Clarify when to wait for starting environments (#33636)

## Why

An execution environment marked `starting` is not yet usable, but unrelated work can continue while it becomes ready.

## What changed

- Add developer guidance that explains execution-environment isolation and the resources that become available after startup.
- Tell the model to wait only when the current task needs the starting environment.
- Retain the guidance across world-state updates without duplicating it in request history.

## Testing

- Cover world-state transitions, history retention, rollback handling, and deferred-environment request deduplication.

GitOrigin-RevId: f12f9204d4cbddce50a70eb0998beb6b66cd2fa9

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

@@ -23,6 +23,7 @@ use codex_protocol::openai_models::InputModality;
 use codex_protocol::openai_models::default_input_modalities;
 use codex_protocol::protocol::APPS_INSTRUCTIONS_OPEN_TAG;
 use codex_protocol::protocol::AskForApproval;
+use codex_protocol::protocol::ENVIRONMENTS_INSTRUCTIONS_OPEN_TAG;
 use codex_protocol::protocol::InterAgentCommunication;
 use codex_protocol::protocol::PLUGINS_INSTRUCTIONS_OPEN_TAG;
 use codex_protocol::protocol::SandboxPolicy;
@@ -1031,6 +1032,9 @@ fn drop_last_n_user_turns_trims_context_updates_above_rolled_back_turn() {
         developer_msg(&format!(
             "{PLUGINS_INSTRUCTIONS_OPEN_TAG}\nROLLED_BACK_PLUGIN_INSTRUCTIONS"
         )),
+        developer_msg(&format!(
+            "{ENVIRONMENTS_INSTRUCTIONS_OPEN_TAG}\nROLLED_BACK_ENVIRONMENT_INSTRUCTIONS"
+        )),
         developer_msg("<collaboration_mode>ROLLED_BACK_DEV_INSTRUCTIONS</collaboration_mode>"),
         developer_msg("<multi_agent_mode>ROLLED_BACK_MULTI_AGENT_MODE</multi_agent_mode>"),
         user_input_text_msg(