Changeset 0.10.0 (#56)

server/providers/provider.go

@@ -3,10 +3,15 @@ package providers
 import (
 	"context"
 	"encoding/json"
+	"errors"
 
 	"git.gobha.me/xcaliber/chat-switchboard/models"
 )
 
+// ── Errors ─────────────────────────────────
+
+var ErrNotSupported = errors.New("operation not supported by this provider")
+
 // ── Provider Interface ──────────────────────
 
 // Provider is the contract for LLM API adapters.
@@ -23,6 +28,10 @@ type Provider interface {
 
 	// ListModels returns available models from this provider.
 	ListModels(ctx context.Context, cfg ProviderConfig) ([]Model, error)
+
+	// Embed generates embeddings for the given input texts.
+	// Returns ErrNotSupported if the provider has no embedding endpoint.
+	Embed(ctx context.Context, cfg ProviderConfig, req EmbeddingRequest) (*EmbeddingResponse, error)
 }
 
 // ── Configuration ───────────────────────────
@@ -88,23 +97,44 @@ type CompletionRequest struct {
 
 // CompletionResponse is the normalized non-streaming response.
 type CompletionResponse struct {
-	Content      string     `json:"content"`
-	Model        string     `json:"model"`
-	FinishReason string     `json:"finish_reason"`
-	InputTokens  int        `json:"input_tokens"`
-	OutputTokens int        `json:"output_tokens"`
-	ToolCalls    []ToolCall `json:"tool_calls,omitempty"` // set when finish_reason is "tool_calls"
+	Content             string     `json:"content"`
+	Model               string     `json:"model"`
+	FinishReason        string     `json:"finish_reason"`
+	InputTokens         int        `json:"input_tokens"`
+	OutputTokens        int        `json:"output_tokens"`
+	CacheCreationTokens int        `json:"cache_creation_tokens,omitempty"`
+	CacheReadTokens     int        `json:"cache_read_tokens,omitempty"`
+	ToolCalls           []ToolCall `json:"tool_calls,omitempty"` // set when finish_reason is "tool_calls"
 }
 
 // StreamEvent is a single chunk from a streaming response.
 type StreamEvent struct {
-	Delta        string     `json:"delta,omitempty"`
-	Reasoning    string     `json:"reasoning,omitempty"`
-	Done         bool       `json:"done,omitempty"`
-	FinishReason string     `json:"finish_reason,omitempty"`
-	ToolCalls    []ToolCall `json:"tool_calls,omitempty"`
-	Model        string     `json:"model,omitempty"`
-	Error        error      `json:"-"`
+	Delta               string     `json:"delta,omitempty"`
+	Reasoning           string     `json:"reasoning,omitempty"`
+	Done                bool       `json:"done,omitempty"`
+	FinishReason        string     `json:"finish_reason,omitempty"`
+	ToolCalls           []ToolCall `json:"tool_calls,omitempty"`
+	Model               string     `json:"model,omitempty"`
+	Error               error      `json:"-"`
+	InputTokens         int        `json:"input_tokens,omitempty"`
+	OutputTokens        int        `json:"output_tokens,omitempty"`
+	CacheCreationTokens int        `json:"cache_creation_tokens,omitempty"`
+	CacheReadTokens     int        `json:"cache_read_tokens,omitempty"`
+}
+
+// ── Embedding Types ────────────────────────
+
+// EmbeddingRequest is the normalized embedding request.
+type EmbeddingRequest struct {
+	Model string   `json:"model"`
+	Input []string `json:"input"` // batch of texts to embed
+}
+
+// EmbeddingResponse is the normalized embedding response.
+type EmbeddingResponse struct {
+	Embeddings  [][]float64 `json:"embeddings"`
+	Model       string      `json:"model"`
+	InputTokens int         `json:"input_tokens"`
 }
 
 // Model represents an available model from a provider, with capabilities.