feat(apr-cli): extend APR_EVAL_DEBUG diagnostic to MBPP harness (PMAT-CODE-MBPP-DIAG-001)

The §69 diagnostic surface (PR #1634) and §70 RC3 fix (PR #1635) closed
the harness-bug class for HumanEval. MBPP's path (run_mbpp_inference
+ run_mbpp_inference_cuda) was not yet instrumented. This PR extends
APR_EVAL_DEBUG to MBPP so future investigation of MBPP failures has
ground-truth diagnostics on the same surface.

What changes:

- run_mbpp_inference (CPU path) now calls
  execute_python_test_with_diagnostics and emits
  /tmp/apr_eval_debug_MBPP_<task>.json when APR_EVAL_DEBUG=1 is set.
- run_mbpp_inference_cuda (CUDA path) gets the same treatment.

What does NOT change:

- run_mbpp_inference still uses the legacy
  AprTransformer::forward_with_cache + AprKVCache path. PMAT-CODE-
  SHIP-005-FIX (PR #1616) replaced this for HumanEval with realizar::
  run_inference + OwnedQuantizedModel::from_apr. MBPP needs the same
  routing fix — but that's a separate multi-PR cascade scope (also
  includes H4 ChatML wrap + R1+R2 extraction equivalents for MBPP).
  Out of scope for this PR.
- MBPP prompts are natural language (not Python signatures), so the
  §70 RC3 import-stripping bug does NOT apply to MBPP.

Why ship this now:

- Pure diagnostic — zero behaviour change for non-APR_EVAL_DEBUG callers
- Lets us run a 1-problem MBPP smoke under APR_EVAL_DEBUG=1 to verify
  the legacy path's failure mode (currently undiagnosed)
- Mirrors the pattern that successfully diagnosed §69 RC3 in 5 minutes
  on gx10

Test plan:

- [x] cargo check -p apr-cli --features inference → clean
- [x] cargo check -p apr-cli --features "inference,cuda,training" → clean
- [x] cargo fmt --all → clean
- [ ] gx10 single-MBPP-problem APR_EVAL_DEBUG=1 smoke (next slice;
      will document MBPP failure mode in a §72-class amendment)

Refs:
- crates/apr-cli/src/commands/eval/inference.rs::write_apr_eval_debug
- contracts/apr-eval-humaneval-harness-invariant-v1.yaml v1.1.0
- PR #1634 (HumanEval diagnostic surface)
- PR #1635 (HumanEval RC3 fix; cascade base for this branch)

Closes task #53 (MBPP harness diagnostic extension; renamed from
"RC3 prompt-preamble fix" since RC3 does not apply to MBPP's NL
prompts — that decision recorded in commit body).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Author: noahgift

crates/apr-cli/src/commands/eval/inference.rs

@@ -1596,7 +1596,19 @@ fn run_mbpp_inference(
             format!("{completion}\n{setup}\n{tests}\n")
         };
 
-        let ok = execute_python_test(&full_program, 10);
+        let exec_result = execute_python_test_with_diagnostics(&full_program, 10);
+        let ok = exec_result.success;
+
+        if std::env::var("APR_EVAL_DEBUG").is_ok() {
+            write_apr_eval_debug(
+                &task_id,
+                &prompt,
+                &tokenizer.decode(&tokens),
+                completion,
+                &full_program,
+                &exec_result,
+            );
+        }
 
         if ok {
             passed += 1;
@@ -1718,7 +1730,19 @@ fn run_mbpp_inference_cuda(
             format!("{completion}\n{setup}\n{tests}\n")
         };
 
-        let ok = execute_python_test(&full_program, 10);
+        let exec_result = execute_python_test_with_diagnostics(&full_program, 10);
+        let ok = exec_result.success;
+
+        if std::env::var("APR_EVAL_DEBUG").is_ok() {
+            write_apr_eval_debug(
+                &task_id,
+                &prompt,
+                &tokenizer.decode(&tokens),
+                completion,
+                &full_program,
+                &exec_result,
+            );
+        }
 
         if ok {
             passed += 1;