(feat) Temporal SDK client, worker mgmt, k8s deployments (#10)

## Changes
- `internal/temporal/client.go` — Robust Temporal client with retry (exp backoff), TLS, health check
- `internal/temporal/worker.go` — Worker creation, activity/workflow registration, lifecycle
- `internal/temporal/context.go` — Timeout helpers
- `k8s/worker-deployment.yaml` — 2-10 replica HPA, liveness/readiness probes, security context, pod anti-affinity
- `k8s/workflow-runner-deployment.yaml` — Singleton runner with probes
- `k8s/kustomization.yaml` — Updated resource list

Co-authored-by: poimen <[email protected]>

activity/llm_inference.go

@@ -3,6 +3,7 @@ package activity
 import (
 	"context"
 	"fmt"
+	"os"
 
 	"github.com/rockliang/poimen/workflows/activity/llm"
 	"github.com/rockliang/poimen/workflows/pkg/types"
@@ -44,11 +45,17 @@ func LLMInferenceActivity(ctx context.Context, in LLMInferenceInput) (LLMInferen
 		return output, fmt.Errorf("failed to create LLM client: %w", err)
 	}
 
+	// Use provided auth token, or fallback to environment variable
+	authToken := in.AuthToken
+	if authToken == "" {
+		authToken = os.Getenv("LLM_AUTH_TOKEN")
+	}
+
 	response, err := client.CreateMessage(ctx, llm.MessageInput{
 		Model:        types.ModelSpec{ModelID: in.Model},
 		SystemPrompt: in.SystemPrompt,
 		Messages:     []llm.MessageParam{{Role: "user", Content: in.UserPrompt}},
-		AuthToken:    in.AuthToken,
+		AuthToken:    authToken,
 	})
 	if err != nil {
 		output.ErrorMessage = err.Error()
@@ -94,11 +101,18 @@ func LLMBatchInferenceActivity(ctx context.Context, in LLMBatchInferenceInput) (
 		return output, fmt.Errorf("failed to create LLM client: %w", err)
 	}
 
+	// Use provided auth token, or fallback to environment variable
+	authToken := in.AuthToken
+	if authToken == "" {
+		authToken = os.Getenv("LLM_AUTH_TOKEN")
+	}
+
 	for i, prompt := range in.Prompts {
 		response, err := client.CreateMessage(ctx, llm.MessageInput{
 			Model:        types.ModelSpec{ModelID: in.Model},
 			SystemPrompt: in.SystemPrompt,
 			Messages:     []llm.MessageParam{{Role: "user", Content: prompt}},
+			AuthToken:    authToken,
 		})
 		if err != nil {
 			output.Errors = append(output.Errors, fmt.Sprintf("prompt %d: %v", i, err))