fix: route gateway images by session model override

(cherry picked from commit 7702071c01)

gateway/run.py

@@ -10035,7 +10035,10 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
             if image_paths:
                 # Decide routing: native (attach pixels) vs text (vision_analyze
                 # pre-run + prepend description).  See agent/image_routing.py.
-                _img_mode = self._decide_image_input_mode()
+                _img_mode = self._decide_image_input_mode(
+                    source=source,
+                    session_key=session_key,
+                )
                 if _img_mode == "native":
                     # Defer attachment to the run_conversation call site.
                     pending_native = getattr(self, "_pending_native_image_paths_by_session", None)
@@ -14381,25 +14384,62 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
         except TypeError:
             executor.shutdown(wait=False)
 
-    def _decide_image_input_mode(self) -> str:
-        """Resolve the image-input routing for the currently active model.
+    def _decide_image_input_mode(
+        self,
+        *,
+        source: Optional[SessionSource] = None,
+        session_key: Optional[str] = None,
+        user_config: Optional[dict] = None,
+        provider: Optional[str] = None,
+        model: Optional[str] = None,
+    ) -> str:
+        """Resolve image-input routing for the effective model this turn.
 
         Returns ``"native"`` (attach pixels on the user turn) or ``"text"``
         (pre-analyze with vision_analyze and prepend the description). See
         agent/image_routing.py for the full decision table.
 
-        The active provider/model are read from config.yaml so the decision
-        tracks ``/model`` switches automatically on the next message.
+        Gateway sessions can have /model overrides that live outside
+        config.yaml. Image preprocessing runs before AIAgent sets the
+        auxiliary_client runtime globals, so resolve the same per-session
+        runtime bundle the upcoming agent turn will use instead of consulting
+        only the persisted default model.
         """
         try:
             from agent.image_routing import decide_image_input_mode
             from agent.auxiliary_client import _read_main_model, _read_main_provider
             from hermes_cli.config import load_config
 
-            cfg = load_config()
-            provider = _read_main_provider()
-            model = _read_main_model()
-            return decide_image_input_mode(provider, model, cfg)
+            cfg = user_config if isinstance(user_config, dict) else load_config()
+            resolved_provider = (provider or "").strip()
+            resolved_model = (model or "").strip()
+
+            needs_session_runtime = not resolved_provider or not resolved_model
+            has_session_identity = source is not None or session_key
+            if needs_session_runtime and has_session_identity:
+                try:
+                    turn_model, runtime_kwargs = self._resolve_session_agent_runtime(
+                        source=source,
+                        session_key=session_key,
+                        user_config=cfg,
+                    )
+                    if not resolved_model and isinstance(turn_model, str):
+                        resolved_model = turn_model.strip()
+                    runtime_provider = runtime_kwargs.get("provider") if isinstance(runtime_kwargs, dict) else None
+                    if not resolved_provider and isinstance(runtime_provider, str):
+                        resolved_provider = runtime_provider.strip()
+                except Exception as exc:
+                    logger.debug(
+                        "image_routing: session runtime resolution failed, falling back to config — %s",
+                        exc,
+                    )
+
+            if not resolved_provider:
+                resolved_provider = _read_main_provider()
+            if not resolved_model:
+                resolved_model = _read_main_model()
+
+            return decide_image_input_mode(resolved_provider, resolved_model, cfg)
         except Exception as exc:
             logger.debug("image_routing: decision failed, falling back to text — %s", exc)
             return "text"

tests/gateway/test_image_input_routing_runtime.py

@@ -0,0 +1,140 @@
+import pytest
+
+from gateway.config import GatewayConfig, Platform, PlatformConfig
+from gateway.platforms.base import MessageEvent, MessageType
+from gateway.run import GatewayRunner
+from gateway.session import SessionSource
+
+
+def _make_runner() -> GatewayRunner:
+    runner = object.__new__(GatewayRunner)
+    runner.config = GatewayConfig(
+        platforms={Platform.TELEGRAM: PlatformConfig(enabled=True, token="fake")}
+    )
+    runner.adapters = {}
+    runner._pending_native_image_paths_by_session = {}
+    runner._session_model_overrides = {}
+    runner._session_reasoning_overrides = {}
+    return runner
+
+
+def _source() -> SessionSource:
+    return SessionSource(
+        platform=Platform.TELEGRAM,
+        chat_id="273403055",
+        chat_type="dm",
+        user_id="42",
+        user_name="Maxim",
+    )
+
+
+def _image_event(text: str = "look") -> MessageEvent:
+    return MessageEvent(
+        text=text,
+        message_type=MessageType.PHOTO,
+        source=_source(),
+        media_urls=["/tmp/cashback.png"],
+        media_types=["image/png"],
+    )
+
+
+def _auto_config() -> dict:
+    return {
+        "agent": {"image_input_mode": "auto"},
+        "auxiliary": {"vision": {"provider": "auto", "model": "", "base_url": ""}},
+        "model": {"provider": "xiaomi", "default": "mimo-v2.5-pro"},
+    }
+
+
+@pytest.mark.asyncio
+async def test_prepare_image_routing_uses_session_vision_model_override(monkeypatch):
+    """Telegram /model overrides must affect native-vs-text image routing.
+
+    Regression: _prepare_inbound_message_text used config.yaml's default model
+    before the per-session model override was installed on auxiliary_client's
+    runtime globals. A Telegram session switched to a vision model still had
+    screenshots pre-analyzed as text when config.default was text-only.
+    """
+    runner = _make_runner()
+    source = _source()
+    event = _image_event()
+    cfg = _auto_config()
+
+    monkeypatch.setattr("gateway.run._load_gateway_config", lambda: cfg)
+    monkeypatch.setattr("hermes_cli.config.load_config", lambda: cfg)
+    monkeypatch.setattr("agent.auxiliary_client._read_main_provider", lambda: "xiaomi")
+    monkeypatch.setattr("agent.auxiliary_client._read_main_model", lambda: "mimo-v2.5-pro")
+    monkeypatch.setattr(
+        runner,
+        "_resolve_session_agent_runtime",
+        lambda **_: ("gpt-5.5", {"provider": "openai-codex"}),
+    )
+
+    def fake_supports(provider, model, config):
+        return provider == "openai-codex" and model == "gpt-5.5"
+
+    monkeypatch.setattr("agent.image_routing._lookup_supports_vision", fake_supports)
+
+    async def fail_enrich(*_args, **_kwargs):
+        pytest.fail("vision-capable session override should use native image routing")
+
+    monkeypatch.setattr(runner, "_enrich_message_with_vision", fail_enrich)
+
+    result = await runner._prepare_inbound_message_text(
+        event=event,
+        source=source,
+        history=[],
+    )
+
+    session_key = runner._session_key_for_source(source)
+    assert result == "look"
+    assert runner._pending_native_image_paths_by_session[session_key] == [
+        "/tmp/cashback.png"
+    ]
+
+
+@pytest.mark.asyncio
+async def test_prepare_image_routing_falls_back_to_text_for_text_only_session_override(monkeypatch):
+    """A text-only session override should get vision_analyze text fallback.
+
+    Regression mirror case: if config.default is a vision model but the current
+    Telegram session is switched to a text-only provider (for example Mimo),
+    auto routing must not attach pixels natively to the text-only model.
+    """
+    runner = _make_runner()
+    source = _source()
+    event = _image_event()
+    cfg = _auto_config()
+    cfg["model"] = {"provider": "openai-codex", "default": "gpt-5.5"}
+
+    monkeypatch.setattr("gateway.run._load_gateway_config", lambda: cfg)
+    monkeypatch.setattr("hermes_cli.config.load_config", lambda: cfg)
+    monkeypatch.setattr("agent.auxiliary_client._read_main_provider", lambda: "openai-codex")
+    monkeypatch.setattr("agent.auxiliary_client._read_main_model", lambda: "gpt-5.5")
+    monkeypatch.setattr(
+        runner,
+        "_resolve_session_agent_runtime",
+        lambda **_: ("mimo-v2.5-pro", {"provider": "xiaomi"}),
+    )
+
+    def fake_supports(provider, model, config):
+        return provider == "openai-codex" and model == "gpt-5.5"
+
+    monkeypatch.setattr("agent.image_routing._lookup_supports_vision", fake_supports)
+
+    async def fake_enrich(user_text, image_paths):
+        assert user_text == "look"
+        assert image_paths == ["/tmp/cashback.png"]
+        return "[vision summary]\n\nlook"
+
+    monkeypatch.setattr(runner, "_enrich_message_with_vision", fake_enrich)
+
+    result = await runner._prepare_inbound_message_text(
+        event=event,
+        source=source,
+        history=[],
+    )
+
+    session_key = runner._session_key_for_source(source)
+    assert result == "[vision summary]\n\nlook"
+    assert runner._pending_native_image_paths_by_session.get(session_key) is None

tests/gateway/test_native_image_buffer_isolation.py

@@ -14,7 +14,7 @@ def _make_runner() -> GatewayRunner:
     runner.adapters = {}
     runner._model = "openai/gpt-4.1-mini"
     runner._base_url = None
-    runner._decide_image_input_mode = lambda: "native"
+    runner._decide_image_input_mode = lambda **_: "native"
     return runner