config

type ClientConfig struct {
	Provider string `yaml:"provider"`
	BaseURL  string `yaml:"base_url"`
	Model    string `yaml:"model"`
	APIKey   string `yaml:"api_key"`
}

type CodeIndexingConfig struct {
	// Enabled accepts true, false or "auto"; auto (the default) enables
	// source-code indexing (it is pure Go and needs no external tool). Source
	// files are split into declaration-level sections and tagged with
	// `type=code` and `language=<name>` metadata, filterable at search time.
	Enabled Toggle `yaml:"enabled"`
	// Extensions extends or overrides the built-in extension→language mapping,
	// e.g. {".phtml": "php"}. Languages: go, javascript, typescript, tsx,
	// python, php.
	Extensions map[string]string `yaml:"extensions"`
}

type Config struct {
	Version   int             `yaml:"version"`
	Store     StoreConfig     `yaml:"store"`
	Index     IndexConfig     `yaml:"index"`
	LLM       LLMConfig       `yaml:"llm"`
	Retrieval RetrievalConfig `yaml:"retrieval"`
	Converter ConverterConfig `yaml:"converter"`
	Indexing  IndexingConfig  `yaml:"indexing"`
}

type ConverterConfig struct {
	Pandoc      PandocConfig         `yaml:"pandoc"`
	LibreOffice LibreOfficeConfig    `yaml:"libreoffice"`
	GenAI       GenAIConverterConfig `yaml:"genai"`
}

type DecompositionConfig struct {
	Enabled       bool `yaml:"enabled"`
	MaxSubQueries int  `yaml:"max_sub_queries"`
}

type FulltextIndexConfig struct {
	Enabled bool    `yaml:"enabled"`
	Path    string  `yaml:"path"`
	Weight  float64 `yaml:"weight"`
}

type GenAIConverterConfig struct {
	// Enabled turns on the GenAI (OCR/LLM) converter. It is opt-in: a DSN and
	// at least one extension are required.
	Enabled bool `yaml:"enabled"`
	// DSN selects the extraction backend, e.g. mistral://?apiKey=${MISTRAL_API_KEY}
	// or marker://host:port.
	DSN string `yaml:"dsn"`
	// Extensions are routed to this converter (e.g. .pdf, .png, .jpg).
	Extensions []string `yaml:"extensions"`
}

type IndexConfig struct {
	Fulltext FulltextIndexConfig `yaml:"fulltext"`
	Vector   VectorIndexConfig   `yaml:"vector"`
}

type IndexingConfig struct {
	MaxWordsPerSection int                `yaml:"max_words_per_section"`
	TaskParallelism    int                `yaml:"task_parallelism"`
	PersistentTasks    bool               `yaml:"persistent_tasks"`
	Code               CodeIndexingConfig `yaml:"code"`
}

type IterativeConfig struct {
	Enabled   bool `yaml:"enabled"`
	MaxRounds int  `yaml:"max_rounds"`
}

type LLMConfig struct {
	Chat       *ClientConfig `yaml:"chat"`
	Embeddings *ClientConfig `yaml:"embeddings"`
}

type LibreOfficeConfig struct {
	// Enabled accepts true, false or "auto"; auto enables the LibreOffice
	// converter when both the libreoffice and pandoc binaries are found. It
	// supersedes the standalone pandoc converter, adding .doc support.
	Enabled Toggle `yaml:"enabled"`
}

type PandocConfig struct {
	// Enabled accepts true, false or "auto"; auto enables the pandoc
	// converter when the binary is found in the PATH.
	Enabled Toggle `yaml:"enabled"`
}

type RetrievalConfig struct {
	Reranking         bool `yaml:"reranking"`
	GroundingCheck    bool `yaml:"grounding_check"`
	GroundingFailOpen bool `yaml:"grounding_fail_open"`
	// MaxTotalWords bounds the prompt size (in words) of the LLM retrieval
	// stages (reranker, judge, evidence evaluator). Keep it low enough that the
	// resulting prompt fits your chat endpoint's context window: words are only
	// a coarse proxy for tokens (~1.8 tokens/word on mixed prose and code), so
	// 18000 words already overflow a 32k-token limit. Zero defers to the
	// library default (12000).
	MaxTotalWords int                 `yaml:"max_total_words"`
	Iterative     IterativeConfig     `yaml:"iterative"`
	Decomposition DecompositionConfig `yaml:"decomposition"`
}

type StoreConfig struct {
	// Driver selects the document store backend; only "sqlite" is supported
	// for now ("postgres" is planned).
	Driver string `yaml:"driver"`
	// DSN is the store location, relative to the .amoxtli directory.
	DSN string `yaml:"dsn"`
}

type Toggle string

type VectorIndexConfig struct {
	// Enabled accepts true, false or "auto"; auto enables the vector index
	// when an embeddings client is configured.
	Enabled    Toggle  `yaml:"enabled"`
	Path       string  `yaml:"path"`
	Weight     float64 `yaml:"weight"`
	VectorSize int     `yaml:"vector_size"`
	MaxWords   int     `yaml:"max_words"`
	// EmbeddingsConcurrency bounds how many embedding batches are computed in
	// parallel for a single document. It is the main lever for large-file
	// indexing latency (one big file is a single task, so cross-file parallelism
	// does not help it). Raise it if your embeddings endpoint tolerates more
	// concurrent requests; lower it to avoid rate limiting (429). 0 defers to the
	// library default.
	EmbeddingsConcurrency int `yaml:"embeddings_concurrency"`
}