feat(llm): a request carries how much the model thinks, in each provider's field

LlmRequest.effort (LlmEffort: low, medium, high, xhigh, max, Anthropic's
names) goes as Anthropic's output_config.effort, as reasoning.effort to
the Responses API and OpenRouter, and as reasoning_effort to OpenAI's chat
completions, Gemini and any other host. endpoint.efforts says which
levels a host takes (Gemini low to high, Mistral none); send refuses
another before anything goes, the fake client too. LlmEffort.outputCeiling
gives the room for output each level wants, as thinking counts towards
the ceiling (Halkyon Learn's ADR 0021, D63).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Tizian 「ティツィアーン」 <raisondetredev@pm.me>

packages/halkyon_llm/test/testing_test.dart

@@ -57,5 +57,26 @@ void main() {
         throwsStateError,
       );
     });
+
+    test("refuses an effort the endpoint's host takes not, as HTTP's does", () {
+      final client = FakeLlmClient()..replyText('Hallo');
+      expect(
+        () => client.send(
+          LlmEndpoint(
+            protocol: LlmProtocol.openai,
+            model: 'm',
+            apiKey: 'k',
+            baseUrl: 'https://api.mistral.ai/v1',
+          ),
+          LlmRequest(
+            messages: _request.messages,
+            maxOutputTokens: 10,
+            effort: LlmEffort.low,
+          ),
+        ),
+        throwsArgumentError,
+      );
+      expect(client.sent, isEmpty);
+    });
   });
 }