Struct QuerySqlRequest 

pub struct QuerySqlRequest {
    pub path: Option<String>,
    pub tables: Option<HashMap<String, String>>,
    pub sql: String,
    pub limit: Option<usize>,
}

Input for the query_sql tool.

Single-file mode: pass path and reference the file as table data. Multi-file mode: pass tables mapping LLM-chosen names → relative paths, then JOIN them in sql. Mutually exclusive — pick one shape per call.

Glob patterns (*, ?, [...]) are supported in both modes — the SQL backend expands them at read time. They stay bounded by --root because the path validator rejects .. and absolute paths up-front.

Fields

path: Option<String>

Single-file shortcut. Registered as table data.

tables: Option<HashMap<String, String>>

Multi-file mode: map of table name → relative path (or glob). Each entry is registered as a SQL table in the same query session so the LLM can JOIN across files.

sql: String

The SQL query.

limit: Option<usize>

Cap on returned rows. Defaults to 100; capped at 1000.

Trait Implementations

impl Debug for QuerySqlRequest

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for QuerySqlRequest

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl JsonSchema for QuerySqlRequest

fn schema_name() -> Cow<'static, str>

The name of the generated JSON Schema.

fn schema_id() -> Cow<'static, str>

Returns a string that uniquely identifies the schema produced by this type.

fn json_schema(generator: &mut SchemaGenerator) -> Schema

Generates a JSON Schema for this type.

fn inline_schema() -> bool

Whether JSON Schemas generated for this type should be included directly in parent schemas, rather than being re-used where possible using the $ref keyword.