feat: Making static prompt values in Rag/File Search configurable in Vector Store Config (#4368)

# What does this PR do?

- Enables users to configure prompts used throughout the File Search /
Vector Retrieval
- Configuration is defined in the Vector Stores Config so they can be
modified at runtime
- Backwards compatible, which means the fields are optional and default
to the previously used values

This is the summary of the new options in the `run.yaml`
```yaml
vector_stores:
  file_search_params:
    header_template: 'knowledge_search tool found {num_chunks} chunks:\nBEGIN of knowledge_search tool results.\n'
    footer_template: 'END of knowledge_search tool results.\n'
  context_prompt_params:
    chunk_annotation_template: 'Result {index}\nContent: {chunk.content}\nMetadata: {metadata}\n'
    context_template: 'The above results were retrieved to help answer the user\'s query: "{query}". Use them as supporting information only in answering this query.{annotation_instruction}\n'
  annotation_prompt_params:
    enable_annotations: true
    annotation_instruction_template: 'Cite sources immediately at the end of sentences before punctuation, using `<|file-id|>` format like \'This is a fact <|file-Cn3MSNn72ENTiiq11Qda4A|>.\'. Do not add
extra punctuation. Use only the file IDs provided, do not invent new ones.'
    chunk_annotation_template: '[{index}] {metadata_text} cite as <|{file_id}|>\n{chunk_text}\n'
```

<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->

## Test Plan
Added tests.

---------

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>

docs/docs/providers/agents/inline_meta-reference.mdx

@@ -15,6 +15,7 @@ Meta's reference implementation of an agent system that can use tools, access ve
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `persistence` | `AgentPersistenceConfig` | No |  |  |
+| `vector_stores_config` | `VectorStoresConfig \| None` | No |  | Configuration for vector store prompt templates and behavior |
 
 ## Sample Configuration
 

docs/docs/providers/tool_runtime/inline_rag-runtime.mdx

@@ -10,6 +10,12 @@ title: inline::rag-runtime
 
 RAG (Retrieval-Augmented Generation) tool runtime for document ingestion, chunking, and semantic search.
 
+## Configuration
+
+| Field | Type | Required | Default | Description |
+|-------|------|----------|---------|-------------|
+| `vector_stores_config` | `VectorStoresConfig` | No | `default_provider_id=None default_embedding_model=None rewrite_query_params=None file_search_params=FileSearchParams(header_template='knowledge_search tool found {num_chunks} chunks:\nBEGIN of knowledge_search tool results.\n', footer_template='END of knowledge_search tool results.\n') context_prompt_params=ContextPromptParams(chunk_annotation_template='Result {index}\nContent: {chunk.content}\nMetadata: {metadata}\n', context_template='The above results were retrieved to help answer the user\'s query: "{query}". Use them as supporting information only in answering this query.{annotation_instruction}\n') annotation_prompt_params=AnnotationPromptParams(enable_annotations=True, annotation_instruction_template=" Cite sources immediately at the end of sentences before punctuation, using `<|file-id|>` format like 'This is a fact <|file-Cn3MSNn72ENTiiq11Qda4A|>.'. Do not add extra punctuation. Use only the file IDs provided, do not invent new ones.", chunk_annotation_template='[{index}] {metadata_text} cite as <|{file_id}|>\n{chunk_text}\n')` | Configuration for vector store prompt templates and behavior |
+
 ## Sample Configuration
 
 ```yaml

src/llama_stack/core/datatypes.py

@@ -18,7 +18,15 @@ from llama_stack.core.storage.datatypes import (
     StorageConfig,
 )
 from llama_stack.log import LoggingConfig
-from llama_stack.providers.utils.memory.constants import DEFAULT_QUERY_REWRITE_PROMPT
+from llama_stack.providers.utils.memory.constants import (
+    DEFAULT_ANNOTATION_INSTRUCTION_TEMPLATE,
+    DEFAULT_CHUNK_ANNOTATION_TEMPLATE,
+    DEFAULT_CHUNK_WITH_SOURCES_TEMPLATE,
+    DEFAULT_CONTEXT_TEMPLATE,
+    DEFAULT_FILE_SEARCH_FOOTER_TEMPLATE,
+    DEFAULT_FILE_SEARCH_HEADER_TEMPLATE,
+    DEFAULT_QUERY_REWRITE_PROMPT,
+)
 from llama_stack_api import (
     Api,
     Benchmark,
@@ -371,6 +379,125 @@ class RewriteQueryParams(BaseModel):
         description="Temperature for query expansion model (0.0 = deterministic, 1.0 = creative).",
     )
 
+    @field_validator("prompt")
+    @classmethod
+    def validate_prompt(cls, v: str) -> str:
+        if "{query}" not in v:
+            raise ValueError("prompt must contain {query} placeholder")
+        return v
+
+    @field_validator("max_tokens")
+    @classmethod
+    def validate_max_tokens(cls, v: int) -> int:
+        if v <= 0:
+            raise ValueError("max_tokens must be positive")
+        if v > 4096:
+            raise ValueError("max_tokens should not exceed 4096")
+        return v
+
+    @field_validator("temperature")
+    @classmethod
+    def validate_temperature(cls, v: float) -> float:
+        if v < 0.0 or v > 2.0:
+            raise ValueError("temperature must be between 0.0 and 2.0")
+        return v
+
+
+class FileSearchParams(BaseModel):
+    """Configuration for file search tool output formatting."""
+
+    header_template: str = Field(
+        default=DEFAULT_FILE_SEARCH_HEADER_TEMPLATE,
+        description="Template for the header text shown before search results. Available placeholders: {num_chunks} number of chunks found.",
+    )
+    footer_template: str = Field(
+        default=DEFAULT_FILE_SEARCH_FOOTER_TEMPLATE,
+        description="Template for the footer text shown after search results.",
+    )
+
+    @field_validator("header_template")
+    @classmethod
+    def validate_header_template(cls, v: str) -> str:
+        if len(v) == 0:
+            raise ValueError("header_template must not be empty")
+        if "{num_chunks}" not in v:
+            raise ValueError("header_template must contain {num_chunks} placeholder")
+        if "knowledge_search" not in v.lower():
+            raise ValueError(
+                "header_template must contain 'knowledge_search' keyword to ensure proper tool identification"
+            )
+        return v
+
+
+class ContextPromptParams(BaseModel):
+    """Configuration for LLM prompt content and chunk formatting."""
+
+    chunk_annotation_template: str = Field(
+        default=DEFAULT_CHUNK_ANNOTATION_TEMPLATE,
+        description="Template for formatting individual chunks in search results. Available placeholders: {index} 1-based chunk index, {chunk.content} chunk content, {metadata} chunk metadata dict.",
+    )
+    context_template: str = Field(
+        default=DEFAULT_CONTEXT_TEMPLATE,
+        description="Template for explaining the search results to the model. Available placeholders: {query} user's query, {num_chunks} number of chunks.",
+    )
+
+    @field_validator("chunk_annotation_template")
+    @classmethod
+    def validate_chunk_annotation_template(cls, v: str) -> str:
+        if len(v) == 0:
+            raise ValueError("chunk_annotation_template must not be empty")
+        if "{chunk.content}" not in v:
+            raise ValueError("chunk_annotation_template must contain {chunk.content} placeholder")
+        if "{index}" not in v:
+            raise ValueError("chunk_annotation_template must contain {index} placeholder")
+        return v
+
+    @field_validator("context_template")
+    @classmethod
+    def validate_context_template(cls, v: str) -> str:
+        if len(v) == 0:
+            raise ValueError("context_template must not be empty")
+        if "{query}" not in v:
+            raise ValueError("context_template must contain {query} placeholder")
+        return v
+
+
+class AnnotationPromptParams(BaseModel):
+    """Configuration for source annotation and attribution features."""
+
+    enable_annotations: bool = Field(
+        default=True,
+        description="Whether to include annotation information in results.",
+    )
+    annotation_instruction_template: str = Field(
+        default=DEFAULT_ANNOTATION_INSTRUCTION_TEMPLATE,
+        description="Instructions for how the model should cite sources. Used when enable_annotations is True.",
+    )
+    chunk_annotation_template: str = Field(
+        default=DEFAULT_CHUNK_WITH_SOURCES_TEMPLATE,
+        description="Template for chunks with annotation information. Available placeholders: {index} 1-based chunk index, {metadata_text} formatted metadata, {file_id} document identifier, {chunk_text} chunk content.",
+    )
+
+    @field_validator("chunk_annotation_template")
+    @classmethod
+    def validate_chunk_annotation_template(cls, v: str) -> str:
+        if len(v) == 0:
+            raise ValueError("chunk_annotation_template must not be empty")
+        if "{index}" not in v:
+            raise ValueError("chunk_annotation_template must contain {index} placeholder")
+        if "{chunk_text}" not in v:
+            raise ValueError("chunk_annotation_template must contain {chunk_text} placeholder")
+        if "{file_id}" not in v:
+            raise ValueError("chunk_annotation_template must contain {file_id} placeholder")
+        return v
+
+    @field_validator("annotation_instruction_template")
+    @classmethod
+    def validate_annotation_instruction_template(cls, v: str) -> str:
+        if len(v) == 0:
+            raise ValueError("annotation_instruction_template must not be empty")
+        return v
+
 
 class VectorStoresConfig(BaseModel):
     """Configuration for vector stores in the stack."""
@@ -387,6 +514,18 @@ class VectorStoresConfig(BaseModel):
         default=None,
         description="Parameters for query rewriting/expansion. None disables query rewriting.",
     )
+    file_search_params: FileSearchParams = Field(
+        default_factory=FileSearchParams,
+        description="Configuration for file search tool output formatting.",
+    )
+    context_prompt_params: ContextPromptParams = Field(
+        default_factory=ContextPromptParams,
+        description="Configuration for LLM prompt content and chunk formatting.",
+    )
+    annotation_prompt_params: AnnotationPromptParams = Field(
+        default_factory=AnnotationPromptParams,
+        description="Configuration for source annotation and attribution features.",
+    )
 
 
 class SafetyConfig(BaseModel):

src/llama_stack/core/resolver.py

@@ -3,6 +3,7 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
+
 import importlib
 import importlib.metadata
 import inspect
@@ -406,13 +407,17 @@ async def instantiate_provider(
         args = [provider_spec.api, inner_impls, deps, dist_registry, policy]
     else:
         method = "get_provider_impl"
+        provider_config = provider.config.copy()
 
+        # Inject vector_stores_config for providers that need it (introspection-based)
         config_type = instantiate_class_type(provider_spec.config_class)
-        config = config_type(**provider.config)
+        if hasattr(config_type, "__fields__") and "vector_stores_config" in config_type.__fields__:
+            provider_config["vector_stores_config"] = run_config.vector_stores
+
+        config = config_type(**provider_config)
         args = [config, deps]
         if "policy" in inspect.signature(getattr(module, method)).parameters:
             args.append(policy)
-
     fn = getattr(module, method)
     impl = await fn(*args)
     impl.__provider_id__ = provider.provider_id

src/llama_stack/core/stack.py

@@ -229,8 +229,6 @@ async def validate_vector_stores_config(vector_stores_config: VectorStoresConfig
     if vector_stores_config.rewrite_query_params:
         if vector_stores_config.rewrite_query_params.model:
             await _validate_rewrite_query_model(vector_stores_config.rewrite_query_params.model, impls)
-        if "{query}" not in vector_stores_config.rewrite_query_params.prompt:
-            raise ValueError("'{query}' placeholder is required in the prompt template")
 
 
 async def _validate_embedding_model(embedding_model: QualifiedModel, impls: dict[Api, Any]) -> None:

src/llama_stack/distributions/ci-tests/config.yaml

@@ -277,5 +277,38 @@ vector_stores:
   default_embedding_model:
     provider_id: sentence-transformers
     model_id: nomic-ai/nomic-embed-text-v1.5
+  file_search_params:
+    header_template: 'knowledge_search tool found {num_chunks} chunks:
+
+      BEGIN of knowledge_search tool results.
+
+      '
+    footer_template: 'END of knowledge_search tool results.
+
+      '
+  context_prompt_params:
+    chunk_annotation_template: 'Result {index}
+
+      Content: {chunk.content}
+
+      Metadata: {metadata}
+
+      '
+    context_template: 'The above results were retrieved to help answer the user''s
+      query: "{query}". Use them as supporting information only in answering this
+      query.{annotation_instruction}
+
+      '
+  annotation_prompt_params:
+    enable_annotations: true
+    annotation_instruction_template: ' Cite sources immediately at the end of sentences
+      before punctuation, using `<|file-id|>` format like ''This is a fact <|file-Cn3MSNn72ENTiiq11Qda4A|>.''.
+      Do not add extra punctuation. Use only the file IDs provided, do not invent
+      new ones.'
+    chunk_annotation_template: '[{index}] {metadata_text} cite as <|{file_id}|>
+
+      {chunk_text}
+
+      '
 safety:
   default_shield_id: llama-guard

src/llama_stack/distributions/ci-tests/run-with-postgres-store.yaml

@@ -286,5 +286,38 @@ vector_stores:
   default_embedding_model:
     provider_id: sentence-transformers
     model_id: nomic-ai/nomic-embed-text-v1.5
+  file_search_params:
+    header_template: 'knowledge_search tool found {num_chunks} chunks:
+
+      BEGIN of knowledge_search tool results.
+
+      '
+    footer_template: 'END of knowledge_search tool results.
+
+      '
+  context_prompt_params:
+    chunk_annotation_template: 'Result {index}
+
+      Content: {chunk.content}
+
+      Metadata: {metadata}
+
+      '
+    context_template: 'The above results were retrieved to help answer the user''s
+      query: "{query}". Use them as supporting information only in answering this
+      query.{annotation_instruction}
+
+      '
+  annotation_prompt_params:
+    enable_annotations: true
+    annotation_instruction_template: ' Cite sources immediately at the end of sentences
+      before punctuation, using `<|file-id|>` format like ''This is a fact <|file-Cn3MSNn72ENTiiq11Qda4A|>.''.
+      Do not add extra punctuation. Use only the file IDs provided, do not invent
+      new ones.'
+    chunk_annotation_template: '[{index}] {metadata_text} cite as <|{file_id}|>
+
+      {chunk_text}
+
+      '
 safety:
   default_shield_id: llama-guard

src/llama_stack/distributions/starter-gpu/config.yaml

@@ -280,5 +280,38 @@ vector_stores:
   default_embedding_model:
     provider_id: sentence-transformers
     model_id: nomic-ai/nomic-embed-text-v1.5
+  file_search_params:
+    header_template: 'knowledge_search tool found {num_chunks} chunks:
+
+      BEGIN of knowledge_search tool results.
+
+      '
+    footer_template: 'END of knowledge_search tool results.
+
+      '
+  context_prompt_params:
+    chunk_annotation_template: 'Result {index}
+
+      Content: {chunk.content}
+
+      Metadata: {metadata}
+
+      '
+    context_template: 'The above results were retrieved to help answer the user''s
+      query: "{query}". Use them as supporting information only in answering this
+      query.{annotation_instruction}
+
+      '
+  annotation_prompt_params:
+    enable_annotations: true
+    annotation_instruction_template: ' Cite sources immediately at the end of sentences
+      before punctuation, using `<|file-id|>` format like ''This is a fact <|file-Cn3MSNn72ENTiiq11Qda4A|>.''.
+      Do not add extra punctuation. Use only the file IDs provided, do not invent
+      new ones.'
+    chunk_annotation_template: '[{index}] {metadata_text} cite as <|{file_id}|>
+
+      {chunk_text}
+
+      '
 safety:
   default_shield_id: llama-guard

src/llama_stack/distributions/starter-gpu/run-with-postgres-store.yaml

@@ -289,5 +289,38 @@ vector_stores:
   default_embedding_model:
     provider_id: sentence-transformers
     model_id: nomic-ai/nomic-embed-text-v1.5
+  file_search_params:
+    header_template: 'knowledge_search tool found {num_chunks} chunks:
+
+      BEGIN of knowledge_search tool results.
+
+      '
+    footer_template: 'END of knowledge_search tool results.
+
+      '
+  context_prompt_params:
+    chunk_annotation_template: 'Result {index}
+
+      Content: {chunk.content}
+
+      Metadata: {metadata}
+
+      '
+    context_template: 'The above results were retrieved to help answer the user''s
+      query: "{query}". Use them as supporting information only in answering this
+      query.{annotation_instruction}
+
+      '
+  annotation_prompt_params:
+    enable_annotations: true
+    annotation_instruction_template: ' Cite sources immediately at the end of sentences
+      before punctuation, using `<|file-id|>` format like ''This is a fact <|file-Cn3MSNn72ENTiiq11Qda4A|>.''.
+      Do not add extra punctuation. Use only the file IDs provided, do not invent
+      new ones.'
+    chunk_annotation_template: '[{index}] {metadata_text} cite as <|{file_id}|>
+
+      {chunk_text}
+
+      '
 safety:
   default_shield_id: llama-guard

src/llama_stack/distributions/starter/config.yaml

@@ -277,5 +277,38 @@ vector_stores:
   default_embedding_model:
     provider_id: sentence-transformers
     model_id: nomic-ai/nomic-embed-text-v1.5
+  file_search_params:
+    header_template: 'knowledge_search tool found {num_chunks} chunks:
+
+      BEGIN of knowledge_search tool results.
+
+      '
+    footer_template: 'END of knowledge_search tool results.
+
+      '
+  context_prompt_params:
+    chunk_annotation_template: 'Result {index}
+
+      Content: {chunk.content}
+
+      Metadata: {metadata}
+
+      '
+    context_template: 'The above results were retrieved to help answer the user''s
+      query: "{query}". Use them as supporting information only in answering this
+      query.{annotation_instruction}
+
+      '
+  annotation_prompt_params:
+    enable_annotations: true
+    annotation_instruction_template: ' Cite sources immediately at the end of sentences
+      before punctuation, using `<|file-id|>` format like ''This is a fact <|file-Cn3MSNn72ENTiiq11Qda4A|>.''.
+      Do not add extra punctuation. Use only the file IDs provided, do not invent
+      new ones.'
+    chunk_annotation_template: '[{index}] {metadata_text} cite as <|{file_id}|>
+
+      {chunk_text}
+
+      '
 safety:
   default_shield_id: llama-guard

src/llama_stack/distributions/starter/run-with-postgres-store.yaml

@@ -286,5 +286,38 @@ vector_stores:
   default_embedding_model:
     provider_id: sentence-transformers
     model_id: nomic-ai/nomic-embed-text-v1.5
+  file_search_params:
+    header_template: 'knowledge_search tool found {num_chunks} chunks:
+
+      BEGIN of knowledge_search tool results.
+
+      '
+    footer_template: 'END of knowledge_search tool results.
+
+      '
+  context_prompt_params:
+    chunk_annotation_template: 'Result {index}
+
+      Content: {chunk.content}
+
+      Metadata: {metadata}
+
+      '
+    context_template: 'The above results were retrieved to help answer the user''s
+      query: "{query}". Use them as supporting information only in answering this
+      query.{annotation_instruction}
+
+      '
+  annotation_prompt_params:
+    enable_annotations: true
+    annotation_instruction_template: ' Cite sources immediately at the end of sentences
+      before punctuation, using `<|file-id|>` format like ''This is a fact <|file-Cn3MSNn72ENTiiq11Qda4A|>.''.
+      Do not add extra punctuation. Use only the file IDs provided, do not invent
+      new ones.'
+    chunk_annotation_template: '[{index}] {metadata_text} cite as <|{file_id}|>
+
+      {chunk_text}
+
+      '
 safety:
   default_shield_id: llama-guard

src/llama_stack/providers/inline/agents/meta_reference/agents.py

@@ -78,6 +78,7 @@ class MetaReferenceAgentsImpl(Agents):
             conversations_api=self.conversations_api,
             prompts_api=self.prompts_api,
             files_api=self.files_api,
+            vector_stores_config=self.config.vector_stores_config,
         )
 
     async def shutdown(self) -> None:

src/llama_stack/providers/inline/agents/meta_reference/config.py

@@ -6,8 +6,9 @@
 
 from typing import Any
 
-from pydantic import BaseModel
+from pydantic import BaseModel, Field
 
+from llama_stack.core.datatypes import VectorStoresConfig
 from llama_stack.core.storage.datatypes import KVStoreReference, ResponsesStoreReference
 
 
@@ -20,6 +21,10 @@ class AgentPersistenceConfig(BaseModel):
 
 class MetaReferenceAgentsImplConfig(BaseModel):
     persistence: AgentPersistenceConfig
+    vector_stores_config: VectorStoresConfig | None = Field(
+        default=None,
+        description="Configuration for vector store prompt templates and behavior",
+    )
 
     @classmethod
     def sample_run_config(cls, __distro_dir__: str) -> dict[str, Any]:

src/llama_stack/providers/inline/agents/meta_reference/responses/openai_responses.py

@@ -80,6 +80,7 @@ class OpenAIResponsesImpl:
         conversations_api: Conversations,
         prompts_api: Prompts,
         files_api: Files,
+        vector_stores_config=None,
     ):
         self.inference_api = inference_api
         self.tool_groups_api = tool_groups_api
@@ -92,6 +93,7 @@ class OpenAIResponsesImpl:
             tool_groups_api=tool_groups_api,
             tool_runtime_api=tool_runtime_api,
             vector_io_api=vector_io_api,
+            vector_stores_config=vector_stores_config,
         )
         self.prompts_api = prompts_api
         self.files_api = files_api

src/llama_stack/providers/inline/agents/meta_reference/responses/tool_executor.py

@@ -12,6 +12,10 @@ from typing import Any
 from opentelemetry import trace
 
 from llama_stack.log import get_logger
+from llama_stack.providers.utils.memory.constants import (
+    DEFAULT_ANNOTATION_INSTRUCTION_TEMPLATE,
+    DEFAULT_CHUNK_WITH_SOURCES_TEMPLATE,
+)
 from llama_stack_api import (
     ImageContentItem,
     OpenAIChatCompletionContentPartImageParam,
@@ -52,10 +56,12 @@ class ToolExecutor:
         tool_groups_api: ToolGroups,
         tool_runtime_api: ToolRuntime,
         vector_io_api: VectorIO,
+        vector_stores_config=None,
     ):
         self.tool_groups_api = tool_groups_api
         self.tool_runtime_api = tool_runtime_api
         self.vector_io_api = vector_io_api
+        self.vector_stores_config = vector_stores_config
 
     async def execute_tool_call(
         self,
@@ -148,13 +154,33 @@ class ToolExecutor:
         for results in all_results:
             search_results.extend(results)
 
-        content_items = []
-        content_items.append(
-            TextContentItem(
-                text=f"knowledge_search tool found {len(search_results)} chunks:\nBEGIN of knowledge_search tool results.\n"
-            )
+        # Get templates from vector stores config, fallback to constants
+
+        # Check if annotations are enabled
+        enable_annotations = (
+            self.vector_stores_config
+            and self.vector_stores_config.annotation_prompt_params
+            and self.vector_stores_config.annotation_prompt_params.enable_annotations
         )
 
+        # Get templates
+        header_template = self.vector_stores_config.file_search_params.header_template
+        footer_template = self.vector_stores_config.file_search_params.footer_template
+        context_template = self.vector_stores_config.context_prompt_params.context_template
+
+        # Get annotation templates (use defaults if annotations disabled)
+        if enable_annotations:
+            chunk_annotation_template = self.vector_stores_config.annotation_prompt_params.chunk_annotation_template
+            annotation_instruction_template = (
+                self.vector_stores_config.annotation_prompt_params.annotation_instruction_template
+            )
+        else:
+            chunk_annotation_template = DEFAULT_CHUNK_WITH_SOURCES_TEMPLATE
+            annotation_instruction_template = DEFAULT_ANNOTATION_INSTRUCTION_TEMPLATE
+
+        content_items = []
+        content_items.append(TextContentItem(text=header_template.format(num_chunks=len(search_results))))
+
         unique_files = set()
         for i, result_item in enumerate(search_results):
             chunk_text = result_item.content[0].text if result_item.content else ""
@@ -166,22 +192,23 @@ class ToolExecutor:
             if result_item.attributes:
                 metadata_text += f", attributes: {result_item.attributes}"
 
-            text_content = f"[{i + 1}] {metadata_text} (cite as <|{file_id}|>)\n{chunk_text}\n"
+            text_content = chunk_annotation_template.format(
+                index=i + 1, metadata_text=metadata_text, file_id=file_id, chunk_text=chunk_text
+            )
             content_items.append(TextContentItem(text=text_content))
             unique_files.add(file_id)
 
-        content_items.append(TextContentItem(text="END of knowledge_search tool results.\n"))
+        content_items.append(TextContentItem(text=footer_template))
 
-        citation_instruction = ""
+        annotation_instruction = ""
         if unique_files:
-            citation_instruction = (
-                " Cite sources immediately at the end of sentences before punctuation, using `<|file-id|>` format (e.g., 'This is a fact <|file-Cn3MSNn72ENTiiq11Qda4A|>.'). "
-                "Do not add extra punctuation. Use only the file IDs provided (do not invent new ones)."
-            )
+            annotation_instruction = annotation_instruction_template
 
         content_items.append(
             TextContentItem(
-                text=f'The above results were retrieved to help answer the user\'s query: "{query}". Use them as supporting information only in answering this query.{citation_instruction}\n',
+                text=context_template.format(
+                    query=query, num_chunks=len(search_results), annotation_instruction=annotation_instruction
+                )
             )
         )
 

src/llama_stack/providers/inline/tool_runtime/rag/config.py

@@ -6,10 +6,17 @@
 
 from typing import Any
 
-from pydantic import BaseModel
+from pydantic import BaseModel, Field
+
+from llama_stack.core.datatypes import VectorStoresConfig
 
 
 class RagToolRuntimeConfig(BaseModel):
+    vector_stores_config: VectorStoresConfig = Field(
+        default_factory=VectorStoresConfig,
+        description="Configuration for vector store prompt templates and behavior",
+    )
+
     @classmethod
     def sample_run_config(cls, __distro_dir__: str, **kwargs: Any) -> dict[str, Any]:
         return {}

src/llama_stack/providers/inline/tool_runtime/rag/memory.py

@@ -221,11 +221,15 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime):
         chunks = chunks[: query_config.max_chunks]
 
         tokens = 0
-        picked: list[InterleavedContentItem] = [
-            TextContentItem(
-                text=f"knowledge_search tool found {len(chunks)} chunks:\nBEGIN of knowledge_search tool results.\n"
-            )
-        ]
+
+        # Get templates from vector stores config
+        vector_stores_config = self.config.vector_stores_config
+        header_template = vector_stores_config.file_search_params.header_template
+        footer_template = vector_stores_config.file_search_params.footer_template
+        chunk_template = vector_stores_config.context_prompt_params.chunk_annotation_template
+        context_template = vector_stores_config.context_prompt_params.context_template
+
+        picked: list[InterleavedContentItem] = [TextContentItem(text=header_template.format(num_chunks=len(chunks)))]
         for i, chunk in enumerate(chunks):
             metadata = chunk.metadata
             tokens += metadata.get("token_count", 0)
@@ -255,13 +259,13 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime):
                 if k not in metadata_keys_to_exclude_from_context:
                     metadata_for_context[k] = metadata[k]
 
-            text_content = query_config.chunk_template.format(index=i + 1, chunk=chunk, metadata=metadata_for_context)
+            text_content = chunk_template.format(index=i + 1, chunk=chunk, metadata=metadata_for_context)
             picked.append(TextContentItem(text=text_content))
 
-        picked.append(TextContentItem(text="END of knowledge_search tool results.\n"))
+        picked.append(TextContentItem(text=footer_template))
         picked.append(
             TextContentItem(
-                text=f'The above results were retrieved to help answer the user\'s query: "{interleaved_content_as_str(content)}". Use them as supporting information only in answering this query.\n',
+                text=context_template.format(query=interleaved_content_as_str(content), annotation_instruction="")
             )
         )
 

src/llama_stack/providers/utils/memory/constants.py

@@ -6,3 +6,17 @@
 
 # Default prompt template for query rewriting in vector search
 DEFAULT_QUERY_REWRITE_PROMPT = "Expand this query with relevant synonyms and related terms. Return only the improved query, no explanations:\n\n{query}\n\nImproved query:"
+
+# Default templates for file search tool output formatting
+DEFAULT_FILE_SEARCH_HEADER_TEMPLATE = (
+    "knowledge_search tool found {num_chunks} chunks:\nBEGIN of knowledge_search tool results.\n"
+)
+DEFAULT_FILE_SEARCH_FOOTER_TEMPLATE = "END of knowledge_search tool results.\n"
+
+# Default templates for LLM prompt content and chunk formatting
+DEFAULT_CHUNK_ANNOTATION_TEMPLATE = "Result {index}\nContent: {chunk.content}\nMetadata: {metadata}\n"
+DEFAULT_CONTEXT_TEMPLATE = 'The above results were retrieved to help answer the user\'s query: "{query}". Use them as supporting information only in answering this query.{annotation_instruction}\n'
+
+# Default templates for source annotation and attribution features
+DEFAULT_ANNOTATION_INSTRUCTION_TEMPLATE = " Cite sources immediately at the end of sentences before punctuation, using `<|file-id|>` format like 'This is a fact <|file-Cn3MSNn72ENTiiq11Qda4A|>.'. Do not add extra punctuation. Use only the file IDs provided, do not invent new ones."
+DEFAULT_CHUNK_WITH_SOURCES_TEMPLATE = "[{index}] {metadata_text} cite as <|{file_id}|>\n{chunk_text}\n"

tests/integration/responses/recordings/1e171766576921b1462c0773e012b63fbc42df98f9612af5eef7613e2b967900.json

@@ -0,0 +1,631 @@
+{
+  "test_id": "tests/integration/responses/test_tool_responses.py::test_response_sequential_file_search[client_with_models-txt=openai/gpt-4o:emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5:dim=768]",
+  "request": {
+    "method": "POST",
+    "url": "https://api.openai.com/v1/v1/chat/completions",
+    "headers": {},
+    "body": {
+      "model": "gpt-4o",
+      "messages": [
+        {
+          "role": "user",
+          "content": "How many experts does the Llama 4 Maverick model have?"
+        },
+        {
+          "role": "assistant",
+          "content": "",
+          "tool_calls": [
+            {
+              "index": 0,
+              "id": "call_FzhOmTdZThRndI5rSASPdAqr",
+              "type": "function",
+              "function": {
+                "name": "knowledge_search",
+                "arguments": "{\"query\":\"Llama 4 Maverick model number of experts\"}"
+              }
+            }
+          ]
+        },
+        {
+          "role": "tool",
+          "tool_call_id": "call_FzhOmTdZThRndI5rSASPdAqr",
+          "content": [
+            {
+              "type": "text",
+              "text": "knowledge_search tool found 1 chunks:\nBEGIN of knowledge_search tool results.\n"
+            },
+            {
+              "type": "text",
+              "text": "[1] document_id: file-797509666839, score: 0.019272319661840426, attributes: {'filename': 'test_sequential_file_search.txt', 'chunk_id': '3907d885-d8e7-a72d-1113-f7080454d97c', 'document_id': 'file-797509666839', 'token_count': 19.0, 'metadata_token_count': 11.0} cite as <|file-797509666839|>\nThe Llama 4 Maverick model has 128 experts in its mixture of experts architecture.\n"
+            },
+            {
+              "type": "text",
+              "text": "END of knowledge_search tool results.\n"
+            },
+            {
+              "type": "text",
+              "text": "The above results were retrieved to help answer the user's query: \"Llama 4 Maverick model number of experts\". Use them as supporting information only in answering this query. Cite sources immediately at the end of sentences before punctuation, using `<|file-id|>` format like 'This is a fact <|file-Cn3MSNn72ENTiiq11Qda4A|>.'. Do not add extra punctuation. Use only the file IDs provided, do not invent new ones.\n"
+            }
+          ]
+        },
+        {
+          "role": "assistant",
+          "content": "The Llama 4 Maverick model has 128 experts in its mixture of experts architecture <|file-797509666839|>."
+        },
+        {
+          "role": "user",
+          "content": "Can you tell me more about the architecture?"
+        }
+      ],
+      "stream": true,
+      "stream_options": {
+        "include_usage": true
+      },
+      "tools": [
+        {
+          "type": "function",
+          "function": {
+            "name": "knowledge_search",
+            "description": "Search for information in a database.",
+            "parameters": {
+              "type": "object",
+              "properties": {
+                "query": {
+                  "type": "string",
+                  "description": "The query to search for. Can be a natural language sentence or keywords."
+                }
+              },
+              "required": [
+                "query"
+              ]
+            }
+          }
+        }
+      ]
+    },
+    "endpoint": "/v1/chat/completions",
+    "model": "gpt-4o"
+  },
+  "response": {
+    "body": [
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-1e1717665769",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": "call_VtFoA9FzgtwNWqenbX1PKi1w",
+                    "function": {
+                      "arguments": "",
+                      "name": "knowledge_search"
+                    },
+                    "type": "function"
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "xPf6"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-1e1717665769",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": "{\"",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "dHP"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-1e1717665769",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": "query",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "a"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-1e1717665769",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": "\":\"",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "n"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-1e1717665769",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": "L",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "ibn6l"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-1e1717665769",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": "lama",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "Zj"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-1e1717665769",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": " ",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "Z1K9G"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-1e1717665769",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": "4",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "SvheX"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-1e1717665769",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": " Maver",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": ""
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-1e1717665769",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": "ick",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "Egj"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-1e1717665769",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": " model",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": ""
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-1e1717665769",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": " architecture",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "2veLpIXn5"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-1e1717665769",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": "\"}",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "EF4"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-1e1717665769",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": "tool_calls",
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "Sp28"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-1e1717665769",
+          "choices": [],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": {
+            "completion_tokens": 22,
+            "prompt_tokens": 400,
+            "total_tokens": 422,
+            "completion_tokens_details": {
+              "accepted_prediction_tokens": 0,
+              "audio_tokens": 0,
+              "reasoning_tokens": 0,
+              "rejected_prediction_tokens": 0
+            },
+            "prompt_tokens_details": {
+              "audio_tokens": 0,
+              "cached_tokens": 0
+            }
+          },
+          "obfuscation": "rszgcNSsbRR1D"
+        }
+      }
+    ],
+    "is_streaming": true
+  },
+  "id_normalization_mapping": {}
+}

tests/integration/responses/recordings/256215277d288407e08176fe22b6c6b5307261c8f4a54bd08786e386f745ab74.json

@@ -0,0 +1,763 @@
+{
+  "test_id": "tests/integration/responses/test_tool_responses.py::test_response_non_streaming_file_search[client_with_models-txt=openai/gpt-4o:emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5:dim=768-llama_experts]",
+  "request": {
+    "method": "POST",
+    "url": "https://api.openai.com/v1/v1/chat/completions",
+    "headers": {},
+    "body": {
+      "model": "gpt-4o",
+      "messages": [
+        {
+          "role": "user",
+          "content": "How many experts does the Llama 4 Maverick model have?"
+        },
+        {
+          "role": "assistant",
+          "content": "",
+          "tool_calls": [
+            {
+              "index": 0,
+              "id": "call_gZXRKN1HMDC16NP9wNPAkP9K",
+              "type": "function",
+              "function": {
+                "name": "knowledge_search",
+                "arguments": "{\"query\":\"Llama 4 Maverick model experts count\"}"
+              }
+            }
+          ]
+        },
+        {
+          "role": "tool",
+          "tool_call_id": "call_gZXRKN1HMDC16NP9wNPAkP9K",
+          "content": [
+            {
+              "type": "text",
+              "text": "knowledge_search tool found 1 chunks:\nBEGIN of knowledge_search tool results.\n"
+            },
+            {
+              "type": "text",
+              "text": "[1] document_id: file-864460993305, score: 0.01141874848523339, attributes: {'filename': 'test_response_non_streaming_file_search.txt', 'chunk_id': '869ae0c0-ab85-ca6f-e5d0-024381443c27', 'document_id': 'file-864460993305', 'token_count': 10.0, 'metadata_token_count': 13.0} cite as <|file-864460993305|>\nLlama 4 Maverick has 128 experts\n"
+            },
+            {
+              "type": "text",
+              "text": "END of knowledge_search tool results.\n"
+            },
+            {
+              "type": "text",
+              "text": "The above results were retrieved to help answer the user's query: \"Llama 4 Maverick model experts count\". Use them as supporting information only in answering this query. Cite sources immediately at the end of sentences before punctuation, using `<|file-id|>` format like 'This is a fact <|file-Cn3MSNn72ENTiiq11Qda4A|>.'. Do not add extra punctuation. Use only the file IDs provided, do not invent new ones.\n"
+            }
+          ]
+        }
+      ],
+      "stream": true,
+      "stream_options": {
+        "include_usage": true
+      },
+      "tools": [
+        {
+          "type": "function",
+          "function": {
+            "name": "knowledge_search",
+            "description": "Search for information in a database.",
+            "parameters": {
+              "type": "object",
+              "properties": {
+                "query": {
+                  "type": "string",
+                  "description": "The query to search for. Can be a natural language sentence or keywords."
+                }
+              },
+              "required": [
+                "query"
+              ]
+            }
+          }
+        }
+      ]
+    },
+    "endpoint": "/v1/chat/completions",
+    "model": "gpt-4o"
+  },
+  "response": {
+    "body": [
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [
+            {
+              "delta": {
+                "content": "",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "SvaNRTSCreICNt"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [
+            {
+              "delta": {
+                "content": "The",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "uI5dQOp434E2B"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [
+            {
+              "delta": {
+                "content": " L",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "S5xCfipngY5Jsu"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [
+            {
+              "delta": {
+                "content": "lama",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "U8KuOQQeWohQ"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [
+            {
+              "delta": {
+                "content": " ",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "zk2skKNLkFwn1Zw"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [
+            {
+              "delta": {
+                "content": "4",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "jVclDXFBOVbnhCb"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [
+            {
+              "delta": {
+                "content": " Maver",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "3CuCCZARj9"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [
+            {
+              "delta": {
+                "content": "ick",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "6pbQvXnE705dF"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [
+            {
+              "delta": {
+                "content": " model",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "8oL0LQrbQe"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [
+            {
+              "delta": {
+                "content": " has",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "DQaAbmXLP8wQ"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [
+            {
+              "delta": {
+                "content": " ",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "AWfDhbEuxBZaxDZ"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [
+            {
+              "delta": {
+                "content": "128",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "BestZ5aIWFH02"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [
+            {
+              "delta": {
+                "content": " experts",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "pAbvQSXU"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [
+            {
+              "delta": {
+                "content": " <",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "Tddmv7Un5cYy1K"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [
+            {
+              "delta": {
+                "content": "|",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "FEEpu3yMVOhWzyv"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [
+            {
+              "delta": {
+                "content": "file",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "SJSLMJJF2hpn"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [
+            {
+              "delta": {
+                "content": "-",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "tM9VcUkheYocNr2"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [
+            {
+              "delta": {
+                "content": "864",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "GEZX6ibeJqJDb"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [
+            {
+              "delta": {
+                "content": "460",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "WktxNU0pSDQCp"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [
+            {
+              "delta": {
+                "content": "993",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "n3FX4Ln5LBia0"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [
+            {
+              "delta": {
+                "content": "305",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "eS0MfdTf1582u"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [
+            {
+              "delta": {
+                "content": "|",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "r1PjmGi346q7Ixf"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [
+            {
+              "delta": {
+                "content": ">.",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "PgIfwA3juex8OG"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": "stop",
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "2ncsenZDLu"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-256215277d28",
+          "choices": [],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": {
+            "completion_tokens": 23,
+            "prompt_tokens": 346,
+            "total_tokens": 369,
+            "completion_tokens_details": {
+              "accepted_prediction_tokens": 0,
+              "audio_tokens": 0,
+              "reasoning_tokens": 0,
+              "rejected_prediction_tokens": 0
+            },
+            "prompt_tokens_details": {
+              "audio_tokens": 0,
+              "cached_tokens": 0
+            }
+          },
+          "obfuscation": "xoNg7P6WIVerb"
+        }
+      }
+    ],
+    "is_streaming": true
+  },
+  "id_normalization_mapping": {}
+}

tests/integration/responses/recordings/29ab0b407d3d3f6bb893470702b7bffe012b864e04f6df6f52adadfd3a50896e.json

@@ -0,0 +1,668 @@
+{
+  "test_id": "tests/integration/responses/test_tool_responses.py::test_response_sequential_file_search[openai_client-txt=openai/gpt-4o:emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5:dim=768]",
+  "request": {
+    "method": "POST",
+    "url": "https://api.openai.com/v1/v1/chat/completions",
+    "headers": {},
+    "body": {
+      "model": "gpt-4o",
+      "messages": [
+        {
+          "role": "user",
+          "content": "How many experts does the Llama 4 Maverick model have?"
+        },
+        {
+          "role": "assistant",
+          "content": "",
+          "tool_calls": [
+            {
+              "index": 0,
+              "id": "call_4ac6gxccWFxDvEl8BizY3BJw",
+              "type": "function",
+              "function": {
+                "name": "knowledge_search",
+                "arguments": "{\"query\":\"Llama 4 Maverick model number of experts\"}"
+              }
+            }
+          ]
+        },
+        {
+          "role": "tool",
+          "tool_call_id": "call_4ac6gxccWFxDvEl8BizY3BJw",
+          "content": [
+            {
+              "type": "text",
+              "text": "knowledge_search tool found 1 chunks:\nBEGIN of knowledge_search tool results.\n"
+            },
+            {
+              "type": "text",
+              "text": "[1] document_id: file-528246887823, score: 0.019272319661840426, attributes: {'filename': 'test_sequential_file_search.txt', 'chunk_id': '3907d885-d8e7-a72d-1113-f7080454d97c', 'document_id': 'file-528246887823', 'token_count': 19.0, 'metadata_token_count': 11.0} cite as <|file-528246887823|>\nThe Llama 4 Maverick model has 128 experts in its mixture of experts architecture.\n"
+            },
+            {
+              "type": "text",
+              "text": "END of knowledge_search tool results.\n"
+            },
+            {
+              "type": "text",
+              "text": "The above results were retrieved to help answer the user's query: \"Llama 4 Maverick model number of experts\". Use them as supporting information only in answering this query. Cite sources immediately at the end of sentences before punctuation, using `<|file-id|>` format like 'This is a fact <|file-Cn3MSNn72ENTiiq11Qda4A|>.'. Do not add extra punctuation. Use only the file IDs provided, do not invent new ones.\n"
+            }
+          ]
+        },
+        {
+          "role": "assistant",
+          "content": "The Llama 4 Maverick model has 128 experts in its mixture of experts architecture <|file-528246887823|>."
+        },
+        {
+          "role": "user",
+          "content": "Can you tell me more about the architecture?"
+        }
+      ],
+      "stream": true,
+      "stream_options": {
+        "include_usage": true
+      },
+      "tools": [
+        {
+          "type": "function",
+          "function": {
+            "name": "knowledge_search",
+            "description": "Search for information in a database.",
+            "parameters": {
+              "type": "object",
+              "properties": {
+                "query": {
+                  "type": "string",
+                  "description": "The query to search for. Can be a natural language sentence or keywords."
+                }
+              },
+              "required": [
+                "query"
+              ]
+            }
+          }
+        }
+      ]
+    },
+    "endpoint": "/v1/chat/completions",
+    "model": "gpt-4o"
+  },
+  "response": {
+    "body": [
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-29ab0b407d3d",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": "call_de3mxedMBHueFpm2b61KzC57",
+                    "function": {
+                      "arguments": "",
+                      "name": "knowledge_search"
+                    },
+                    "type": "function"
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "WnRz"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-29ab0b407d3d",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": "{\"",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "Tdk"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-29ab0b407d3d",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": "query",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "b"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-29ab0b407d3d",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": "\":\"",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "5"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-29ab0b407d3d",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": "L",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "ixufu"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-29ab0b407d3d",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": "lama",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "JP"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-29ab0b407d3d",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": " ",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "vJSE0"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-29ab0b407d3d",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": "4",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "1ps8E"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-29ab0b407d3d",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": " Maver",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": ""
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-29ab0b407d3d",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": "ick",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "YB0"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-29ab0b407d3d",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": " model",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": ""
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-29ab0b407d3d",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": " architecture",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "DgrymXGGS"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-29ab0b407d3d",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": " details",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "rcnLxZVgmKPeIW"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-29ab0b407d3d",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": "\"}",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "uu6"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-29ab0b407d3d",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": "tool_calls",
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "Loyb"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-29ab0b407d3d",
+          "choices": [],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": {
+            "completion_tokens": 23,
+            "prompt_tokens": 400,
+            "total_tokens": 423,
+            "completion_tokens_details": {
+              "accepted_prediction_tokens": 0,
+              "audio_tokens": 0,
+              "reasoning_tokens": 0,
+              "rejected_prediction_tokens": 0
+            },
+            "prompt_tokens_details": {
+              "audio_tokens": 0,
+              "cached_tokens": 0
+            }
+          },
+          "obfuscation": "3H5M4ak9Z9li3"
+        }
+      }
+    ],
+    "is_streaming": true
+  },
+  "id_normalization_mapping": {}
+}

tests/integration/responses/recordings/2dc865d055f3ce6d4438143a67da353cef0e3ea0e3c6044c04018e1718853084.json

@@ -0,0 +1,925 @@
+{
+  "test_id": "tests/integration/responses/test_tool_responses.py::test_response_sequential_file_search[client_with_models-txt=openai/gpt-4o:emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5:dim=768]",
+  "request": {
+    "method": "POST",
+    "url": "https://api.openai.com/v1/v1/chat/completions",
+    "headers": {},
+    "body": {
+      "model": "gpt-4o",
+      "messages": [
+        {
+          "role": "user",
+          "content": "How many experts does the Llama 4 Maverick model have?"
+        },
+        {
+          "role": "assistant",
+          "content": "",
+          "tool_calls": [
+            {
+              "index": 0,
+              "id": "call_FzhOmTdZThRndI5rSASPdAqr",
+              "type": "function",
+              "function": {
+                "name": "knowledge_search",
+                "arguments": "{\"query\":\"Llama 4 Maverick model number of experts\"}"
+              }
+            }
+          ]
+        },
+        {
+          "role": "tool",
+          "tool_call_id": "call_FzhOmTdZThRndI5rSASPdAqr",
+          "content": [
+            {
+              "type": "text",
+              "text": "knowledge_search tool found 1 chunks:\nBEGIN of knowledge_search tool results.\n"
+            },
+            {
+              "type": "text",
+              "text": "[1] document_id: file-797509666839, score: 0.019272319661840426, attributes: {'filename': 'test_sequential_file_search.txt', 'chunk_id': '3907d885-d8e7-a72d-1113-f7080454d97c', 'document_id': 'file-797509666839', 'token_count': 19.0, 'metadata_token_count': 11.0} cite as <|file-797509666839|>\nThe Llama 4 Maverick model has 128 experts in its mixture of experts architecture.\n"
+            },
+            {
+              "type": "text",
+              "text": "END of knowledge_search tool results.\n"
+            },
+            {
+              "type": "text",
+              "text": "The above results were retrieved to help answer the user's query: \"Llama 4 Maverick model number of experts\". Use them as supporting information only in answering this query. Cite sources immediately at the end of sentences before punctuation, using `<|file-id|>` format like 'This is a fact <|file-Cn3MSNn72ENTiiq11Qda4A|>.'. Do not add extra punctuation. Use only the file IDs provided, do not invent new ones.\n"
+            }
+          ]
+        }
+      ],
+      "stream": true,
+      "stream_options": {
+        "include_usage": true
+      },
+      "tools": [
+        {
+          "type": "function",
+          "function": {
+            "name": "knowledge_search",
+            "description": "Search for information in a database.",
+            "parameters": {
+              "type": "object",
+              "properties": {
+                "query": {
+                  "type": "string",
+                  "description": "The query to search for. Can be a natural language sentence or keywords."
+                }
+              },
+              "required": [
+                "query"
+              ]
+            }
+          }
+        }
+      ]
+    },
+    "endpoint": "/v1/chat/completions",
+    "model": "gpt-4o"
+  },
+  "response": {
+    "body": [
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": "",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "X2XnRCilRPxgou"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": "The",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "sNrUscXR9a5ZW"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": " L",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "lUIVgc5y4Soo2E"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": "lama",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "BLLf5MHrUd3S"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": " ",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "bFCci6Tu59o9tmD"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": "4",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "dVnRcXTaDdrpaMB"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": " Maver",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "3r72Ztc1P3"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": "ick",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "DuesapCBztIIr"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": " model",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "ZUoA9UPcfp"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": " has",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "bm7beCvKpP24"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": " ",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "IhzX818vDFrNi78"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": "128",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "lSq0KBU2Y8ZJS"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": " experts",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "f9iewxru"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": " in",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "nPgE2TSRe4N3i"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": " its",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "nyDiyR4g3Bcu"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": " mixture",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "nAYDkbgt"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": " of",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "ZTB7U1lyTE7gO"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": " experts",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "XYAqh8Ah"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": " architecture",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "Jnw"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": " <",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "OtEY9P1EWChz9k"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": "|",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "7bE355cFwUnztmk"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": "file",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "okss4UeCv655"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": "-",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "0vKQVPNH34N6JPH"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": "797",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "lzhiEt8HDEE5F"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": "509",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "ZvxUlUnrIYGiP"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": "666",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "ylx50KiWqHw95"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": "839",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "WbLvgnaEKF5fe"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": "|",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "dP1oyCP9PCHRKCF"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": ">.",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "tsyjM2ubYy8raG"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": "stop",
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "dVYz9fwa19"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-2dc865d055f3",
+          "choices": [],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": {
+            "completion_tokens": 29,
+            "prompt_tokens": 355,
+            "total_tokens": 384,
+            "completion_tokens_details": {
+              "accepted_prediction_tokens": 0,
+              "audio_tokens": 0,
+              "reasoning_tokens": 0,
+              "rejected_prediction_tokens": 0
+            },
+            "prompt_tokens_details": {
+              "audio_tokens": 0,
+              "cached_tokens": 0
+            }
+          },
+          "obfuscation": "vdEJGR6vOpTQR"
+        }
+      }
+    ],
+    "is_streaming": true
+  },
+  "id_normalization_mapping": {}
+}

tests/integration/responses/recordings/9b13d4fa1a58ff6bce3ae987031a1b338ba57f16540ee60d77cd3563eddc801e.json

@@ -0,0 +1,925 @@
+{
+  "test_id": "tests/integration/responses/test_tool_responses.py::test_response_sequential_file_search[openai_client-txt=openai/gpt-4o:emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5:dim=768]",
+  "request": {
+    "method": "POST",
+    "url": "https://api.openai.com/v1/v1/chat/completions",
+    "headers": {},
+    "body": {
+      "model": "gpt-4o",
+      "messages": [
+        {
+          "role": "user",
+          "content": "How many experts does the Llama 4 Maverick model have?"
+        },
+        {
+          "role": "assistant",
+          "content": "",
+          "tool_calls": [
+            {
+              "index": 0,
+              "id": "call_4ac6gxccWFxDvEl8BizY3BJw",
+              "type": "function",
+              "function": {
+                "name": "knowledge_search",
+                "arguments": "{\"query\":\"Llama 4 Maverick model number of experts\"}"
+              }
+            }
+          ]
+        },
+        {
+          "role": "tool",
+          "tool_call_id": "call_4ac6gxccWFxDvEl8BizY3BJw",
+          "content": [
+            {
+              "type": "text",
+              "text": "knowledge_search tool found 1 chunks:\nBEGIN of knowledge_search tool results.\n"
+            },
+            {
+              "type": "text",
+              "text": "[1] document_id: file-528246887823, score: 0.019272319661840426, attributes: {'filename': 'test_sequential_file_search.txt', 'chunk_id': '3907d885-d8e7-a72d-1113-f7080454d97c', 'document_id': 'file-528246887823', 'token_count': 19.0, 'metadata_token_count': 11.0} cite as <|file-528246887823|>\nThe Llama 4 Maverick model has 128 experts in its mixture of experts architecture.\n"
+            },
+            {
+              "type": "text",
+              "text": "END of knowledge_search tool results.\n"
+            },
+            {
+              "type": "text",
+              "text": "The above results were retrieved to help answer the user's query: \"Llama 4 Maverick model number of experts\". Use them as supporting information only in answering this query. Cite sources immediately at the end of sentences before punctuation, using `<|file-id|>` format like 'This is a fact <|file-Cn3MSNn72ENTiiq11Qda4A|>.'. Do not add extra punctuation. Use only the file IDs provided, do not invent new ones.\n"
+            }
+          ]
+        }
+      ],
+      "stream": true,
+      "stream_options": {
+        "include_usage": true
+      },
+      "tools": [
+        {
+          "type": "function",
+          "function": {
+            "name": "knowledge_search",
+            "description": "Search for information in a database.",
+            "parameters": {
+              "type": "object",
+              "properties": {
+                "query": {
+                  "type": "string",
+                  "description": "The query to search for. Can be a natural language sentence or keywords."
+                }
+              },
+              "required": [
+                "query"
+              ]
+            }
+          }
+        }
+      ]
+    },
+    "endpoint": "/v1/chat/completions",
+    "model": "gpt-4o"
+  },
+  "response": {
+    "body": [
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": "",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "qxiMbOb2xONvED"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": "The",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "G58v6jnZjGOYu"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": " L",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "fxvK2E9KzsZ4Qh"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": "lama",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "KMh23BEbyBFf"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": " ",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "khZLqq9dq1JVs50"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": "4",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "daMaLef5moqoEc6"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": " Maver",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "Cd9EAwdwxo"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": "ick",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "I0JQB094ggRj3"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": " model",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "ucfxMhve2z"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": " has",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "m4H3KsvURIcc"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": " ",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "adn7icPrZiPsOKU"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": "128",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "eXJB2DbT4sjvW"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": " experts",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "zcFMcygQ"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": " in",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "nipPRlDuOEz8K"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": " its",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "vnV7BYmJvj04"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": " mixture",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "hrijN588"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": " of",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "FcjZ5PIO2jswL"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": " experts",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "k9tHak4g"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": " architecture",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "Mv3"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": " <",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "FeQKZfXsh61kLW"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": "|",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "N7d96ngH25hy1DD"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": "file",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "X78VovNmcAxM"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": "-",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "x6AspjfSKgMx1nV"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": "528",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "7NZLsXRVCQOtG"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": "246",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "9G7Fo1P4gaW9E"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": "887",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "XHaRH6aQEwpXx"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": "823",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "Ui4dA5C7hyBs3"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": "|",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "G3N92kgznwmVeJv"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": ">.",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "XB0HKF8UhE71LI"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": "stop",
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": null,
+          "obfuscation": "0XQKNcPPlW"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-9b13d4fa1a58",
+          "choices": [],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_83554c687e",
+          "usage": {
+            "completion_tokens": 29,
+            "prompt_tokens": 355,
+            "total_tokens": 384,
+            "completion_tokens_details": {
+              "accepted_prediction_tokens": 0,
+              "audio_tokens": 0,
+              "reasoning_tokens": 0,
+              "rejected_prediction_tokens": 0
+            },
+            "prompt_tokens_details": {
+              "audio_tokens": 0,
+              "cached_tokens": 0
+            }
+          },
+          "obfuscation": "3g8L2kMn2uVi0"
+        }
+      }
+    ],
+    "is_streaming": true
+  },
+  "id_normalization_mapping": {}
+}

tests/integration/responses/recordings/a85a6b4b83b5cc55c03d941a9e35d55137e8e85e36c7adc10d0421f6912cd883.json

@@ -0,0 +1,763 @@
+{
+  "test_id": "tests/integration/responses/test_tool_responses.py::test_response_non_streaming_file_search[openai_client-txt=openai/gpt-4o:emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5:dim=768-llama_experts]",
+  "request": {
+    "method": "POST",
+    "url": "https://api.openai.com/v1/v1/chat/completions",
+    "headers": {},
+    "body": {
+      "model": "gpt-4o",
+      "messages": [
+        {
+          "role": "user",
+          "content": "How many experts does the Llama 4 Maverick model have?"
+        },
+        {
+          "role": "assistant",
+          "content": "",
+          "tool_calls": [
+            {
+              "index": 0,
+              "id": "call_UKFNZA0eSkL6fZHbs8ygBd5W",
+              "type": "function",
+              "function": {
+                "name": "knowledge_search",
+                "arguments": "{\"query\":\"Llama 4 Maverick model number of experts\"}"
+              }
+            }
+          ]
+        },
+        {
+          "role": "tool",
+          "tool_call_id": "call_UKFNZA0eSkL6fZHbs8ygBd5W",
+          "content": [
+            {
+              "type": "text",
+              "text": "knowledge_search tool found 1 chunks:\nBEGIN of knowledge_search tool results.\n"
+            },
+            {
+              "type": "text",
+              "text": "[1] document_id: file-861837565219, score: 0.015252754664575433, attributes: {'filename': 'test_response_non_streaming_file_search.txt', 'chunk_id': '869ae0c0-ab85-ca6f-e5d0-024381443c27', 'document_id': 'file-861837565219', 'token_count': 10.0, 'metadata_token_count': 13.0} cite as <|file-861837565219|>\nLlama 4 Maverick has 128 experts\n"
+            },
+            {
+              "type": "text",
+              "text": "END of knowledge_search tool results.\n"
+            },
+            {
+              "type": "text",
+              "text": "The above results were retrieved to help answer the user's query: \"Llama 4 Maverick model number of experts\". Use them as supporting information only in answering this query. Cite sources immediately at the end of sentences before punctuation, using `<|file-id|>` format like 'This is a fact <|file-Cn3MSNn72ENTiiq11Qda4A|>.'. Do not add extra punctuation. Use only the file IDs provided, do not invent new ones.\n"
+            }
+          ]
+        }
+      ],
+      "stream": true,
+      "stream_options": {
+        "include_usage": true
+      },
+      "tools": [
+        {
+          "type": "function",
+          "function": {
+            "name": "knowledge_search",
+            "description": "Search for information in a database.",
+            "parameters": {
+              "type": "object",
+              "properties": {
+                "query": {
+                  "type": "string",
+                  "description": "The query to search for. Can be a natural language sentence or keywords."
+                }
+              },
+              "required": [
+                "query"
+              ]
+            }
+          }
+        }
+      ]
+    },
+    "endpoint": "/v1/chat/completions",
+    "model": "gpt-4o"
+  },
+  "response": {
+    "body": [
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [
+            {
+              "delta": {
+                "content": "",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "6wH8vOctR2svNR"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [
+            {
+              "delta": {
+                "content": "The",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "5oz2dxNtl8vK6"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [
+            {
+              "delta": {
+                "content": " L",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "GKLiyEQApk31hb"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [
+            {
+              "delta": {
+                "content": "lama",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "I9X1EqJkuSbT"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [
+            {
+              "delta": {
+                "content": " ",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "5ISAGK6ExeKonxW"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [
+            {
+              "delta": {
+                "content": "4",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "D5w6XfYvfRb83fN"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [
+            {
+              "delta": {
+                "content": " Maver",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "IK92tDE63Z"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [
+            {
+              "delta": {
+                "content": "ick",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "9YxtDVmhxn6PF"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [
+            {
+              "delta": {
+                "content": " model",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "rnfyd19aew"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [
+            {
+              "delta": {
+                "content": " has",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "ovivqJM70Xwx"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [
+            {
+              "delta": {
+                "content": " ",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "A4SovCFionNzutJ"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [
+            {
+              "delta": {
+                "content": "128",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "huURqdjMt0b6n"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [
+            {
+              "delta": {
+                "content": " experts",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "jlM0JVa0"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [
+            {
+              "delta": {
+                "content": " <",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "Yyble5FrnTFCZk"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [
+            {
+              "delta": {
+                "content": "|",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "O0xPhtHpRbYoxrG"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [
+            {
+              "delta": {
+                "content": "file",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "N0d49Zf2BV9X"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [
+            {
+              "delta": {
+                "content": "-",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "XURNgWoMJ6UVFW4"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [
+            {
+              "delta": {
+                "content": "861",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "u889HDzEmluhx"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [
+            {
+              "delta": {
+                "content": "837",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "bzhHS40hC5a9O"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [
+            {
+              "delta": {
+                "content": "565",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "gOOIEbz760wrK"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [
+            {
+              "delta": {
+                "content": "219",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "BxOCPExRyzb1l"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [
+            {
+              "delta": {
+                "content": "|",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "YWbtDfSqck38Ean"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [
+            {
+              "delta": {
+                "content": ">.",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "ujVxH137evJENw"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": "stop",
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": null,
+          "obfuscation": "baBBFRPewx"
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "rec-a85a6b4b83b5",
+          "choices": [],
+          "created": 0,
+          "model": "gpt-4o-2024-08-06",
+          "object": "chat.completion.chunk",
+          "service_tier": "default",
+          "system_fingerprint": "fp_a4d13246c5",
+          "usage": {
+            "completion_tokens": 23,
+            "prompt_tokens": 348,
+            "total_tokens": 371,
+            "completion_tokens_details": {
+              "accepted_prediction_tokens": 0,
+              "audio_tokens": 0,
+              "reasoning_tokens": 0,
+              "rejected_prediction_tokens": 0
+            },
+            "prompt_tokens_details": {
+              "audio_tokens": 0,
+              "cached_tokens": 0
+            }
+          },
+          "obfuscation": "amtwuUWgCoeCm"
+        }
+      }
+    ],
+    "is_streaming": true
+  },
+  "id_normalization_mapping": {}
+}

tests/integration/responses/recordings/models-48e344be78178094bdd599f7cf97f076fdd1c176a6120fca9786d83807719f1a-fc0119e1.json

@@ -0,0 +1,547 @@
+{
+  "test_id": "tests/integration/responses/test_basic_responses.py::test_include_logprobs_streaming[txt=openai/gpt-4o]",
+  "request": {
+    "method": "POST",
+    "url": "https://generativelanguage.googleapis.com/v1beta/openai/v1/models",
+    "headers": {},
+    "body": {},
+    "endpoint": "/v1/models",
+    "model": ""
+  },
+  "response": {
+    "body": [
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/embedding-gecko-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Embedding Gecko"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-pro",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Pro"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-exp",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash Experimental"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash 001"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-exp-image-generation",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash (Image Generation) Experimental"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-lite-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash-Lite 001"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-lite",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash-Lite"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-lite-preview-02-05",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash-Lite Preview 02-05"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-lite-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash-Lite Preview"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-exp-1206",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Experimental 1206"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-preview-tts",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash Preview TTS"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-pro-preview-tts",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Pro Preview TTS"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemma-3-1b-it",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemma 3 1B"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemma-3-4b-it",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemma 3 4B"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemma-3-12b-it",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemma 3 12B"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemma-3-27b-it",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemma 3 27B"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemma-3n-e4b-it",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemma 3n E4B"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemma-3n-e2b-it",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemma 3n E2B"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-flash-latest",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Flash Latest"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-flash-lite-latest",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Flash-Lite Latest"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-pro-latest",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Pro Latest"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-lite",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash-Lite"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-image-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Nano Banana"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-image",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Nano Banana"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-preview-09-2025",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash Preview Sep 2025"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-lite-preview-09-2025",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash-Lite Preview Sep 2025"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-3-pro-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 3 Pro Preview"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-3-pro-image-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Nano Banana Pro"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/nano-banana-pro-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Nano Banana Pro"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-robotics-er-1.5-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Robotics-ER 1.5 Preview"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-computer-use-preview-10-2025",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Computer Use Preview 10-2025"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/deep-research-pro-preview-12-2025",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Deep Research Pro Preview (Dec-12-2025)"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/embedding-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Embedding 001"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/text-embedding-004",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Text Embedding 004"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-embedding-exp-03-07",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Embedding Experimental 03-07"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-embedding-exp",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Embedding Experimental"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-embedding-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Embedding 001"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/aqa",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Model that performs Attributed Question Answering."
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/imagen-4.0-generate-preview-06-06",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Imagen 4 (Preview)"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/imagen-4.0-ultra-generate-preview-06-06",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Imagen 4 Ultra (Preview)"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/imagen-4.0-generate-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Imagen 4"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/imagen-4.0-ultra-generate-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Imagen 4 Ultra"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/imagen-4.0-fast-generate-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Imagen 4 Fast"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/veo-2.0-generate-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Veo 2"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/veo-3.0-generate-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Veo 3"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/veo-3.0-fast-generate-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Veo 3 fast"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/veo-3.1-generate-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Veo 3.1"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/veo-3.1-fast-generate-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Veo 3.1 fast"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-native-audio-latest",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash Native Audio Latest"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-native-audio-preview-09-2025",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash Native Audio Preview 09-2025"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/lyria-realtime-exp",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Lyria Realtime Experimental"
+        }
+      }
+    ],
+    "is_streaming": false
+  },
+  "id_normalization_mapping": {}
+}

tests/integration/responses/recordings/models-54503512995f4c6db759e2e7f2580f445f42b1c1d3714fa8a3acaac3d476e481-fc0119e1.json

@@ -0,0 +1,547 @@
+{
+  "test_id": "tests/integration/responses/test_basic_responses.py::test_include_logprobs_with_function_tools[txt=openai/gpt-4o]",
+  "request": {
+    "method": "POST",
+    "url": "https://generativelanguage.googleapis.com/v1beta/openai/v1/models",
+    "headers": {},
+    "body": {},
+    "endpoint": "/v1/models",
+    "model": ""
+  },
+  "response": {
+    "body": [
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/embedding-gecko-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Embedding Gecko"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-pro",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Pro"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-exp",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash Experimental"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash 001"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-exp-image-generation",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash (Image Generation) Experimental"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-lite-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash-Lite 001"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-lite",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash-Lite"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-lite-preview-02-05",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash-Lite Preview 02-05"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-lite-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash-Lite Preview"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-exp-1206",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Experimental 1206"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-preview-tts",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash Preview TTS"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-pro-preview-tts",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Pro Preview TTS"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemma-3-1b-it",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemma 3 1B"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemma-3-4b-it",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemma 3 4B"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemma-3-12b-it",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemma 3 12B"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemma-3-27b-it",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemma 3 27B"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemma-3n-e4b-it",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemma 3n E4B"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemma-3n-e2b-it",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemma 3n E2B"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-flash-latest",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Flash Latest"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-flash-lite-latest",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Flash-Lite Latest"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-pro-latest",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Pro Latest"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-lite",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash-Lite"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-image-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Nano Banana"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-image",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Nano Banana"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-preview-09-2025",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash Preview Sep 2025"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-lite-preview-09-2025",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash-Lite Preview Sep 2025"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-3-pro-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 3 Pro Preview"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-3-pro-image-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Nano Banana Pro"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/nano-banana-pro-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Nano Banana Pro"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-robotics-er-1.5-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Robotics-ER 1.5 Preview"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-computer-use-preview-10-2025",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Computer Use Preview 10-2025"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/deep-research-pro-preview-12-2025",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Deep Research Pro Preview (Dec-12-2025)"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/embedding-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Embedding 001"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/text-embedding-004",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Text Embedding 004"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-embedding-exp-03-07",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Embedding Experimental 03-07"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-embedding-exp",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Embedding Experimental"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-embedding-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Embedding 001"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/aqa",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Model that performs Attributed Question Answering."
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/imagen-4.0-generate-preview-06-06",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Imagen 4 (Preview)"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/imagen-4.0-ultra-generate-preview-06-06",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Imagen 4 Ultra (Preview)"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/imagen-4.0-generate-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Imagen 4"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/imagen-4.0-ultra-generate-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Imagen 4 Ultra"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/imagen-4.0-fast-generate-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Imagen 4 Fast"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/veo-2.0-generate-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Veo 2"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/veo-3.0-generate-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Veo 3"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/veo-3.0-fast-generate-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Veo 3 fast"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/veo-3.1-generate-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Veo 3.1"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/veo-3.1-fast-generate-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Veo 3.1 fast"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-native-audio-latest",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash Native Audio Latest"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-native-audio-preview-09-2025",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash Native Audio Preview 09-2025"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/lyria-realtime-exp",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Lyria Realtime Experimental"
+        }
+      }
+    ],
+    "is_streaming": false
+  },
+  "id_normalization_mapping": {}
+}

tests/integration/responses/recordings/models-875254c069dcb861033e5a4e9100179cc21c0864901048f21574b80ff24fb75d-fc0119e1.json

@@ -0,0 +1,547 @@
+{
+  "test_id": "tests/integration/responses/test_basic_responses.py::test_include_logprobs_with_web_search[txt=openai/gpt-4o]",
+  "request": {
+    "method": "POST",
+    "url": "https://generativelanguage.googleapis.com/v1beta/openai/v1/models",
+    "headers": {},
+    "body": {},
+    "endpoint": "/v1/models",
+    "model": ""
+  },
+  "response": {
+    "body": [
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/embedding-gecko-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Embedding Gecko"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-pro",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Pro"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-exp",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash Experimental"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash 001"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-exp-image-generation",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash (Image Generation) Experimental"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-lite-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash-Lite 001"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-lite",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash-Lite"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-lite-preview-02-05",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash-Lite Preview 02-05"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-lite-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash-Lite Preview"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-exp-1206",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Experimental 1206"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-preview-tts",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash Preview TTS"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-pro-preview-tts",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Pro Preview TTS"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemma-3-1b-it",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemma 3 1B"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemma-3-4b-it",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemma 3 4B"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemma-3-12b-it",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemma 3 12B"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemma-3-27b-it",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemma 3 27B"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemma-3n-e4b-it",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemma 3n E4B"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemma-3n-e2b-it",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemma 3n E2B"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-flash-latest",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Flash Latest"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-flash-lite-latest",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Flash-Lite Latest"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-pro-latest",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Pro Latest"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-lite",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash-Lite"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-image-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Nano Banana"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-image",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Nano Banana"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-preview-09-2025",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash Preview Sep 2025"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-lite-preview-09-2025",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash-Lite Preview Sep 2025"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-3-pro-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 3 Pro Preview"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-3-pro-image-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Nano Banana Pro"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/nano-banana-pro-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Nano Banana Pro"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-robotics-er-1.5-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Robotics-ER 1.5 Preview"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-computer-use-preview-10-2025",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Computer Use Preview 10-2025"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/deep-research-pro-preview-12-2025",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Deep Research Pro Preview (Dec-12-2025)"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/embedding-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Embedding 001"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/text-embedding-004",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Text Embedding 004"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-embedding-exp-03-07",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Embedding Experimental 03-07"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-embedding-exp",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Embedding Experimental"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-embedding-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Embedding 001"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/aqa",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Model that performs Attributed Question Answering."
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/imagen-4.0-generate-preview-06-06",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Imagen 4 (Preview)"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/imagen-4.0-ultra-generate-preview-06-06",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Imagen 4 Ultra (Preview)"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/imagen-4.0-generate-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Imagen 4"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/imagen-4.0-ultra-generate-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Imagen 4 Ultra"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/imagen-4.0-fast-generate-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Imagen 4 Fast"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/veo-2.0-generate-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Veo 2"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/veo-3.0-generate-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Veo 3"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/veo-3.0-fast-generate-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Veo 3 fast"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/veo-3.1-generate-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Veo 3.1"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/veo-3.1-fast-generate-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Veo 3.1 fast"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-native-audio-latest",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash Native Audio Latest"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-native-audio-preview-09-2025",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash Native Audio Preview 09-2025"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/lyria-realtime-exp",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Lyria Realtime Experimental"
+        }
+      }
+    ],
+    "is_streaming": false
+  },
+  "id_normalization_mapping": {}
+}

tests/integration/responses/recordings/models-cc7501817830a20cc746a1d560a75f58b9111b77fa24864ac237da21d62a8ced-fc0119e1.json

@@ -0,0 +1,547 @@
+{
+  "test_id": "tests/integration/responses/test_basic_responses.py::test_include_logprobs_non_streaming[txt=openai/gpt-4o]",
+  "request": {
+    "method": "POST",
+    "url": "https://generativelanguage.googleapis.com/v1beta/openai/v1/models",
+    "headers": {},
+    "body": {},
+    "endpoint": "/v1/models",
+    "model": ""
+  },
+  "response": {
+    "body": [
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/embedding-gecko-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Embedding Gecko"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-pro",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Pro"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-exp",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash Experimental"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash 001"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-exp-image-generation",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash (Image Generation) Experimental"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-lite-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash-Lite 001"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-lite",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash-Lite"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-lite-preview-02-05",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash-Lite Preview 02-05"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.0-flash-lite-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.0 Flash-Lite Preview"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-exp-1206",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Experimental 1206"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-preview-tts",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash Preview TTS"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-pro-preview-tts",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Pro Preview TTS"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemma-3-1b-it",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemma 3 1B"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemma-3-4b-it",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemma 3 4B"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemma-3-12b-it",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemma 3 12B"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemma-3-27b-it",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemma 3 27B"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemma-3n-e4b-it",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemma 3n E4B"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemma-3n-e2b-it",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemma 3n E2B"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-flash-latest",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Flash Latest"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-flash-lite-latest",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Flash-Lite Latest"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-pro-latest",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Pro Latest"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-lite",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash-Lite"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-image-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Nano Banana"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-image",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Nano Banana"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-preview-09-2025",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash Preview Sep 2025"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-lite-preview-09-2025",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash-Lite Preview Sep 2025"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-3-pro-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 3 Pro Preview"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-3-pro-image-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Nano Banana Pro"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/nano-banana-pro-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Nano Banana Pro"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-robotics-er-1.5-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Robotics-ER 1.5 Preview"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-computer-use-preview-10-2025",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Computer Use Preview 10-2025"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/deep-research-pro-preview-12-2025",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Deep Research Pro Preview (Dec-12-2025)"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/embedding-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Embedding 001"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/text-embedding-004",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Text Embedding 004"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-embedding-exp-03-07",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Embedding Experimental 03-07"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-embedding-exp",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Embedding Experimental"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-embedding-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini Embedding 001"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/aqa",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Model that performs Attributed Question Answering."
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/imagen-4.0-generate-preview-06-06",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Imagen 4 (Preview)"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/imagen-4.0-ultra-generate-preview-06-06",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Imagen 4 Ultra (Preview)"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/imagen-4.0-generate-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Imagen 4"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/imagen-4.0-ultra-generate-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Imagen 4 Ultra"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/imagen-4.0-fast-generate-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Imagen 4 Fast"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/veo-2.0-generate-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Veo 2"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/veo-3.0-generate-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Veo 3"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/veo-3.0-fast-generate-001",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Veo 3 fast"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/veo-3.1-generate-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Veo 3.1"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/veo-3.1-fast-generate-preview",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Veo 3.1 fast"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-native-audio-latest",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash Native Audio Latest"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/gemini-2.5-flash-native-audio-preview-09-2025",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Gemini 2.5 Flash Native Audio Preview 09-2025"
+        }
+      },
+      {
+        "__type__": "openai.types.model.Model",
+        "__data__": {
+          "id": "models/lyria-realtime-exp",
+          "created": null,
+          "object": "model",
+          "owned_by": "google",
+          "display_name": "Lyria Realtime Experimental"
+        }
+      }
+    ],
+    "is_streaming": false
+  },
+  "id_normalization_mapping": {}
+}

tests/unit/core/test_stack_validation.py

@@ -90,14 +90,12 @@ class TestVectorStoresValidation:
 
     async def test_validate_rewrite_query_prompt_missing_placeholder(self):
         """Test validation fails when prompt template is missing {query} placeholder."""
-        config = VectorStoresConfig(
-            rewrite_query_params=RewriteQueryParams(
-                prompt="This prompt has no placeholder",
-            ),
-        )
+        from pydantic import ValidationError
 
-        with pytest.raises(ValueError, match="'\\{query\\}' placeholder is required"):
-            await validate_vector_stores_config(config, {})
+        with pytest.raises(ValidationError, match=r"prompt must contain \{query\} placeholder"):
+            RewriteQueryParams(
+                prompt="This prompt has no placeholder",
+            )
 
 
 class TestSafetyConfigValidation:

tests/unit/core/test_vector_stores_config.py

@@ -0,0 +1,170 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+import pytest
+from pydantic import ValidationError
+
+from llama_stack.core.datatypes import QualifiedModel, RewriteQueryParams, VectorStoresConfig
+
+
+class TestVectorStoresConfigValidation:
+    """Test validation of VectorStoresConfig prompt templates."""
+
+    def test_default_config_is_valid(self):
+        """Test that default configuration passes all validation."""
+        config = VectorStoresConfig()
+
+        # Verify all sub-configs exist with valid templates
+        assert config.file_search_params.header_template is not None
+        assert config.context_prompt_params.chunk_annotation_template is not None
+        assert config.annotation_prompt_params.chunk_annotation_template is not None
+
+        # Verify required placeholders are present
+        assert "{num_chunks}" in config.file_search_params.header_template
+        assert "knowledge_search" in config.file_search_params.header_template.lower()
+        assert "{chunk.content}" in config.context_prompt_params.chunk_annotation_template
+        assert "{query}" in config.context_prompt_params.context_template
+
+    def test_template_validation_errors(self):
+        """Test that templates fail validation for common errors."""
+        from llama_stack.core.datatypes import AnnotationPromptParams, ContextPromptParams, FileSearchParams
+
+        # Empty templates fail
+        with pytest.raises(ValidationError, match="must not be empty"):
+            FileSearchParams(header_template="")
+
+        # Missing required placeholders fail
+        with pytest.raises(ValidationError, match="must contain {num_chunks} placeholder"):
+            FileSearchParams(header_template="search found results")
+
+        with pytest.raises(ValidationError, match="must contain 'knowledge_search' keyword"):
+            FileSearchParams(header_template="search found {num_chunks} results")
+
+        with pytest.raises(ValidationError, match="must contain {chunk.content} placeholder"):
+            ContextPromptParams(chunk_annotation_template="Result {index}: some content")
+
+        with pytest.raises(ValidationError, match="must contain {query} placeholder"):
+            ContextPromptParams(context_template="Retrieved results. Use as context.")
+
+        with pytest.raises(ValidationError, match="must contain {file_id} placeholder"):
+            AnnotationPromptParams(chunk_annotation_template="[{index}] {chunk_text}")
+
+    def test_rewrite_query_params_validation(self):
+        """Test RewriteQueryParams validation."""
+        model = QualifiedModel(provider_id="test", model_id="test-model")
+
+        # Valid config works
+        valid_params = RewriteQueryParams(
+            model=model, prompt="Expand this query: {query}", max_tokens=100, temperature=0.5
+        )
+        assert valid_params.prompt == "Expand this query: {query}"
+
+        # Invalid configurations fail
+        with pytest.raises(ValidationError, match="prompt must contain \\{query\\} placeholder"):
+            RewriteQueryParams(model=model, prompt="No placeholder here")
+
+        with pytest.raises(ValidationError, match="max_tokens must be positive"):
+            RewriteQueryParams(model=model, max_tokens=0)
+
+        with pytest.raises(ValidationError, match="temperature must be between 0.0 and 2.0"):
+            RewriteQueryParams(model=model, temperature=3.0)
+
+    def test_custom_configuration(self):
+        """Test complete custom configuration."""
+        from llama_stack.core.datatypes import AnnotationPromptParams, ContextPromptParams, FileSearchParams
+
+        config = VectorStoresConfig(
+            default_provider_id="test-provider",
+            default_embedding_model=QualifiedModel(provider_id="test", model_id="embedding-model"),
+            file_search_params=FileSearchParams(
+                header_template="Custom knowledge_search found {num_chunks} items:\nSTART\n", footer_template="END\n"
+            ),
+            context_prompt_params=ContextPromptParams(
+                chunk_annotation_template="Item {index}: {chunk.content} | Meta: {metadata}\n",
+                context_template='Results for "{query}": Use carefully.\n',
+            ),
+            annotation_prompt_params=AnnotationPromptParams(
+                enable_annotations=False,
+                annotation_instruction_template=" Custom citation format.",
+                chunk_citation_template="[{index}] {metadata_text} --> {file_id}\n{chunk_text}\n",
+            ),
+        )
+
+        assert config.default_provider_id == "test-provider"
+        assert "Custom knowledge_search" in config.file_search_params.header_template
+        assert config.annotation_prompt_params.enable_annotations is False
+
+
+class TestOptionalArchitecture:
+    """Test optional sub-config architecture and constants fallback."""
+
+    def test_guaranteed_defaults_behavior(self):
+        """Test that sub-configs are always instantiated with defaults."""
+        # Sub-configs are always instantiated due to default_factory
+        config = VectorStoresConfig()
+        assert config.file_search_params is not None
+        assert config.context_prompt_params is not None
+        assert config.annotation_prompt_params is not None
+        assert "{num_chunks}" in config.file_search_params.header_template
+
+    def test_guaranteed_defaults_match_constants(self):
+        """Test that guaranteed defaults match expected constant values."""
+        from llama_stack.providers.utils.memory.constants import (
+            DEFAULT_CONTEXT_TEMPLATE,
+            DEFAULT_FILE_SEARCH_HEADER_TEMPLATE,
+        )
+
+        # Create config with guaranteed defaults
+        config = VectorStoresConfig()
+
+        # Verify defaults match constants
+        header_template = config.file_search_params.header_template
+        context_template = config.context_prompt_params.context_template
+
+        assert header_template == DEFAULT_FILE_SEARCH_HEADER_TEMPLATE
+        assert context_template == DEFAULT_CONTEXT_TEMPLATE
+
+        # Verify templates can be formatted successfully
+        formatted_header = header_template.format(num_chunks=3)
+        assert "3" in formatted_header
+        assert "knowledge_search" in formatted_header.lower()
+
+        formatted_context = context_template.format(
+            query="test query", annotation_instruction=" Cite sources properly."
+        )
+        assert "test query" in formatted_context
+
+    def test_end_to_end_template_usage(self):
+        """Test that guaranteed defaults lead to working template output."""
+        # Create config with guaranteed defaults
+        config = VectorStoresConfig()
+
+        header_template = config.file_search_params.header_template
+        chunk_template = config.context_prompt_params.chunk_annotation_template
+
+        # Generate realistic output
+        test_chunks = [
+            {"content": "Paris is the capital of France.", "metadata": {"doc": "geo.pdf"}},
+            {"content": "London is the capital of England.", "metadata": {"doc": "cities.txt"}},
+        ]
+
+        header_output = header_template.format(num_chunks=len(test_chunks))
+        chunk_outputs = []
+        for i, chunk_data in enumerate(test_chunks):
+
+            class MockChunk:
+                content = chunk_data["content"]
+
+            chunk_output = chunk_template.format(index=i + 1, chunk=MockChunk(), metadata=chunk_data["metadata"])
+            chunk_outputs.append(chunk_output)
+
+        complete_output = header_output + "".join(chunk_outputs)
+
+        # Verify output is substantial and contains expected content
+        assert len(complete_output) > 100
+        assert "knowledge_search" in complete_output.lower()
+        assert "Paris is the capital" in complete_output
+        assert "London is the capital" in complete_output

tests/unit/rag/test_rag_query.py

@@ -8,21 +8,26 @@ from unittest.mock import AsyncMock, MagicMock
 
 import pytest
 
+from llama_stack.providers.inline.tool_runtime.rag.config import RagToolRuntimeConfig
 from llama_stack.providers.inline.tool_runtime.rag.memory import MemoryToolRuntimeImpl
 from llama_stack_api import Chunk, ChunkMetadata, QueryChunksResponse, RAGQueryConfig
 
 
 class TestRagQuery:
     async def test_query_raises_on_empty_vector_store_ids(self):
+        config = RagToolRuntimeConfig()
         rag_tool = MemoryToolRuntimeImpl(
-            config=MagicMock(), vector_io_api=MagicMock(), inference_api=MagicMock(), files_api=MagicMock()
+            config=config, vector_io_api=MagicMock(), inference_api=MagicMock(), files_api=MagicMock()
         )
         with pytest.raises(ValueError):
             await rag_tool.query(content=MagicMock(), vector_store_ids=[])
 
     async def test_query_chunk_metadata_handling(self):
+        # Create config with default templates
+        config = RagToolRuntimeConfig()
+
         rag_tool = MemoryToolRuntimeImpl(
-            config=MagicMock(), vector_io_api=MagicMock(), inference_api=MagicMock(), files_api=MagicMock()
+            config=config, vector_io_api=MagicMock(), inference_api=MagicMock(), files_api=MagicMock()
         )
         content = "test query content"
         vector_store_ids = ["db1"]
@@ -33,9 +38,8 @@ class TestRagQuery:
             source="test_source",
             metadata_token_count=5,
         )
-        interleaved_content = MagicMock()
         chunk = Chunk(
-            content=interleaved_content,
+            content="This is test chunk content from document 1",
             chunk_id="chunk1",
             metadata={
                 "key1": "value1",
@@ -78,8 +82,11 @@ class TestRagQuery:
             RAGQueryConfig(mode="wrong_mode")
 
     async def test_query_adds_vector_store_id_to_chunk_metadata(self):
+        # Create config with default templates
+        config = RagToolRuntimeConfig()
+
         rag_tool = MemoryToolRuntimeImpl(
-            config=MagicMock(),
+            config=config,
             vector_io_api=MagicMock(),
             inference_api=MagicMock(),
             files_api=MagicMock(),