From 00fc83c0819e8e5f0d122f44f4fb3f883cadc8f5 Mon Sep 17 00:00:00 2001
From: Test <test@example.com>
Date: Sat, 5 Sep 2026 00:46:40 -0700
Subject: [PATCH] feat: add JWT auth token support to LLM inference activities

---
 action/llm/client.go       | 6 ++++++
 action/llm_inference.go    | 5 ++++-
 k8s/git-commit.yaml        | 2 +-
 k8s/worker-deployment.yaml | 2 +-
 4 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/action/llm/client.go b/action/llm/client.go
index b49e495..007fa21 100644
--- a/action/llm/client.go
+++ b/action/llm/client.go
@@ -57,6 +57,7 @@ type MessageInput struct {
 	Model        statemachine.ModelSpec
 	SystemPrompt string
 	Messages     []MessageParam
+	AuthToken    string // Optional JWT token for authenticated endpoints
 }
 
 // MessageParam represents a message parameter.
@@ -136,6 +137,11 @@ func (c *OpenAIClient) CreateMessage(ctx context.Context, in MessageInput) (stri
 
 	httpReq.Header.Set("Content-Type", "application/json")
 
+	// Add authentication header if token provided
+	if in.AuthToken != "" {
+		httpReq.Header.Set("Authorization", fmt.Sprintf("Bearer %s", in.AuthToken))
+	}
+
 	// Send request
 	resp, err := c.httpClient.Do(httpReq)
 	if err != nil {
diff --git a/action/llm_inference.go b/action/llm_inference.go
index 128f199..e6980ae 100644
--- a/action/llm_inference.go
+++ b/action/llm_inference.go
@@ -15,6 +15,7 @@ type LLMInferenceInput struct {
 	UserPrompt    string                 `json:"user_prompt"`    // User message
 	Temperature   float64                `json:"temperature,omitempty"`   // LLM temperature (0-1)
 	MaxTokens     int                    `json:"max_tokens,omitempty"`    // Max output tokens
+	AuthToken     string                 `json:"auth_token,omitempty"`    // JWT token for authenticated endpoints
 }
 
 // LLMInferenceOutput is output from LLMInferenceActivity
@@ -53,7 +54,7 @@ func LLMInferenceActivity(ctx context.Context, in LLMInferenceInput) (LLMInferen
 	}
 
 	// Call LLM
-	logger.logf("info", "Calling LLM API (model=%s, prompt_len=%d)", in.Model, len(in.UserPrompt))
+	logger.logf("info", "Calling LLM API (model=%s, prompt_len=%d, auth=%v)", in.Model, len(in.UserPrompt), in.AuthToken != "")
 
 	response, err := client.CreateMessage(ctx, llm.MessageInput{
 		Model: statemachine.ModelSpec{
@@ -66,6 +67,7 @@ func LLMInferenceActivity(ctx context.Context, in LLMInferenceInput) (LLMInferen
 				Content: in.UserPrompt,
 			},
 		},
+		AuthToken: in.AuthToken,
 	})
 
 	if err != nil {
@@ -88,6 +90,7 @@ type LLMBatchInferenceInput struct {
 	SystemPrompt string                   `json:"system_prompt"`
 	Prompts      []string                 `json:"prompts"`       // List of user prompts
 	Temperature  float64                  `json:"temperature,omitempty"`
+	AuthToken    string                   `json:"auth_token,omitempty"`    // JWT token for authenticated endpoints
 }
 
 // LLMBatchInferenceOutput is output from batch inference
diff --git a/k8s/git-commit.yaml b/k8s/git-commit.yaml
index b44e511..112aab1 100644
--- a/k8s/git-commit.yaml
+++ b/k8s/git-commit.yaml
@@ -9,6 +9,6 @@ metadata:
     app.kubernetes.io/name: poimen
     app.kubernetes.io/component: orchestrator
 data:
-  GIT_COMMIT: "e07b9504"  # Updated automatically by CI/CD
+  GIT_COMMIT: "991c1f97"  # Updated automatically by CI/CD
   GIT_BRANCH: "main"
   DEPLOYMENT_DATE: "2026-09-05"
diff --git a/k8s/worker-deployment.yaml b/k8s/worker-deployment.yaml
index 5464649..e2fe1e7 100644
--- a/k8s/worker-deployment.yaml
+++ b/k8s/worker-deployment.yaml
@@ -13,7 +13,7 @@ spec:
       labels:
         app: poimen-worker
       annotations:
-        git-commit: "e07b9504"  # ✅ Updated on each push, triggers rolling restart
+        git-commit: "991c1f97"  # ✅ Updated on each push, triggers rolling restart
         deployment-date: "2026-09-05"
     spec:
       containers: