outcome="useful")
|
|
content = out.read_text()
|
|
assert 'outcome: "useful"' in content
|
|
assert "## Outcome" in content
|
|
assert "- Signal: useful" in content
|
|
|
|
|
|
def test_correction_in_frontmatter_and_body(tmp_path):
|
|
out = save_query_result(
|
|
"what hashes passwords?", "MD5", tmp_path / "memory",
|
|
outcome="corrected", correction="It's bcrypt, see PasswordHasher",
|
|
)
|
|
content = out.read_text()
|
|
assert 'correction: "It\'s bcrypt, see PasswordHasher"' in content
|
|
assert "- Correction: It's bcrypt, see PasswordHasher" in content
|
|
|
|
|
|
def test_no_outcome_means_no_outcome_section(tmp_path):
|
|
"""Backward compatible: a result without an outcome looks exactly as before."""
|
|
out = save_query_result("q", "a", tmp_path / "memory")
|
|
content = out.read_text()
|
|
assert "outcome:" not in content
|
|
assert "## Outcome" not in content
|
|
|
|
|
|
def test_invalid_outcome_rejected(tmp_path):
|
|
with pytest.raises(ValueError):
|
|
save_query_result("q", "a", tmp_path / "memory", outcome="great")
|