feat(models): add Anthropic Messages dialect

docs/guide/infer.md

@@ -57,6 +57,40 @@ used, not whether the service starts.
 
 Models with a `path` field (and no `api_base`) or an `infer` section in the YAML config are automatically launched by `sieval run` and stopped after evaluation completes.
 
+### Anthropic Messages
+
+To call the native Anthropic Messages API, select the dialect explicitly and
+provide an external endpoint and credential:
+
+```yaml
+models:
+  claude:
+    name: claude-sonnet-4-5
+    dialect: anthropic_messages
+    api_base: https://api.anthropic.com/v1
+    api_key: "<your Anthropic API key>"
+    args:
+      max_tokens: 1024
+```
+
+The dialect sends JSON or SSE requests to `POST /v1/messages`. Every request
+must specify `max_tokens`; set a model-wide default under `models.<name>.args`,
+as above, or override it for one task under `tasks.<name>.infer_args`.
+
+Anthropic Messages has no per-request `seed`. Deterministic mode therefore does
+not inject one for this dialect, and an explicit `seed` is rejected before any
+network I/O.
+
+Raw request passthrough is intentionally unavailable. `dialect_options` cannot
+inject arbitrary Anthropic body fields or HTTP headers; in particular, there is
+currently no way to send the `anthropic-beta` header. Features that require a
+beta header are unsupported until they receive an explicit, audited mapping.
+
+The YAML loader does not expand environment-variable expressions in `api_key`.
+Replace the placeholder above through your configuration/secret-management
+workflow; omit `api_key` only when the target endpoint does not require
+authentication.
+
 ## Environment Variables
 
 Custom environment variables can be passed through the YAML config's `infer.env` section. Values are injected into the inference engine process.

sieval/core/models/dialect.py

@@ -627,11 +627,17 @@ def validate(self, plan: RuntimePlanView, req: Request, response: Response) -> N
         # must be able to serve.  Only the projected request decides which
         # response channels this particular call must return.
         required = set(required_response_channels(req))
+        finish_reasons = response.finish_reasons
+        refused = (
+            finish_reasons is not None
+            and bool(finish_reasons)
+            and all(reason == "refusal" for reason in finish_reasons)
+        )
         for name, rule in self.rules.items():
             value = getattr(response, name)
             if rule.guarantee is Guarantee.NEVER and value is not None:
                 raise OutputContractError(f"dialect promised {name!r} would be absent")
-            if name in required:
+            if name in required and not refused:
                 if rule.guarantee is not Guarantee.PRESENT_OR_ERROR:
                     raise OutputContractError(
                         f"{name!r} is required but has {rule.guarantee.value} guarantee"
@@ -643,7 +649,7 @@ def validate(self, plan: RuntimePlanView, req: Request, response: Response) -> N
             if value is not None:
                 rule.validator(value)
 
-        if req.session.opaque_continuation is not None:
+        if req.session.opaque_continuation is not None and not refused:
             reasoning = response.reasoning
             if reasoning is None or any(
                 item is None

sieval/core/models/dialect_registry.py

@@ -30,6 +30,10 @@
 from .connection_factory import CONNECTION_FACTORY_REGISTRY
 from .deployment import ConnectionPool, Deployment, RouteIntent, resolve_route
 from .dialect import Dialect, active_request_leaves
+from .dialects.anthropic_messages import (
+    CAPABILITY_DECISIONS as ANTHROPIC_MESSAGES_CAPABILITY_DECISIONS,
+)
+from .dialects.anthropic_messages import AnthropicMessagesDialect
 from .dialects.openai_chat import (
     CAPABILITY_DECISIONS as OPENAI_CHAT_CAPABILITY_DECISIONS,
 )
@@ -321,6 +325,10 @@ def _bind_openai_responses(connection: Any, requested_model_id: str) -> Dialect:
     return OpenAIResponsesDialect(connection, requested_model_id)
 
 
+def _bind_anthropic_messages(connection: Any, requested_model_id: str) -> Dialect:
+    return AnthropicMessagesDialect(connection, requested_model_id)
+
+
 def _binder(
     function: Callable[[Any, str], Dialect],
     decisions: Mapping[str, DialectCapabilityDecision],
@@ -355,6 +363,13 @@ def _binder(
                 OPENAI_RESPONSES_CAPABILITY_DECISIONS,
             ),
         ),
+        "anthropic_messages": _binder(
+            _bind_anthropic_messages,
+            cast(
+                Mapping[str, DialectCapabilityDecision],
+                ANTHROPIC_MESSAGES_CAPABILITY_DECISIONS,
+            ),
+        ),
     }
 )
 
@@ -395,7 +410,8 @@ def _registered_decisions(
         "anthropic_messages": _spec(
             "anthropic_messages",
             "async_http_json",
-            request_seed_support=RequestSeedSupport.RESERVED,
+            decisions=_registered_decisions("anthropic_messages"),
+            request_seed_support=RequestSeedSupport.UNSUPPORTED,
             input_kinds=("chat",),
             input_modalities=("text", "image", "tool_call", "tool_result"),
         ),