Removes computeAutoApproval() and tightens up canAutoApprove() as the source of truth (#126)

Previously, `parseToolCall()` was using `computeAutoApproval()`, which
was a somewhat parallel implementation of `canAutoApprove()` in order to
get `SafeCommandReason` metadata for presenting information to the user.
The only function that was using `SafeCommandReason` was
`useMessageGrouping()`, but it turns out that function was unused, so
this PR removes `computeAutoApproval()` and all code related to it.

More importantly, I believe this fixes
https://github.com/openai/codex/issues/87 because
`computeAutoApproval()` was calling `parse()` from `shell-quote` without
wrapping it in a try-catch. This PR updates `canAutoApprove()` to use a
tighter try-catch block that is specific to `parse()` and returns an
appropriate `SafetyAssessment` in the event of an error, based on the
`ApprovalPolicy`.

Signed-off-by: Michael Bolin <mbolin@openai.com>

codex-cli/src/utils/agent/review.ts

@@ -1,11 +1,3 @@
-import type { SafeCommandReason } from "../../approvals";
-
-export type CommandReviewDetails = {
-  cmd: Array<string>;
-  cmdReadableText: string;
-  autoApproval: SafeCommandReason | null;
-};
-
 export enum ReviewDecision {
   YES = "yes",
   NO_CONTINUE = "no-continue",