Add ANTHROPIC_API_KEY to deployment workflow

Pass the secret to the deploy job and export it for docker-compose.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

.github/workflows/docker_build.yml

@@ -161,6 +161,7 @@ jobs:
       ADMIN_IMAGE: ${{ needs.build-all.outputs.admin_image_tag }}
       JFR_SIDECAR_IMAGE: ${{ needs.build-all.outputs.jfr_sidecar_image_tag }}
       OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
       GPT_MODEL_NAME: ${{ secrets.GPT_MODEL_NAME }}
       EAGLE_ENABLE_S3: ${{ secrets.EAGLE_ENABLE_S3 }}
       DO_SPACES_ACCESS_KEY: ${{ secrets.DO_SPACES_ACCESS_KEY }}
@@ -279,6 +280,7 @@ jobs:
           export ADMIN_IMAGE="${ADMIN_IMAGE}"
           export JFR_SIDECAR_IMAGE="${JFR_SIDECAR_IMAGE}"
           export OPENAI_API_KEY="${OPENAI_API_KEY}"
+          export ANTHROPIC_API_KEY="${ANTHROPIC_API_KEY}"
           export GPT_MODEL_NAME="${GPT_MODEL_NAME:-gpt-4o}"
           export EAGLE_ENABLE_S3="${EAGLE_ENABLE_S3:-false}"
           export DO_SPACES_ACCESS_KEY="${DO_SPACES_ACCESS_KEY}"

docker-compose.prod.yml

@@ -26,6 +26,7 @@ services:
       - "40032:40032"
     environment:
       OPENAI_API_KEY: "${OPENAI_API_KEY:-}"
+      ANTHROPIC_API_KEY: "${ANTHROPIC_API_KEY:-}"
       EAGLE_ENABLE_S3: "${EAGLE_ENABLE_S3:-false}"
       DO_SPACES_ENDPOINT: "${DO_SPACES_ENDPOINT:-https://sfo3.digitaloceanspaces.com}"
       DO_SPACES_ACCESS_KEY: "${DO_SPACES_ACCESS_KEY:-}"
@@ -73,6 +74,7 @@ services:
       - "40034:40032"  # Different host port for staging
     environment:
       OPENAI_API_KEY: "${OPENAI_API_KEY:-}"
+      ANTHROPIC_API_KEY: "${ANTHROPIC_API_KEY:-}"
       EAGLE_ENABLE_S3: "${EAGLE_ENABLE_S3:-false}"
       DO_SPACES_ENDPOINT: "${DO_SPACES_ENDPOINT:-https://sfo3.digitaloceanspaces.com}"
       DO_SPACES_ACCESS_KEY: "${DO_SPACES_ACCESS_KEY:-}"

src/main/go/net/eagle0/admin_server/admin_server.go

@@ -1169,7 +1169,7 @@ type SettingInfo struct {
 
 // LLM model dropdown options
 var llmProviderOptions = []string{"openai", "claude"}
-var openAiModelOptions = []string{"gpt-5-mini", "gpt-5.2", "gpt-4.1", "gpt-4.1-mini", "gpt-4o", "gpt-4o-mini", "o1", "o1-mini", "o3-mini"}
+var openAiModelOptions = []string{"gpt-5-mini", "gpt-5.1", "gpt-5.2", "gpt-4.1", "gpt-4.1-mini", "gpt-4o", "gpt-4o-mini", "o1", "o1-mini", "o3-mini"}
 var claudeModelOptions = []string{"claude-sonnet-4-20250514", "claude-opus-4-20250514", "claude-3-7-sonnet-20250219", "claude-3-5-sonnet-20241022", "claude-3-5-haiku-20241022"}
 
 type SettingsPageData struct {

src/main/scala/net/eagle0/common/llm_integration/ClaudeServiceImpl.scala

@@ -27,12 +27,20 @@ object ClaudeServiceImpl {
     "stream"     -> true
   )
 
-  private def messageVector(inputText: String): Vector[Map[String, String]] =
+  private def messageVector(
+      inputText: String,
+      partialCompletion: Option[String]
+  ): Vector[Map[String, String]] =
     Vector(
       Map(
         "role"    -> "user",
         "content" -> inputText
       )
+    ) ++ partialCompletion.map(pc =>
+      Map(
+        "role"    -> "assistant",
+        "content" -> pc
+      )
     )
 
   private def baseRequest(timeoutSeconds: Int): HttpRequest.Builder =
@@ -47,15 +55,17 @@ object ClaudeServiceImpl {
 
 class ClaudeServiceImpl(
     val timeoutSeconds: Int = 10,
-    val defaultModelName: String = "claude-3-5-sonnet-20240620"
+    val defaultModelName: String = "claude-sonnet-4-20250514"
 ) extends ExternalTextGenerationServiceImpl {
   implicit val jsonFormats: DefaultFormats.type = DefaultFormats
 
   private def requestDictionary(
-      inputText: String
+      inputText: String,
+      partialCompletion: Option[String]
   ): Map[String, Any] =
     dictionaryFor(modelName = defaultModelName) + ("messages" -> messageVector(
-      inputText
+      inputText,
+      partialCompletion
     ))
 
   override def makeRequest(
@@ -71,7 +81,7 @@ class ClaudeServiceImpl(
       .POST(
         BodyPublishers.ofString(
           Serialization.write(
-            requestDictionary(inputText = inputText)
+            requestDictionary(inputText = inputText, partialCompletion = partialCompletion)
           )
         )
       )
@@ -99,7 +109,9 @@ class ClaudeServiceImpl(
                   completed = false
                 )
               )
-            case _                      => ???
+            case other                  =>
+              // May be a different delta type (e.g., tool use), log and skip
+              println(s"Unexpected content_block_delta format: $other")
           }
         case JString("content_block_start") => ()
         case JString("content_block_stop")  => ()
@@ -118,7 +130,9 @@ class ClaudeServiceImpl(
           val errorType    = (errorDetails \ "type").extract[String]
           val errorMessage = (errorDetails \ "message").extract[String]
           println(s"Got an \"($errorType)\" error from Claude: $errorMessage")
-        case _                              => ???
+        case other                          =>
+          // Unknown event type, log and skip
+          println(s"Unknown Claude streaming event type: $other")
       }
     }
   }

src/main/scala/net/eagle0/common/llm_integration/OpenAIChatCompletionsServiceImpl.scala

@@ -19,14 +19,24 @@ object OpenAIChatCompletionsServiceImpl {
   private val baseURL             = new URL("https://api.openai.com/v1/chat/completions")
   private val temperature: Double = 1.0
 
+  // Non-reasoning models have -mini or -nano suffix; all others support reasoning_effort
+  private val nonReasoningSuffixes = Set("-mini", "-nano")
+
+  private def isReasoningModel(modelName: String): Boolean =
+    !nonReasoningSuffixes.exists(suffix => modelName.contains(suffix))
+
   private def dictionaryFor(
       modelName: String
-  ): Map[String, Any]            = Map(
-    "model"            -> modelName,
-    "temperature"      -> temperature,
-    "stream"           -> true,
-    "reasoning_effort" -> "none"
-  )
+  ): Map[String, Any] = {
+    val baseParams = Map(
+      "model"       -> modelName,
+      "temperature" -> temperature,
+      "stream"      -> true
+    )
+    // Only include reasoning_effort for reasoning models (o1, o3, etc.)
+    if isReasoningModel(modelName) then baseParams + ("reasoning_effort" -> "none")
+    else baseParams
+  }
 
   private def messageVector(
       inputText: String,