fix(exa): fall back to highlights/summary when text is missing (#42213)

* fix(exa): fall back to highlights/summary when text is missing (#36905)

* test: type exa search transformation test helpers

* test(exa): drop type: ignore in test helper and trim redundant comments

* test(exa): move snippet fallback test to tests/unit and parametrize it

Uses a real httpx.Response instead of a Mock and annotates snippet as Final.

* fix(exa): inline snippet fallback since Final is not allowed inside a loop

---------

Co-authored-by: ryan-crabbe-berri <ryan@berri.ai>

litellm/llms/exa_ai/search/transformation.py

@@ -165,6 +165,8 @@ class ExaAISearchConfig(BaseSearchConfig):
         - results[].title → SearchResult.title
         - results[].url → SearchResult.url
         - results[].text → SearchResult.snippet
+        - results[].highlights → SearchResult.snippet (fallback when "text" is absent)
+        - results[].summary → SearchResult.snippet (fallback when "text" and "highlights" are absent)
         - results[].publishedDate → SearchResult.date
         - No last_updated field in Exa AI response (set to None)
 
@@ -183,7 +185,10 @@ class ExaAISearchConfig(BaseSearchConfig):
             search_result = SearchResult(
                 title=result.get("title", ""),
                 url=result.get("url", ""),
-                snippet=result.get("text", ""),  # Exa AI uses "text" for content
+                snippet=result.get("text")
+                or "\n\n".join(result.get("highlights") or [])
+                or result.get("summary")
+                or "",
                 date=result.get("publishedDate"),  # ISO 8601 datetime string
                 last_updated=None,  # Exa AI doesn't provide last_updated in response
             )

tests/unit/llms/exa_ai/search/test_transformation.py

@@ -0,0 +1,33 @@
+from typing import Final
+from unittest.mock import Mock
+
+import httpx
+import pytest
+
+from litellm.llms.exa_ai.search.transformation import ExaAISearchConfig
+
+
+@pytest.mark.parametrize(
+    ("content_fields", "expected_snippet"),
+    [
+        ({"text": "full text"}, "full text"),
+        ({"highlights": ["first highlight", "second highlight"]}, "first highlight\n\nsecond highlight"),
+        ({"summary": "a summary"}, "a summary"),
+        ({"text": "full text", "highlights": ["a highlight"], "summary": "a summary"}, "full text"),
+        ({"highlights": ["a highlight"], "summary": "a summary"}, "a highlight"),
+        ({"text": "", "highlights": ["a highlight"]}, "a highlight"),
+        ({"highlights": [], "summary": "a summary"}, "a summary"),
+        ({}, ""),
+    ],
+)
+def test_transform_search_response_snippet_falls_back_through_content_modes(
+    content_fields: dict[str, str | list[str]], expected_snippet: str
+):
+    raw_response: Final = httpx.Response(
+        200,
+        json={"results": [{"title": "Title", "url": "https://example.com", **content_fields}]},
+    )
+
+    response: Final = ExaAISearchConfig().transform_search_response(raw_response, logging_obj=Mock())
+
+    assert response.results[0].snippet == expected_snippet