[codex] Add token budget context feature (#27438)

## Why

The model should be able to see bounded context-window budget metadata
when the `token_budget` feature is enabled. The full-window message is
only injected with full context, while normal turns get a smaller
follow-up only when reported usage first crosses a budget threshold.

## What changed

- Added the `TokenBudget` feature flag.
- Added `<token_budget>` developer fragments for full context-window
metadata and current-window remaining tokens.
- Inserted the threshold message during normal turn handling by
comparing token usage before and after sampling, avoiding persistent
threshold bookkeeping.
- Added core integration coverage for full-context-only metadata and
25/50/75 percent threshold messages.

## Verification

- `just test -p codex-core token_budget`
- `git diff --check`
This commit is contained in:
pakrym-oai authored and GitHub committed 2026-06-10 20:07:06 -07:00
1 parent ab4ce40042
commit 658af936fd
14 files changed
+399 -7

No files matched your search

+1
View File
@@ -30,6 +30,7 @@ const CONTEXTUAL_DEVELOPER_PREFIXES: &[&str] = &[
COLLABORATION_MODE_OPEN_TAG,
REALTIME_CONVERSATION_OPEN_TAG,
"<personality_spec>",
"<token_budget>",
];
pub(crate) fn is_contextual_user_message_content(message: &[ContentItem]) -> bool {