Support typed content in contextual prompt fragments (#54776)

## Why

Contextual fragments and extension-owned world-state sections currently return strings, limiting them to text content.

## What changed

- Return `ContentItem` from fragment bodies and rendering, preserving classification and attribution. Apply text markers only to `InputText`; pass other content through unchanged.
- Allow extension prompt and world-state contributions to carry typed content, and preserve media in context-window hints.
- Hash non-text world-state fragments by their serialized content and role while retaining the existing text hashing behavior.
- Add shared content-to-tool-output conversion that preserves image references, image detail, and audio.

## Testing

Add coverage for typed world-state hashing and preservation of image content and attribution. Expand code-mode output tests to cover input text, output text, file-backed and inline images, and audio.

GitOrigin-RevId: 2ed00d466a3f169b151202f3eef71e667ea64be1
This commit is contained in:
pakrym-oai
2026-10-17 04:02:21 +00:00
committed by copyberry
parent 3b8f43a06b
commit ce0323f2f2
162 changed files with 1109 additions and 570 deletions
@@ -1,5 +1,7 @@
use super::ContextualUserFragment;
use codex_protocol::models::ContentItem;
use codex_protocol::models::ContentItemKind;
use codex_protocol::models::input_text;
#[derive(Debug, Clone, PartialEq, Eq)]
pub(crate) struct CompactionSummary {
@@ -33,7 +35,7 @@ impl ContextualUserFragment for CompactionSummary {
("", "")
}
fn body(&self) -> String {
self.summary.clone()
fn body(&self) -> ContentItem {
input_text(self.summary.clone())
}
}