Use max input token defaults (#10951)

Addresses #8133 

We're currently using a hardcoded `0` value for max input tokens rather
than our `DEFAULT_MAX_TOKEN_INPUT` value. I'm not sure if this was done
intentionally, but this change switches the value to use our constant

Author: melissa-barca

extensions/positron-assistant/src/models.ts

@@ -658,7 +658,7 @@ abstract class AILanguageModel implements positron.ai.LanguageModelChatProvider
 				provider: this.provider,
 				providerName: this.providerName,
 				capabilities: this.capabilities,
-				defaultMaxInput: model.maxInputTokens ?? 0,
+				defaultMaxInput: model.maxInputTokens ?? DEFAULT_MAX_TOKEN_INPUT,
 				defaultMaxOutput: model.maxOutputTokens ?? DEFAULT_MAX_TOKEN_OUTPUT
 			})
 		);
@@ -815,7 +815,7 @@ export class OpenAILanguageModel extends AILanguageModel implements positron.ai.
 				provider: this.provider,
 				providerName: this.providerName,
 				capabilities: this.capabilities,
-				defaultMaxInput: modelDef.maxInputTokens ?? 0,
+				defaultMaxInput: modelDef.maxInputTokens ?? DEFAULT_MAX_TOKEN_INPUT,
 				defaultMaxOutput: modelDef.maxOutputTokens ?? DEFAULT_MAX_TOKEN_OUTPUT
 			})
 		);
@@ -841,7 +841,7 @@ export class OpenAILanguageModel extends AILanguageModel implements positron.ai.
 					provider: this.provider,
 					providerName: this.providerName,
 					capabilities: this.capabilities,
-					defaultMaxInput: 0,
+					defaultMaxInput: model.maxInputTokens ?? DEFAULT_MAX_TOKEN_INPUT,
 					defaultMaxOutput: model.maxOutputTokens ?? DEFAULT_MAX_TOKEN_OUTPUT
 				})
 			);