iter cma.2: harness binary + 4 tasks + reference solutions + 4 integration tests

Sibling standalone Cargo crate `harness/` under
experiments/2026-05-12-cross-model-authoring/ (out-of-workspace
idiom carried forward from cma.1 verbatim). Six modules:
strip_locations (regex pass for form-asymmetric location info,
calibrated against five real `ail check`/`ail parse` stderr
captures), pipeline (subprocess wrapper for parse|check|build +
5s-timeout exec; preflight on ail+clang), ionos (blocking reqwest
client + retry policy per spec), mock (canned-response loader),
scoring (CSV + summary.md), tasks (definition struct + loader).
main.rs ties them into the per-(cohort,task) loop with budget
accounting and per-turn artefact recording.

Four MVP tasks land with reference solutions that compile, build,
and execute green through the actual ail+clang pipeline:
t1_add_three (chained `+` + io/print_int), t2_length (polymorphic
List + recursion), t3_main_prints (minimal IO module), t4_count_zeros
(prelude Eq Int + branched if). Reference solutions stay in canonical
AILang form — param_modes is omitted when every parameter is the
Implicit default, consistent with the existing examples/ corpus.

13/13 tests green: 5 lib unit (strip_locations) + 5 integration
(strip_locations against verbatim captured fixtures) + 1
verify_references (drives every reference through the real
ail+clang pipeline) + 1 mock_full_run (full eight-row sweep with
mixed green-on-turn-2 + turn-limit cycles) + 1 budget_abort
(synthetic budget exhaustion with budget_abort rows + run_status).

Two implementer-phase repairs beyond the plan, both small and
surfaced in the iter journal Concerns:
1. pipeline.rs renames the program file to `<module-name>.ail.json`
   between parse and check because `ail check` enforces filename
   stem == module name (compiler contract the plan did not anticipate).
2. main.rs fills synthetic budget_abort rows for tasks the outer
   loop never reached so scores.csv preserves the expected eight-row
   shape on budget exhaustion.

One plan/text mismatch carried over: README "Total 8 passed" reflects
the plan's four-suite count; actual sweep produces 13. Doc-fix
candidate for cma.3.

cma.3 (live IONOS run + DESIGN.md addendum + roadmap edits) remains
out of scope.

bench/orchestrator-stats/2026-05-12-iter-cma.2.json

@@ -0,0 +1,31 @@
+{
+  "iter_id": "cma.2",
+  "date": "2026-05-12",
+  "mode": "standard",
+  "outcome": "DONE",
+  "tasks_total": 13,
+  "tasks_completed": 13,
+  "reloops_per_task": {
+    "1": 0,
+    "2": 0,
+    "3": 0,
+    "4": 0,
+    "5": 0,
+    "6": 0,
+    "7": 0,
+    "8": 0,
+    "9": 0,
+    "10": 0,
+    "11": 0,
+    "12": 1,
+    "13": 0
+  },
+  "review_loops_spec": 0,
+  "review_loops_quality": 0,
+  "blocked_reason": null,
+  "notes": [
+    "Task 3 + Task 12 each landed one implementer-phase repair (pipeline filename-matching; budget-abort row-filling) — both flagged as Concerns in the journal, not re-loops against the spec/quality checks. reloops_per_task['12'] = 1 records the budget_abort test going RED-then-GREEN after the main.rs repair.",
+    "All 13 tests pass: 5 lib unit (strip_locations) + 5 strip_locations integration + 1 verify_references + 1 mock_full_run + 1 budget_abort.",
+    "AIL_BIN env required for verify_references and mock_full_run tests when ail is not on PATH."
+  ]
+}