feat: Update model profile and statistics tracking

- Updated model profile to support new cost parameters: costPerCachedInToken and costPerReasoningOutToken.
- Enhanced AgentRequestStatistic to track cached input tokens and reasoning output tokens.
- Modified CompletionStatistics to include cached input tokens and reasoning output tokens.
- Updated AzureAiClient, CachedClient, and other clients to handle new statistics fields.
- Introduced Timings class to capture detailed timing metrics for requests.
- Adjusted Usage class to include input and output token details.
- Updated properties files to include new cost parameters for cached and reasoning tokens.

src/test/java/de/extio/lmlib/client/oai/CompletionClientTest.java

@@ -28,7 +28,7 @@ import de.extio.lmlib.client.oai.completion.text.TextCompletionClient;
 import de.extio.lmlib.grader.Grader;
 import de.extio.lmlib.profile.ModelCategory;
 
-@Disabled("This test requires a running Llama server")
+// @Disabled("This test requires a running Llama server")
 @SpringBootTest(webEnvironment = WebEnvironment.NONE)
 @SpringBootConfiguration
 @ComponentScan(basePackages = "de.extio.lmlib")

src/test/resources/llama3.3-70b-azure.properties

@@ -10,4 +10,6 @@ modelName=Llama-3.3-70B-Instruct
 url=XXX
 apiKey=XXX
 cost1MInTokens=0.71
+cost1MCachedInTokens=0.71
 cost1MOutTokens=0.71
+cost1MReasoningOutTokens=0

src/test/resources/local-chatcompletion.properties

@@ -10,6 +10,8 @@ modelName=
 url=http://localhost:5001
 apiKey=
 cost1MInTokens=0
+cost1MCachedInTokens=0
 cost1MOutTokens=0
+cost1MReasoningOutTokens=0
 reasoningEffort=medium
 reasoningSummaryDetails=auto

src/test/resources/local-completion.properties

@@ -10,4 +10,6 @@ modelName=
 url=http://localhost:5001
 apiKey=
 cost1MInTokens=0
+cost1MCachedInTokens=0
 cost1MOutTokens=0
+cost1MReasoningOutTokens=0