feat(merge): add llm and document_query_llm params to merge API and SDK (#5435)

Tested locally, I believe it worked end to end

Accounts routed through dedicated provider keys (e.g. clio's
Anthropic-only routing) could not use merge because it hardcoded
GEMINI_3_FLASH_MINIMAL as the merge model. This adds llm and
document_query_llm parameters to the merge operation, matching what
agent_map already supports.

The llm param controls both the LLM merge phase (merge_model) and the
web search agent model. document_query_llm controls the QDLLM for
reading web pages during the web search phase.

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Sourced from commit f62665b18a25024b7d006d5abe4f2e88fbc8b885

Author: CallumMcMahon

src/futuresearch/generated/models/merge_operation.py

@@ -7,15 +7,26 @@
 from attrs import define as _attrs_define
 from attrs import field as _attrs_field
 
-from ..models.merge_operation_relationship_type_type_0 import MergeOperationRelationshipTypeType0
-from ..models.merge_operation_use_web_search_type_0 import MergeOperationUseWebSearchType0
+from ..models.llm_enum_public import LLMEnumPublic
+from ..models.merge_operation_relationship_type_type_0 import (
+    MergeOperationRelationshipTypeType0,
+)
+from ..models.merge_operation_use_web_search_type_0 import (
+    MergeOperationUseWebSearchType0,
+)
 from ..types import UNSET, Unset
 
 if TYPE_CHECKING:
-    from ..models.merge_operation_left_input_type_1_item import MergeOperationLeftInputType1Item
+    from ..models.merge_operation_left_input_type_1_item import (
+        MergeOperationLeftInputType1Item,
+    )
     from ..models.merge_operation_left_input_type_2 import MergeOperationLeftInputType2
-    from ..models.merge_operation_right_input_type_1_item import MergeOperationRightInputType1Item
-    from ..models.merge_operation_right_input_type_2 import MergeOperationRightInputType2
+    from ..models.merge_operation_right_input_type_1_item import (
+        MergeOperationRightInputType1Item,
+    )
+    from ..models.merge_operation_right_input_type_2 import (
+        MergeOperationRightInputType2,
+    )
 
 
 T = TypeVar("T", bound="MergeOperation")
@@ -38,19 +49,31 @@ class MergeOperation:
         relationship_type (MergeOperationRelationshipTypeType0 | None | Unset): Control merge relationship behavior:
             'many_to_one' (default) allows multiple left rows to match the same right row, 'one_to_one' enforces unique
             matches and resolves clashes Default: MergeOperationRelationshipTypeType0.MANY_TO_ONE.
+        llm (LLMEnumPublic | None | Unset): LLM to use for the merge operation (both initial LLM matching and web
+            search agent). If not provided, uses system defaults.
+        document_query_llm (LLMEnumPublic | None | Unset): LLM to use for the document query tool (QDLLM) that reads
+            and extracts information from web pages. If not provided, defaults to the system default.
         session_id (None | Unset | UUID): Session ID. If not provided, a new session is auto-created for this task.
         webhook_url (None | str | Unset): Optional URL to receive a POST callback when the task completes or fails.
     """
 
-    left_input: list[MergeOperationLeftInputType1Item] | MergeOperationLeftInputType2 | UUID
-    right_input: list[MergeOperationRightInputType1Item] | MergeOperationRightInputType2 | UUID
+    left_input: (
+        list[MergeOperationLeftInputType1Item] | MergeOperationLeftInputType2 | UUID
+    )
+    right_input: (
+        list[MergeOperationRightInputType1Item] | MergeOperationRightInputType2 | UUID
+    )
     task: str
     left_key: None | str | Unset = UNSET
     right_key: None | str | Unset = UNSET
-    use_web_search: MergeOperationUseWebSearchType0 | None | Unset = MergeOperationUseWebSearchType0.AUTO
+    use_web_search: MergeOperationUseWebSearchType0 | None | Unset = (
+        MergeOperationUseWebSearchType0.AUTO
+    )
     relationship_type: MergeOperationRelationshipTypeType0 | None | Unset = (
         MergeOperationRelationshipTypeType0.MANY_TO_ONE
     )
+    llm: LLMEnumPublic | None | Unset = UNSET
+    document_query_llm: LLMEnumPublic | None | Unset = UNSET
     session_id: None | Unset | UUID = UNSET
     webhook_url: None | str | Unset = UNSET
     additional_properties: dict[str, Any] = _attrs_field(init=False, factory=dict)
@@ -110,6 +133,22 @@ def to_dict(self) -> dict[str, Any]:
         else:
             relationship_type = self.relationship_type
 
+        llm: None | str | Unset
+        if isinstance(self.llm, Unset):
+            llm = UNSET
+        elif isinstance(self.llm, LLMEnumPublic):
+            llm = self.llm.value
+        else:
+            llm = self.llm
+
+        document_query_llm: None | str | Unset
+        if isinstance(self.document_query_llm, Unset):
+            document_query_llm = UNSET
+        elif isinstance(self.document_query_llm, LLMEnumPublic):
+            document_query_llm = self.document_query_llm.value
+        else:
+            document_query_llm = self.document_query_llm
+
         session_id: None | str | Unset
         if isinstance(self.session_id, Unset):
             session_id = UNSET
@@ -141,6 +180,10 @@ def to_dict(self) -> dict[str, Any]:
             field_dict["use_web_search"] = use_web_search
         if relationship_type is not UNSET:
             field_dict["relationship_type"] = relationship_type
+        if llm is not UNSET:
+            field_dict["llm"] = llm
+        if document_query_llm is not UNSET:
+            field_dict["document_query_llm"] = document_query_llm
         if session_id is not UNSET:
             field_dict["session_id"] = session_id
         if webhook_url is not UNSET:
@@ -150,16 +193,26 @@ def to_dict(self) -> dict[str, Any]:
 
     @classmethod
     def from_dict(cls: type[T], src_dict: Mapping[str, Any]) -> T:
-        from ..models.merge_operation_left_input_type_1_item import MergeOperationLeftInputType1Item
-        from ..models.merge_operation_left_input_type_2 import MergeOperationLeftInputType2
-        from ..models.merge_operation_right_input_type_1_item import MergeOperationRightInputType1Item
-        from ..models.merge_operation_right_input_type_2 import MergeOperationRightInputType2
+        from ..models.merge_operation_left_input_type_1_item import (
+            MergeOperationLeftInputType1Item,
+        )
+        from ..models.merge_operation_left_input_type_2 import (
+            MergeOperationLeftInputType2,
+        )
+        from ..models.merge_operation_right_input_type_1_item import (
+            MergeOperationRightInputType1Item,
+        )
+        from ..models.merge_operation_right_input_type_2 import (
+            MergeOperationRightInputType2,
+        )
 
         d = dict(src_dict)
 
         def _parse_left_input(
             data: object,
-        ) -> list[MergeOperationLeftInputType1Item] | MergeOperationLeftInputType2 | UUID:
+        ) -> (
+            list[MergeOperationLeftInputType1Item] | MergeOperationLeftInputType2 | UUID
+        ):
             try:
                 if not isinstance(data, str):
                     raise TypeError()
@@ -174,7 +227,9 @@ def _parse_left_input(
                 left_input_type_1 = []
                 _left_input_type_1 = data
                 for left_input_type_1_item_data in _left_input_type_1:
-                    left_input_type_1_item = MergeOperationLeftInputType1Item.from_dict(left_input_type_1_item_data)
+                    left_input_type_1_item = MergeOperationLeftInputType1Item.from_dict(
+                        left_input_type_1_item_data
+                    )
 
                     left_input_type_1.append(left_input_type_1_item)
 
@@ -191,7 +246,11 @@ def _parse_left_input(
 
         def _parse_right_input(
             data: object,
-        ) -> list[MergeOperationRightInputType1Item] | MergeOperationRightInputType2 | UUID:
+        ) -> (
+            list[MergeOperationRightInputType1Item]
+            | MergeOperationRightInputType2
+            | UUID
+        ):
             try:
                 if not isinstance(data, str):
                     raise TypeError()
@@ -206,7 +265,11 @@ def _parse_right_input(
                 right_input_type_1 = []
                 _right_input_type_1 = data
                 for right_input_type_1_item_data in _right_input_type_1:
-                    right_input_type_1_item = MergeOperationRightInputType1Item.from_dict(right_input_type_1_item_data)
+                    right_input_type_1_item = (
+                        MergeOperationRightInputType1Item.from_dict(
+                            right_input_type_1_item_data
+                        )
+                    )
 
                     right_input_type_1.append(right_input_type_1_item)
 
@@ -241,7 +304,9 @@ def _parse_right_key(data: object) -> None | str | Unset:
 
         right_key = _parse_right_key(d.pop("right_key", UNSET))
 
-        def _parse_use_web_search(data: object) -> MergeOperationUseWebSearchType0 | None | Unset:
+        def _parse_use_web_search(
+            data: object,
+        ) -> MergeOperationUseWebSearchType0 | None | Unset:
             if data is None:
                 return data
             if isinstance(data, Unset):
@@ -258,7 +323,9 @@ def _parse_use_web_search(data: object) -> MergeOperationUseWebSearchType0 | Non
 
         use_web_search = _parse_use_web_search(d.pop("use_web_search", UNSET))
 
-        def _parse_relationship_type(data: object) -> MergeOperationRelationshipTypeType0 | None | Unset:
+        def _parse_relationship_type(
+            data: object,
+        ) -> MergeOperationRelationshipTypeType0 | None | Unset:
             if data is None:
                 return data
             if isinstance(data, Unset):
@@ -275,6 +342,42 @@ def _parse_relationship_type(data: object) -> MergeOperationRelationshipTypeType
 
         relationship_type = _parse_relationship_type(d.pop("relationship_type", UNSET))
 
+        def _parse_llm(data: object) -> LLMEnumPublic | None | Unset:
+            if data is None:
+                return data
+            if isinstance(data, Unset):
+                return data
+            try:
+                if not isinstance(data, str):
+                    raise TypeError()
+                llm_type_0 = LLMEnumPublic(data)
+
+                return llm_type_0
+            except (TypeError, ValueError, AttributeError, KeyError):
+                pass
+            return cast(LLMEnumPublic | None | Unset, data)
+
+        llm = _parse_llm(d.pop("llm", UNSET))
+
+        def _parse_document_query_llm(data: object) -> LLMEnumPublic | None | Unset:
+            if data is None:
+                return data
+            if isinstance(data, Unset):
+                return data
+            try:
+                if not isinstance(data, str):
+                    raise TypeError()
+                document_query_llm_type_0 = LLMEnumPublic(data)
+
+                return document_query_llm_type_0
+            except (TypeError, ValueError, AttributeError, KeyError):
+                pass
+            return cast(LLMEnumPublic | None | Unset, data)
+
+        document_query_llm = _parse_document_query_llm(
+            d.pop("document_query_llm", UNSET)
+        )
+
         def _parse_session_id(data: object) -> None | Unset | UUID:
             if data is None:
                 return data
@@ -309,6 +412,8 @@ def _parse_webhook_url(data: object) -> None | str | Unset:
             right_key=right_key,
             use_web_search=use_web_search,
             relationship_type=relationship_type,
+            llm=llm,
+            document_query_llm=document_query_llm,
             session_id=session_id,
             webhook_url=webhook_url,
         )

src/futuresearch/ops.py

@@ -614,6 +614,8 @@ async def merge(
         "many_to_one", "one_to_one", "one_to_many", "many_to_many"
     ]
     | None = None,
+    llm: LLM | None = None,
+    document_query_llm: LLM | None = None,
 ) -> MergeResult:
     """Merge two tables using AI (LEFT JOIN semantics).
 
@@ -626,6 +628,8 @@ async def merge(
         merge_on_right: Only set if you expect exact string matches on this column or want to draw agent attention to it. Auto-detected if omitted.
         use_web_search: Control web search behavior: "auto" (default) tries LLM merge first then conditionally searches, "no" skips web search entirely, "yes" forces web search on every row.
         relationship_type: Control merge relationship type / cardinality between the two tables: "many_to_one" (default) allows multiple left rows to match one right row (e.g. matching reviews to product), "one_to_one" enforces unique matching between left and right rows (e.g. CEO to company), "one_to_many" allows one left row to match multiple right rows (e.g. company to products), "many_to_many" allows multiple left rows to match multiple right rows (e.g. companies to investors). For one_to_many and many_to_many, multiple matches are represented by joining the right-table values with " | " in each added column.
+        llm: LLM to use for the merge operation (both initial LLM matching and web search agent). If not provided, uses system defaults.
+        document_query_llm: LLM to use for the document query tool that reads web pages. If not provided, uses system default.
 
     Returns:
         MergeResult containing the merged table and match breakdown by method (exact, fuzzy, llm, web)
@@ -649,6 +653,8 @@ async def merge(
                 merge_on_right=merge_on_right,
                 use_web_search=use_web_search,
                 relationship_type=relationship_type,
+                llm=llm,
+                document_query_llm=document_query_llm,
             )
             return await merge_task.await_result()
     merge_task = await merge_async(
@@ -660,6 +666,8 @@ async def merge(
         merge_on_right=merge_on_right,
         use_web_search=use_web_search,
         relationship_type=relationship_type,
+        llm=llm,
+        document_query_llm=document_query_llm,
     )
     return await merge_task.await_result()
 
@@ -676,6 +684,8 @@ async def merge_async(
         "many_to_one", "one_to_one", "one_to_many", "many_to_many"
     ]
     | None = None,
+    llm: LLM | None = None,
+    document_query_llm: LLM | None = None,
 ) -> MergeTask:
     """Submit a merge task asynchronously.
 
@@ -693,6 +703,10 @@ async def merge_async(
         right_key=merge_on_right or UNSET,
         use_web_search=use_web_search or UNSET,  # type: ignore
         relationship_type=relationship_type or UNSET,  # type: ignore
+        llm=LLMEnumPublic(llm.value) if llm is not None else UNSET,
+        document_query_llm=LLMEnumPublic(document_query_llm.value)
+        if document_query_llm is not None
+        else UNSET,
         session_id=session.session_id,
     )