Struct SanitizedContent 

pub struct SanitizedContent {
    pub body: String,
    pub source: ContentSource,
    pub injection_flags: Vec<InjectionFlag>,
    pub was_truncated: bool,
}

Result of the sanitization pipeline for a single piece of content.

The body field is the processed text ready to insert into the agent’s message history. Callers should inspect injection_flags for threat intelligence and was_truncated to decide whether to emit a “content was truncated” notice to the user.

Examples

use zeph_sanitizer::{ContentSanitizer, ContentSource, ContentSourceKind};
use zeph_config::ContentIsolationConfig;

let sanitizer = ContentSanitizer::new(&ContentIsolationConfig::default());
let result = sanitizer.sanitize(
    "normal tool output",
    ContentSource::new(ContentSourceKind::ToolResult),
);
assert!(!result.was_truncated);
assert!(result.injection_flags.is_empty());
assert!(result.body.contains("normal tool output"));

Fields

body: String

The processed, possibly spotlighted body ready to insert into message history.

source: ContentSource

Provenance metadata for this content.

injection_flags: Vec<InjectionFlag>

Injection patterns matched during detection (advisory — content is never removed).

was_truncated: bool

true when content was truncated to max_content_size.

Trait Implementations

impl Clone for SanitizedContent

fn clone(&self) -> SanitizedContent

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for SanitizedContent

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

Formats the value using the given formatter.