Integrate BACKBEAT SDK and resolve KACHING license validation

Major integrations and fixes:
- Added BACKBEAT SDK integration for P2P operation timing
- Implemented beat-aware status tracking for distributed operations
- Added Docker secrets support for secure license management
- Resolved KACHING license validation via HTTPS/TLS
- Updated docker-compose configuration for clean stack deployment
- Disabled rollback policies to prevent deployment failures
- Added license credential storage (CHORUS-DEV-MULTI-001)

Technical improvements:
- BACKBEAT P2P operation tracking with phase management
- Enhanced configuration system with file-based secrets
- Improved error handling for license validation
- Clean separation of KACHING and CHORUS deployment stacks

🤖 Generated with [Claude Code](https://claude.ai/code)

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

vendor/github.com/sashabaranov/go-openai/chat_stream.go

@@ -0,0 +1,112 @@
+package openai
+
+import (
+	"context"
+	"net/http"
+)
+
+type ChatCompletionStreamChoiceDelta struct {
+	Content      string        `json:"content,omitempty"`
+	Role         string        `json:"role,omitempty"`
+	FunctionCall *FunctionCall `json:"function_call,omitempty"`
+	ToolCalls    []ToolCall    `json:"tool_calls,omitempty"`
+	Refusal      string        `json:"refusal,omitempty"`
+
+	// This property is used for the "reasoning" feature supported by deepseek-reasoner
+	// which is not in the official documentation.
+	// the doc from deepseek:
+	// - https://api-docs.deepseek.com/api/create-chat-completion#responses
+	ReasoningContent string `json:"reasoning_content,omitempty"`
+}
+
+type ChatCompletionStreamChoiceLogprobs struct {
+	Content []ChatCompletionTokenLogprob `json:"content,omitempty"`
+	Refusal []ChatCompletionTokenLogprob `json:"refusal,omitempty"`
+}
+
+type ChatCompletionTokenLogprob struct {
+	Token       string                                 `json:"token"`
+	Bytes       []int64                                `json:"bytes,omitempty"`
+	Logprob     float64                                `json:"logprob,omitempty"`
+	TopLogprobs []ChatCompletionTokenLogprobTopLogprob `json:"top_logprobs"`
+}
+
+type ChatCompletionTokenLogprobTopLogprob struct {
+	Token   string  `json:"token"`
+	Bytes   []int64 `json:"bytes"`
+	Logprob float64 `json:"logprob"`
+}
+
+type ChatCompletionStreamChoice struct {
+	Index                int                                 `json:"index"`
+	Delta                ChatCompletionStreamChoiceDelta     `json:"delta"`
+	Logprobs             *ChatCompletionStreamChoiceLogprobs `json:"logprobs,omitempty"`
+	FinishReason         FinishReason                        `json:"finish_reason"`
+	ContentFilterResults ContentFilterResults                `json:"content_filter_results,omitempty"`
+}
+
+type PromptFilterResult struct {
+	Index                int                  `json:"index"`
+	ContentFilterResults ContentFilterResults `json:"content_filter_results,omitempty"`
+}
+
+type ChatCompletionStreamResponse struct {
+	ID                  string                       `json:"id"`
+	Object              string                       `json:"object"`
+	Created             int64                        `json:"created"`
+	Model               string                       `json:"model"`
+	Choices             []ChatCompletionStreamChoice `json:"choices"`
+	SystemFingerprint   string                       `json:"system_fingerprint"`
+	PromptAnnotations   []PromptAnnotation           `json:"prompt_annotations,omitempty"`
+	PromptFilterResults []PromptFilterResult         `json:"prompt_filter_results,omitempty"`
+	// An optional field that will only be present when you set stream_options: {"include_usage": true} in your request.
+	// When present, it contains a null value except for the last chunk which contains the token usage statistics
+	// for the entire request.
+	Usage *Usage `json:"usage,omitempty"`
+}
+
+// ChatCompletionStream
+// Note: Perhaps it is more elegant to abstract Stream using generics.
+type ChatCompletionStream struct {
+	*streamReader[ChatCompletionStreamResponse]
+}
+
+// CreateChatCompletionStream — API call to create a chat completion w/ streaming
+// support. It sets whether to stream back partial progress. If set, tokens will be
+// sent as data-only server-sent events as they become available, with the
+// stream terminated by a data: [DONE] message.
+func (c *Client) CreateChatCompletionStream(
+	ctx context.Context,
+	request ChatCompletionRequest,
+) (stream *ChatCompletionStream, err error) {
+	urlSuffix := chatCompletionsSuffix
+	if !checkEndpointSupportsModel(urlSuffix, request.Model) {
+		err = ErrChatCompletionInvalidModel
+		return
+	}
+
+	request.Stream = true
+	reasoningValidator := NewReasoningValidator()
+	if err = reasoningValidator.Validate(request); err != nil {
+		return
+	}
+
+	req, err := c.newRequest(
+		ctx,
+		http.MethodPost,
+		c.fullURL(urlSuffix, withModel(request.Model)),
+		withBody(request),
+	)
+	if err != nil {
+		return nil, err
+	}
+
+	resp, err := sendRequestStream[ChatCompletionStreamResponse](c, req)
+	if err != nil {
+		return
+	}
+	stream = &ChatCompletionStream{
+		streamReader: resp,
+	}
+	return
+}