test(sessions): add 10 replay cases with JSONL fixture load/save

coder-mtj · coder-mtj · commit 278e6baf4055 · 2026-07-06T08:55:38.000+08:00
10 replay scenarios defined in cases.py with round-trip
JSONL fixture support. Mirrors Go trpc-agent-go session/replaytest.

Signed-off-by: coder-mtj &lt;coder-mtj@users.noreply.github.com&gt;
diff --git a/tests/sessions/replay_consistency/cases.py b/tests/sessions/replay_consistency/cases.py
diff --git a/tests/sessions/replay_consistency/fixtures/case_001_single_turn.jsonl b/tests/sessions/replay_consistency/fixtures/case_001_single_turn.jsonl
@@ -0,0 +1,5 @@
+{"type": "case_header", "name": "single_turn_text", "app_name": "test-app", "user_id": "user-1", "session_id": "session-001", "initial_state": {"app:welcome": "true"}}
+{"type": "event", "author": "user", "invocation_id": "", "role": "user", "text": "Hello, who are you?", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "assistant", "invocation_id": "", "role": "assistant", "text": "I am an AI assistant.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "memory_write", "memory": "User greeted the assistant", "topics": ["conversation"]}
+{"type": "memory_query", "query": "greeting", "limit": 5}
diff --git a/tests/sessions/replay_consistency/fixtures/case_002_multi_turn.jsonl b/tests/sessions/replay_consistency/fixtures/case_002_multi_turn.jsonl
@@ -0,0 +1,11 @@
+{"type": "case_header", "name": "multi_turn_state_updates", "app_name": "test-app", "user_id": "user-1", "session_id": "session-002", "initial_state": {}}
+{"type": "event", "author": "user", "invocation_id": "", "role": "user", "text": "What is my name?", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "assistant", "invocation_id": "", "role": "assistant", "text": "Your name is Bob.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "user", "invocation_id": "", "role": "user", "text": "Remember that I like coffee.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "assistant", "invocation_id": "", "role": "assistant", "text": "I will remember that you like coffee.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "user", "invocation_id": "", "role": "user", "text": "What did I ask you to remember?", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "assistant", "invocation_id": "", "role": "assistant", "text": "You asked me to remember that you like coffee.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "memory_write", "memory": "User name is Bob", "topics": ["identity"]}
+{"type": "memory_write", "memory": "User likes coffee", "topics": ["preferences"]}
+{"type": "memory_query", "query": "Bob", "limit": 5}
+{"type": "memory_query", "query": "coffee", "limit": 5}
diff --git a/tests/sessions/replay_consistency/fixtures/case_003_tool_call.jsonl b/tests/sessions/replay_consistency/fixtures/case_003_tool_call.jsonl
@@ -0,0 +1,7 @@
+{"type": "case_header", "name": "tool_call_roundtrip", "app_name": "test-app", "user_id": "user-1", "session_id": "session-003", "initial_state": {}}
+{"type": "event", "author": "user", "invocation_id": "", "role": "user", "text": "What is the weather?", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "assistant", "invocation_id": "", "role": "assistant", "text": "", "tool_calls": [{"id": "call-1", "name": "get_weather", "arguments": "{\"city\":\"Beijing\"}"}], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "tool", "invocation_id": "", "role": "tool", "text": "", "tool_calls": [], "tool_response": {"id": "call-1", "name": "get_weather", "content": "Sunny, 25°C"}, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "assistant", "invocation_id": "", "role": "assistant", "text": "The weather in Beijing is sunny, 25°C.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "memory_write", "memory": "User checked weather for Beijing", "topics": ["action"]}
+{"type": "memory_query", "query": "weather", "limit": 5}
diff --git a/tests/sessions/replay_consistency/fixtures/case_004_state_updates.jsonl b/tests/sessions/replay_consistency/fixtures/case_004_state_updates.jsonl
@@ -0,0 +1,4 @@
+{"type": "case_header", "name": "scoped_state_overwrite", "app_name": "test-app", "user_id": "user-1", "session_id": "session-004", "initial_state": {"user:score": "0", "app:round": "1"}}
+{"type": "event", "author": "assistant", "invocation_id": "", "role": "assistant", "text": "Starting round 1.", "tool_calls": [], "tool_response": null, "state_delta": {"user:score": "10"}, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "user", "invocation_id": "", "role": "user", "text": "I found the answer.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "assistant", "invocation_id": "", "role": "assistant", "text": "Score updated.", "tool_calls": [], "tool_response": null, "state_delta": {"user:score": "25", "app:round": "2"}, "filter_key": "", "branch": "", "tag": ""}
diff --git a/tests/sessions/replay_consistency/fixtures/case_005_memory_rw.jsonl b/tests/sessions/replay_consistency/fixtures/case_005_memory_rw.jsonl
@@ -0,0 +1,11 @@
+{"type": "case_header", "name": "memory_multi_author_search", "app_name": "test-app", "user_id": "user-2", "session_id": "session-005", "initial_state": {}}
+{"type": "event", "author": "user", "invocation_id": "", "role": "user", "text": "I enjoy hiking on weekends.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "assistant", "invocation_id": "", "role": "assistant", "text": "That's great! Hiking is wonderful.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "user", "invocation_id": "", "role": "user", "text": "Also I prefer tea over coffee.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "assistant", "invocation_id": "", "role": "assistant", "text": "Noted - you prefer tea.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "memory_write", "memory": "User enjoys hiking", "topics": ["hobbies"]}
+{"type": "memory_write", "memory": "User prefers tea", "topics": ["preferences"]}
+{"type": "memory_write", "memory": "User is health conscious", "topics": ["lifestyle"]}
+{"type": "memory_query", "query": "hiking", "limit": 3}
+{"type": "memory_query", "query": "tea", "limit": 3}
+{"type": "memory_query", "query": "preferences", "limit": 5}
diff --git a/tests/sessions/replay_consistency/fixtures/case_006_summary.jsonl b/tests/sessions/replay_consistency/fixtures/case_006_summary.jsonl
@@ -0,0 +1,8 @@
+{"type": "case_header", "name": "summary_generation", "app_name": "test-app", "user_id": "user-1", "session_id": "session-006", "initial_state": {}}
+{"type": "event", "author": "user", "invocation_id": "", "role": "user", "text": "Help me plan a trip to Shanghai.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "assistant", "invocation_id": "", "role": "assistant", "text": "Sure! When would you like to go?", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "user", "invocation_id": "", "role": "user", "text": "Next month, for 3 days.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "assistant", "invocation_id": "", "role": "assistant", "text": "I recommend visiting the Bund and Yu Garden.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "user", "invocation_id": "", "role": "user", "text": "Great, also I need hotel recommendations.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "assistant", "invocation_id": "", "role": "assistant", "text": "I can search for hotels near the Bund.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "summary_step", "after_event_index": 6, "filter_key": "", "force": true}
diff --git a/tests/sessions/replay_consistency/fixtures/case_007_summary_truncation.jsonl b/tests/sessions/replay_consistency/fixtures/case_007_summary_truncation.jsonl
@@ -0,0 +1,11 @@
+{"type": "case_header", "name": "summary_with_truncation", "app_name": "test-app", "user_id": "user-1", "session_id": "session-007", "initial_state": {}}
+{"type": "event", "author": "user", "invocation_id": "", "role": "user", "text": "Message 1: Greetings.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "assistant", "invocation_id": "", "role": "assistant", "text": "Response 1: Hello!", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "user", "invocation_id": "", "role": "user", "text": "Message 2: Question about weather.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "assistant", "invocation_id": "", "role": "assistant", "text": "Response 2: It's sunny.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "user", "invocation_id": "", "role": "user", "text": "Message 3: Thank you.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "assistant", "invocation_id": "", "role": "assistant", "text": "Response 3: You're welcome.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "user", "invocation_id": "", "role": "user", "text": "Message 4: Can you summarize?", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "assistant", "invocation_id": "", "role": "assistant", "text": "Response 4: Here is the summary.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "summary_step", "after_event_index": 6, "filter_key": "weather", "force": true}
+{"type": "summary_step", "after_event_index": 8, "filter_key": "", "force": true}
diff --git a/tests/sessions/replay_consistency/fixtures/case_008_track_events.jsonl b/tests/sessions/replay_consistency/fixtures/case_008_track_events.jsonl
@@ -0,0 +1,6 @@
+{"type": "case_header", "name": "track_events", "app_name": "test-app", "user_id": "user-1", "session_id": "session-008", "initial_state": {}}
+{"type": "event", "author": "user", "invocation_id": "", "role": "user", "text": "Run a calculation.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "assistant", "invocation_id": "", "role": "assistant", "text": "Running calculation...", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "track_event", "track": "tool_execution", "payload": "{\"tool\":\"calculator\",\"duration_ms\":150,\"status\":\"success\"}"}
+{"type": "track_event", "track": "tool_execution", "payload": "{\"tool\":\"calculator\",\"duration_ms\":200,\"status\":\"success\"}"}
+{"type": "track_event", "track": "subtask_status", "payload": "{\"subtask\":\"verification\",\"status\":\"passed\"}"}
diff --git a/tests/sessions/replay_consistency/fixtures/case_009_concurrent_writes.jsonl b/tests/sessions/replay_consistency/fixtures/case_009_concurrent_writes.jsonl
@@ -0,0 +1,8 @@
+{"type": "case_header", "name": "concurrent_out_of_order_writes", "app_name": "test-app", "user_id": "user-3", "session_id": "session-009", "initial_state": {}}
+{"type": "event", "author": "user", "invocation_id": "", "role": "user", "text": "Start parallel task A.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "user", "invocation_id": "", "role": "user", "text": "Start parallel task B.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "assistant", "invocation_id": "", "role": "assistant", "text": "Task A result.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "assistant", "invocation_id": "", "role": "assistant", "text": "Task B result.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "user", "invocation_id": "", "role": "user", "text": "Merge results.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "memory_write", "memory": "Parallel task A completed", "topics": ["task"]}
+{"type": "memory_write", "memory": "Parallel task B completed", "topics": ["task"]}
diff --git a/tests/sessions/replay_consistency/fixtures/case_010_error_recovery.jsonl b/tests/sessions/replay_consistency/fixtures/case_010_error_recovery.jsonl
@@ -0,0 +1,10 @@
+{"type": "case_header", "name": "error_recovery", "app_name": "test-app", "user_id": "user-1", "session_id": "session-010", "initial_state": {}}
+{"type": "event", "author": "user", "invocation_id": "", "role": "user", "text": "Normal message 1.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "assistant", "invocation_id": "", "role": "assistant", "text": "Normal response 1.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "user", "invocation_id": "", "role": "user", "text": "Duplicate test message.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "user", "invocation_id": "", "role": "user", "text": "Duplicate test message.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "assistant", "invocation_id": "", "role": "assistant", "text": "Response to duplicate.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "user", "invocation_id": "", "role": "user", "text": "Final message.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "event", "author": "assistant", "invocation_id": "", "role": "assistant", "text": "Final response.", "tool_calls": [], "tool_response": null, "state_delta": null, "filter_key": "", "branch": "", "tag": ""}
+{"type": "memory_write", "memory": "Normal operation recorded", "topics": ["status"]}
+{"type": "memory_write", "memory": "Normal operation recorded", "topics": ["status"]}
diff --git a/tests/sessions/replay_consistency/test_cases.py b/tests/sessions/replay_consistency/test_cases.py
@@ -0,0 +1,132 @@
+# Tencent is pleased to support the open source community by making
+# tRPC-Agent-Python available.
+#
+# Copyright (C) 2026 Tencent. All rights reserved.
+#
+# tRPC-Agent-Python is licensed under Apache-2.0.
+
+"""Unit tests for replay case definitions and JSONL fixture loading."""
+
+from __future__ import annotations
+
+import os
+import json
+import pathlib
+
+import pytest
+
+
+class TestReplayCases:
+    """Tests for replay case definitions."""
+
+    def test_all_10_cases_defined(self):
+        """Exactly 10 replay cases must be defined."""
+        from tests.sessions.replay_consistency.cases import _replay_cases
+        cases = _replay_cases()
+        assert len(cases) == 10, f"Expected 10 cases, got {len(cases)}"
+
+    def test_each_case_has_required_fields(self):
+        """Every case must have name, app_name, user_id, session_id."""
+        from tests.sessions.replay_consistency.cases import _replay_cases
+        for case in _replay_cases():
+            assert case.name, f"Case missing name"
+            assert case.app_name, f"Case {case.name} missing app_name"
+            assert case.user_id, f"Case {case.name} missing user_id"
+            assert case.session_id, f"Case {case.name} missing session_id"
+
+    def test_at_least_one_case_has_tool_call(self):
+        """At least one case should include tool_call events."""
+        from tests.sessions.replay_consistency.cases import _replay_cases
+        found = False
+        for case in _replay_cases():
+            for evt in case.events:
+                if evt.tool_calls:
+                    found = True
+                    break
+        assert found, "No case includes tool_call events"
+
+    def test_at_least_one_case_has_summary_steps(self):
+        """At least one case should exercise summary generation."""
+        from tests.sessions.replay_consistency.cases import _replay_cases
+        found = False
+        for case in _replay_cases():
+            if case.summary_steps:
+                found = True
+                break
+        assert found, "No case includes summary steps"
+
+    def test_at_least_one_case_has_track_events(self):
+        """At least one case should exercise track events."""
+        from tests.sessions.replay_consistency.cases import _replay_cases
+        found = False
+        for case in _replay_cases():
+            if case.track_events:
+                found = True
+                break
+        assert found, "No case includes track events"
+
+
+class TestJSONLFixtures:
+    """Tests for JSONL fixture loading."""
+
+    @pytest.fixture
+    def fixtures_dir(self) -> pathlib.Path:
+        return pathlib.Path(__file__).parent / "fixtures"
+
+    def test_all_10_jsonl_fixtures_exist(self, fixtures_dir):
+        """All 10 JSONL fixture files must be present."""
+        expected = [
+            "case_001_single_turn.jsonl",
+            "case_002_multi_turn.jsonl",
+            "case_003_tool_call.jsonl",
+            "case_004_state_updates.jsonl",
+            "case_005_memory_rw.jsonl",
+            "case_006_summary.jsonl",
+            "case_007_summary_truncation.jsonl",
+            "case_008_track_events.jsonl",
+            "case_009_concurrent_writes.jsonl",
+            "case_010_error_recovery.jsonl",
+        ]
+        for name in expected:
+            path = fixtures_dir / name
+            assert path.exists(), f"Missing fixture: {name}"
+
+    def test_can_load_case_from_jsonl(self, fixtures_dir):
+        """Each JSONL fixture must be loadable into a ReplayCase."""
+        from tests.sessions.replay_consistency.cases import load_case_from_jsonl
+        path = fixtures_dir / "case_001_single_turn.jsonl"
+        case = load_case_from_jsonl(str(path))
+        assert case.name == "single_turn_text"
+        assert len(case.events) > 0
+        assert len(case.memory_writes) > 0
+
+    def test_roundtrip_case_to_jsonl(self, fixtures_dir):
+        """Saving and reloading a case should produce identical data."""
+        from tests.sessions.replay_consistency.cases import _replay_cases, save_case_to_jsonl, load_case_from_jsonl
+        import tempfile
+        for case in _replay_cases():
+            with tempfile.NamedTemporaryFile(
+                mode="w", suffix=".jsonl", delete=False
+            ) as f:
+                save_case_to_jsonl(case, f.name)
+                f.flush()
+                reloaded = load_case_from_jsonl(f.name)
+            assert reloaded.name == case.name
+            assert reloaded.session_id == case.session_id
+            assert len(reloaded.events) == len(case.events)
+            os.unlink(f.name)
+
+    def test_jsonl_format_is_valid_json(self, fixtures_dir):
+        """Each line in JSONL must be valid JSON."""
+        for path in fixtures_dir.glob("case_*.jsonl"):
+            with open(path, "r", encoding="utf-8") as f:
+                for i, line in enumerate(f, 1):
+                    line = line.strip()
+                    if not line:
+                        continue
+                    try:
+                        json.loads(line)
+                    except json.JSONDecodeError as e:
+                        pytest.fail(
+                            f"{path.name}:{i} invalid JSON: {e}"
+                        )
