fix: prevent repeating interrupted turns (#9043)

## What
Record a model-visible `<turn_aborted>` marker in history when a turn is
interrupted, and treat it as a session prefix.

## Why
When a turn is interrupted, Codex emits `TurnAborted` but previously did
not persist anything model-visible in the conversation history. On the
next user turn, the model can’t tell the previous work was aborted and
may resume/repeat earlier actions (including duplicated side effects
like re-opening PRs).

Fixes: https://github.com/openai/codex/issues/9042

## How
On `TurnAbortReason::Interrupted`, append a hidden user message
containing a `<turn_aborted>…</turn_aborted>` marker and flush.
Treat `<turn_aborted>` like `<environment_context>` for session-prefix
filtering.
Add a regression test to ensure follow-up turns don’t repeat side
effects from an aborted turn.

## Testing
`just fmt`
`just fix -p codex-core`
`cargo test -p codex-core -- --test-threads=1`
`cargo test --all-features -- --test-threads=1`

---------

Co-authored-by: Skylar Graika <sgraika127@gmail.com>
Co-authored-by: jif-oai <jif@openai.com>
Co-authored-by: Eric Traut <etraut@openai.com>

codex-rs/core/src/context_manager/history.rs

@@ -2,6 +2,7 @@ use crate::codex::TurnContext;
 use crate::context_manager::normalize;
 use crate::instructions::SkillInstructions;
 use crate::instructions::UserInstructions;
+use crate::session_prefix::is_session_prefix;
 use crate::truncate::TruncationPolicy;
 use crate::truncate::approx_token_count;
 use crate::truncate::approx_tokens_from_byte_count;
@@ -328,12 +329,6 @@ fn estimate_reasoning_length(encoded_len: usize) -> usize {
         .saturating_sub(650)
 }
 
-fn is_session_prefix(text: &str) -> bool {
-    let trimmed = text.trim_start();
-    let lowered = trimmed.to_ascii_lowercase();
-    lowered.starts_with("<environment_context>")
-}
-
 pub(crate) fn is_user_turn_boundary(item: &ResponseItem) -> bool {
     let ResponseItem::Message { role, content, .. } = item else {
         return false;