llm

type ChatRequest struct {
	Messages []api.Message
	Tools    api.Tools
	Format   json.RawMessage
	Options  *api.Options
	Think    *api.ThinkValue
	Shift    bool

	Logprobs    bool
	TopLogprobs int
}

type ChatResponse struct {
	Message            api.Message   `json:"message"`
	DoneReason         DoneReason    `json:"done_reason"`
	Done               bool          `json:"done"`
	PromptEvalCount    int           `json:"prompt_eval_count"`
	PromptEvalDuration time.Duration `json:"prompt_eval_duration"`
	EvalCount          int           `json:"eval_count"`
	EvalDuration       time.Duration `json:"eval_duration"`
	Logprobs           []Logprob     `json:"logprobs,omitempty"`
}

type CompletionRequest struct {
	Prompt  string
	Format  json.RawMessage
	Media   []MediaData
	Options *api.Options

	Grammar         string // set before sending the request to the subprocess
	Shift           bool
	Truncate        bool
	PreservedTokens []string // parser tokens to render as text; ignored by non-llama-server runners
	ToolCallTag     string   // raw generic tool parser tag, if any
	LeadingBOS      string   // textual BOS emitted by Go rendering, if any

	// Logprobs specifies whether to include log probabilities in the response
	Logprobs bool

	// TopLogprobs specifies the number of most likely alternative tokens to return (0-20)
	TopLogprobs int

	// Image generation fields
	Width  int32 `json:"width,omitempty"`
	Height int32 `json:"height,omitempty"`
	Steps  int32 `json:"steps,omitempty"`
	Seed   int64 `json:"seed,omitempty"`
}

type CompletionResponse struct {
	Content            string        `json:"content"`
	DoneReason         DoneReason    `json:"done_reason"`
	Done               bool          `json:"done"`
	PromptEvalCount    int           `json:"prompt_eval_count"`
	PromptEvalDuration time.Duration `json:"prompt_eval_duration"`
	EvalCount          int           `json:"eval_count"`
	EvalDuration       time.Duration `json:"eval_duration"`

	// Logprobs contains log probability information if requested
	Logprobs []Logprob `json:"logprobs,omitempty"`

	// Image contains base64-encoded image data for image generation
	Image string `json:"image,omitempty"`

	// Step is the current step in image generation
	Step int `json:"step,omitempty"`

	// TotalSteps is the total number of steps for image generation
	TotalSteps int `json:"total_steps,omitempty"`
}

type DoneReason int

type ExitStatus int

type LlamaServer interface {
	ModelPath() string
	Load(ctx context.Context, systemInfo ml.SystemInfo, gpus []ml.DeviceInfo, requireFull bool) ([]ml.DeviceID, error)
	Ping(ctx context.Context) error
	WaitUntilRunning(ctx context.Context) error
	Completion(ctx context.Context, req CompletionRequest, fn func(CompletionResponse)) error
	Chat(ctx context.Context, req ChatRequest, fn func(ChatResponse)) error
	ApplyChatTemplate(ctx context.Context, req ChatRequest) (string, error)
	Embedding(ctx context.Context, input string) ([]float32, int, error)
	Tokenize(ctx context.Context, content string) ([]int, error)
	Detokenize(ctx context.Context, tokens []int) (string, error)
	Close() error
	MemorySize() (total, vram uint64)
	VRAMByGPU(id ml.DeviceID) uint64
	Pid() int
	GetPort() int
	GetDeviceInfos(ctx context.Context) []ml.DeviceInfo
	HasExited() bool
	ContextLength() int
}

type LlamaServerConfig struct {
	DisableJinja   bool
	ContextShift   bool
	EnableMTP      bool
	DraftModelPath string
}

type Logprob struct {
	TokenLogprob
	TopLogprobs []TokenLogprob `json:"top_logprobs,omitempty"`
}

type MediaData struct {
	Data []byte `json:"data"`
	ID   int    `json:"id"`
	Kind MediaKind
}

type MediaKind string

type Message struct {
	Role       string
	Content    string
	Thinking   string
	Media      []MediaData
	ToolCalls  []api.ToolCall
	ToolName   string
	ToolCallID string
}

type ServerStatus int

type ServerStatusResponse struct {
	Status   ServerStatus `json:"status"`
	Progress float32      `json:"progress"`
}

type StatusWriter struct {
	// contains filtered or unexported fields
}

type TokenLogprob struct {
	Token   string  `json:"token"`
	Logprob float64 `json:"logprob"`
}