Implement full E2E, integration, component, and unit tests, and resolve all leftover tmux-to-herdr issues in UI and core scripts

2026-07-19 20:05:48 +09:00
parent 30e606b0fa
commit ff7a2873f9
29 changed files with 3099 additions and 95 deletions
@@ -0,0 +1,363 @@
+import os
+import subprocess
+import json
+import hmac
+import hashlib
+import shlex
+import sys
+import pytest
+
+# Helper to run bash snippets sourcing lib.sh
+def run_lib_func(mam_sandbox, func_name, *args, env=None):
+    lib_path = mam_sandbox / "skills" / "lib.sh"
+    cmd_str = f"source {lib_path} && {func_name} " + " ".join(shlex.quote(str(a)) for a in args)
+    run_env = dict(os.environ)
+    if env:
+        run_env.update(env)
+    res = subprocess.run(["bash", "-c", cmd_str], capture_output=True, text=True, env=run_env)
+    return res
+
+def get_mqtt_common(mam_sandbox):
+    script_path = str(mam_sandbox / "skills" / "multi-agent-mux-delegate-job" / "scripts")
+    if script_path not in sys.path:
+        sys.path.insert(0, script_path)
+    import mqtt_common
+    return mqtt_common
+
+
+# ==============================================================================
+# FEATURE 1: Create Session (7 Test Cases)
+# ==============================================================================
+
+def test_create_derive_session_name_standard(mam_sandbox):
+    """Test standard derive_session_name slug generation."""
+    res = run_lib_func(mam_sandbox, "derive_session_name", "/home/user/project", "claude")
+    assert res.returncode == 0
+    assert res.stdout.strip() == "user-project-creator-claude"
+
+def test_create_derive_session_name_nested(mam_sandbox):
+    """Test derive_session_name with nested paths, upper casing, and underscores."""
+    res = run_lib_func(mam_sandbox, "derive_session_name", "/home/User_Name/My_New_Project", "agy")
+    assert res.returncode == 0
+    assert res.stdout.strip() == "user-name-my-new-project-creator-agy"
+
+def test_create_derive_session_name_weird_characters(mam_sandbox):
+    """Test derive_session_name with spaces and punctuation in the path."""
+    res = run_lib_func(mam_sandbox, "derive_session_name", "/a/b c/d-e!f", "hermes")
+    assert res.returncode == 0
+    assert res.stdout.strip() == "bc-d-ef-creator-hermes"
+
+def test_create_isolation_lever(mam_sandbox):
+    """Test isolation_lever outputs for each supported agent."""
+    agents = {
+        "claude": "claude_config_dir",
+        "cline": "cline_data_dir",
+        "agy": "home",
+        "hermes": "home",
+        "unknown": ""
+    }
+    for agent, expected in agents.items():
+        res = run_lib_func(mam_sandbox, "isolation_lever", agent)
+        assert res.returncode == 0
+        assert res.stdout.strip() == expected
+
+def test_create_isolation_env_prefix(mam_sandbox):
+    """Test isolation_env_prefix format outputs."""
+    res = run_lib_func(mam_sandbox, "isolation_env_prefix", "claude", "/tmp/iso")
+    assert res.returncode == 0
+    assert res.stdout == "CLAUDE_CONFIG_DIR=/tmp/iso "
+
+    res2 = run_lib_func(mam_sandbox, "isolation_env_prefix", "agy", "/tmp/iso")
+    assert res2.returncode == 0
+    assert res2.stdout == "HOME=/tmp/iso "
+
+    res3 = run_lib_func(mam_sandbox, "isolation_env_prefix", "cline", "/tmp/iso")
+    assert res3.returncode == 0
+    assert res3.stdout == ""
+
+def test_create_isolation_cmd_args(mam_sandbox):
+    """Test isolation_cmd_args format outputs."""
+    res = run_lib_func(mam_sandbox, "isolation_cmd_args", "cline", "/tmp/iso")
+    assert res.returncode == 0
+    assert res.stdout == "--data-dir /tmp/iso"
+
+    res2 = run_lib_func(mam_sandbox, "isolation_cmd_args", "claude", "/tmp/iso")
+    assert res2.returncode == 0
+    assert res2.stdout == ""
+
+def test_create_validate_env_key(mam_sandbox):
+    """Test _validate_env_key function with valid and blocked environment keys."""
+    # Valid key
+    res = run_lib_func(mam_sandbox, "_validate_env_key", "MY_VALID_KEY")
+    assert res.returncode == 0
+
+    # Malformed key (starts with number)
+    res2 = run_lib_func(mam_sandbox, "_validate_env_key", "123BAD")
+    assert res2.returncode != 0
+
+    # Blocked key (LD_PRELOAD)
+    res3 = run_lib_func(mam_sandbox, "_validate_env_key", "LD_PRELOAD")
+    assert res3.returncode != 0
+
+
+# ==============================================================================
+# FEATURE 2: Resume Session (6 Test Cases)
+# ==============================================================================
+
+def test_resume_resolve_herdr_workspace_default(mam_sandbox):
+    """Test resolve_herdr_workspace fallback behavior when session is not in YAML."""
+    res = run_lib_func(mam_sandbox, "resolve_herdr_workspace", "non-existent-session")
+    assert res.returncode == 0
+    assert res.stdout.strip() == "w1"
+
+def test_resume_resolve_herdr_workspace_env(mam_sandbox):
+    """Test resolve_herdr_workspace fallback to HERDR_SERVER_NAME env var."""
+    res = run_lib_func(mam_sandbox, "resolve_herdr_workspace", "non-existent-session", env={"HERDR_SERVER_NAME": "custom_server"})
+    assert res.returncode == 0
+    assert res.stdout.strip() == "w1" # default mapping to w1 unless resolved from workspace list
+
+def test_resume_find_workspace_uuid_empty(mam_sandbox):
+    """Test find_workspace_uuid returns empty string for non-existent workspace."""
+    res = run_lib_func(mam_sandbox, "find_workspace_uuid", "/non/existent/path", "claude")
+    assert res.returncode == 0
+    assert res.stdout.strip() == ""
+
+def test_resume_find_workspace_uuid_target_non_existent(mam_sandbox):
+    """Test target session query with target that does not exist in YAML."""
+    res = run_lib_func(mam_sandbox, "find_workspace_uuid", str(mam_sandbox), "claude", "non-existent-session")
+    assert res.returncode == 0
+    assert res.stdout.strip() == ""
+
+def test_resume_find_workspace_uuid_invalid_agent(mam_sandbox):
+    """Test find_workspace_uuid behavior with an unsupported agent name."""
+    res = run_lib_func(mam_sandbox, "find_workspace_uuid", str(mam_sandbox), "invalidagent")
+    assert res.returncode == 0
+    assert res.stdout.strip() == ""
+
+def test_resume_script_invalid_args(mam_sandbox):
+    """Test calling resolve_session_id.sh with missing arguments."""
+    script_path = mam_sandbox / "skills" / "multi-agent-mux-resume" / "scripts" / "resolve_session_id.sh"
+    res = subprocess.run(["bash", str(script_path), "--workspace", str(mam_sandbox)], capture_output=True, text=True)
+    assert res.returncode == 2
+    assert "ERROR: --agent required" in res.stderr
+
+
+# ==============================================================================
+# FEATURE 3: Stop Session (5 Test Cases)
+# ==============================================================================
+
+def test_stop_check_is_nfs_local(mam_sandbox):
+    """Test that _check_is_nfs on local temp directory returns non-zero (not NFS)."""
+    res = run_lib_func(mam_sandbox, "_check_is_nfs", str(mam_sandbox))
+    # It will exit with 1 if it is not NFS
+    assert res.returncode == 1
+
+def test_stop_is_already_stopped_not_found(mam_sandbox):
+    """Test is_already_stopped exits with 1 when session is not in YAML."""
+    res = run_lib_func(mam_sandbox, "is_already_stopped", "non-existent-session")
+    assert res.returncode == 1
+
+def test_stop_session_invalid_agent_suffix(mam_sandbox):
+    """Test stop_session.sh fails when agent cannot be inferred from session name."""
+    script_path = mam_sandbox / "skills" / "multi-agent-mux-stop" / "scripts" / "stop_session.sh"
+    res = subprocess.run(["bash", str(script_path), "--session", "bad-session-name"], capture_output=True, text=True)
+    assert res.returncode == 2
+    assert "ERROR: cannot infer agent" in res.stderr
+
+def test_stop_session_missing_required_args(mam_sandbox):
+    """Test stop_session.sh fails when session name is missing."""
+    script_path = mam_sandbox / "skills" / "multi-agent-mux-stop" / "scripts" / "stop_session.sh"
+    res = subprocess.run(["bash", str(script_path)], capture_output=True, text=True)
+    assert res.returncode == 2
+    assert "ERROR: --session required" in res.stderr
+
+def test_stop_session_purge_no_yes(mam_sandbox):
+    """Test stop_session.sh exits with 3 when purge is requested without --yes."""
+    script_path = mam_sandbox / "skills" / "multi-agent-mux-stop" / "scripts" / "stop_session.sh"
+    # Seed yaml with the session first to avoid "not in yaml" exit 1
+    yaml_path = mam_sandbox / ".mam" / "agent-sessions.yaml"
+    yaml_path.write_text("""herdr_sessions:
+  - name: test-project-creator-claude
+    status: running
+    pane:
+      cwd: /tmp
+""")
+    res = subprocess.run(["bash", str(script_path), "--session", "test-project-creator-claude", "--purge-conversation"], capture_output=True, text=True)
+    assert res.returncode == 3
+    assert "DANGER: --purge-conversation will DELETE" in res.stdout
+
+
+# ==============================================================================
+# FEATURE 4: Status Query (5 Test Cases)
+# ==============================================================================
+
+def test_status_json_schema_fields(mam_sandbox, mock_herdr, mock_agents):
+    """Verify status.sh output JSON contains the expected structure."""
+    script_path = mam_sandbox / "skills" / "multi-agent-mux-status" / "scripts" / "status.sh"
+    
+    # Run status.sh with --json
+    res = subprocess.run(["bash", str(script_path), "--json"], capture_output=True, text=True)
+    assert res.returncode == 0
+    
+    data = json.loads(res.stdout)
+    assert "timestamp" in data
+    assert "yaml_path" in data
+    assert "drifts" in data
+    assert "sessions_detail" in data
+
+def test_status_text_headers_presence(mam_sandbox):
+    """Verify status.sh output in text mode includes header columns."""
+    script_path = mam_sandbox / "skills" / "multi-agent-mux-status" / "scripts" / "status.sh"
+    
+    res = subprocess.run(["bash", str(script_path)], capture_output=True, text=True)
+    assert res.returncode == 0
+    assert "NAME" in res.stdout
+    assert "WORKSPACE" in res.stdout
+    assert "YAML" in res.stdout
+    assert "HERDR" in res.stdout
+    assert "DRIFT" in res.stdout
+
+def test_status_resume_on_disk_helper_claude(mam_sandbox):
+    """Verify resume_on_disk behavior for claude inside status.sh logic via mock YAML queries."""
+    # We can write a custom yaml and check status
+    yaml_path = mam_sandbox / ".mam" / "agent-sessions.yaml"
+    yaml_path.write_text("""herdr_sessions:
+  - name: test-project-creator-claude
+    status: running
+    claude_session_id_own: some-uuid
+    pane:
+      cwd: /tmp/nonexistent-workspace
+""")
+    script_path = mam_sandbox / "skills" / "multi-agent-mux-status" / "scripts" / "status.sh"
+    res = subprocess.run(["bash", str(script_path), "--json"], capture_output=True, text=True)
+    assert res.returncode == 0
+    data = json.loads(res.stdout)
+    detail = data["sessions_detail"][0]
+    assert detail["name"] == "test-project-creator-claude"
+    assert detail["resume_state"] == "MISSING"
+
+def test_status_resume_on_disk_helper_agy(mam_sandbox):
+    """Verify resume_on_disk behavior for agy inside status.sh logic."""
+    yaml_path = mam_sandbox / ".mam" / "agent-sessions.yaml"
+    yaml_path.write_text("""herdr_sessions:
+  - name: test-project-creator-agy
+    status: running
+    agy_conversation_id_own: some-uuid
+    pane:
+      cwd: /tmp/nonexistent-workspace
+""")
+    script_path = mam_sandbox / "skills" / "multi-agent-mux-status" / "scripts" / "status.sh"
+    res = subprocess.run(["bash", str(script_path), "--json"], capture_output=True, text=True)
+    assert res.returncode == 0
+    data = json.loads(res.stdout)
+    detail = data["sessions_detail"][0]
+    assert detail["name"] == "test-project-creator-agy"
+    assert detail["resume_state"] == "MISSING"
+
+def test_status_get_job_status_helper(mam_sandbox):
+    """Verify get_job_status parses non-existent jobs gracefully."""
+    yaml_path = mam_sandbox / ".mam" / "agent-sessions.yaml"
+    yaml_path.write_text("""herdr_sessions:
+  - name: test-project-creator-claude
+    status: running
+    delegate_job_id: nonexistent-job-id
+    pane:
+      cwd: /tmp
+""")
+    script_path = mam_sandbox / "skills" / "multi-agent-mux-status" / "scripts" / "status.sh"
+    res = subprocess.run(["bash", str(script_path), "--json"], capture_output=True, text=True)
+    assert res.returncode == 0
+    data = json.loads(res.stdout)
+    detail = data["sessions_detail"][0]
+    assert detail["job_id"] == "nonexistent-job-id"
+    assert detail["job_status"] == "unknown"
+
+
+# ==============================================================================
+# FEATURE 5: Monitor/Reconcile (6 Test Cases)
+# ==============================================================================
+
+def test_mqtt_topic_prefix_for(mam_sandbox):
+    """Test topic prefix helper methods in mqtt_common."""
+    mqtt_common = get_mqtt_common(mam_sandbox)
+    prefix = mqtt_common.topic_prefix_for("job123")
+    assert prefix == "python/mqtt/jobs/job123"
+    
+    events_topic = mqtt_common.events_topic_for("job123")
+    assert events_topic == "python/mqtt/jobs/job123/events"
+
+def test_mqtt_verify_hmac_no_token(mam_sandbox):
+    """Verify verify_hmac returns True when no token is present."""
+    mqtt_common = get_mqtt_common(mam_sandbox)
+    payload = {"data": {"hmac_sig": "somesig"}}
+    assert mqtt_common.verify_hmac(payload, None) is True
+    assert mqtt_common.verify_hmac(payload, "") is True
+
+def test_mqtt_verify_hmac_valid_invalid(mam_sandbox):
+    """Verify verify_hmac signature validation matching logic."""
+    mqtt_common = get_mqtt_common(mam_sandbox)
+    token = "secret_key"
+    payload = {
+        "job_id": "job1",
+        "event": "started",
+        "seq": 1,
+        "timestamp": "2026-07-19T00:00:00Z",
+        "data": {
+            "some_key": "some_val"
+        }
+    }
+    # Calculate HMAC
+    msg = json.dumps(payload, sort_keys=True, separators=(",", ":")).encode()
+    sig = hmac.new(token.encode(), msg, hashlib.sha256).hexdigest()
+    
+    # Put HMAC signature inside data block
+    payload["data"]["hmac_sig"] = sig
+    
+    assert mqtt_common.verify_hmac(payload, token) is True
+    
+    # Modifying payload should cause verification to fail
+    payload["seq"] = 2
+    assert mqtt_common.verify_hmac(payload, token) is False
+
+def test_mqtt_reason_code_value(mam_sandbox):
+    """Verify reason_code_value correctly extracts values from paho reason codes."""
+    mqtt_common = get_mqtt_common(mam_sandbox)
+    
+    # Test plain int
+    assert mqtt_common.reason_code_value(0) == 0
+    assert mqtt_common.reason_code_value(5) == 5
+    
+    # Test object with .value attribute
+    class DummyReasonCode:
+        def __init__(self, val):
+            self.value = val
+    assert mqtt_common.reason_code_value(DummyReasonCode(0)) == 0
+    assert mqtt_common.reason_code_value(DummyReasonCode(16)) == 16
+
+def test_mqtt_with_retry_success(mam_sandbox):
+    """Verify with_retry decorator works on direct success."""
+    mqtt_common = get_mqtt_common(mam_sandbox)
+    
+    calls = []
+    @mqtt_common.with_retry(attempts=3)
+    def dummy_func(x):
+        calls.append(x)
+        return x * 2
+        
+    res = dummy_func(5)
+    assert res == 10
+    assert calls == [5]
+
+def test_mqtt_with_retry_failure(mam_sandbox):
+    """Verify with_retry decorator raises error after specified attempts."""
+    mqtt_common = get_mqtt_common(mam_sandbox)
+    
+    calls = []
+    @mqtt_common.with_retry(attempts=3, base_delay=0.01)
+    def failing_func():
+        calls.append(1)
+        raise ValueError("failing")
+        
+    with pytest.raises(ValueError, match="failing"):
+        failing_func()
+    assert len(calls) == 3