Files
brain-of-reese/tests/unit/test_settings_catalog.py
T
ducoterra f27106a638
Build and Push Containers / build-and-push-app (push) Successful in 1m43s
Build and Push Containers / build-and-push-db (push) Successful in 12s
phase: 172_thinking_level
All verification complete. Final report:

**Phase 172 final verification pass — all tasks (01–05) were already complete; verified the whole phase, no code fixes needed.**

- **Verified implementation:** `Settings.llm_thinking_level: str = "low"` + `CATALOG` row (`LLM (aipi)` / "Thinking level", plain: not secret/restart/overridable-exempt) + `.env.example` line under `BOR_LLM_CHAT_MODEL` + README table row; `_thinking_extra_body()` → `reasoning_effort` via `extra_body` on `chat()` + `chat_stream()` when trimmed-non-empty, key absent (byte-identical) when empty, embeddings untouched; per-turn line gains `thinking=<value>` (`-` when empty) before `thinking_chars`.
- **Tests/lint/coverage (all green):** `uv run pytest` → 4084 passed · `uv run pytest --cov=app --cov-report=term-missing` → 4084 passed, `app/` **99%** (>90%) · `uv run ruff check .` → All checks passed · `uv run pyright` → 0 errors, 0 warnings.
- **Completion criteria:** (1) `pytest -k "config and thinking"` 4 passed + `.env.example` grep ✓ (2) live `GET /api/admin/settings` curl shows the row (str, `low`, `default`) + integration PUT/DELETE round-trip ✓ (3) 9 mocked-client unit tests assert `extra_body` present/absent ✓ (4) log-line tests assert `low`/`high`/`-`/whitespace ✓ (5) suite + coverage + lint ✓ (6) `test_thinking_level.py` 3/3 in isolation; `test_admin_settings_panel.py` 12/12; `test_admin_settings_layout.py` 5/5 ✓ (7) atomic commit + phase move = the harness's job (task files already in `complete/`; I ran no git index/history commands).
- **Documentation:** README.md reviewed in full — verified consistent (env table complete vs `.env.example`, catalog restart/non-overridable claims re-verified at runtime); AGENTS.md reviewed in full — verified consistent (no rule affected, A5 = no UI change). No changes needed. **Flag (not fixable here):** PLAN.md §9's per-turn-line spec predates the phase-172 `thinking=` field; PLAN.md is off-limits per protocol.
- **Next pending phase:** none — `todo/` contains only phase 172 (the harness moves it on this pass's success).
2026-10-10 13:19:10 -04:00

116 lines
4.2 KiB
Python

"""Phase 168 (task 02): the settings catalogue is complete and consistent.
The Settings panel (task 05) is GENERATED from
``app/core/settings_catalog.py`` — never hand-written — so these pins
are load-bearing: ``set(CATALOG) == set(Settings.model_fields)`` fails
the build the moment a new ``Settings`` field lands without its
metadata (it can never silently disappear from the panel), the group
table is closed both directions, and the capability sets are exactly
the LOCKED decisions (A3/A4).
"""
from __future__ import annotations
from app.config import Settings
from app.core.settings_catalog import (
CATALOG,
GROUPS,
NON_OVERRIDABLE,
RESTART_REQUIRED,
SECRETS,
SettingMeta,
env_var,
)
def test_catalog_covers_exactly_model_fields() -> None:
"""The completeness pin (both directions, the diff in the message)."""
catalog_keys = set(CATALOG)
field_names = set(Settings.model_fields)
missing = sorted(field_names - catalog_keys)
extra = sorted(catalog_keys - field_names)
assert not missing, (
f"Settings fields missing from the catalogue (invisible in the "
f"panel): {missing}"
)
assert not extra, (
f"Catalogue entries with no Settings field (stale): {extra}"
)
assert set(CATALOG) == set(Settings.model_fields)
def test_groups_closed_both_directions() -> None:
catalog_groups = {meta.group for meta in CATALOG.values()}
only_in_groups = sorted(set(GROUPS) - catalog_groups)
only_in_catalog = sorted(catalog_groups - set(GROUPS))
assert not only_in_groups, f"GROUPS entries with no catalogue member: {only_in_groups}"
assert not only_in_catalog, f"Catalogue groups missing from GROUPS: {only_in_catalog}"
def test_every_meta_carries_its_own_key() -> None:
for key, meta in CATALOG.items():
assert isinstance(meta, SettingMeta)
assert meta.key == key
def test_secrets_are_exactly_the_masked_set() -> None:
# LOCKED A4: write-only, masked — the 3 named secrets +
# database_url (read-only, but its URL carries credentials).
assert set(SECRETS) == {
"llm_api_key",
"admin_password",
"session_secret",
"database_url",
}
def test_non_overridable_is_exactly_locked_a3() -> None:
# LOCKED A3: database_url builds the engine that would read the
# override (chicken-and-egg brick); embedding_dim is fixed in the
# chunks table by A6 (a dim override would corrupt retrieval).
assert set(NON_OVERRIDABLE) == {"database_url", "embedding_dim"}
def test_restart_required_is_the_boot_wired_set() -> None:
# LOCKED A4: logging, the gzip middleware (compress_min_bytes), the
# static mount (static_dir), create_engine (db_pool_*), and
# SessionMiddleware (session_*).
assert set(RESTART_REQUIRED) == {
"log_level",
"compress_min_bytes",
"static_dir",
"db_pool_size",
"db_pool_max_overflow",
"db_pool_recycle",
"session_secret",
"session_max_age",
"session_cookie",
}
def test_env_var_is_bare_key_upper_prefixed() -> None:
assert env_var("relevance_threshold") == "BOR_RELEVANCE_THRESHOLD"
for key in CATALOG:
assert env_var(key).startswith("BOR_")
def test_llm_thinking_level_is_a_plain_live_overridable_row() -> None:
"""Phase 172 (task 01): the new ``llm_thinking_level`` pair sits in
``LLM (aipi)`` with the ``Thinking level`` label and is plain —
not ``secret`` (a free-form text value, like ``llm_chat_model``),
not ``restart_required`` (the LLM client reads the setting per
request via ``get_settings()`` — live), overridable (the overlay is
generic over ``str`` fields)."""
meta = CATALOG["llm_thinking_level"]
assert meta.group == "LLM (aipi)"
assert meta.label == "Thinking level"
assert "llm_thinking_level" not in SECRETS
assert "llm_thinking_level" not in RESTART_REQUIRED
assert "llm_thinking_level" not in NON_OVERRIDABLE
def test_labels_nonempty_and_unique() -> None:
labels = [meta.label for meta in CATALOG.values()]
assert all(label.strip() for label in labels), "empty label in the catalogue"
duplicates = sorted({label for label in labels if labels.count(label) > 1})
assert not duplicates, f"duplicate labels: {duplicates}"