Files
agentic-pd-hybrid/tests/test_policy_scoring.py
Gahow Wang a785b83023 test(policy): unit tests for Algorithm 1 lex scoring
Adds the project's first test suite. Covers the
score_candidate() pure function from the previous refactor
commit, validating the qualitative properties that
KVC_ROUTER_ALGORITHM.md §3.1 and §4.2 rely on.

Tests / properties:
  - determinism: same args -> same tuple
  - shape: 4-int tuple
  - primary term: overlap dominates pure sticky
  - primary term: sticky_bonus credited
  - tie-2 inflight: lower wins
  - tie-3 assigned: lower wins
  - strict lex order: sticky wins position-1 over fresh-idle
  - load_floor disabled by default
  - load_floor gated off when sticky=True
  - load_floor zero during warmup (mean=0)
  - load_floor proportional to deficit (200/100/0 at 0/50/100% load)
  - load_floor does not underflow when overloaded
  - real per-session overlap beats load_floor on warm D
  - boilerplate overlap loses to load_floor on cold D
    (the cold-D fix from E1_E2_FIX_DESIGN §Q2)

Test infrastructure:
  - tests/ package with README explaining the GPU-free
    scope and the run instruction
  - pyproject.toml [dependency-groups] test = [pytest>=8]
    (install via `uv sync --group test`)
  - pyproject.toml [tool.pytest.ini_options] sets testpaths

Verified locally: 14/14 passing under pytest 9.0.3 in an
isolated 3.13 venv. No SGLang / GPU touched.
2026-05-12 23:54:48 +08:00

190 lines
6.8 KiB
Python

"""Unit tests for Algorithm 1 (KvAwarePolicy score_candidate).
Reference: docs/KVC_ROUTER_ALGORITHM.md §3.1. The lex-score is
(overlap + sticky_bonus*sticky + floor_bonus,
sticky,
-inflight,
-assigned)
These tests pin down the qualitative properties that the algorithm's
correctness arguments rely on. They run without SGLang/GPU.
"""
from __future__ import annotations
from agentic_pd_hybrid.policies import score_candidate
def _score(**overrides):
"""Helper: build a score with all defaults and per-test overrides."""
args = dict(
overlap=0,
sticky=False,
inflight=0,
assigned=0,
mean_assigned=0.0,
sticky_bonus=1,
load_floor_bonus=0,
)
args.update(overrides)
return score_candidate(**args)
# -- Determinism ----------------------------------------------------------------
def test_score_is_pure():
"""Same kwargs must produce the same tuple (no hidden state)."""
a = _score(overlap=3, sticky=True, inflight=1, assigned=7)
b = _score(overlap=3, sticky=True, inflight=1, assigned=7)
assert a == b
def test_score_returns_4_tuple():
s = _score()
assert isinstance(s, tuple)
assert len(s) == 4
assert all(isinstance(x, int) for x in s)
# -- Primary term: overlap dominates sticky --------------------------------------
def test_overlap_strictly_dominates_pure_sticky():
"""Theorem-2 building block: any positive overlap on a non-sticky D wins
against a sticky-only D with zero overlap (sticky_bonus=1)."""
overlap = _score(overlap=2, sticky=False)
sticky_only = _score(overlap=0, sticky=True)
assert overlap > sticky_only
def test_overlap_plus_sticky_beats_overlap_alone():
"""Two D's with equal overlap: sticky one wins (sticky_bonus contributes
to primary AND wins tie-1)."""
sticky_d = _score(overlap=5, sticky=True)
fresh_d = _score(overlap=5, sticky=False)
assert sticky_d > fresh_d
# -- Tie breakers ----------------------------------------------------------------
def test_tiebreaker_inflight_lower_wins():
"""Equal primary & sticky: prefer the D with fewer in-flight requests."""
low = _score(overlap=3, sticky=False, inflight=0, assigned=10)
high = _score(overlap=3, sticky=False, inflight=5, assigned=10)
assert low > high
def test_tiebreaker_assigned_lower_wins():
"""Equal primary & sticky & inflight: prefer rarely-picked D."""
rare = _score(overlap=3, sticky=False, inflight=2, assigned=1)
frequent = _score(overlap=3, sticky=False, inflight=2, assigned=99)
assert rare > frequent
def test_tiebreaker_strict_lex_order():
"""Sticky always beats non-sticky on tie-1 even if non-sticky has lower
inflight (the lex order is strict, position 1 outranks positions 2/3)."""
sticky_busy = _score(overlap=4, sticky=True, inflight=10, assigned=10)
fresh_idle = _score(overlap=4, sticky=False, inflight=0, assigned=0)
# Note: with sticky_bonus=1 added to position 0, sticky_busy actually wins
# on position 0 first (5 > 4). Force equal primary by lowering sticky's
# overlap.
sticky_busy_eq_primary = _score(overlap=3, sticky=True, inflight=10, assigned=10)
fresh_idle_eq_primary = _score(overlap=4, sticky=False, inflight=0, assigned=0)
# Now equal primary (3+1=4 vs 4). Sticky wins position 1.
assert sticky_busy_eq_primary > fresh_idle_eq_primary
# -- Load-floor bonus ------------------------------------------------------------
def test_load_floor_disabled_by_default():
"""load_floor_bonus=0 → no contribution to primary."""
s = _score(overlap=0, sticky=False, mean_assigned=10, assigned=0)
assert s[0] == 0
def test_load_floor_gated_off_when_sticky():
"""Even with load_floor_bonus>0, sticky D does NOT receive the boost.
Otherwise a session would migrate away from its warm D under load."""
sticky_under_loaded = _score(
overlap=0, sticky=True, mean_assigned=10, assigned=0, load_floor_bonus=200
)
# primary = overlap(0) + sticky_bonus(1) + floor(0) = 1
assert sticky_under_loaded[0] == 1
def test_load_floor_zero_when_mean_zero():
"""Warmup case: mean_assigned=0 -> no D gets boost -> degenerate to lex
tiebreak by iteration order."""
s = _score(
overlap=0, sticky=False, mean_assigned=0, assigned=0, load_floor_bonus=200
)
assert s[0] == 0
def test_load_floor_proportional_to_deficit():
"""floor_bonus = K * deficit / mean. assigned=0, mean=10, K=200 -> 200."""
s_zero = _score(
overlap=0, sticky=False, mean_assigned=10, assigned=0, load_floor_bonus=200
)
s_half = _score(
overlap=0, sticky=False, mean_assigned=10, assigned=5, load_floor_bonus=200
)
s_full = _score(
overlap=0, sticky=False, mean_assigned=10, assigned=10, load_floor_bonus=200
)
# deficit = max(0, 10-0)=10 -> bonus = int(200*10/10) = 200
# deficit = max(0, 10-5)=5 -> bonus = int(200*5/10) = 100
# deficit = max(0, 10-10)=0 -> bonus = 0
assert s_zero[0] == 200
assert s_half[0] == 100
assert s_full[0] == 0
def test_load_floor_does_not_underflow_when_overloaded():
"""assigned > mean -> deficit clamped to 0, no negative bonus."""
s = _score(
overlap=0, sticky=False, mean_assigned=10, assigned=50, load_floor_bonus=200
)
assert s[0] == 0
# -- Routing intent: real overlap beats load-floor bonus -------------------------
def test_real_prefix_overlap_beats_load_floor_on_warm_d():
"""E1_E2_FIX_DESIGN_ZH §Q2: load_floor should be set such that
real per-session prefix overlap outweighs the cold-D bonus.
With overlap=800 (a per-session prefix) and load_floor_bonus=200,
a warm D (high overlap, possibly high load) should still win against
a cold D with floor bonus."""
warm = _score(
overlap=800, sticky=True, mean_assigned=10, assigned=10, load_floor_bonus=200
)
cold = _score(
overlap=0, sticky=False, mean_assigned=10, assigned=0, load_floor_bonus=200
)
# warm primary = 800 + 1 + 0 = 801. cold primary = 0 + 0 + 200 = 200.
assert warm[0] == 801
assert cold[0] == 200
assert warm > cold
def test_boilerplate_overlap_loses_to_load_floor_for_cold_d():
"""Same §Q2: load_floor should beat cross-session boilerplate overlap.
If load_floor_bonus=200 and the worst-case boilerplate overlap is ~50,
a fresh cold D should still win against a slightly-warm-from-boilerplate D."""
warm_boilerplate = _score(
overlap=50, sticky=False, mean_assigned=10, assigned=10, load_floor_bonus=200
)
cold_under_loaded = _score(
overlap=0, sticky=False, mean_assigned=10, assigned=0, load_floor_bonus=200
)
# warm_boilerplate primary = 50 + 0 + 0 = 50 (assigned=mean, no deficit).
# cold_under_loaded primary = 0 + 0 + 200 = 200.
assert cold_under_loaded > warm_boilerplate