Cyrene_v2/internal/runtime/model/model.go

// Package model provides a vendor-agnostic LLM adapter layer for Cyrene v2.
//
// It defines a normalized Message/Request/Response vocabulary, a single
// Adapter interface implemented by OpenAIChatAdapter (which speaks the
// OpenAI-compatible /chat/completions protocol used by OpenAI, DashScope/百炼,
// local gateways and proxies), a per-role Router, an automatic fallback Chain,
// multimodal (vision) detection, and per-call CallRecord accounting.
//
// The full tool loop (schema registration, argument binding, result re-feed) is
// deferred to M2; this package only carries interface-level placeholders
// (ToolSpec) so the wire contract is ready without executing any loop.
package model

import "time"

// Role identifies who authored a message. The values are vendor-agnostic and
// translated to each provider's own role vocabulary by the adapter.
type Role string

const (
	// RoleSystem is a system/instruction message.
	RoleSystem Role = "system"
	// RoleUser is an end-user message.
	RoleUser Role = "user"
	// RoleAssistant is an assistant (model) message.
	RoleAssistant Role = "assistant"
	// RoleTool is a tool-result message (reserved for the M2 tool loop).
	RoleTool Role = "tool"
)

// ContentType describes the kind of payload inside a Content part.
type ContentType string

const (
	// ContentTypeText is a plain-text content part.
	ContentTypeText ContentType = "text"
	// ContentTypeImage is an image content part.
	ContentTypeImage ContentType = "image_url"
	// ContentTypeToolCall is an assistant-originated tool invocation part
	// (Anthropic tool_use / OpenAI tool_calls), carried on a RoleAssistant turn.
	ContentTypeToolCall ContentType = "tool_call"
	// ContentTypeToolResult is a tool execution result part, carried on a RoleTool
	// turn and encoded natively (Anthropic tool_result / OpenAI tool message).
	ContentTypeToolResult ContentType = "tool_result"
)

// Content is a single, possibly multimodal, part of a message.
type Content struct {
	// Type distinguishes a text part from an image / tool part.
	Type ContentType
	// Text is the text payload when Type == ContentTypeText, or the result body
	// when Type == ContentTypeToolResult.
	Text string
	// ImageURL is the image source when Type == ContentTypeImage. It may be a
	// data: URI or an http(s):// URL.
	ImageURL string
	// ToolCallID correlates the part to a provider tool_use/tool_call id: the call
	// id for ContentTypeToolCall, or the tool_use_id being answered for
	// ContentTypeToolResult.
	ToolCallID string
	// ToolCallName is the invoked tool name when Type == ContentTypeToolCall.
	ToolCallName string
	// ToolArgs is the structured argument object when Type == ContentTypeToolCall.
	// It is never a JSON-encoded string.
	ToolArgs map[string]any
	// IsError marks a ContentTypeToolResult part as an execution failure so the
	// provider's tool_result.is_error / error flag is set natively.
	IsError bool
}

// Message is a single conversation turn, normalized across providers.
type Message struct {
	Role Role
	// Content carries one or more parts. A text-only message uses a single
	// ContentTypeText part.
	Content []Content
	// SenderName is the human-readable display name of the message's sender
	// (design/16 §4.6). It is transport metadata used by the context-assembly
	// layer to label third-party messages for the model (e.g. "[第三方 · 昵称]"),
	// never a substitute for the strongly typed sender identity carried on the
	// channel layer. Empty means the sender is unlabeled (the owner, or an
	// unknown/unresolved sender), and callers may leave it unset.
	SenderName string
	// ToolCallID correlates a RoleTool turn to the provider tool_use/tool_call id
	// it answers, and ToolCallName is the invoked tool name carried as a
	// convenience for callers that render the result. Both are set by the tool
	// loop when it feeds a result back, and consumed by the adapters to emit
	// native tool_result / tool-message blocks.
	ToolCallID   string
	ToolCallName string
}

// TextMessage builds a text-only message.
func TextMessage(role Role, text string) Message {
	return Message{Role: role, Content: []Content{{Type: ContentTypeText, Text: text}}}
}

// ImageMessage builds a message carrying optional text plus an image. imageURL
// may be a data: URI or an http(s):// URL. An empty text omits the text part.
func ImageMessage(role Role, text, imageURL string) Message {
	parts := make([]Content, 0, 2)
	if text != "" {
		parts = append(parts, Content{Type: ContentTypeText, Text: text})
	}
	parts = append(parts, Content{Type: ContentTypeImage, ImageURL: imageURL})
	return Message{Role: role, Content: parts}
}

// ToolResultMessage builds a RoleTool turn carrying the native result of one tool
// call. toolUseID must equal the provider id of the tool_use block this result
// answers; isError marks an execution failure; text is the result body.
func ToolResultMessage(toolUseID, text string, isError bool) Message {
	return Message{Role: RoleTool, ToolCallID: toolUseID,
		Content: []Content{{Type: ContentTypeToolResult, Text: text, ToolCallID: toolUseID, IsError: isError}}}
}

// AssistantToolCallMessage builds a RoleAssistant turn advertising the tool calls
// the model requested, so a subsequent RoleTool turn can be correlated to them by
// the provider (OpenAI tool_call_id / Anthropic tool_use_id).
func AssistantToolCallMessage(calls []ToolCall) Message {
	parts := make([]Content, 0, len(calls))
	for _, c := range calls {
		parts = append(parts, Content{Type: ContentTypeToolCall, ToolCallID: c.ID, ToolCallName: c.Name, ToolArgs: c.Args})
	}
	return Message{Role: RoleAssistant, Content: parts}
}

// ToolSpec is an interface-level placeholder for a tool/function schema. The
// full tool loop (registration, argument binding, result re-feed) is M2; here
// it only lets a request advertise tools to the provider in the wire contract.
type ToolSpec struct {
	Name        string
	Description string
	// Parameters is the JSON Schema for the tool arguments. Populated from M2.
	Parameters any
}

// ToolCall is a single assistant-originated tool invocation parsed from a
// provider's tool_use content block. Args is the structured argument object
// (never a serialized JSON string), so a tool loop can bind it directly without
// re-parsing.
type ToolCall struct {
	// ID is the provider tool_use/tool_call id, so a tool loop can correlate the
	// resulting RoleTool message to the exact call (Anthropic tool_use_id / OpenAI
	// tool_call_id). Empty when the provider emitted no id.
	ID string
	// Name is the tool being invoked.
	Name string
	// Args are the tool arguments, decoded from the provider's structured
	// tool_use.input object. It is never a JSON-encoded string.
	Args map[string]any
}

// Request is a completion request, normalized across providers.
type Request struct {
	// Model overrides the adapter's configured default model. Empty means the
	// adapter default (or the chain step model) applies.
	Model    string
	Messages []Message
	// Temperature is the sampling temperature. nil means the provider default.
	Temperature *float64
	// MaxTokens caps the generated tokens. Zero means the provider default.
	MaxTokens int
	// Purpose labels the call for CallRecord accounting (e.g. "chat").
	Purpose string
	// Tools is the interface-level placeholder for M2 function calling.
	Tools []ToolSpec
	// ToolChoice optionally directs how the provider selects a tool. It is an
	// opaque provider-agnostic directive (e.g. {"type":"auto"} or {"type":"tool",
	// "name":"x"}); empty means the provider default. Passed through verbatim to
	// protocols that support it (Anthropic's tool_choice).
	ToolChoice any
}

// Response is a normalized completion result.
type Response struct {
	// Model is the model that produced the response.
	Model   string
	Content string
	// Message is the normalized assistant message.
	Message Message
	// ToolCalls carries any tool_use blocks the assistant emitted. Empty when the
	// response is pure text.
	ToolCalls []ToolCall
	// PromptTokens, CompletionTokens and TotalTokens report provider usage when
	// available; zero when the provider does not return it.
	PromptTokens     int
	CompletionTokens int
	TotalTokens      int
}

// CallRecord describes a single successfully completed LLM call, for the M9
// monitor/frontend. A failed attempt emits no record.
type CallRecord struct {
	// Model is the model that served the request.
	Model string
	// Purpose labels what the call was for.
	Purpose string
	// Tokens is the total token consumption reported by the provider.
	Tokens int
	// TookMs is the end-to-end call latency in milliseconds.
	TookMs int64
}

// Options carries per-call knobs layered on top of the Request.
type Options struct {
	// Timeout bounds a single HTTP call. Zero uses the adapter client timeout.
	Timeout time.Duration
}