generated from coulomb/repo-seed
tegwick
586ed90948
- session_memory/core/cursor.py: size/mtime change detection sidecar - session_memory/config.toml: store paths, retention caps, per-source globs (claude on, codex/grok off for Phase 1), repo->domain map - session_memory/ingest.py: discover->normalize->store->digest->evict; --dry-run creates/writes nothing; python -m session_memory.ingest - tests/test_ingest.py; live dry-run parsed 84/85 real local sessions Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
82 lines
2.9 KiB
Python
82 lines
2.9 KiB
Python
"""Ingest sweep + cursor tests (T06)."""
|
|
|
|
import json
|
|
import os
|
|
import sys
|
|
|
|
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
|
|
|
from session_memory.core.cursor import Cursors # noqa: E402
|
|
from session_memory.ingest import run_sweep # noqa: E402
|
|
|
|
|
|
def test_cursor_change_detection(tmp_path):
|
|
f = tmp_path / "a.jsonl"
|
|
f.write_text("{}\n")
|
|
cur = Cursors(str(tmp_path / "cur.json"))
|
|
assert cur.is_changed(str(f)) is True
|
|
cur.mark(str(f))
|
|
assert cur.is_changed(str(f)) is False
|
|
f.write_text("{}\n{}\n") # grow
|
|
assert cur.is_changed(str(f)) is True
|
|
|
|
|
|
def _claude_session_file(dir_path, native):
|
|
os.makedirs(dir_path, exist_ok=True)
|
|
p = os.path.join(dir_path, f"{native}.jsonl")
|
|
recs = [
|
|
{"type": "user", "uuid": "u1", "sessionId": native,
|
|
"timestamp": "2026-06-06T10:00:00Z", "cwd": "/home/worsch/agentic-resources",
|
|
"gitBranch": "main", "message": {"role": "user", "content": "hi"}},
|
|
{"type": "assistant", "uuid": "a1", "parentUuid": "u1", "sessionId": native,
|
|
"timestamp": "2026-06-06T10:00:02Z",
|
|
"message": {"role": "assistant", "model": "claude-opus-4-8",
|
|
"usage": {"input_tokens": 5, "output_tokens": 2},
|
|
"content": [{"type": "text", "text": "hello"}]}},
|
|
]
|
|
with open(p, "w", encoding="utf-8") as f:
|
|
for r in recs:
|
|
f.write(json.dumps(r) + "\n")
|
|
return p
|
|
|
|
|
|
def _config(tmp_path, projects_dir):
|
|
return {
|
|
"store": {
|
|
"db_path": str(tmp_path / ".store/mem.db"),
|
|
"blob_dir": str(tmp_path / ".store/blobs"),
|
|
"cursor": str(tmp_path / ".store/cursors.json"),
|
|
},
|
|
"retention": {"raw_soft_cap_bytes": 10**12, "raw_hard_cap_bytes": 10**12,
|
|
"raw_max_age_days": 10**6, "distilled_cap_bytes": 10**12},
|
|
"sources": {"claude": {"enabled": True, "root": str(projects_dir), "glob": "*/*.jsonl"}},
|
|
"repo_domain_map": {"agentic-resources": "helix_forge"},
|
|
}
|
|
|
|
|
|
def test_run_sweep_end_to_end(tmp_path):
|
|
projects = tmp_path / "projects"
|
|
_claude_session_file(str(projects / "-home-worsch-agentic-resources"), "sess-aaa")
|
|
cfg = _config(tmp_path, projects)
|
|
|
|
res = run_sweep(cfg)
|
|
assert res.discovered == 1
|
|
assert res.ingested == 1
|
|
assert res.analyzed == 1
|
|
assert res.retention is not None
|
|
|
|
# re-run: cursor skips the unchanged file (idempotent, cheap)
|
|
res2 = run_sweep(cfg)
|
|
assert res2.skipped_unchanged == 1
|
|
assert res2.ingested == 0
|
|
|
|
|
|
def test_dry_run_writes_nothing(tmp_path):
|
|
projects = tmp_path / "projects"
|
|
_claude_session_file(str(projects / "-home-worsch-agentic-resources"), "sess-bbb")
|
|
cfg = _config(tmp_path, projects)
|
|
res = run_sweep(cfg, dry_run=True)
|
|
assert res.discovered == 1 and res.ingested == 1
|
|
assert res.retention is None
|
|
assert not os.path.exists(cfg["store"]["db_path"]) # no store created
|