Changeset 0.10.0 (#56)

server/providers/anthropic.go

@@ -38,10 +38,12 @@ func (p *AnthropicProvider) ChatCompletion(ctx context.Context, cfg ProviderConf
 	}
 
 	result := &CompletionResponse{
-		Model:        resp.Model,
-		FinishReason: resp.StopReason,
-		InputTokens:  resp.Usage.InputTokens,
-		OutputTokens: resp.Usage.OutputTokens,
+		Model:               resp.Model,
+		FinishReason:        resp.StopReason,
+		InputTokens:         resp.Usage.InputTokens,
+		OutputTokens:        resp.Usage.OutputTokens,
+		CacheCreationTokens: resp.Usage.CacheCreationInputTokens,
+		CacheReadTokens:     resp.Usage.CacheReadInputTokens,
 	}
 
 	// Extract text and tool_use blocks
@@ -89,6 +91,9 @@ func (p *AnthropicProvider) StreamCompletion(ctx context.Context, cfg ProviderCo
 		var toolCalls []ToolCall
 		var currentToolIdx int = -1
 
+		// Usage accumulates across stream events
+		var inputTokens, outputTokens, cacheCreation, cacheRead int
+
 		scanner := bufio.NewScanner(body)
 		for scanner.Scan() {
 			line := scanner.Text()
@@ -105,6 +110,14 @@ func (p *AnthropicProvider) StreamCompletion(ctx context.Context, cfg ProviderCo
 			}
 
 			switch event.Type {
+			case "message_start":
+				// Capture input token counts (including cache)
+				if event.Message != nil {
+					inputTokens = event.Message.Usage.InputTokens
+					cacheCreation = event.Message.Usage.CacheCreationInputTokens
+					cacheRead = event.Message.Usage.CacheReadInputTokens
+				}
+
 			case "content_block_start":
 				if event.ContentBlock != nil && event.ContentBlock.Type == "tool_use" {
 					currentToolIdx++
@@ -126,10 +139,19 @@ func (p *AnthropicProvider) StreamCompletion(ctx context.Context, cfg ProviderCo
 				}
 
 			case "message_delta":
+				// Capture output tokens
+				if event.Usage != nil {
+					outputTokens = event.Usage.OutputTokens
+				}
+
 				stopReason := event.Delta.StopReason
 				ev := StreamEvent{
-					Done:         true,
-					FinishReason: stopReason,
+					Done:                true,
+					FinishReason:        stopReason,
+					InputTokens:         inputTokens,
+					OutputTokens:        outputTokens,
+					CacheCreationTokens: cacheCreation,
+					CacheReadTokens:     cacheRead,
 				}
 				if stopReason == "tool_use" {
 					ev.FinishReason = "tool_calls"
@@ -181,6 +203,13 @@ func (p *AnthropicProvider) ListModels(_ context.Context, _ ProviderConfig) ([]M
 	return out, nil
 }
 
+// ── Embeddings ─────────────────────────────
+
+// Embed is not supported by the Anthropic API.
+func (p *AnthropicProvider) Embed(_ context.Context, _ ProviderConfig, _ EmbeddingRequest) (*EmbeddingResponse, error) {
+	return nil, ErrNotSupported
+}
+
 // ── HTTP Layer ──────────────────────────────
 
 func (p *AnthropicProvider) doRequest(ctx context.Context, cfg ProviderConfig, req CompletionRequest) (io.ReadCloser, error) {
@@ -366,20 +395,30 @@ type anthropicResponse struct {
 		Name  string          `json:"name,omitempty"`
 		Input json.RawMessage `json:"input,omitempty"`
 	} `json:"content"`
-	Usage struct {
-		InputTokens  int `json:"input_tokens"`
-		OutputTokens int `json:"output_tokens"`
-	} `json:"usage"`
+	Usage anthropicUsage `json:"usage"`
+}
+
+type anthropicUsage struct {
+	InputTokens              int `json:"input_tokens"`
+	OutputTokens             int `json:"output_tokens"`
+	CacheCreationInputTokens int `json:"cache_creation_input_tokens"`
+	CacheReadInputTokens     int `json:"cache_read_input_tokens"`
 }
 
 type anthropicStreamEvent struct {
-	Type  string `json:"type"`
+	Type    string `json:"type"`
+	Message *struct {
+		Usage anthropicUsage `json:"usage"`
+	} `json:"message,omitempty"`
 	Delta struct {
 		Type        string `json:"type"`
 		Text        string `json:"text"`
 		StopReason  string `json:"stop_reason"`
 		PartialJSON string `json:"partial_json"`
 	} `json:"delta"`
+	Usage *struct {
+		OutputTokens int `json:"output_tokens"`
+	} `json:"usage,omitempty"`
 	ContentBlock *struct {
 		Type string `json:"type"`
 		ID   string `json:"id"`