feat: init commint

backend/apps/modelhub/services.py

@@ -21,6 +21,12 @@ from openai import (
 
 from apps.modelhub.crypto import CredentialEncryptionError, decrypt_secret
 from apps.modelhub.models import ModelDeployment, ModelInvocation
+from apps.modelhub.structured_output import (
+    STRUCTURED_OUTPUT_TEST_PROMPT,
+    STRUCTURED_OUTPUT_TEST_SCHEMA,
+    StructuredOutputError,
+    build_structured_request,
+)
 
 TRANSIENT_ERRORS = (APIConnectionError, APITimeoutError, RateLimitError)
 
@@ -44,6 +50,7 @@ def _request_completion(
     *,
     temperature: float,
     max_output_tokens: int,
+    response_format: dict[str, Any] | None = None,
     timeout_seconds: float | None = None,
 ) -> CompletionResult:
     provider = deployment.provider
@@ -57,11 +64,16 @@ def _request_completion(
         # Retry here so the platform can expose it instead of waiting on opaque SDK retries.
         max_retries=0,
     )
+    request_options: dict[str, Any] = {
+        "model": deployment.model_name,
+        "messages": messages,
+        "temperature": temperature,
+        "max_tokens": max_output_tokens,
+    }
+    if response_format is not None:
+        request_options["response_format"] = response_format
     response = client.chat.completions.create(
-        model=deployment.model_name,
-        messages=messages,
-        temperature=temperature,
-        max_tokens=max_output_tokens,
+        **request_options,
     )
     content = response.choices[0].message.content or ""
     usage = response.usage
@@ -96,13 +108,21 @@ def execute_invocation(
     *,
     temperature: float | None = None,
     max_output_tokens: int | None = None,
+    output_schema: dict[str, Any] | None = None,
+    schema_name: str | None = None,
     on_retry: Callable[[int, str], None] | None = None,
     total_timeout_seconds: float | None = None,
 ) -> ModelInvocation:
     """在总时间预算内调用模型，分类错误、限制重试并记录脱敏终态。"""
 
     deployment = invocation.deployment
-    if deployment is None or not deployment.enabled or not deployment.provider.enabled:
+    if (
+        deployment is None
+        or deployment.archived_at is not None
+        or deployment.provider.archived_at is not None
+        or not deployment.enabled
+        or not deployment.provider.enabled
+    ):
         invocation.status = "failed"
         invocation.error_code = "deployment_unavailable"
         invocation.error_message = "模型配置或渠道未启用"
@@ -110,6 +130,27 @@ def execute_invocation(
         invocation.save(update_fields=["status", "error_code", "error_message", "finished_at"])
         return invocation
 
+    request_messages = messages
+    response_format = None
+    structured_metadata = None
+    if output_schema is not None:
+        try:
+            request_messages, response_format, structured_metadata = build_structured_request(
+                messages,
+                mode=deployment.structured_output_mode,
+                output_schema=output_schema,
+                schema_name=schema_name or f"invocation_{invocation.public_id.hex}",
+            )
+        except StructuredOutputError as error:
+            invocation.status = "failed"
+            invocation.error_code = error.code
+            invocation.error_message = str(error)
+            invocation.finished_at = timezone.now()
+            invocation.save(
+                update_fields=["status", "error_code", "error_message", "finished_at"]
+            )
+            return invocation
+
     invocation.status = "running"
     invocation.started_at = timezone.now()
     invocation.model_snapshot = {
@@ -121,8 +162,18 @@ def execute_invocation(
         "capability": deployment.capability,
         "temperature": temperature if temperature is not None else deployment.default_temperature,
         "max_output_tokens": max_output_tokens or deployment.max_output_tokens,
+        "structured_output": structured_metadata,
     }
-    invocation.save(update_fields=["status", "started_at", "model_snapshot"])
+    if structured_metadata is not None:
+        invocation.input_snapshot = {
+            **invocation.input_snapshot,
+            "structured_output": structured_metadata,
+            "output_schema": output_schema,
+            "response_format": response_format,
+        }
+    invocation.save(
+        update_fields=["status", "started_at", "model_snapshot", "input_snapshot"]
+    )
     started = monotonic()
     result: CompletionResult | None = None
     last_error: Exception | None = None
@@ -136,17 +187,21 @@ def execute_invocation(
         try:
             result = _request_completion(
                 deployment,
-                messages,
+                request_messages,
                 temperature=temperature
                 if temperature is not None
                 else deployment.default_temperature,
                 max_output_tokens=max_output_tokens or deployment.max_output_tokens,
+                response_format=response_format,
                 timeout_seconds=remaining,
             )
             invocation.retry_count = attempt
             break
         except Exception as error:  # provider libraries expose several subclasses
             code, message, transient = _error_details(error)
+            if response_format is not None and code == "bad_request":
+                code = "structured_output_unsupported"
+                message = "模型渠道拒绝当前结构化输出配置"
             last_error = error
             invocation.retry_count = attempt
             if not transient or attempt == 1:
@@ -199,3 +254,21 @@ def create_model_test(
         input_snapshot={"messages": [{"role": "user", "content": prompt}]},
         created_by=user,
     )
+
+
+def create_structured_output_test(
+    deployment: ModelDeployment,
+    user=None,
+) -> ModelInvocation:
+    """创建单次、不可修复的结构化输出能力测试。"""
+
+    return ModelInvocation.objects.create(
+        deployment=deployment,
+        invocation_type="structured_output_test",
+        input_snapshot={
+            "messages": [{"role": "user", "content": STRUCTURED_OUTPUT_TEST_PROMPT}],
+            "output_schema": STRUCTURED_OUTPUT_TEST_SCHEMA,
+            "schema_name": f"deployment_{deployment.id}_structured_output_test",
+        },
+        created_by=user,
+    )