Defer initial context insertion until the first turn (#14313)

## Summary
- defer fresh-session `build_initial_context()` until the first real
turn instead of seeding model-visible context during startup
- rely on the existing `reference_context_item == None` turn-start path
to inject full initial context on that first real turn (and again after
baseline resets such as compaction)
- add a regression test for `InitialHistory::New` and update affected
deterministic tests / snapshots around developer-message layout,
collaboration instructions, personality updates, and compact request
shapes

## Notes
- this PR does not add any special empty-thread `/compact` behavior
- most of the snapshot churn is the direct result of moving the initial
model-visible context from startup to the first real turn, so first-turn
request layouts no longer contain a pre-user startup copy of permissions
/ environment / other developer-visible context
- remote manual `/compact` with no prior user still skips the remote
compact request; local first-turn `/compact` still issues a compact
request, but that request now reflects the lack of startup-seeded
context

---------

Co-authored-by: Codex <noreply@openai.com>

codex-rs/core/tests/suite/personality.rs

@@ -867,7 +867,7 @@ async fn user_turn_personality_remote_model_template_includes_update_message() -
     let developer_texts = request.message_input_texts("developer");
     let personality_text = developer_texts
         .iter()
-        .find(|text| text.contains("<personality_spec>"))
+        .find(|text| text.contains(remote_friendly_message))
         .expect("expected personality update message in developer input");
 
     assert!(