test_protocol.py

"""Tests for tui_gateway JSON-RPC protocol plumbing."""

import io
import json
import sys
import threading
import time
import types
from unittest.mock import MagicMock, patch

import pytest

_original_stdout = sys.stdout


@pytest.fixture(autouse=True)
def _restore_stdout():
    yield
    sys.stdout = _original_stdout


@pytest.fixture()
def server():
    with patch.dict("sys.modules", {
        "hermes_constants": MagicMock(get_hermes_home=MagicMock(return_value="/tmp/hermes_test")),
        "hermes_cli.env_loader": MagicMock(),
        "hermes_cli.banner": MagicMock(),
        "hermes_state": MagicMock(),
    }):
        import importlib
        mod = importlib.import_module("tui_gateway.server")
        yield mod
        mod._sessions.clear()
        mod._pending.clear()
        mod._answers.clear()
        mod._methods.clear()
        importlib.reload(mod)


@pytest.fixture()
def capture(server):
    """Redirect server's real stdout to a StringIO and return (server, buf)."""
    buf = io.StringIO()
    server._real_stdout = buf
    return server, buf


# ── JSON-RPC envelope ────────────────────────────────────────────────


def test_unknown_method(server):
    resp = server.handle_request({"id": "1", "method": "bogus"})
    assert resp["error"]["code"] == -32601


def test_ok_envelope(server):
    assert server._ok("r1", {"x": 1}) == {
        "jsonrpc": "2.0", "id": "r1", "result": {"x": 1},
    }


def test_err_envelope(server):
    assert server._err("r2", 4001, "nope") == {
        "jsonrpc": "2.0", "id": "r2", "error": {"code": 4001, "message": "nope"},
    }


# ── write_json ───────────────────────────────────────────────────────


def test_write_json(capture):
    server, buf = capture
    assert server.write_json({"test": True})
    assert json.loads(buf.getvalue()) == {"test": True}


def test_write_json_broken_pipe(server):
    class _Broken:
        def write(self, _): raise BrokenPipeError
        def flush(self): raise BrokenPipeError

    server._real_stdout = _Broken()
    assert server.write_json({"x": 1}) is False


def test_write_json_closed_stream_returns_false(server):
    """ValueError ('I/O on closed file') used to bubble up; treat as gone."""

    class _Closed:
        def write(self, _): raise ValueError("I/O operation on closed file")
        def flush(self): raise ValueError("I/O operation on closed file")

    server._real_stdout = _Closed()
    assert server.write_json({"x": 1}) is False


def test_write_json_unicode_encode_error_re_raises(server):
    """A non-UTF-8 stdout encoding raises UnicodeEncodeError (a ValueError
    subclass).  It must NOT be swallowed as 'peer gone' — that would let
    `entry.py` exit cleanly via the False path and hide the real config
    bug.  We re-raise so the existing crash-log infrastructure records it."""

    class _AsciiOnly:
        def write(self, line):
            line.encode("ascii")  # raises UnicodeEncodeError on non-ascii
        def flush(self): pass

    server._real_stdout = _AsciiOnly()
    with pytest.raises(UnicodeEncodeError):
        server.write_json({"msg": "héllo"})


def test_write_json_unrelated_value_error_re_raises(server):
    """Only ValueError('...closed file...') means peer gone.  Other
    ValueErrors are programming errors and must surface."""

    class _BadValue:
        def write(self, _): raise ValueError("something else entirely")
        def flush(self): pass

    server._real_stdout = _BadValue()
    with pytest.raises(ValueError, match="something else entirely"):
        server.write_json({"x": 1})


def test_write_json_non_serializable_payload_re_raises(server):
    """Non-JSON-safe payloads are programming errors — they must NOT be
    silently dropped via the False path (which would trigger a clean exit
    in entry.py and mask the real bug)."""
    import io

    server._real_stdout = io.StringIO()
    with pytest.raises(TypeError):
        server.write_json({"obj": object()})


def test_write_json_peer_gone_oserror_on_flush_returns_false(server):
    """A flush that raises a peer-gone OSError (EPIPE) must not strand
    the lock or crash; it returns False so the dispatcher exits cleanly."""
    import errno

    written = []

    class _FlushPeerGone:
        def write(self, line): written.append(line)
        def flush(self): raise OSError(errno.EPIPE, "broken pipe")

    server._real_stdout = _FlushPeerGone()
    assert server.write_json({"x": 1}) is False
    assert written and json.loads(written[0]) == {"x": 1}


def test_write_json_non_peer_gone_oserror_re_raises(server):
    """Host I/O failures (ENOSPC, EACCES, EIO …) are NOT peer-gone — they
    must re-raise so the crash log records them instead of looking like
    a clean disconnect via the False path."""
    import errno

    class _DiskFull:
        def write(self, _): raise OSError(errno.ENOSPC, "no space left")
        def flush(self): pass

    server._real_stdout = _DiskFull()
    with pytest.raises(OSError, match="no space"):
        server.write_json({"x": 1})


def test_write_json_skips_flush_when_disable_flush_true(monkeypatch):
    """`StdioTransport` skips flush when `_DISABLE_FLUSH` is true.

    Tests the runtime *behaviour* via direct module-attr patch.  The env
    var → module constant wiring is covered by the dedicated env test
    below; reloading server.py here would re-register atexit hooks and
    recreate the worker pool.
    """
    import importlib

    transport_mod = importlib.import_module("tui_gateway.transport")
    monkeypatch.setattr(transport_mod, "_DISABLE_FLUSH", True)

    flushed = {"count": 0}
    written = []

    class _Stream:
        def write(self, line): written.append(line)
        def flush(self): flushed["count"] += 1

    stream = _Stream()
    transport = transport_mod.StdioTransport(lambda: stream, threading.Lock())

    assert transport.write({"x": 1}) is True
    assert flushed["count"] == 0


def test_disable_flush_env_var_actually_wires_to_module_constant(monkeypatch):
    """End-to-end: setting `HERMES_TUI_GATEWAY_NO_FLUSH=1` and importing
    `tui_gateway.transport` fresh actually flips `_DISABLE_FLUSH` true.

    Reloads only the transport module — server.py is untouched so its
    atexit hooks/worker pool stay intact."""
    import importlib

    monkeypatch.setenv("HERMES_TUI_GATEWAY_NO_FLUSH", "1")
    transport_mod = importlib.reload(importlib.import_module("tui_gateway.transport"))

    try:
        assert transport_mod._DISABLE_FLUSH is True
    finally:
        # Restore the env-disabled state so other tests see the default.
        monkeypatch.delenv("HERMES_TUI_GATEWAY_NO_FLUSH", raising=False)
        importlib.reload(transport_mod)


# ── _emit ────────────────────────────────────────────────────────────


def test_emit_with_payload(capture):
    server, buf = capture
    server._emit("test.event", "s1", {"key": "val"})
    msg = json.loads(buf.getvalue())

    assert msg["method"] == "event"
    assert msg["params"]["type"] == "test.event"
    assert msg["params"]["session_id"] == "s1"
    assert msg["params"]["payload"]["key"] == "val"


def test_emit_without_payload(capture):
    server, buf = capture
    server._emit("ping", "s2")

    assert "payload" not in json.loads(buf.getvalue())["params"]


# ── Blocking prompt round-trip ───────────────────────────────────────


def test_block_and_respond(capture):
    server, _ = capture
    result = [None]

    threading.Thread(
        target=lambda: result.__setitem__(0, server._block("test.prompt", "s1", {"q": "?"}, timeout=5)),
    ).start()

    for _ in range(100):
        if server._pending:
            break
        threading.Event().wait(0.01)

    rid = next(iter(server._pending))
    server._answers[rid] = "my_answer"
    # _pending values are (sid, Event) tuples — unpack to set the Event
    _, ev = server._pending[rid]
    ev.set()

    threading.Event().wait(0.1)
    assert result[0] == "my_answer"


def test_clear_pending(server):
    ev = threading.Event()
    # _pending values are (sid, Event) tuples
    server._pending["r1"] = ("sid-x", ev)
    server._clear_pending()

    assert ev.is_set()
    assert server._answers["r1"] == ""


# ── Session lookup ───────────────────────────────────────────────────


def test_sess_missing(server):
    _, err = server._sess({"session_id": "nope"}, "r1")
    assert err["error"]["code"] == 4001


def test_sess_found(server):
    server._sessions["abc"] = {"agent": MagicMock()}
    s, err = server._sess({"session_id": "abc"}, "r1")

    assert s is not None
    assert err is None


# ── session.resume payload ────────────────────────────────────────────


def test_session_resume_returns_hydrated_messages(server, monkeypatch):
    class _DB:
        def get_session(self, _sid):
            return {"id": "20260409_010101_abc123"}

        def get_session_by_title(self, _title):
            return None

        def reopen_session(self, _sid):
            return None

        def get_messages_as_conversation(self, _sid, include_ancestors=False):
            return [
                {"role": "user", "content": "hello"},
                {"role": "assistant", "content": "yo"},
                {"role": "tool", "content": "searched"},
                {"role": "assistant", "content": "   "},
                {"role": "assistant", "content": None},
                {"role": "narrator", "content": "skip"},
            ]

    monkeypatch.setattr(server, "_get_db", lambda: _DB())
    monkeypatch.setattr(server, "_make_agent", lambda sid, key, session_id=None: object())
    monkeypatch.setattr(server, "_init_session", lambda sid, key, agent, history, cols=80: None)
    monkeypatch.setattr(server, "_session_info", lambda _agent: {"model": "test/model"})

    resp = server.handle_request(
        {
            "id": "r1",
            "method": "session.resume",
            "params": {"session_id": "20260409_010101_abc123", "cols": 100},
        }
    )

    assert "error" not in resp
    assert resp["result"]["message_count"] == 3
    assert resp["result"]["messages"] == [
        {"role": "user", "text": "hello"},
        {"role": "assistant", "text": "yo"},
        {"role": "tool", "name": "tool", "context": ""},
    ]


# ── Config I/O ───────────────────────────────────────────────────────


def test_config_load_missing(server, tmp_path):
    server._hermes_home = tmp_path
    assert server._load_cfg() == {}


def test_config_roundtrip(server, tmp_path):
    server._hermes_home = tmp_path
    server._save_cfg({"model": "test/model"})
    assert server._load_cfg()["model"] == "test/model"


# ── _cli_exec_blocked ────────────────────────────────────────────────


@pytest.mark.parametrize("argv", [
    [],
    ["setup"],
    ["gateway"],
    ["sessions", "browse"],
    ["config", "edit"],
])
def test_cli_exec_blocked(server, argv):
    assert server._cli_exec_blocked(argv) is not None


@pytest.mark.parametrize("argv", [
    ["version"],
    ["sessions", "list"],
])
def test_cli_exec_allowed(server, argv):
    assert server._cli_exec_blocked(argv) is None


# ── slash.exec skill command interception ────────────────────────────


def test_slash_exec_rejects_skill_commands(server):
    """slash.exec must reject skill commands so the TUI falls through to command.dispatch."""
    # Register a mock session
    sid = "test-session"
    server._sessions[sid] = {"session_key": sid, "agent": None}

    # Mock scan_skill_commands to return a known skill
    fake_skills = {"/hermes-agent-dev": {"name": "hermes-agent-dev", "description": "Dev workflow"}}

    with patch("agent.skill_commands.get_skill_commands", return_value=fake_skills):
        resp = server.handle_request({
            "id": "r1",
            "method": "slash.exec",
            "params": {"command": "hermes-agent-dev", "session_id": sid},
        })

    # Should return an error so the TUI's .catch() fires command.dispatch
    assert "error" in resp
    assert resp["error"]["code"] == 4018
    assert "skill command" in resp["error"]["message"]


def test_slash_exec_handles_plugin_commands_in_live_gateway(server):
    """Plugin slash commands return normal slash.exec output without using the worker."""
    sid = "test-session"

    class Worker:
        def __init__(self):
            self.calls = []

        def run(self, cmd):
            self.calls.append(cmd)
            return f"worker:{cmd}"

    worker = Worker()
    server._sessions[sid] = {"session_key": sid, "agent": None, "slash_worker": worker}

    with patch(
        "hermes_cli.plugins.get_plugin_command_handler",
        lambda name: (lambda arg: f"plugin:{arg}") if name == "plugin-cmd" else None,
    ):
        resp = server.handle_request({
            "id": "r-plugin-slash",
            "method": "slash.exec",
            "params": {"command": "plugin-cmd hello", "session_id": sid},
        })

    assert "error" not in resp
    assert resp["result"] == {"output": "plugin:hello"}
    assert worker.calls == []


def test_slash_exec_plugin_lookup_failure_falls_back_to_worker(server):
    """Plugin discovery failures must not break ordinary slash-worker commands."""
    sid = "test-session"

    class Worker:
        def __init__(self):
            self.calls = []

        def run(self, cmd):
            self.calls.append(cmd)
            return f"worker:{cmd}"

    worker = Worker()
    server._sessions[sid] = {"session_key": sid, "agent": None, "slash_worker": worker}

    with patch(
        "hermes_cli.plugins.get_plugin_command_handler",
        side_effect=RuntimeError("discovery boom"),
    ):
        resp = server.handle_request({
            "id": "r-plugin-lookup-failure",
            "method": "slash.exec",
            "params": {"command": "help", "session_id": sid},
        })

    assert "error" not in resp
    assert resp["result"] == {"output": "worker:help"}
    assert worker.calls == ["help"]


def test_slash_exec_plugin_handler_error_returns_output(server):
    """Plugin handler failures return slash output so the TUI does not redispatch."""
    sid = "test-session"

    class Worker:
        def __init__(self):
            self.calls = []

        def run(self, cmd):
            self.calls.append(cmd)
            return f"worker:{cmd}"

    def handler(arg):
        raise RuntimeError(f"handler boom: {arg}")

    worker = Worker()
    server._sessions[sid] = {"session_key": sid, "agent": None, "slash_worker": worker}

    with patch(
        "hermes_cli.plugins.get_plugin_command_handler",
        lambda name: handler if name == "plugin-cmd" else None,
    ):
        resp = server.handle_request({
            "id": "r-plugin-handler-error",
            "method": "slash.exec",
            "params": {"command": "plugin-cmd hello", "session_id": sid},
        })

    assert "error" not in resp
    assert resp["result"] == {"output": "Plugin command error: handler boom: hello"}
    assert worker.calls == []


@pytest.mark.parametrize("cmd", ["retry", "queue hello", "q hello", "steer fix the test", "plan"])
def test_slash_exec_rejects_pending_input_commands(server, cmd):
    """slash.exec must reject commands that use _pending_input in the CLI."""
    sid = "test-session"
    server._sessions[sid] = {"session_key": sid, "agent": None}

    resp = server.handle_request({
        "id": "r1",
        "method": "slash.exec",
        "params": {"command": cmd, "session_id": sid},
    })

    assert "error" in resp
    assert resp["error"]["code"] == 4018
    assert "pending-input command" in resp["error"]["message"]


def test_command_dispatch_queue_sends_message(server):
    """command.dispatch /queue returns {type: 'send', message: ...} for the TUI."""
    sid = "test-session"
    server._sessions[sid] = {"session_key": sid}

    resp = server.handle_request({
        "id": "r1",
        "method": "command.dispatch",
        "params": {"name": "queue", "arg": "tell me about quantum computing", "session_id": sid},
    })

    assert "error" not in resp
    result = resp["result"]
    assert result["type"] == "send"
    assert result["message"] == "tell me about quantum computing"


def test_command_dispatch_queue_requires_arg(server):
    """command.dispatch /queue without an argument returns an error."""
    sid = "test-session"
    server._sessions[sid] = {"session_key": sid}

    resp = server.handle_request({
        "id": "r2",
        "method": "command.dispatch",
        "params": {"name": "queue", "arg": "", "session_id": sid},
    })

    assert "error" in resp
    assert resp["error"]["code"] == 4004


def test_skills_manage_search_uses_tools_hub_sources(server):
    result = type("Result", (), {
        "description": "Build better terminal demos",
        "name": "showroom",
    })()
    auth = MagicMock(return_value="auth")
    router = MagicMock(return_value=["source"])
    search = MagicMock(return_value=[result])
    fake_hub = types.SimpleNamespace(
        GitHubAuth=auth,
        create_source_router=router,
        unified_search=search,
    )

    with patch.dict(sys.modules, {"tools.skills_hub": fake_hub}):
        resp = server.handle_request({
            "id": "skills-search",
            "method": "skills.manage",
            "params": {"action": "search", "query": "showroom"},
        })

    assert "error" not in resp
    assert resp["result"] == {
        "results": [{"description": "Build better terminal demos", "name": "showroom"}]
    }
    auth.assert_called_once_with()
    router.assert_called_once_with("auth")
    search.assert_called_once_with("showroom", ["source"], source_filter="all", limit=20)


def test_command_dispatch_steer_fallback_sends_message(server):
    """command.dispatch /steer with no active agent falls back to send."""
    sid = "test-session"
    server._sessions[sid] = {"session_key": sid, "agent": None}

    resp = server.handle_request({
        "id": "r3",
        "method": "command.dispatch",
        "params": {"name": "steer", "arg": "focus on testing", "session_id": sid},
    })

    assert "error" not in resp
    result = resp["result"]
    assert result["type"] == "send"
    assert result["message"] == "focus on testing"


def test_command_dispatch_retry_finds_last_user_message(server):
    """command.dispatch /retry walks session['history'] to find the last user message."""
    sid = "test-session"
    history = [
        {"role": "user", "content": "first question"},
        {"role": "assistant", "content": "first answer"},
        {"role": "user", "content": "second question"},
        {"role": "assistant", "content": "second answer"},
    ]
    server._sessions[sid] = {
        "session_key": sid,
        "agent": None,
        "history": history,
        "history_lock": threading.Lock(),
        "history_version": 0,
    }

    resp = server.handle_request({
        "id": "r4",
        "method": "command.dispatch",
        "params": {"name": "retry", "session_id": sid},
    })

    assert "error" not in resp
    result = resp["result"]
    assert result["type"] == "send"
    assert result["message"] == "second question"
    # Verify history was truncated: everything from last user message onward removed
    assert len(server._sessions[sid]["history"]) == 2
    assert server._sessions[sid]["history"][-1]["role"] == "assistant"
    assert server._sessions[sid]["history_version"] == 1


def test_command_dispatch_retry_empty_history(server):
    """command.dispatch /retry with empty history returns error."""
    sid = "test-session"
    server._sessions[sid] = {
        "session_key": sid,
        "agent": None,
        "history": [],
        "history_lock": threading.Lock(),
        "history_version": 0,
    }

    resp = server.handle_request({
        "id": "r5",
        "method": "command.dispatch",
        "params": {"name": "retry", "session_id": sid},
    })

    assert "error" in resp
    assert resp["error"]["code"] == 4018


def test_command_dispatch_retry_handles_multipart_content(server):
    """command.dispatch /retry extracts text from multipart content lists."""
    sid = "test-session"
    history = [
        {"role": "user", "content": [
            {"type": "text", "text": "analyze this"},
            {"type": "image_url", "image_url": {"url": "data:image/png;base64,..."}}
        ]},
        {"role": "assistant", "content": "I see the image."},
    ]
    server._sessions[sid] = {
        "session_key": sid,
        "agent": None,
        "history": history,
        "history_lock": threading.Lock(),
        "history_version": 0,
    }

    resp = server.handle_request({
        "id": "r6",
        "method": "command.dispatch",
        "params": {"name": "retry", "session_id": sid},
    })

    assert "error" not in resp
    result = resp["result"]
    assert result["type"] == "send"
    assert result["message"] == "analyze this"


def test_command_dispatch_returns_skill_payload(server):
    """command.dispatch returns structured skill payload for the TUI to send()."""
    sid = "test-session"
    server._sessions[sid] = {"session_key": sid}

    fake_skills = {"/hermes-agent-dev": {"name": "hermes-agent-dev", "description": "Dev workflow"}}
    fake_msg = "Loaded skill content here"

    with patch("agent.skill_commands.scan_skill_commands", return_value=fake_skills), \
         patch("agent.skill_commands.build_skill_invocation_message", return_value=fake_msg):
        resp = server.handle_request({
            "id": "r2",
            "method": "command.dispatch",
            "params": {"name": "hermes-agent-dev", "session_id": sid},
        })

    assert "error" not in resp
    result = resp["result"]
    assert result["type"] == "skill"
    assert result["message"] == fake_msg
    assert result["name"] == "hermes-agent-dev"


def test_command_dispatch_awaits_async_plugin_handler(server):
    async def _handler(arg):
        return f"async:{arg}"

    with patch(
        "hermes_cli.plugins.get_plugin_command_handler",
        lambda name: _handler if name == "async-cmd" else None,
    ):
        resp = server.handle_request({
            "id": "r-plugin",
            "method": "command.dispatch",
            "params": {"name": "async-cmd", "arg": "hello"},
        })

    assert "error" not in resp
    assert resp["result"] == {"type": "plugin", "output": "async:hello"}


# ── dispatch(): pool routing for long handlers (#12546) ──────────────


def test_dispatch_runs_short_handlers_inline(server):
    """Non-long handlers return their response synchronously from dispatch()."""
    server._methods["fast.ping"] = lambda rid, params: server._ok(rid, {"pong": True})

    resp = server.dispatch({"id": "r1", "method": "fast.ping", "params": {}})

    assert resp == {"jsonrpc": "2.0", "id": "r1", "result": {"pong": True}}


def test_dispatch_offloads_long_handlers_and_emits_via_stdout(capture):
    """Long handlers run on the pool and write their response via write_json."""
    server, buf = capture
    server._methods["slash.exec"] = lambda rid, params: server._ok(rid, {"output": "hi"})

    resp = server.dispatch({"id": "r2", "method": "slash.exec", "params": {}})
    assert resp is None

    for _ in range(50):
        if buf.getvalue():
            break
        time.sleep(0.01)

    written = json.loads(buf.getvalue())
    assert written == {"jsonrpc": "2.0", "id": "r2", "result": {"output": "hi"}}


def test_dispatch_long_handler_does_not_block_fast_handler(server):
    """A slow long handler must not prevent a concurrent fast handler from completing."""
    released = threading.Event()
    server._methods["slash.exec"] = lambda rid, params: (released.wait(timeout=5), server._ok(rid, {"done": True}))[1]
    server._methods["fast.ping"] = lambda rid, params: server._ok(rid, {"pong": True})

    t0 = time.monotonic()
    assert server.dispatch({"id": "slow", "method": "slash.exec", "params": {}}) is None

    fast_resp = server.dispatch({"id": "fast", "method": "fast.ping", "params": {}})
    fast_elapsed = time.monotonic() - t0

    assert fast_resp["result"] == {"pong": True}
    assert fast_elapsed < 0.5, f"fast handler blocked for {fast_elapsed:.2f}s behind slow handler"

    released.set()


def test_dispatch_session_compress_does_not_block_fast_handler(server):
    """Manual TUI compaction can take minutes, so it must not block the RPC loop."""
    released = threading.Event()

    def slow_compress(rid, params):
        released.wait(timeout=5)
        return server._ok(rid, {"done": True})

    server._methods["session.compress"] = slow_compress
    server._methods["fast.ping"] = lambda rid, params: server._ok(rid, {"pong": True})

    t0 = time.monotonic()
    assert server.dispatch({"id": "slow", "method": "session.compress", "params": {}}) is None

    fast_resp = server.dispatch({"id": "fast", "method": "fast.ping", "params": {}})
    fast_elapsed = time.monotonic() - t0

    assert fast_resp["result"] == {"pong": True}
    assert fast_elapsed < 0.5, f"fast handler blocked for {fast_elapsed:.2f}s behind session.compress"

    released.set()


def test_dispatch_long_handler_exception_produces_error_response(capture):
    """An exception inside a pool-dispatched handler still yields a JSON-RPC error."""
    server, buf = capture

    def boom(rid, params):
        raise RuntimeError("kaboom")

    server._methods["slash.exec"] = boom

    server.dispatch({"id": "r3", "method": "slash.exec", "params": {}})

    for _ in range(50):
        if buf.getvalue():
            break
        time.sleep(0.01)

    written = json.loads(buf.getvalue())
    assert written["id"] == "r3"
    assert written["error"]["code"] == -32000
    assert "kaboom" in written["error"]["message"]


def test_dispatch_unknown_long_method_still_goes_inline(server):
    """Method name not in _LONG_HANDLERS takes the sync path even if handler is slow."""
    server._methods["some.method"] = lambda rid, params: server._ok(rid, {"ok": True})

    resp = server.dispatch({"id": "r4", "method": "some.method", "params": {}})

    assert resp["result"] == {"ok": True}