fix(dsl): handle citation contexts without source text

CHANGELOG.md

@@ -10,6 +10,7 @@ Versioning: [Semantic Versioning](https://semver.org/spec/v2.0.0.html)
 ## [Unreleased]
 
 ### Fixed
+- **Citation validation**: Preserve LLM-provided citations when a validation context does not include source text, instead of raising a `TypeError`.
 - **v2 message handling**: Preserve caller-owned message lists and nested content across request preparation and retries for OpenAI-compatible, Cohere, Mistral, OpenRouter, Writer, and xAI handlers. ([#2417](https://github.com/567-labs/instructor/issues/2417), [#2428](https://github.com/567-labs/instructor/issues/2428))
 - **v2 JSON extraction**: Prefer the final complete top-level JSON value in text responses and retain every JSON object when multiple objects arrive in one streaming chunk.
 - **v2 schemas**: Treat fields with Pydantic `default_factory` values as optional in generated OpenAI tool schemas.

instructor/v2/dsl/citation.py

@@ -68,6 +68,8 @@ def validate_sources(self, info: ValidationInfo) -> "CitationMixin":
 
         # Get the context from the info
         text_chunks = info.context.get("context", None)
+        if text_chunks is None:
+            return self
 
         # Get the spans of the substring_phrase in the context
         spans = list(self.get_spans(text_chunks))

tests/coverage/test_dsl_small_coverage.py

@@ -46,6 +46,17 @@ def test_citation_keeps_quotes_without_context_and_recovers_fuzzy_quotes() -> No
     assert list(cited.get_spans(context)) == [(21, 42)]
 
 
+def test_citation_keeps_quotes_when_validation_context_lacks_context_key() -> None:
+    quotes = ["Jaxon is 20 years old"]
+
+    cited = Claim.model_validate(
+        {"fact": "age", "substring_quotes": quotes},
+        context={"request_id": "req_123"},
+    )
+
+    assert cited.substring_quotes == quotes
+
+
 @pytest.mark.parametrize(
     ("value", "complete"),
     [("", False), ("  \n\t", False), ('{"ok": true}', True), ('{"ok":', False)],