evals: add pi backend

evals/tests/test_backend.py

@@ -44,6 +44,12 @@ class TestLoadBackend:
         assert flash_backend.family == "gemini"
         assert flash_backend.model == "gemini-2.5-flash"
 
+    def test_loads_pi_backend(self, backends_dir):
+        backend = load_backend("pi", backends_dir)
+        assert backend.name == "pi"
+        assert backend.cli == "pi"
+        assert backend.family == "pi"
+
 
 class TestBackendBuildCommand:
     def test_claude_build_command(self, backends_dir, monkeypatch):
@@ -60,6 +66,12 @@ class TestBackendBuildCommand:
         cmd = backend.build_command("/tmp/workdir")
         assert cmd[0] == "codex"
 
+    def test_pi_build_command_loads_local_superpowers_package(self, backends_dir, monkeypatch):
+        monkeypatch.setenv("SUPERPOWERS_ROOT", "/tmp/superpowers")
+        backend = load_backend("pi", backends_dir)
+        cmd = backend.build_command("/tmp/workdir")
+        assert cmd == ["pi", "-e", "/tmp/superpowers"]
+
 
 class TestBackendEnvValidation:
     def test_missing_env_raises(self, backends_dir, monkeypatch):
@@ -125,6 +137,21 @@ class TestBackendFamily:
         backend = load_backend("codex", backends_dir)
         assert backend.family == "codex"
 
+    def test_pi_backend_family(self):
+        backend = Backend(
+            name="pi",
+            cli="pi",
+            args=[],
+            required_env=[],
+            hooks={"pre_run": [], "post_run": []},
+            shutdown="/quit",
+            idle={},
+            startup_timeout=30,
+            terminal={},
+            session_logs={},
+        )
+        assert backend.family == "pi"
+
     def test_variant_name_preserves_family(self):
         backend = Backend(
             name="claude-opus-4-6",

evals/tests/test_engine.py

@@ -4,7 +4,7 @@ import json
 import subprocess
 from pathlib import Path
 
-from drill.engine import RunResult, ScenarioConfig, VerifyConfig, snapshot_filesystem
+from drill.engine import Engine, RunResult, ScenarioConfig, VerifyConfig, snapshot_filesystem
 
 
 class TestVerifyConfig:
@@ -138,6 +138,40 @@ class TestEngineAssertionIntegration:
         assert (tmp_path / "meta.json").exists()
 
 
+class TestEnginePiBackend:
+    def test_resolves_pi_session_log_root(self, tmp_path: Path) -> None:
+        scenario = tmp_path / "scenario.yaml"
+        scenario.write_text("scenario: test-pi\n")
+        backends = tmp_path / "backends"
+        backends.mkdir()
+        (backends / "pi.yaml").write_text(
+            """
+name: pi
+cli: pi
+args: []
+required_env: []
+hooks:
+  pre_run: []
+  post_run: []
+shutdown: /quit
+idle: {}
+startup_timeout: 1
+terminal: {}
+session_logs:
+  pattern: ~/.pi/agent/sessions/**/*.jsonl
+"""
+        )
+        engine = Engine(
+            scenario_path=scenario,
+            backend_name="pi",
+            backends_dir=backends,
+            fixtures_dir=tmp_path,
+            results_dir=tmp_path,
+        )
+
+        assert engine._resolve_log_dir(tmp_path) == Path.home() / ".pi" / "agent" / "sessions"
+
+
 class TestEngineRunParams:
     def test_run_result_uses_custom_output_dir(self, tmp_path: Path) -> None:
         custom_dir = tmp_path / "custom" / "run-00"

evals/tests/test_normalizer.py

@@ -3,9 +3,11 @@ import json
 from drill.normalizer import (
     collect_new_logs,
     filter_codex_logs_by_cwd,
+    filter_pi_logs_by_cwd,
     normalize_claude_logs,
     normalize_codex_logs,
     normalize_gemini_logs,
+    normalize_pi_logs,
     snapshot_log_dir,
 )
 
@@ -137,6 +139,56 @@ class TestNormalizeCodexLogs:
         assert normalized[1]["source"] == "native"
 
 
+class TestNormalizePiLogs:
+    def test_filter_by_cwd_keeps_matching_session_headers(self, tmp_path):
+        target = "/tmp/drill-target"
+        match = tmp_path / "match.jsonl"
+        match.write_text(json.dumps({"type": "session", "cwd": target}) + "\n")
+        other = tmp_path / "other.jsonl"
+        other.write_text(json.dumps({"type": "session", "cwd": "/tmp/other"}) + "\n")
+        malformed = tmp_path / "malformed.jsonl"
+        malformed.write_text("not json\n")
+
+        assert filter_pi_logs_by_cwd([match, other, malformed], target) == [match]
+
+    def test_normalizes_assistant_tool_calls_from_session_entries(self):
+        lines = [
+            json.dumps({"type": "session", "cwd": "/tmp/project"}),
+            json.dumps(
+                {
+                    "type": "message",
+                    "message": {
+                        "role": "assistant",
+                        "content": [
+                            {"type": "text", "text": "I will inspect this."},
+                            {
+                                "type": "toolCall",
+                                "name": "read",
+                                "arguments": {"path": "README.md"},
+                            },
+                            {
+                                "type": "toolCall",
+                                "name": "bash",
+                                "arguments": {"command": "git status"},
+                            },
+                            {
+                                "type": "toolCall",
+                                "name": "subagent",
+                                "arguments": {"agent": "reviewer"},
+                            },
+                        ],
+                    },
+                }
+            ),
+        ]
+
+        assert normalize_pi_logs("\n".join(lines)) == [
+            {"tool": "Read", "args": {"path": "README.md"}, "source": "native"},
+            {"tool": "Bash", "args": {"command": "git status"}, "source": "shell"},
+            {"tool": "subagent", "args": {"agent": "reviewer"}, "source": "native"},
+        ]
+
+
 class TestNormalizeGeminiLogs:
     def test_normalizes_jsonl_tool_calls(self):
         lines = [