fix(gateway): isolate telegram forum topic sessions

tests/gateway/test_session_hygiene.py

@@ -8,9 +8,19 @@ The hygiene system uses the SAME compression config as the agent:
 so CLI and messaging platforms behave identically.
 """
 
-import pytest
+import importlib
+import sys
+import types
+from datetime import datetime
+from types import SimpleNamespace
 from unittest.mock import patch, MagicMock, AsyncMock
+
+import pytest
+
 from agent.model_metadata import estimate_messages_tokens_rough
+from gateway.config import GatewayConfig, Platform, PlatformConfig
+from gateway.platforms.base import BasePlatformAdapter, MessageEvent, SendResult
+from gateway.session import SessionEntry, SessionSource
 
 
 # ---------------------------------------------------------------------------
@@ -41,6 +51,32 @@ def _make_large_history_tokens(target_tokens: int) -> list:
     return _make_history(n_msgs, content_size=content_size)
 
 
+class HygieneCaptureAdapter(BasePlatformAdapter):
+    def __init__(self):
+        super().__init__(PlatformConfig(enabled=True, token="fake-token"), Platform.TELEGRAM)
+        self.sent = []
+
+    async def connect(self) -> bool:
+        return True
+
+    async def disconnect(self) -> None:
+        return None
+
+    async def send(self, chat_id, content, reply_to=None, metadata=None) -> SendResult:
+        self.sent.append(
+            {
+                "chat_id": chat_id,
+                "content": content,
+                "reply_to": reply_to,
+                "metadata": metadata,
+            }
+        )
+        return SendResult(success=True, message_id="hygiene-1")
+
+    async def get_chat_info(self, chat_id: str):
+        return {"id": chat_id}
+
+
 # ---------------------------------------------------------------------------
 # Detection threshold tests (model-aware, unified with compression config)
 # ---------------------------------------------------------------------------
@@ -202,3 +238,90 @@ class TestTokenEstimation:
         # Should be well above the 170K threshold for a 200k model
         threshold = int(200_000 * 0.85)
         assert tokens > threshold
+
+
+@pytest.mark.asyncio
+async def test_session_hygiene_messages_stay_in_originating_topic(monkeypatch, tmp_path):
+    fake_dotenv = types.ModuleType("dotenv")
+    fake_dotenv.load_dotenv = lambda *args, **kwargs: None
+    monkeypatch.setitem(sys.modules, "dotenv", fake_dotenv)
+
+    class FakeCompressAgent:
+        def __init__(self, **kwargs):
+            self.model = kwargs.get("model")
+
+        def _compress_context(self, messages, *_args, **_kwargs):
+            return ([{"role": "assistant", "content": "compressed"}], None)
+
+    fake_run_agent = types.ModuleType("run_agent")
+    fake_run_agent.AIAgent = FakeCompressAgent
+    monkeypatch.setitem(sys.modules, "run_agent", fake_run_agent)
+
+    gateway_run = importlib.import_module("gateway.run")
+    GatewayRunner = gateway_run.GatewayRunner
+
+    adapter = HygieneCaptureAdapter()
+    runner = object.__new__(GatewayRunner)
+    runner.config = GatewayConfig(
+        platforms={Platform.TELEGRAM: PlatformConfig(enabled=True, token="fake-token")}
+    )
+    runner.adapters = {Platform.TELEGRAM: adapter}
+    runner.hooks = SimpleNamespace(emit=AsyncMock(), loaded_hooks=False)
+    runner.session_store = MagicMock()
+    runner.session_store.get_or_create_session.return_value = SessionEntry(
+        session_key="agent:main:telegram:group:-1001:17585",
+        session_id="sess-1",
+        created_at=datetime.now(),
+        updated_at=datetime.now(),
+        platform=Platform.TELEGRAM,
+        chat_type="group",
+    )
+    runner.session_store.load_transcript.return_value = _make_history(6, content_size=400)
+    runner.session_store.has_any_sessions.return_value = True
+    runner.session_store.rewrite_transcript = MagicMock()
+    runner.session_store.append_to_transcript = MagicMock()
+    runner._running_agents = {}
+    runner._pending_messages = {}
+    runner._pending_approvals = {}
+    runner._session_db = None
+    runner._is_user_authorized = lambda _source: True
+    runner._set_session_env = lambda _context: None
+    runner._run_agent = AsyncMock(
+        return_value={
+            "final_response": "ok",
+            "messages": [],
+            "tools": [],
+            "history_offset": 0,
+            "last_prompt_tokens": 0,
+        }
+    )
+
+    monkeypatch.setattr(gateway_run, "_hermes_home", tmp_path)
+    monkeypatch.setattr(gateway_run, "_resolve_runtime_agent_kwargs", lambda: {"api_key": "fake"})
+    monkeypatch.setattr(
+        "agent.model_metadata.get_model_context_length",
+        lambda *_args, **_kwargs: 100,
+    )
+    monkeypatch.setenv("TELEGRAM_HOME_CHANNEL", "795544298")
+
+    event = MessageEvent(
+        text="hello",
+        source=SessionSource(
+            platform=Platform.TELEGRAM,
+            chat_id="-1001",
+            chat_type="group",
+            thread_id="17585",
+        ),
+        message_id="1",
+    )
+
+    result = await runner._handle_message(event)
+
+    assert result == "ok"
+    assert len(adapter.sent) == 2
+    assert adapter.sent[0]["chat_id"] == "-1001"
+    assert "Session is large" in adapter.sent[0]["content"]
+    assert adapter.sent[0]["metadata"] == {"thread_id": "17585"}
+    assert adapter.sent[1]["chat_id"] == "-1001"
+    assert "Compressed:" in adapter.sent[1]["content"]
+    assert adapter.sent[1]["metadata"] == {"thread_id": "17585"}