ducoterra
5d679f5184
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/.
265 lines
10 KiB
Python
265 lines
10 KiB
Python
"""Unit tests: settings defaults & env overrides."""
|
||
from __future__ import annotations
|
||
|
||
import json
|
||
from typing import Any
|
||
|
||
import pytest
|
||
from pydantic import ValidationError
|
||
from pydantic_settings import SettingsError
|
||
|
||
from app.config import _ALLOWED_IMPORT_EXTENSIONS, Settings # pyright: ignore[reportPrivateUsage]
|
||
|
||
|
||
def _settings(**kwargs: Any) -> Settings:
|
||
"""Build Settings without reading a .env file (deterministic tests)."""
|
||
kwargs.setdefault("_env_file", None)
|
||
return Settings(**kwargs) # pyright: ignore[reportCallIssue] (kwarg exists at runtime)
|
||
|
||
|
||
def test_defaults_match_locked_decisions(monkeypatch: pytest.MonkeyPatch) -> None:
|
||
# The test process sets BOR_RELEVANCE_THRESHOLD=0.30 for the mock-
|
||
# calibrated in-process suites (see tests/conftest.py) — the *default*
|
||
# under test is the production one.
|
||
monkeypatch.delenv("BOR_RELEVANCE_THRESHOLD", raising=False)
|
||
s = _settings()
|
||
assert s.llm_chat_model == "turbo"
|
||
assert s.llm_embed_model == "embed"
|
||
# A5 extended (phase 30): one-shot completions default to the ``lite``
|
||
# model on the same endpoint.
|
||
assert s.llm_summary_model == "lite"
|
||
assert s.embedding_dim == 768
|
||
assert s.llm_base_url.endswith("/v1")
|
||
# A8 (revised): the honesty gate input is the best cosine, default 0.62.
|
||
assert s.relevance_threshold == 0.62
|
||
# A7 (revised): hybrid retrieval — cosine top-N ∪ FTS top-N, RRF-fused.
|
||
assert s.hybrid_vector_candidates >= 1
|
||
assert s.hybrid_lexical_candidates >= 1
|
||
assert s.rrf_k >= 1
|
||
assert s.top_n_docs >= 1
|
||
# Owner instruction 2026-08-22: answers may run up to 32 768 tokens.
|
||
assert s.max_output_tokens == 32_768
|
||
# Phase 17: the model's thinking streams by default (kill-switch off).
|
||
assert s.stream_thinking is True
|
||
assert len(s.suggestions) >= 3
|
||
# A9 (revised 2026-08-27): the import scope covers all seventeen
|
||
# A9 formats (original seven + quadlet family + jinja).
|
||
assert s.import_extension_set == {
|
||
".md", ".markdown", ".txt", ".yaml", ".yml", ".json", ".py",
|
||
".container", ".network", ".volume", ".image", ".pod",
|
||
".kube", ".swap", ".os", ".endpoint", ".j2",
|
||
}
|
||
|
||
|
||
NEW_A9_FORMATS = (
|
||
"container", "network", "volume", "image", "pod",
|
||
"kube", "swap", "os", "endpoint", "j2",
|
||
)
|
||
|
||
|
||
def test_allowed_import_extensions_contains_all_seventeen_formats() -> None:
|
||
"""The validator's base set is the full A9 set: the original seven
|
||
plus the ten added 2026-08-27 (quadlet family + ``j2``). The
|
||
never-widen contract bounds :py:data:`import_extensions` against
|
||
exactly this set."""
|
||
assert {
|
||
"md", "markdown", "txt", "yaml", "yml", "json", "py",
|
||
*NEW_A9_FORMATS,
|
||
} == _ALLOWED_IMPORT_EXTENSIONS
|
||
|
||
|
||
def test_default_import_extensions_include_the_ten_new_formats() -> None:
|
||
"""A9 revised 2026-08-27 (owner permission): the quadlet family +
|
||
``j2`` are imported by default — no env configuration needed — with
|
||
the original seven first (order is cosmetic, the set is what
|
||
matters)."""
|
||
s = _settings()
|
||
for ext in NEW_A9_FORMATS:
|
||
assert ext in s.import_extensions
|
||
assert s.import_extension_set == (
|
||
{".md", ".markdown", ".txt", ".yaml", ".yml", ".json", ".py"}
|
||
| {f".{ext}" for ext in NEW_A9_FORMATS}
|
||
)
|
||
|
||
|
||
def test_env_override(monkeypatch) -> None:
|
||
monkeypatch.setenv("BOR_RELEVANCE_THRESHOLD", "0.42")
|
||
monkeypatch.setenv("BOR_LLM_CHAT_MODEL", "juggernaut")
|
||
s = _settings()
|
||
assert s.relevance_threshold == 0.42
|
||
assert s.llm_chat_model == "juggernaut"
|
||
|
||
|
||
def test_llm_summary_model_env_override(monkeypatch) -> None:
|
||
"""Phase 30: ``BOR_LLM_SUMMARY_MODEL`` overrides the ``lite`` default"""
|
||
monkeypatch.setenv("BOR_LLM_SUMMARY_MODEL", "mini")
|
||
s = _settings()
|
||
assert s.llm_summary_model == "mini"
|
||
|
||
|
||
def test_summary_max_chars_default_and_env_override(monkeypatch: pytest.MonkeyPatch) -> None:
|
||
"""Phase 30: document content sent to the ``lite`` model is capped at
|
||
``BOR_SUMMARY_MAX_CHARS`` (default 12 000 chars per call)."""
|
||
monkeypatch.delenv("BOR_SUMMARY_MAX_CHARS", raising=False)
|
||
assert _settings().summary_max_chars == 12_000
|
||
monkeypatch.setenv("BOR_SUMMARY_MAX_CHARS", "5000")
|
||
assert _settings().summary_max_chars == 5000
|
||
|
||
|
||
def test_max_output_tokens_env_override(monkeypatch) -> None:
|
||
monkeypatch.setenv("BOR_MAX_OUTPUT_TOKENS", "1234")
|
||
s = _settings()
|
||
assert s.max_output_tokens == 1234
|
||
|
||
|
||
def test_agent_max_rounds_default_and_env_override(monkeypatch: pytest.MonkeyPatch) -> None:
|
||
"""Phase 45: the per-tool budgets are gone — ``BOR_AGENT_MAX_ROUNDS``
|
||
(default 10) is the single agent-loop knob; ``0`` is the no-tools
|
||
kill switch."""
|
||
monkeypatch.delenv("BOR_AGENT_MAX_ROUNDS", raising=False)
|
||
assert _settings().agent_max_rounds == 10
|
||
monkeypatch.setenv("BOR_AGENT_MAX_ROUNDS", "5")
|
||
assert _settings().agent_max_rounds == 5
|
||
monkeypatch.setenv("BOR_AGENT_MAX_ROUNDS", "0")
|
||
assert _settings().agent_max_rounds == 0
|
||
|
||
|
||
def test_agent_max_rounds_rejects_negative(monkeypatch: pytest.MonkeyPatch) -> None:
|
||
"""``0`` is the kill switch — a negative value is a typo, so the
|
||
validator fails loudly at startup."""
|
||
monkeypatch.setenv("BOR_AGENT_MAX_ROUNDS", "-1")
|
||
with pytest.raises(ValidationError, match="agent_max_rounds"):
|
||
_settings()
|
||
|
||
|
||
def test_stream_thinking_default_true_and_env_parse(monkeypatch: pytest.MonkeyPatch) -> None:
|
||
"""Phase 17 kill-switch (``BOR_STREAM_THINKING``): on by default,
|
||
``0``/``false`` turn the ``thinking`` SSE frames off."""
|
||
assert _settings().stream_thinking is True
|
||
assert _settings(stream_thinking=False).stream_thinking is False
|
||
monkeypatch.setenv("BOR_STREAM_THINKING", "0")
|
||
assert _settings().stream_thinking is False
|
||
monkeypatch.setenv("BOR_STREAM_THINKING", "false")
|
||
assert _settings().stream_thinking is False
|
||
monkeypatch.setenv("BOR_STREAM_THINKING", "1")
|
||
assert _settings().stream_thinking is True
|
||
|
||
|
||
def test_import_extensions_env_override_is_a_csv_list(monkeypatch) -> None:
|
||
monkeypatch.setenv("BOR_IMPORT_EXTENSIONS", "md,yml")
|
||
s = _settings()
|
||
assert s.import_extension_set == {".md", ".yml"}
|
||
|
||
|
||
def test_import_extensions_rejects_unknown_format(monkeypatch) -> None:
|
||
"""A typo in the CSV fails at startup (loudly), not by silently
|
||
walking zero files."""
|
||
monkeypatch.setenv("BOR_IMPORT_EXTENSIONS", "md,docx")
|
||
with pytest.raises(ValidationError, match="docx"):
|
||
_settings()
|
||
|
||
|
||
def test_import_extensions_rejects_empty(monkeypatch) -> None:
|
||
monkeypatch.setenv("BOR_IMPORT_EXTENSIONS", " ")
|
||
with pytest.raises(ValidationError):
|
||
_settings()
|
||
|
||
|
||
def test_import_extensions_validator_accepts_new_a9_formats(monkeypatch) -> None:
|
||
"""A9 revised 2026-08-27: the new names are first-class — the
|
||
never-widen contract now holds against the widened base set, so a
|
||
narrowing CSV with quadlet/jinja names is accepted."""
|
||
monkeypatch.setenv("BOR_IMPORT_EXTENSIONS", "md,container,j2")
|
||
s = _settings()
|
||
assert s.import_extension_set == {".md", ".container", ".j2"}
|
||
|
||
|
||
def test_import_extensions_validator_still_rejects_unknown(monkeypatch) -> None:
|
||
"""Truly unknown extensions still fail loudly at startup (the
|
||
validator is intact — only the allowed base set widened)."""
|
||
monkeypatch.setenv("BOR_IMPORT_EXTENSIONS", "md,xyz")
|
||
with pytest.raises(ValidationError, match="xyz"):
|
||
_settings()
|
||
|
||
|
||
def test_git_sources_default_empty_and_sources_dir_default() -> None:
|
||
"""Phase 28: no git sources by default (backwards-compatible with the
|
||
``--source`` / ``DEFAULT_SOURCES`` fallback); the clone location stays
|
||
a raw string (``~`` is expanded by the import script, not the setting)."""
|
||
s = _settings()
|
||
assert s.git_sources == ""
|
||
assert s.git_source_list == []
|
||
assert s.sources_dir == "~/bor-sources"
|
||
|
||
|
||
def test_git_sources_env_override_parses_comma_separated_list(
|
||
monkeypatch: pytest.MonkeyPatch,
|
||
) -> None:
|
||
"""``BOR_GIT_SOURCES`` is a raw CSV: entries are trimmed and empty
|
||
entries dropped; URLs are stored untouched (no scheme parsing here)."""
|
||
monkeypatch.setenv(
|
||
"BOR_GIT_SOURCES",
|
||
"https://github.com/user/homelab.git, "
|
||
" git@github.com:user/deployments.git ,, https://git.reeseapps.com/x/y.git ",
|
||
)
|
||
s = _settings()
|
||
# The raw CSV string is preserved untouched (no parsing in the setting).
|
||
assert s.git_sources == (
|
||
"https://github.com/user/homelab.git, "
|
||
" git@github.com:user/deployments.git ,, https://git.reeseapps.com/x/y.git "
|
||
)
|
||
assert s.git_source_list == [
|
||
"https://github.com/user/homelab.git",
|
||
"git@github.com:user/deployments.git",
|
||
"https://git.reeseapps.com/x/y.git",
|
||
]
|
||
|
||
|
||
def test_git_sources_whitespace_only_yields_empty_list(monkeypatch) -> None:
|
||
"""A configured-but-blank value behaves the same as unset: no git
|
||
sources, so the script falls back to its legacy local defaults."""
|
||
monkeypatch.setenv("BOR_GIT_SOURCES", " , , ")
|
||
s = _settings()
|
||
assert s.git_source_list == []
|
||
|
||
|
||
def test_sources_dir_env_override_is_raw_string(monkeypatch: pytest.MonkeyPatch) -> None:
|
||
monkeypatch.setenv("BOR_SOURCES_DIR", "/data/bor/sources")
|
||
s = _settings()
|
||
assert s.sources_dir == "/data/bor/sources"
|
||
|
||
|
||
def test_suggestions_default_is_three_plus_real_questions() -> None:
|
||
s = _settings()
|
||
assert len(s.suggestions) >= 3
|
||
assert all(isinstance(q, str) and q.strip() for q in s.suggestions)
|
||
# Distinct chips only — duplicates in the onboarding row are noise.
|
||
assert len({q.strip().lower() for q in s.suggestions}) == len(s.suggestions)
|
||
|
||
|
||
def test_suggestions_env_override_is_json_list(monkeypatch) -> None:
|
||
override = [
|
||
"How do I back up with Borg?",
|
||
"How is my K3S cluster set up?",
|
||
"How do I deploy a service?",
|
||
]
|
||
monkeypatch.setenv("BOR_SUGGESTIONS", json.dumps(override))
|
||
s = _settings()
|
||
assert s.suggestions == override
|
||
|
||
|
||
def test_suggestions_malformed_json_fails_loudly(monkeypatch) -> None:
|
||
monkeypatch.setenv("BOR_SUGGESTIONS", "[not valid json")
|
||
with pytest.raises(SettingsError):
|
||
_settings()
|
||
|
||
|
||
def test_effective_api_key_fallback(monkeypatch) -> None:
|
||
monkeypatch.delenv("AIPI_KEY", raising=False)
|
||
s = _settings()
|
||
assert s.effective_api_key == "not-needed"
|
||
|
||
monkeypatch.setenv("AIPI_KEY", "sk-from-env")
|
||
s2 = _settings()
|
||
assert s2.effective_api_key == "sk-from-env"
|