fix(execution): match only replies that mean the model takes no images

strix/core/execution.py

@@ -6,6 +6,7 @@ import asyncio
 import contextlib
 import inspect
 import logging
+import re
 import uuid
 from collections.abc import Callable
 from dataclasses import replace
@@ -57,6 +58,16 @@ logger = logging.getLogger(__name__)
 StreamEventSink = Callable[[str, Any], None]
 
 _INPUT_REJECTION_CODES = frozenset({400, 404, 422})
+# Replies meaning "this model takes no images", not image errors in general: a
+# context overflow that counts "image/vision expansion" must not match.
+_IMAGE_REJECTION = re.compile(
+    r"no endpoints found that support image input"  # OpenRouter
+    r"|image_url is only supported by certain models"  # OpenAI
+    r"|is not a multimodal model|at most 0 image\(s\)"  # vLLM
+    r"|does not support image input"  # LiteLLM's Fireworks check
+    r"|doesn't support the image field",  # Bedrock Converse
+    re.IGNORECASE,
+)
 _MAX_COMPACTIONS_PER_CYCLE = 2
 
 
@@ -157,7 +168,9 @@ def _model_error_status_code(exc: BaseException) -> int | None:
 
 
 def _is_image_rejection(exc: BaseException) -> bool:
-    return _model_error_status_code(exc) in _INPUT_REJECTION_CODES and "image" in str(exc).lower()
+    return _model_error_status_code(exc) in _INPUT_REJECTION_CODES and bool(
+        _IMAGE_REJECTION.search(str(exc))
+    )
 
 
 def _is_transient_model_error(exc: BaseException) -> bool:

tests/test_execution_transient_retry.py

@@ -175,6 +175,41 @@ async def test_run_cycle_does_not_retry_permanent_error(
         await _run_once(monkeypatch, streams)
 
 
+@pytest.mark.parametrize(
+    ("status", "message", "expected"),
+    [
+        (
+            404,
+            "litellm.NotFoundError: NotFoundError: OpenrouterException - "
+            '{"error":{"message":"No endpoints found that support image input","code":404,'
+            '"metadata":{"failed_routing_step":"Filter by Image Support"}}}',
+            True,
+        ),
+        (400, "Invalid content type. image_url is only supported by certain models.", True),
+        (400, "my-model is not a multimodal model", True),
+        (400, "This model doesn't support the image field for user messages.", True),
+        (
+            400,
+            "OpenRouterException: Message: This model's maximum context length is 1048576 "
+            "tokens, but the request requires 1073484 tokens (942412 input including "
+            "image/vision expansion + 131072 for the completion). Reduce the input length "
+            "or max_tokens.",
+            False,
+        ),
+        (400, "At most 5 image(s) may be provided in one prompt.", False),
+        (
+            400,
+            "Upstream error from Relace: Generation stopped with an incomplete tool call",
+            False,
+        ),
+        (500, "No endpoints found that support image input", False),
+    ],
+)
+def test_is_image_rejection(status: int, message: str, expected: bool) -> None:
+    exc = APIStatusError(message, response=httpx.Response(status, request=_request()), body=None)
+    assert execution._is_image_rejection(exc) is expected
+
+
 async def _run_with_image_session(
     monkeypatch: pytest.MonkeyPatch, streams: list[_FakeStream]
 ) -> tuple[Any, int, int]:
@@ -208,20 +243,3 @@ async def test_run_cycle_strips_images_on_image_rejection(
     assert result is streams[1]
     assert attempts == 2
     assert strips == 1
-
-
-@pytest.mark.asyncio
-async def test_run_cycle_does_not_strip_images_on_unrelated_client_error(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    bad_request = BadRequestError(
-        "Upstream error from Relace: Generation stopped with an incomplete tool call",
-        response=httpx.Response(400, request=_request()),
-        body=None,
-    )
-    streams = [_FakeStream(exc=bad_request), _FakeStream()]
-    result, attempts, strips = await _run_with_image_session(monkeypatch, streams)
-
-    assert result is streams[1]
-    assert attempts == 2
-    assert strips == 0