bvandeusenandClaude Opus 5.5
869046dda2
CI & Build / Python lint (push) Successful in 3s
CI & Build / Plugin hooks (push) Successful in 14s
CI & Build / TypeScript typecheck (push) Successful in 54s
CI & Build / integration (push) Successful in 59s
CI & Build / Python tests (push) Successful in 2m1s
CI & Build / Build & push image (push) Successful in 27s
Each arm spec now carries its tuning pair (Surface, moved verbatim into retrieval_pipeline) and a Declared block - what the telemetry readout must know and cannot read off its rows. The two ranked stages that are not arms (preference_slot, rule_via_lesson) are RankedSource specs, and the note slots carry their own declaration. - retrieval_surfaces.SURFACES = the TUNED_ARMS tuning, same order - retrieval_registry.POINTS ranked rows = one per spec in RANKED; the lookups, asked, ambient and pull rows stay declared there - rule_usage.RANKED_SOURCES = RULE_RANKED_SOURCES + moment_rule Settings keys, defaults, prose and order are unchanged (checked field by field against HEAD). tests/test_retrieval_specs.py pins the derivation. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
72 lines
3.2 KiB
Python
72 lines
3.2 KiB
Python
"""The specs are the registry (milestone 456 step 5).
|
|
|
|
Three lists used to be kept by hand beside the arms — the tuning table, the
|
|
ranked rows of the telemetry registry, and the rule-usage denominator — with
|
|
tests to make them agree. They are now read off the pipeline's specs. 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
|
|
assert point.fixed_query == d.fixed_query
|
|
# A quiet source must say why, and only a quiet source may (#2475).
|
|
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():
|
|
"""Rule 167: 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)
|