feat(import): index quadlet unit files and jinja templates (A9 revision)
Phase 47 (owner permission 2026-08-27, TODO.md L10–11, roadmap R1): the
full Podman quadlet family (.container, .network, .volume, .image,
.pod, .kube, .swap, .os, .endpoint) and .j2 Jinja templates join the
allowed + default A9 import formats, chunked as plain text (owner
decision — no TOML/Jinja-aware splitter). No env configuration needed:
a default import now indexes them.
- app/config.py: _ALLOWED_IMPORT_EXTENSIONS + the default
import_extensions CSV gain the ten names (the original seven first);
the never-widen BOR_IMPORT_EXTENSIONS validator is untouched and
still rejects truly unknown extensions.
- app/rag/chunker.py: ten _FORMAT_CHUNKERS entries -> chunk_text
(HARD_MAX_CHARS 1200 honored, unknown-suffix fallback unchanged);
docstring/comments cite the A9 revision 2026-08-27.
- tests/fixtures/docs/homelab/: quadlet/compose.container (realistic
quadlet TOML, >1500 chars, [Unit]/[Service]/[Container] sections,
RESE-QUADLET-SENTINEL-77aa), quadlet/lan.network,
quadlet/cache.volume, templates/deploy.j2 (for/set/if Jinja
constructs + RESE-JINJA-SENTINEL-33dd). Every suite that seeds the
fixture tree updates its 9 -> 13 document-count constants.
- tests/unit/test_config.py: allowed set carries all seventeen formats,
default CSV + dotted import_extension_set include the ten, the
validator accepts the new names and still rejects unknowns.
- tests/unit/test_chunker.py: dispatch parity with chunk_text for every
new suffix (parametrized), the .container fixture chunks >=2 under
the cap with the sentinel surviving, the .j2 fixture keeps {{ }}
verbatim, the unknown-suffix fallback is unchanged.
- tests/unit/test_importer.py: a default-extensions walk over a temp
tree indexes exactly the ten new files (unknown/hidden/excluded
filtered), the original seven still walk, stem-title fallback holds.
- tests/integration/test_import_quadlet_jinja.py (new): import_sources
over a temp tree with .container/.volume/.j2 -> documents + chunks
rows with stem titles; delta re-import updates only the changed .j2
doc; prune drops the deleted .volume doc with cascade.
- tests/e2e/test_quadlet_jinja_import.py (new, story suite, mock-only,
isolation): GET /api/docs (admin session) lists the four new-format
docs with non-zero chunk counts and stem titles; the Sources table
renders a row + .doc-link per file; the phase-26 modal shows the
.container TOML ([Container] section + sentinel) with stem title and
the container format badge; a RESE-JINJA-SENTINEL-33dd question
FTS-matches the .j2 chunk -> honest-positive (A8: LOW requires zero
FTS hits) — the bubble is not .is-deflected and a source chip names
templates/deploy.j2.
- README.md + .env.example: the extended default format set (A9
revised 2026-08-27, plain-text chunking, narrow-only rule intact).
- .agent/PLAN.md: the A9 revision (owner-locked R1) — A9 row status,
the revision note under the anchors table, and the §5 chunking-policy
+ §11 workflow lines. The only PLAN edit this phase.
Gates: uv run pytest 795 passed; app/ coverage TOTAL 99% (>90%);
ruff check + pyright clean; story E2E 4/4 in isolation (DB up);
regression E2E suites test_import_documents (3) / test_sync_button
(3) / test_git_sources_admin (6) green in isolation.
Also records the 47_quadlet_jinja_import task-file moves (01–03)
todo/ -> complete/.
This commit is contained in:
@@ -28,6 +28,11 @@ EXPECTED_DOCS = {
|
||||
("docs", "homelab/scripts/uptime_probe.py"),
|
||||
("docs", "homelab/ssh/ssh_aliases.txt"),
|
||||
("docs", "homelab/tables.md"), # phase 44: the markdown-tables fixture
|
||||
# phase 47 (A9 revised 2026-08-27): quadlet family + jinja fixtures
|
||||
("docs", "homelab/quadlet/compose.container"),
|
||||
("docs", "homelab/quadlet/lan.network"),
|
||||
("docs", "homelab/quadlet/cache.volume"),
|
||||
("docs", "homelab/templates/deploy.j2"),
|
||||
}
|
||||
|
||||
|
||||
@@ -37,13 +42,19 @@ def test_import_fixtures_end_to_end(admin_client, db) -> None:
|
||||
llm = FakeEmbedder()
|
||||
|
||||
summary = asyncio.run(import_sources([FIXTURES], llm, session=db))
|
||||
# Nine A9-format files (phase 44 added homelab/tables.md);
|
||||
# .hidden/junk.md is out of scope (A9 revised).
|
||||
assert (summary.files, summary.added, summary.unchanged) == (9, 9, 0)
|
||||
assert summary.chunks >= 9
|
||||
assert summary.formats == {"md": 5, "yaml": 1, "json": 1, "py": 1, "txt": 1}
|
||||
# Thirteen A9-format files (phase 44 added homelab/tables.md, phase 47
|
||||
# added the quadlet + j2 fixtures); .hidden/junk.md is out of scope
|
||||
# (A9 revised).
|
||||
assert (summary.files, summary.added, summary.unchanged) == (13, 13, 0)
|
||||
assert summary.chunks >= 13
|
||||
assert summary.formats == {
|
||||
"md": 5, "yaml": 1, "json": 1, "py": 1, "txt": 1,
|
||||
"container": 1, "network": 1, "volume": 1, "j2": 1, # phase 47
|
||||
}
|
||||
# PLAN §9 per-format summary line: highest count first, then alpha.
|
||||
assert summary.format_counts() == "md:5,json:1,py:1,txt:1,yaml:1"
|
||||
assert summary.format_counts() == (
|
||||
"md:5,container:1,j2:1,json:1,network:1,py:1,txt:1,volume:1,yaml:1"
|
||||
)
|
||||
|
||||
docs = db.scalars(select(Document)).all()
|
||||
assert {(d.source, d.path) for d in docs} == EXPECTED_DOCS
|
||||
@@ -57,6 +68,10 @@ def test_import_fixtures_end_to_end(admin_client, db) -> None:
|
||||
assert titles["homelab/scripts/uptime_probe.py"] == "uptime_probe"
|
||||
assert titles["homelab/networking/static-dns.json"] == "static-dns"
|
||||
assert titles["homelab/ssh/ssh_aliases.txt"] == "ssh_aliases"
|
||||
assert titles["homelab/quadlet/compose.container"] == "compose"
|
||||
assert titles["homelab/quadlet/lan.network"] == "lan"
|
||||
assert titles["homelab/quadlet/cache.volume"] == "cache"
|
||||
assert titles["homelab/templates/deploy.j2"] == "deploy"
|
||||
# Hidden junk was never imported.
|
||||
assert not any(".hidden" in d.path for d in docs)
|
||||
# Full content is stored — that is what the RAG context will be.
|
||||
@@ -92,13 +107,13 @@ def test_import_fixtures_end_to_end(admin_client, db) -> None:
|
||||
r = admin_client.get("/api/docs") # phase 16: the catalog is admin-only
|
||||
assert r.status_code == 200
|
||||
body = r.json()
|
||||
assert len(body["documents"]) == 9
|
||||
assert len(body["documents"]) == 13
|
||||
assert all(d["chunks"] >= 1 for d in body["documents"])
|
||||
|
||||
# Idempotent re-run: nothing re-embedded.
|
||||
calls_before = len(llm.calls)
|
||||
s2 = asyncio.run(import_sources([FIXTURES], llm, session=db))
|
||||
assert s2.unchanged == 9 and s2.added == 0
|
||||
assert s2.unchanged == 13 and s2.added == 0
|
||||
assert len(llm.calls) == calls_before # unchanged → no embedding requests
|
||||
|
||||
db.execute(text("TRUNCATE chunks, documents, query_log"))
|
||||
|
||||
Reference in New Issue
Block a user