llm

type CatalogHealth struct {
	Path        string    `json:"path"`
	Exists      bool      `json:"exists"`
	ModifiedAt  time.Time `json:"modified_at,omitempty"`
	Size        int64     `json:"size,omitempty"`
	Models      int       `json:"models,omitempty"`
	Deployments int       `json:"deployments,omitempty"`
	Offerings   int       `json:"offerings,omitempty"`
	Stale       bool      `json:"stale,omitempty"`
	StaleAfter  time.Time `json:"stale_after,omitempty"`
	Source      string    `json:"source,omitempty"`
	Error       string    `json:"error,omitempty"`
}

type CatalogMaintenance interface {
	RefreshCatalog(ctx context.Context, providerID string) (CatalogSnapshot, error)
	CatalogHealth(ctx context.Context) CatalogHealth
	StatePaths() StatePaths
	DefaultProviderFilter(ctx context.Context) string
	Preflight(ctx context.Context) PreflightReport
	PreflightWithOptions(ctx context.Context, opts PreflightOptions) PreflightReport
	ProviderStateSecurityStatus() ProviderStateSecurity
	MigrateProviderSecrets() error
	MigrateProviderSecretsContext(ctx context.Context) error
}

type CatalogSnapshot struct {
	Models    []Model   `json:"models"`
	CachePath string    `json:"cache_path,omitempty"`
	RemoteURL string    `json:"remote_url,omitempty"`
	Stale     bool      `json:"stale,omitempty"`
	LoadedAt  time.Time `json:"loaded_at"`
}

type ChatOptions struct {
	Provider             string          `json:"provider,omitempty"`
	Model                string          `json:"model,omitempty"`
	Temperature          *float64        `json:"temperature,omitempty"`
	MaxTokens            int             `json:"max_tokens,omitempty"`
	Stream               bool            `json:"stream,omitempty"`
	Tools                []EyrieTool     `json:"tools,omitempty"`
	System               string          `json:"system,omitempty"`
	EnableCaching        bool            `json:"enable_caching,omitempty"`
	ResponseFormat       *ResponseFormat `json:"response_format,omitempty"`
	ReasoningEffort      string          `json:"reasoning_effort,omitempty"`
	ThinkingBudgetTokens int             `json:"thinking_budget_tokens,omitempty"`
	ThinkingMode         string          `json:"thinking_mode,omitempty"`
	ThinkingDisplay      string          `json:"thinking_display,omitempty"`
	ThinkingEnabled      *bool           `json:"thinking_enabled,omitempty"`
	// GLMThinkingEnabled toggles GLM/Z.ai extended reasoning via the provider's
	// non-OpenAI thinking={"type":"enabled"|"disabled"} request parameter. Only
	// applied for OpenAI-compatible providers whose compat config sets
	// ThinkingFormat to "zai". When nil the parameter is omitted and the model
	// uses its default (GLM defaults to enabled).
	GLMThinkingEnabled *bool             `json:"glm_thinking_enabled,omitempty"`
	VirtualKeyID       string            `json:"virtual_key_id,omitempty"`
	KimiContextCacheID string            `json:"kimi_context_cache_id,omitempty"`
	KimiCacheResetTTL  bool              `json:"kimi_cache_reset_ttl,omitempty"`
	TopP               *float64          `json:"top_p,omitempty"`
	TopK               *int              `json:"top_k,omitempty"`
	StopSequences      []string          `json:"stop_sequences,omitempty"`
	ToolChoice         *ToolChoiceOption `json:"tool_choice,omitempty"`
	MetadataUserID     string            `json:"metadata_user_id,omitempty"`
	ServiceTier        string            `json:"service_tier,omitempty"`
	OutputEffort       string            `json:"output_effort,omitempty"`
	OutputSchema       string            `json:"output_schema,omitempty"`
	PresencePenalty    *float64          `json:"presence_penalty,omitempty"`
	FrequencyPenalty   *float64          `json:"frequency_penalty,omitempty"`
	N                  *int              `json:"n,omitempty"`
	LogProbs           *bool             `json:"logprobs,omitempty"`
	TopLogProbs        *int              `json:"top_logprobs,omitempty"`
	Seed               *int              `json:"seed,omitempty"`
	Store              *bool             `json:"store,omitempty"`
	Metadata           map[string]string `json:"metadata,omitempty"`
	Modalities         []string          `json:"modalities,omitempty"`
	AudioConfig        string            `json:"audio_config,omitempty"`
	Prediction         string            `json:"prediction,omitempty"`
	WebSearchOptions   string            `json:"web_search_options,omitempty"`
}

type CheckStatus string

type ContentPart struct {
	Type       string          `json:"type"`
	Text       string          `json:"text,omitempty"`
	ImageURL   *ImageURLPart   `json:"image_url,omitempty"`
	InputAudio *InputAudioPart `json:"input_audio,omitempty"`
}

type ContinuationConfig struct {
	MaxContinuations int
	MaxTotalTokens   int
}

type CredentialManager interface {
	SaveCredential(ctx context.Context, providerID, secret string) (CredentialStatus, error)
	RemoveCredential(ctx context.Context, providerID string) error
	CredentialStatus(ctx context.Context, providerID string) (CredentialStatus, error)
	SaveCredentialEnv(ctx context.Context, envVar, secret string) error
	HasCredentialEnv(ctx context.Context, envVar string) bool
	CredentialEnvKeys(providerID string) []string
	ResolveCredential(ctx context.Context, secret string) CredentialResolution
	CredentialProviders(context.Context) []CredentialProviderOption
	ApplyCredentials(ctx context.Context, providerID string) (CatalogSnapshot, error)
}

type CredentialProviderOption struct {
	ProviderID   string `json:"provider_id"`
	DeploymentID string `json:"deployment_id,omitempty"`
	EnvVar       string `json:"env_var"`
	DisplayName  string `json:"display_name"`
	Inferred     bool   `json:"inferred,omitempty"`
	RequiresKey  bool   `json:"requires_key"`
	Rank         int    `json:"rank"`
}

type CredentialResolution struct {
	FormatOK                bool   `json:"format_ok"`
	FormatError             string `json:"format_error,omitempty"`
	Providers               []CredentialProviderOption
	ProbeDisambiguationUsed bool `json:"probe_disambiguation_used,omitempty"`
}

type CredentialStatus struct {
	Configured          bool   `json:"configured"`
	ProviderID          string `json:"provider_id,omitempty"`
	EnvironmentVariable string `json:"environment_variable,omitempty"`
	EnvironmentConflict bool   `json:"environment_conflict,omitempty"`
	Verified            bool   `json:"verified,omitempty"`
	Masked              string `json:"masked,omitempty"`
	EnvVar              string `json:"env_var,omitempty"`
}

type DeploymentSummary struct {
	RoutingSource string `json:"routing_source,omitempty"`
	RoutingStages int    `json:"routing_stages,omitempty"`
	Formatted     string `json:"formatted"`
}

type EventStreamer interface {
	Next() bool
	Event() EyrieStreamEvent
	Err() error
	Close() error
}

type EyrieConfig struct {
	Provider   string `json:"provider,omitempty"`
	APIKey     string `json:"-"`
	BaseURL    string `json:"base_url,omitempty"`
	Model      string `json:"model,omitempty"`
	MaxRetries int    `json:"max_retries,omitempty"`
}

type EyrieMessage struct {
	Role         string        `json:"role"`
	Content      string        `json:"content,omitempty"`
	Thinking     string        `json:"thinking,omitempty"`
	ContentParts []ContentPart `json:"content_parts,omitempty"`
	Images       []string      `json:"images,omitempty"`
	ToolUse      []ToolCall    `json:"tool_use,omitempty"`
	ToolResults  []ToolResult  `json:"tool_results,omitempty"`
}

type EyrieResponse struct {
	Content        string         `json:"content"`
	Thinking       string         `json:"thinking,omitempty"`
	Usage          *EyrieUsage    `json:"usage,omitempty"`
	ToolCalls      []ToolCall     `json:"tool_calls,omitempty"`
	FinishReason   string         `json:"finish_reason"`
	RequestID      string         `json:"request_id,omitempty"`
	OrganizationID string         `json:"organization_id,omitempty"`
	Route          *ResolvedRoute `json:"route,omitempty"`
}

type EyrieStreamEvent struct {
	Type       string      `json:"type"`
	Content    string      `json:"content,omitempty"`
	ToolCall   *ToolCall   `json:"tool_call,omitempty"`
	Thinking   string      `json:"thinking,omitempty"`
	Error      string      `json:"error,omitempty"`
	Warning    string      `json:"warning,omitempty"`
	RequestID  string      `json:"request_id,omitempty"`
	Usage      *EyrieUsage `json:"usage,omitempty"`
	StopReason string      `json:"stop_reason,omitempty"`
	// TTFT and TTFTms both carry time-to-first-token in milliseconds but ride
	// different events: the dedicated "ttft" event populates TTFT, while the
	// terminal "done" event populates TTFTms. The engine normalizes the two
	// into a single value (preferring TTFTms, falling back to TTFT). Both are
	// retained for wire compatibility with existing producers/consumers.
	TTFTms int            `json:"ttft_ms,omitempty"`
	TTFT   int            `json:"ttft,omitempty"`
	Route  *ResolvedRoute `json:"route,omitempty"`
}

type EyrieTool struct {
	Name        string                 `json:"name"`
	Description string                 `json:"description"`
	Parameters  map[string]interface{} `json:"parameters"`
}

type EyrieUsage struct {
	PromptTokens        int `json:"prompt_tokens"`
	CompletionTokens    int `json:"completion_tokens"`
	TotalTokens         int `json:"total_tokens"`
	CacheCreationTokens int `json:"cache_creation_tokens,omitempty"`
	CacheReadTokens     int `json:"cache_read_tokens,omitempty"`
	ThinkingTokens      int `json:"thinking_tokens,omitempty"`
}

type Gateway struct {
	ID                    string `json:"id"`
	DisplayName           string `json:"display_name"`
	DeploymentID          string `json:"deployment_id,omitempty"`
	CredentialEnv         string `json:"credential_env"`
	RequiresKey           bool   `json:"requires_key"`
	SortOrder             int    `json:"sort_order"`
	ChatPreference        int    `json:"chat_preference"`
	SupportsLiveDiscovery bool   `json:"supports_live_discovery"`
	CredentialConfigured  bool   `json:"credential_configured"`
	DeploymentConfigured  bool   `json:"deployment_configured"`
	ModelCount            int    `json:"model_count"`
	RegionLabel           string `json:"region_label,omitempty"`
	RegionRequired        bool   `json:"region_required"`
	Active                bool   `json:"active"`
}

type GatewayInspector interface {
	GatewayDefinitions() []Gateway
	Gateways(ctx context.Context) []Gateway
	GatewayRegion(providerID string) (label string, required bool)
	SetGatewayRegion(ctx context.Context, providerID, value string) error
	GatewayForModel(ctx context.Context, modelID string) string
	CanonicalModel(ctx context.Context, modelID string) string
	DeploymentRoutingEnabled(override *bool) bool
	DeploymentStatus(ctx context.Context, activeModel string) (string, error)
	DeploymentSummary(ctx context.Context, activeModel string) (DeploymentSummary, error)
	RoutingPreview(ctx context.Context, modelID string) (string, error)
}

type GenerateRequest struct {
	Messages     []EyrieMessage
	SystemPrompt string
	Tools        []EyrieTool
	Requirements Requirements
	Preference   Preference
	Limits       Limits
	Metadata     Metadata
	Temperature  *float64
	OutputSchema string
	Options      GenerationOptions
}

type GenerationOptions struct {
	EnableCaching        bool
	ReasoningEffort      string
	ThinkingBudgetTokens int
	ThinkingMode         string
	ThinkingDisplay      string
	ThinkingEnabled      *bool
	// GLMThinkingEnabled toggles GLM/Z.ai extended reasoning via the provider's
	// non-OpenAI thinking={"type":"enabled"|"disabled"} request parameter. Only
	// applied for OpenAI-compatible providers whose compat config sets
	// ThinkingFormat to "zai". When nil the parameter is omitted and the model
	// uses its default (GLM defaults to enabled).
	GLMThinkingEnabled *bool
	VirtualKeyID       string
	KimiContextCacheID string
	KimiCacheResetTTL  bool
	TopP               *float64
	TopK               *int
	StopSequences      []string
	ToolChoice         *ToolChoiceOption
	ServiceTier        string
	OutputEffort       string
	PresencePenalty    *float64
	FrequencyPenalty   *float64
	N                  *int
	LogProbs           *bool
	TopLogProbs        *int
	Seed               *int
	Store              *bool
	Metadata           map[string]string
	Modalities         []string
	AudioConfig        string
	Prediction         string
	WebSearchOptions   string
}

type Generator interface {
	Generate(ctx context.Context, req GenerateRequest) (*EyrieResponse, error)
	Stream(ctx context.Context, req GenerateRequest) (EventStreamer, error)
}

type ImageURLPart struct {
	URL    string `json:"url"`
	Detail string `json:"detail,omitempty"`
}

type InputAudioPart struct {
	Data   string `json:"data"`
	Format string `json:"format"`
}

type Intent string

type Limits struct {
	MaxOutputTokens      int           `json:"max_output_tokens,omitempty"`
	MaxContinuations     int           `json:"max_continuations,omitempty"`
	MaxTotalOutputTokens int           `json:"max_total_output_tokens,omitempty"`
	Timeout              time.Duration `json:"timeout,omitempty"`
}

type Metadata struct {
	SessionID string `json:"session_id,omitempty"`
	TurnID    string `json:"turn_id,omitempty"`
	UserID    string `json:"user_id,omitempty"`
	ProjectID string `json:"project_id,omitempty"`
}

type Model struct {
	ID               string          `json:"id"`
	ProviderID       string          `json:"provider_id"`
	CanonicalID      string          `json:"canonical_id,omitempty"`
	DisplayName      string          `json:"display_name"`
	Description      string          `json:"description,omitempty"`
	Owner            string          `json:"owner,omitempty"`
	GatewayID        string          `json:"gateway_id,omitempty"`
	ContextWindow    int             `json:"context_window,omitempty"`
	MaxOutputTokens  int             `json:"max_output_tokens,omitempty"`
	InputPricePer1M  float64         `json:"input_price_per_1m,omitempty"`
	OutputPricePer1M float64         `json:"output_price_per_1m,omitempty"`
	PriceKnown       bool            `json:"price_known"`
	Capabilities     []string        `json:"capabilities,omitempty"`
	Source           string          `json:"source,omitempty"`
	LiveMetadata     json.RawMessage `json:"live_metadata,omitempty"`
}

type ModelCatalog interface {
	ListModels(ctx context.Context, providerID string, refresh bool) ([]Model, error)
	ListLiveModels(ctx context.Context, providerID string) ([]Model, error)
	ListPublicModels(ctx context.Context, providerID string) ([]Model, error)
	ModelInfo(ctx context.Context, modelID string) (Model, bool, error)
	ModelProviders(ctx context.Context) ([]string, error)
	DefaultModel(ctx context.Context, provider, fallback string) string
	PreferredModel(ctx context.Context, provider string, class ModelClass, fallback string) string
	PreferredModels(ctx context.Context, primaryProvider string, class ModelClass, limit int) []string
	ModelClassOf(ctx context.Context, modelID string) ModelClass
	ProviderForModel(ctx context.Context, modelID string) string
	PrimaryModel(ctx context.Context) string
	ModelNames(ctx context.Context) []string
	Catalog(ctx context.Context) (CatalogSnapshot, error)
}

type ModelClass string

type NativeCompactionRequest struct {
	Provider        string
	Model           string
	Messages        []EyrieMessage
	ContextWindow   int
	ThresholdPct    int
	MaxOutputTokens int
}

type NativeCompactor interface {
	SupportsNativeCompaction(ctx context.Context, provider, model string) bool
	CompactNative(ctx context.Context, req NativeCompactionRequest) (string, error)
}

type Preference struct {
	Intent            Intent  `json:"intent,omitempty"`
	PreferredProvider string  `json:"-"`
	PreferredModelID  string  `json:"preferred_model_id,omitempty"`
	AllowFallback     bool    `json:"allow_fallback,omitempty"`
	MaximumCostUSD    float64 `json:"maximum_cost_usd,omitempty"`
}

type PreflightCheck struct {
	Name   string      `json:"name"`
	Status CheckStatus `json:"status"`
	Detail string      `json:"detail,omitempty"`
}

type PreflightOptions struct {
	VerifyLive bool `json:"verify_live,omitempty"`
}

type PreflightReport struct {
	Ready        bool             `json:"ready"`
	LiveVerified bool             `json:"live_verified"`
	Checks       []PreflightCheck `json:"checks"`
}

type Provider interface {
	Generator
	ModelCatalog
	CredentialManager
	SelectionManager
	GatewayInspector
	CatalogMaintenance
	NativeCompactor
}

type ProviderStateSecurity struct {
	Path       string `json:"path"`
	HasSecrets bool   `json:"has_secrets"`
	Detail     string `json:"detail,omitempty"`
	Error      string `json:"error,omitempty"`
}

type Requirements struct {
	Streaming      bool
	Tools          bool
	Vision         bool
	StructuredJSON bool
	Reasoning      bool
	MinimumContext int `json:"minimum_context,omitempty"`
}

type ResolvedRoute struct {
	Provider          string `json:"provider"`
	Model             string `json:"model"`
	DeploymentRouting bool   `json:"deployment_routing,omitempty"`
}

type ResponseFormat struct {
	Type   string `json:"type"`
	Schema string `json:"schema,omitempty"`
}

type Selection struct {
	Provider                string `json:"provider"`
	Model                   string `json:"model"`
	HasConfiguredDeployment bool   `json:"has_configured_deployment"`
	DeploymentRouting       bool   `json:"deployment_routing"`
}

type SelectionManager interface {
	ActiveSelection(ctx context.Context) ResolvedRoute
	EffectiveSelection(ctx context.Context, opts SelectionOptions) Selection
	SetActiveProvider(ctx context.Context, provider string) error
	SetActiveModel(ctx context.Context, modelID string) error
	SetSelection(ctx context.Context, provider, modelID string) error
	ClearSelection(ctx context.Context) error
}

type SelectionOptions struct {
	ProviderOverride          string
	ModelOverride             string
	DeploymentRoutingOverride *bool
}

type StatePaths struct {
	Catalog        string `json:"catalog"`
	ProviderConfig string `json:"provider_config"`
}

type StreamResult struct {
	Events    <-chan EyrieStreamEvent
	RequestID string
	// contains filtered or unexported fields
}

type ToolCall = tools.ToolCall

type ToolChoiceOption struct {
	Type                   string `json:"type"`
	Name                   string `json:"name,omitempty"`
	DisableParallelToolUse bool   `json:"disable_parallel_tool_use,omitempty"`
}

type ToolResult = tools.ToolResult