chat

type Message struct {
	Role      Role   `json:"role"`
	Content   string `json:"content"`
	Reasoning string `json:"reasoning"`
	// Assistant tool calls
	ToolCalls []ToolCall `json:"tool_calls"`
	// OpenAI: An optional name for the participant. Provides the model information to differentiate between participants of the same role.
	Name string `json:"name"`
	// OpenAI: Assistant refusal message
	Refusal string `json:"refusal"`
	// Anthropic: User boolean indicating whether function call resulted in an error.
	IsErr bool `json:"is_err"`
}

type Options struct {
	// OpenAI: Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
	FrequencyPenalty *float64
	// OpenAI: Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the `content` of `message`.
	Logprobs bool
	// OpenAI: An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and [reasoning tokens](https://platform.openai.com/docs/guides/reasoning).
	MaxCompletionTokens uint
	// The maximum number of tokens to generate before stopping.
	MaxTokens uint
	// OpenAI: How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs.
	// N *uint
	// OpenAI: Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
	PresencePenalty float64
	// OpenAI: This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result. Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend.
	Seed *int64
	// OpenAI: What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
	// Anthropic: Amount of randomness injected into the response. Defaults to `1.0`. Ranges from `0.0` to `1.0`. Use `temperature` closer to `0.0` for analytical / multiple choice, and closer to `1.0` for creative and generative tasks. Note that even with `temperature` of `0.0`, the results will not be fully deterministic.
	Temperature *float64
	// OpenAI: An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. `logprobs` must be set to `true` if this parameter is used.
	TopLogprobs *int32
	TopP        *float64
	TopK        *float32
	// OpenAI: Whether to enable [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling) during tool use.
	ParallelToolCalls *bool
	// OpenAI: Cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field.
	// Google:  Resource name of a context cache that can be used in subsequent requests.
	PromptCacheKey string
	// OpenAI: A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
	SafetyIdentifier string
	// OpenAI: This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
	User string
	// OpenAI: Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.
	LogitBias map[string]int64
	// OpenAI: **o-series models only** Constrains effort on reasoning for [reasoning models](https://platform.openai.com/docs/guides/reasoning). (Accepts [ReasoningEffortUnion.ofString])
	// Ollama: Think controls whether thinking/reasoning models will think before responding. (Accepts both [ReasoningEffortUnion.ofString] and [ReasoningEffortUnion.ofBool])
	ReasoningEffort *ReasoningEffortUnion
	// OpenAI: Specifies the processing type used for serving the request. Any of "auto", "default", "flex", "scale", "priority".
	// Anthropic: Any of "auto", "standard_only"
	ServiceTier string
	// OpenAI: Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
	// Anthropic: Custom text sequences that will cause the model to stop generating.
	Stop []string
	// Schema specifying the format that the model must output.
	//
	// *Supported providers*: OpenAI, Ollama
	ResponseFormat *jsonschema.Schema
	// Anthropic: Enable extended thinking. Must be ≥1024 and less than `max_tokens`.
	Thinking uint64
	// Ollama: How long the model will stay loaded into memory following the request.
	KeepAlive *time.Duration
	// Google:
	//     - `text/plain` (default)
	//     - `application/json`
	ResponseMIMEType string
	// OpenAI: Include usage statistics in streaming mode.
	IncludeStreamMetrics bool
	// l337: Controls channel buffering for streaming responses. Defaults to `0` (unbuffered).
	StreamingBufferSize int
}

type Parameter interface {
	Apply(*Parameters) error
}

type ParameterFunc func(*Parameters) error

type Parameters struct {
	Messages  []Message
	SessionID uuid.UUID
}

type ReasoningEffortLevel string

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

type Role string

type RunResponse struct {
	SessionID uuid.UUID                       `json:"session_id"`
	Messages  []Message                       `json:"messages"`
	Metrics   map[uuid.UUID][]metrics.Metrics `json:"metrics"`
}

type ToolCall struct {
	// Unique identifier for the tool call.
	ID string `json:"id"`
	// Raw LLM arguments.
	Arguments string `json:"arguments"`
	// Tool name
	Name string `json:"name"`
}