Add enable_tools, enabled_tools, session_id to /v1/messages endpoint

Support the same shorthand as /v1/chat/completions: enable_tools=true
with an optional enabled_tools list uses built-in server tools without
requiring full Anthropic tool definitions. session_id is passed through
for sandbox isolation. max_tokens is now optional.

studio/backend/models/inference.py

@@ -621,7 +621,7 @@ class AnthropicTool(BaseModel):
 
 class AnthropicMessagesRequest(BaseModel):
     model: str = "default"
-    max_tokens: int
+    max_tokens: Optional[int] = None
     messages: list[AnthropicMessage]
     system: Optional[Union[str, list]] = None
     tools: Optional[list[AnthropicTool]] = None
@@ -632,6 +632,10 @@ class AnthropicMessagesRequest(BaseModel):
     top_k: Optional[int] = None
     stop_sequences: Optional[list[str]] = None
     metadata: Optional[dict] = None
+    # [x-unsloth] extensions — mirror the OpenAI endpoint convenience fields
+    enable_tools: Optional[bool] = None
+    enabled_tools: Optional[list[str]] = None
+    session_id: Optional[str] = None
     model_config = {"extra": "allow"}
 
 

studio/backend/routes/inference.py

@@ -2255,16 +2255,26 @@ async def anthropic_messages(
     cancel_event = threading.Event()
 
     # ── Tool-calling path ─────────────────────────────────────
-    use_tools = (
-        payload.tools
-        and len(payload.tools) > 0
-        and llama_backend.supports_tools
+    # Two ways to enable tools:
+    # 1. Anthropic-style: send full tool definitions in payload.tools
+    # 2. Unsloth shorthand: enable_tools=true + optional enabled_tools list
+    use_tools = llama_backend.supports_tools and (
+        (payload.tools and len(payload.tools) > 0)
+        or payload.enable_tools
     )
 
     if use_tools:
         from core.inference.tools import ALL_TOOLS
 
-        openai_tools = anthropic_tools_to_openai(payload.tools)
+        if payload.tools and len(payload.tools) > 0:
+            openai_tools = anthropic_tools_to_openai(payload.tools)
+        elif payload.enabled_tools is not None:
+            openai_tools = [
+                t for t in ALL_TOOLS
+                if t["function"]["name"] in payload.enabled_tools
+            ]
+        else:
+            openai_tools = ALL_TOOLS
 
         # Build tool-use system prompt nudge (same logic as /chat/completions)
         _tool_names = {t["function"]["name"] for t in openai_tools}
@@ -2339,6 +2349,7 @@ async def anthropic_messages(
                 max_tool_iterations = 25,
                 auto_heal_tool_calls = True,
                 tool_call_timeout = 300,
+                session_id = payload.session_id,
             )
 
         if payload.stream:

studio/backend/tests/test_anthropic_messages.py

@@ -41,13 +41,19 @@ from core.inference.anthropic_compat import (
 class TestAnthropicModels:
 
     def test_minimal_request(self):
+        req = AnthropicMessagesRequest(
+            messages = [{"role": "user", "content": "Hi"}],
+        )
+        assert req.max_tokens is None
+        assert req.model == "default"
+        assert req.stream is False
+
+    def test_max_tokens_optional(self):
         req = AnthropicMessagesRequest(
             max_tokens = 100,
             messages = [{"role": "user", "content": "Hi"}],
         )
         assert req.max_tokens == 100
-        assert req.model == "default"
-        assert req.stream is False
 
     def test_system_as_string(self):
         req = AnthropicMessagesRequest(
@@ -81,6 +87,25 @@ class TestAnthropicModels:
         )
         assert req.stream is False
 
+    def test_enable_tools_shorthand(self):
+        req = AnthropicMessagesRequest(
+            messages = [{"role": "user", "content": "Hi"}],
+            enable_tools = True,
+            enabled_tools = ["web_search", "python"],
+            session_id = "my-session",
+        )
+        assert req.enable_tools is True
+        assert req.enabled_tools == ["web_search", "python"]
+        assert req.session_id == "my-session"
+
+    def test_extension_fields_default_none(self):
+        req = AnthropicMessagesRequest(
+            messages = [{"role": "user", "content": "Hi"}],
+        )
+        assert req.enable_tools is None
+        assert req.enabled_tools is None
+        assert req.session_id is None
+
     def test_response_model_defaults(self):
         resp = AnthropicMessagesResponse()
         assert resp.type == "message"