bvandeusenandClaude Opus 5.5
914f31359c
CI & Build / Python lint (push) Successful in 5s
CI & Build / Plugin hooks (push) Successful in 17s
CI & Build / TypeScript typecheck (push) Successful in 57s
CI & Build / integration (push) Successful in 1m19s
CI & Build / Python tests (push) Successful in 2m2s
CI & Build / Build & push image (push) Successful in 15s
Docstrings, section headers and assertion messages drop the record number, milestone or step that introduced the behaviour, and incident accounts are restated as the present-tense failure shape. A dead pointer to a design doc that is not in the repo is removed. Renamed to the property they check: test_the_old_shape_would_be_caught -> test_a_rank_then_scope_query_is_caught test_a_ledger_repeat_no_longer_produces_that_case_at_all -> test_a_ledger_repeat_is_counted_not_withheld test_the_header_no_longer_promises_once_per_session -> test_the_header_explains_the_seen_marker test_the_portal_case_no_longer_stamps_one_canon_onto_a_whole_file -> test_one_canon_is_not_stamped_onto_a_whole_file test_the_repos_own_prose_no_longer_defines_with -> test_the_repos_own_prose_does_not_define_with test_the_original_regression_create_note_with_content -> test_the_real_server_refuses_content_on_create_note Fixture and example ids stay: "note 5" in a supersession chain, "rule 156" in an illustrative question, `#2275` as the hex-versus-citation case, `#3244` as the example of a bare number, fixed dates in date-filter tests. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
71 lines
3.1 KiB
Python
71 lines
3.1 KiB
Python
"""The specs are the registry.
|
|
|
|
Three lists sit beside the arms — the tuning table, the ranked rows of the
|
|
telemetry registry, and the rule-usage denominator — and all three are read
|
|
off the pipeline's specs rather than kept by hand. These
|
|
pin the derivation itself: every arm is tunable, every ranked source is
|
|
measured with the declaration its spec carries, and the rule-usage
|
|
denominator counts exactly the rule surfaces a ranker chose.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
from scribe.services import retrieval_pipeline as rp
|
|
from scribe.services.retrieval_registry import POINTS, UNBIDDEN
|
|
from scribe.services.retrieval_surfaces import SURFACES
|
|
from scribe.services.rule_usage import RANKED_SOURCES, is_ambient
|
|
|
|
|
|
def test_every_arm_is_one_tunable_surface_in_the_order_settings_lists_them():
|
|
assert [arm.source for arm in rp.TUNED_ARMS] == list(SURFACES)
|
|
for arm in rp.TUNED_ARMS:
|
|
assert arm.tuning is not None, f"{arm.source} has no floor or budget"
|
|
# The join key: the surface a tuner moves and the rows it is judged by
|
|
# must name the same arm.
|
|
assert arm.tuning.name == arm.source
|
|
assert SURFACES[arm.source] is arm.tuning
|
|
|
|
|
|
def test_every_ranked_source_is_measured_as_its_spec_declares():
|
|
sources = [spec.source for spec in rp.RANKED]
|
|
assert len(sources) == len(set(sources)), f"a source is declared twice: {sources}"
|
|
for spec in rp.RANKED:
|
|
d = spec.declared
|
|
assert d is not None and d.what.strip(), f"{spec.source} declares nothing"
|
|
point = POINTS[spec.source]
|
|
assert point.kind == UNBIDDEN
|
|
assert point.what == d.what
|
|
# A quiet source must say why, and only a quiet source may.
|
|
assert point.expects_traffic == (not d.quiet_because)
|
|
assert point.quiet_because == d.quiet_because
|
|
|
|
|
|
def test_the_slots_are_measured_but_never_tuned():
|
|
for slot in (rp.PREFERENCE_SLOT, *rp.NOTE_SLOTS):
|
|
assert slot.source in POINTS
|
|
assert slot.source not in SURFACES
|
|
|
|
|
|
def test_the_rule_denominator_is_every_rule_surface_a_ranker_chose():
|
|
rule_arms = {arm.source for arm in rp.RULE_ARMS}
|
|
assert rule_arms <= set(RANKED_SOURCES)
|
|
assert set(RANKED_SOURCES) == (
|
|
rule_arms | {rp.PREFERENCE_SLOT_SOURCE, rp.VIA_LESSON_SOURCE,
|
|
rp.MOMENT_RULE_SOURCE}
|
|
)
|
|
# And a notes arm is not a RULE surface: its lines are not rules, so a
|
|
# rule pull cannot confirm them.
|
|
for arm in rp.NOTE_ARMS:
|
|
assert is_ambient(arm.source)
|
|
|
|
|
|
def test_an_arm_added_without_tuning_would_be_caught():
|
|
"""The first test has to be able to bite. SURFACES skips an arm
|
|
with no tuning rather than raising, so an arm added without one would
|
|
silently be untunable — and the order-equality assertion is what notices,
|
|
as this replays with one such arm appended."""
|
|
bare = rp.RuleArm("x_rule", band=False, compact_tail=False,
|
|
checkpoint=False, preference_slot=False)
|
|
arms = (*rp.TUNED_ARMS, bare)
|
|
derived = {a.tuning.name: a.tuning for a in arms if a.tuning is not None}
|
|
assert [a.source for a in arms] != list(derived)
|