feat(phase2): P1c

tests/test_phase2_offline_battle.py

@@ -0,0 +1,87 @@
+"""Offline battles driven by FakeLLMClient through the NL policy (P1.3/P1.4)."""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from pf1e_simulator.client import FakeLLMClient
+from pf1e_simulator.loaders import load_combatant
+from pf1e_simulator.map import load_map
+from pf1e_simulator.nl_policy import NLPolicy
+from pf1e_simulator.prompt import PromptPack
+from pf1e_simulator.prompt_builder import PromptBuilder
+from pf1e_simulator.runner import EncounterSpec, Side, run_encounter
+
+ROOT = Path(__file__).resolve().parents[1]
+MAP = ROOT / "data" / "maps" / "sample_arena.yaml"
+
+
+def _c(path: str):
+    return load_combatant(ROOT / "data" / path)
+
+
+def _duel_spec() -> EncounterSpec:
+    """A fast 1v1 (goblin archer vs orc) on the sample arena."""
+    return EncounterSpec(
+        map=load_map(MAP),
+        round_cap=20,
+        sides=(
+            Side(name="players", combatants=(_c("monsters/goblin.json"),), zone="A"),
+            Side(name="monsters", combatants=(_c("monsters/orc.json"),), zone="B"),
+        ),
+    )
+
+
+def _pack() -> PromptPack:
+    return PromptPack.load(ROOT / "tests" / "fixtures" / "prompt_pack")
+
+
+def _builder() -> PromptBuilder:
+    return PromptBuilder(pack=_pack())
+
+
+def _make_client(script: list[str], *, builder: PromptBuilder) -> FakeLLMClient:
+    return FakeLLMClient(
+        script=script,
+        prompt_version=builder.prompt_version("nl_default"),
+    )
+
+
+def test_offline_battle_total_defense_draw() -> None:
+    """Both sides play total_defense → draw at round_cap (20 rounds, 40 calls)."""
+    spec = _duel_spec()
+    builder = _builder()
+    # 60 responses is plenty for 40 turns (20 rounds x 2 combatants)
+    script = ['[{"kind": "total_defense"}]'] * 60
+    client = _make_client(script, builder=builder)
+    policy = NLPolicy(client=client, builder=builder)
+
+    report, _outcomes = run_encounter(spec, runs=1, seed=1, llm_policy=policy, collect_runs=True)
+
+    # Draw at round_cap
+    assert report.draws == 1
+    assert report.wins.get("players", 0) == 0
+    assert report.wins.get("monsters", 0) == 0
+    assert report.avg_rounds == 20
+    # 20 rounds x 2 combatants = 40 policy invocations
+    assert client.stats.calls == 40
+
+
+def test_offline_battle_fallback() -> None:
+    """Fallback-driven battle: script of invalid JSON forces fallback on every turn."""
+    spec = _duel_spec()
+    builder = _builder()
+    # Each turn: 2 completes (first parse fail, retry parse fail → fallback).
+    # Max 20 rounds x 2 combatants x 2 = 80 completes. Use 100 for margin.
+    script = ["not json"] * 100
+    client = _make_client(script, builder=builder)
+    policy = NLPolicy(client=client, builder=builder)
+
+    report, _outcomes = run_encounter(spec, runs=1, seed=1, llm_policy=policy, collect_runs=True)
+
+    # The battle should complete (not exhaust script)
+    assert report.runs == 1
+    assert report.draws + sum(report.wins.values()) == 1
+    # At least some calls happened; script not exhausted
+    assert client.stats.calls > 0
+    assert client.stats.calls <= 100