refactor: LangGraph gateway layer for UI-agnostic graph and thread access (#295)

* feat(gateway): graph gateway protocol

* refactor(cli): wire gateway in cli/tui

* refactor(gateway): centralize runtime gateway init

* chore(gateway): restrict RunRequest message type

* feat(gateway): add langgraph server gateway

* chore(cli): tighten serve runtime state typing

* refactor(cli): route async task state reads through graph gateway

* refactor(gateway): support graph targets in server gateway

* refactor(cli): route session commands through graph gateway

* refactor(cli): fold thread store under graph gateway

* refactor(gateway): route graph state access through gateway

* refactor(channels): wire graph gateway

* refactor(memory): preserve graph threads for cloning

* feat(gateway): add thread cloning

* fix(tui): pass effective workspace for thread creation

* chore(memory): add workspare dir to memory worker metadata

* fix(sessions): filter preloaded UUID registy entries by the current scope

* test(fakes): use https

* refactor(consumer): consolidate imports

* fix(stream): optional summarization event

* fix(gateway): resolve abbreviated thread IDs by search

* fix(gateway): page server thread listings

* fix(gateway): emit pending interrupt events

* style: fmt

* feat(gateway): persist workspace_dir & model in thread metadata

* fix(gateway): page server thread prefix resolution

* fix(gateway): expose server thread list metadata

* refactor: add back type def

* refactor: tighten types

* revert: add back worker thread deletion

The worker thread forking changes are out of scope for now, so to
maintain parity with the existing behavior we'll leave this intact.

* fix(gateway): apply compaction to server thread history

* refactor(stream): restore direct summary replay suppression

* fix(gateway): preserve compaction state and server stream output

* fix(gateway): close local stream generator on cancellation

---------

Co-authored-by: Xi Zhang <106144707+X-iZhang@users.noreply.github.com>

tests/test_threads_command.py

@@ -1,10 +1,11 @@
 """Tests for the /threads command."""
 
-from unittest.mock import AsyncMock, MagicMock, patch
+from unittest.mock import MagicMock
 
 from rich.table import Table
 
 from tests.conftest import run_async as _run
+from tests.fakes import FakeGraphGateway, FakeThreadStore
 
 
 def _ctx(**overrides):
@@ -12,11 +13,13 @@ def _ctx(**overrides):
 
     ui = MagicMock()
     ui.supports_interactive = overrides.pop("supports_interactive", True)
+    store = overrides.pop("thread_store", FakeThreadStore())
     return CommandContext(
         agent=None,
         thread_id=overrides.pop("thread_id", "tid-1"),
         ui=ui,
         workspace_dir=overrides.pop("workspace_dir", "/ws"),
+        graph_gateway=FakeGraphGateway(thread_store=store),
     ), ui
 
 
@@ -25,11 +28,7 @@ class TestThreadsCommand:
         from EvoScientist.commands.implementation.session import ThreadsCommand
 
         ctx, ui = _ctx()
-        with patch(
-            "EvoScientist.sessions.list_threads",
-            new=AsyncMock(return_value=[]),
-        ):
-            _run(ThreadsCommand().execute(ctx, []))
+        _run(ThreadsCommand().execute(ctx, []))
         ui.append_system.assert_called_once()
         assert "No saved sessions" in ui.append_system.call_args.args[0]
 
@@ -53,11 +52,9 @@ class TestThreadsCommand:
                 "updated_at": None,
             },
         ]
-        with patch(
-            "EvoScientist.sessions.list_threads",
-            new=AsyncMock(return_value=threads),
-        ):
-            _run(ThreadsCommand().execute(ctx, []))
+        store = FakeThreadStore(threads=threads)
+        ctx.graph_gateway = FakeGraphGateway(thread_store=store)
+        _run(ThreadsCommand().execute(ctx, []))
         ui.mount_renderable.assert_called_once()
         table = ui.mount_renderable.call_args.args[0]
         assert isinstance(table, Table)
@@ -81,11 +78,9 @@ class TestThreadsCommand:
                 "updated_at": None,
             }
         ]
-        with patch(
-            "EvoScientist.sessions.list_threads",
-            new=AsyncMock(return_value=threads),
-        ):
-            _run(ThreadsCommand().execute(ctx, []))
+        store = FakeThreadStore(threads=threads)
+        ctx.graph_gateway = FakeGraphGateway(thread_store=store)
+        _run(ThreadsCommand().execute(ctx, []))
         ui.append_system.assert_not_called()
 
     def test_channel_mode_drops_model_column(self):
@@ -102,11 +97,9 @@ class TestThreadsCommand:
                 "updated_at": None,
             }
         ]
-        with patch(
-            "EvoScientist.sessions.list_threads",
-            new=AsyncMock(return_value=threads),
-        ):
-            _run(ThreadsCommand().execute(ctx, []))
+        store = FakeThreadStore(threads=threads)
+        ctx.graph_gateway = FakeGraphGateway(thread_store=store)
+        _run(ThreadsCommand().execute(ctx, []))
         # Channel mode: no Model column. 4 columns: ID, Preview, Msgs, Last Used.
         table = ui.mount_renderable.call_args.args[0]
         column_headers = [col.header for col in table.columns]