core: remove redundant TurnContext and Prompt fields (#28638)

## Why

`TurnContext` had accumulated dead fields and cached projections of
values already owned by its per-turn `Config` or `ModelInfo`. Keeping
both copies made ownership unclear and allowed artificial split-brain
states, such as a compatibility hash differing from the model metadata
it came from.

`Prompt` similarly carried a write-only personality after personality
selection had already been materialized into its base instructions.

This makes the canonical owner explicit: configuration-backed values
come from `config`, model-derived values come from `model_info`, and
prompts contain only data consumed by request construction.

## What changed

- Remove the unused `ghost_snapshot`, `codex_self_exe`, and
`thread_source` fields.
- Remove duplicate `comp_hash`, `truncation_policy`, `features`,
`shell_environment_policy`, `codex_linux_sandbox_exe`, `compact_prompt`,
and `tool_mode` fields.
- Read those values directly from `TurnContext::config` or
`TurnContext::model_info` at their consumers.
- Remove the write-only `Prompt::personality` field and its constructor
assignments.
- Preserve review-turn inheritance of the parent turn's shell policy,
Linux sandbox executable, and compact prompt through the review config.

## Testing

- `cargo check -p codex-core --tests`

codex-rs/core/src/user_shell_command.rs

@@ -11,7 +11,10 @@ fn user_shell_command_fragment(
     exec_output: &ExecToolCallOutput,
     turn_context: &TurnContext,
 ) -> UserShellCommand {
-    let output = format_exec_output_str(exec_output, turn_context.truncation_policy);
+    let output = format_exec_output_str(
+        exec_output,
+        turn_context.model_info.truncation_policy.into(),
+    );
     UserShellCommand::new(command, exec_output.exit_code, exec_output.duration, output)
 }