paper-dynasty-database/tests/test_formula_engine.py
Cal Corum 569dc53c00 test: add Tier 1 and Tier 2 refractor system test cases
Implements all gap tests identified in the PO review for the refractor
card progression system (Phase 1 foundation).

TIER 1 (critical):
- T1-1: Negative singles guard in compute_batter_value — documents that
  hits=1, doubles=1, triples=1 produces singles=-1 and flows through
  unclamped (value=8.0, not 10.0)
- T1-2: SP tier boundary precision with floats — outs=29 (IP=9.666) stays
  T0, outs=30 (IP=10.0) promotes to T1; also covers T2 float boundary
- T1-3: evaluate-game with non-existent game_id returns 200 with empty results
- T1-4: Seed threshold ordering + positivity invariant (t1<t2<t3<t4, all >0)

TIER 2 (high):
- T2-1: fully_evolved=True persists when stats are zeroed or drop below
  previous tier — no-regression applies to both tier and fully_evolved flag
- T2-2: Parametrized edge cases for _determine_card_type: DH, C, 2B, empty
  string, None, and compound "SP/RP" (resolves to "sp", SP checked first)
- T2-3: evaluate-game with zero StratPlay rows returns empty batch result
- T2-4: GET /teams/{id}/refractors with valid team and zero states is empty
- T2-5: GET /teams/99999/refractors documents 200+empty (no team existence check)
- T2-6: POST /cards/{id}/evaluate with zero season stats stays at T0 value=0.0
- T2-9: Per-player error isolation — patches source module so router's local
  from-import picks up the patched version; one failure, one success = evaluated=1
- T2-10: Each card_type has exactly one RefractorTrack after seeding

All 101 tests pass (15 PostgreSQL-only tests skip without POSTGRES_HOST).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-24 09:02:30 -05:00

324 lines
11 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

"""Tests for the formula engine (WP-09).
Unit tests only — no database required. Stats inputs are simple namespace
objects whose attributes match what BattingSeasonStats/PitchingSeasonStats expose.
Tier thresholds used (from refractor_tracks.json seed data):
Batter: t1=37, t2=149, t3=448, t4=896
SP: t1=10, t2=40, t3=120, t4=240
RP: t1=3, t2=12, t3=35, t4=70
"""
from types import SimpleNamespace
import pytest
from app.services.formula_engine import (
compute_batter_value,
compute_rp_value,
compute_sp_value,
compute_value_for_track,
tier_from_value,
)
# ---------------------------------------------------------------------------
# Helpers
# ---------------------------------------------------------------------------
def batter_stats(**kwargs):
"""Build a minimal batter stats object with all fields defaulting to 0."""
defaults = {"pa": 0, "hits": 0, "doubles": 0, "triples": 0, "hr": 0}
defaults.update(kwargs)
return SimpleNamespace(**defaults)
def pitcher_stats(**kwargs):
"""Build a minimal pitcher stats object with all fields defaulting to 0."""
defaults = {"outs": 0, "strikeouts": 0}
defaults.update(kwargs)
return SimpleNamespace(**defaults)
def track_dict(card_type: str) -> dict:
"""Return the locked threshold dict for a given card_type."""
return {
"batter": {
"card_type": "batter",
"t1_threshold": 37,
"t2_threshold": 149,
"t3_threshold": 448,
"t4_threshold": 896,
},
"sp": {
"card_type": "sp",
"t1_threshold": 10,
"t2_threshold": 40,
"t3_threshold": 120,
"t4_threshold": 240,
},
"rp": {
"card_type": "rp",
"t1_threshold": 3,
"t2_threshold": 12,
"t3_threshold": 35,
"t4_threshold": 70,
},
}[card_type]
def track_ns(card_type: str):
"""Return a namespace (attribute-style) track for a given card_type."""
return SimpleNamespace(**track_dict(card_type))
# ---------------------------------------------------------------------------
# compute_batter_value
# ---------------------------------------------------------------------------
def test_batter_formula_single_and_double():
"""4 PA, 1 single, 1 double: PA=4, TB=1+2=3, value = 4 + 3×2 = 10."""
stats = batter_stats(pa=4, hits=2, doubles=1)
assert compute_batter_value(stats) == 10.0
def test_batter_formula_no_hits():
"""4 PA, 0 hits: TB=0, value = 4 + 0 = 4."""
stats = batter_stats(pa=4)
assert compute_batter_value(stats) == 4.0
def test_batter_formula_hr_heavy():
"""4 PA, 2 HR: TB = 0 singles + 4×2 = 8, value = 4 + 8×2 = 20."""
stats = batter_stats(pa=4, hits=2, hr=2)
assert compute_batter_value(stats) == 20.0
# ---------------------------------------------------------------------------
# compute_sp_value
# ---------------------------------------------------------------------------
def test_sp_formula_standard():
"""18 outs + 5 K: IP = 18/3 = 6.0, value = 6.0 + 5 = 11.0."""
stats = pitcher_stats(outs=18, strikeouts=5)
assert compute_sp_value(stats) == 11.0
# ---------------------------------------------------------------------------
# compute_rp_value
# ---------------------------------------------------------------------------
def test_rp_formula_standard():
"""3 outs + 2 K: IP = 3/3 = 1.0, value = 1.0 + 2 = 3.0."""
stats = pitcher_stats(outs=3, strikeouts=2)
assert compute_rp_value(stats) == 3.0
# ---------------------------------------------------------------------------
# Zero stats
# ---------------------------------------------------------------------------
def test_batter_zero_stats_returns_zero():
"""All-zero batter stats must return 0.0."""
assert compute_batter_value(batter_stats()) == 0.0
def test_sp_zero_stats_returns_zero():
"""All-zero SP stats must return 0.0."""
assert compute_sp_value(pitcher_stats()) == 0.0
def test_rp_zero_stats_returns_zero():
"""All-zero RP stats must return 0.0."""
assert compute_rp_value(pitcher_stats()) == 0.0
# ---------------------------------------------------------------------------
# Formula dispatch by track name
# ---------------------------------------------------------------------------
def test_dispatch_batter():
"""compute_value_for_track('batter', ...) delegates to compute_batter_value."""
stats = batter_stats(pa=4, hits=2, doubles=1)
assert compute_value_for_track("batter", stats) == compute_batter_value(stats)
def test_dispatch_sp():
"""compute_value_for_track('sp', ...) delegates to compute_sp_value."""
stats = pitcher_stats(outs=18, strikeouts=5)
assert compute_value_for_track("sp", stats) == compute_sp_value(stats)
def test_dispatch_rp():
"""compute_value_for_track('rp', ...) delegates to compute_rp_value."""
stats = pitcher_stats(outs=3, strikeouts=2)
assert compute_value_for_track("rp", stats) == compute_rp_value(stats)
def test_dispatch_unknown_raises():
"""An unrecognised card_type must raise ValueError."""
with pytest.raises(ValueError, match="Unknown card_type"):
compute_value_for_track("dh", batter_stats())
# ---------------------------------------------------------------------------
# tier_from_value — batter thresholds (t1=37, t2=149, t3=448, t4=896)
# ---------------------------------------------------------------------------
def test_tier_exact_t1_boundary():
"""value=37 is exactly t1 for batter → T1."""
assert tier_from_value(37, track_dict("batter")) == 1
def test_tier_just_below_t1():
"""value=36 is just below t1=37 for batter → T0."""
assert tier_from_value(36, track_dict("batter")) == 0
def test_tier_t4_boundary():
"""value=896 is exactly t4 for batter → T4."""
assert tier_from_value(896, track_dict("batter")) == 4
def test_tier_above_t4():
"""value above t4 still returns T4 (fully evolved)."""
assert tier_from_value(1000, track_dict("batter")) == 4
def test_tier_t2_boundary():
"""value=149 is exactly t2 for batter → T2."""
assert tier_from_value(149, track_dict("batter")) == 2
def test_tier_t3_boundary():
"""value=448 is exactly t3 for batter → T3."""
assert tier_from_value(448, track_dict("batter")) == 3
def test_tier_accepts_namespace_track():
"""tier_from_value must work with attribute-style track objects (Peewee models)."""
assert tier_from_value(37, track_ns("batter")) == 1
# ---------------------------------------------------------------------------
# T1-1: Negative singles guard in compute_batter_value
# ---------------------------------------------------------------------------
def test_batter_negative_singles_component():
"""hits=1, doubles=1, triples=1, hr=0 produces singles=-1.
What: The formula computes singles = hits - doubles - triples - hr.
With hits=1, doubles=1, triples=1, hr=0 the result is singles = -1,
which is a physically impossible stat line but valid arithmetic input.
Why: Document the formula's actual behaviour when given an incoherent stat
line so that callers are aware that no clamping or guard exists. If a
guard is added in the future, this test will catch the change in behaviour.
singles = 1 - 1 - 1 - 0 = -1
tb = (-1)*1 + 1*2 + 1*3 + 0*4 = -1 + 2 + 3 = 4
value = pa + tb*2 = 0 + 4*2 = 8
"""
stats = batter_stats(hits=1, doubles=1, triples=1, hr=0)
# singles will be -1; the formula does NOT clamp, so TB = 4 and value = 8.0
result = compute_batter_value(stats)
assert result == 8.0, (
f"Expected 8.0 (negative singles flows through unclamped), got {result}"
)
def test_batter_negative_singles_is_not_clamped():
"""A singles value below zero is NOT clamped to zero by the formula.
What: Confirms that singles < 0 propagates into TB rather than being
floored at 0. If clamping were added, tb would be 0*1 + 1*2 + 1*3 = 5
and value would be 10.0, not 8.0.
Why: Guards future refactors — if someone adds `singles = max(0, ...)`,
this assertion will fail immediately, surfacing the behaviour change.
"""
stats = batter_stats(hits=1, doubles=1, triples=1, hr=0)
unclamped_value = compute_batter_value(stats)
# If singles were clamped to 0: tb = 0+2+3 = 5, value = 10.0
clamped_value = 10.0
assert unclamped_value != clamped_value, (
"Formula appears to clamp negative singles — behaviour has changed"
)
# ---------------------------------------------------------------------------
# T1-2: Tier boundary precision with float SP values
# ---------------------------------------------------------------------------
def test_sp_tier_just_below_t1_outs29():
"""SP with outs=29 produces IP=9.666..., which is below T1 threshold (10) → T0.
What: 29 outs / 3 = 9.6666... IP + 0 K = 9.6666... value.
The SP T1 threshold is 10.0, so this value is strictly below T1.
Why: Floating-point IP values accumulate slowly for pitchers. A bug that
truncated or rounded IP upward could cause premature tier advancement.
Verify that tier_from_value uses a >= comparison (not >) and handles
non-integer values correctly.
"""
stats = pitcher_stats(outs=29, strikeouts=0)
value = compute_sp_value(stats)
assert value == pytest.approx(29 / 3) # 9.6666...
assert value < 10.0 # strictly below T1
assert tier_from_value(value, track_dict("sp")) == 0
def test_sp_tier_exactly_t1_outs30():
"""SP with outs=30 produces IP=10.0, exactly at T1 threshold → T1.
What: 30 outs / 3 = 10.0 IP + 0 K = 10.0 value.
The SP T1 threshold is 10.0, so value == t1 satisfies the >= condition.
Why: Off-by-one or strictly-greater-than comparisons would classify
this as T0 instead of T1. The boundary value must correctly promote
to the matching tier.
"""
stats = pitcher_stats(outs=30, strikeouts=0)
value = compute_sp_value(stats)
assert value == 10.0
assert tier_from_value(value, track_dict("sp")) == 1
def test_sp_float_value_at_exact_t2_boundary():
"""SP value exactly at T2 threshold (40.0) → T2.
What: outs=120 -> IP=40.0, strikeouts=0 -> value=40.0.
T2 threshold for SP is 40. The >= comparison must promote to T2.
Why: Validates that all four tier thresholds use inclusive lower-bound
comparisons for float values, not just T1.
"""
stats = pitcher_stats(outs=120, strikeouts=0)
value = compute_sp_value(stats)
assert value == 40.0
assert tier_from_value(value, track_dict("sp")) == 2
def test_sp_float_value_just_below_t2():
"""SP value just below T2 (39.999...) stays at T1.
What: outs=119 -> IP=39.6666..., strikeouts=0 -> value=39.666...
This is strictly less than T2=40, so tier should be 1 (already past T1=10).
Why: Confirms that sub-threshold float values are not prematurely promoted
due to floating-point comparison imprecision.
"""
stats = pitcher_stats(outs=119, strikeouts=0)
value = compute_sp_value(stats)
assert value == pytest.approx(119 / 3) # 39.666...
assert value < 40.0
assert tier_from_value(value, track_dict("sp")) == 1