Add agent rehearsal harness, findings, and per-run evidence for split-loop-with-lambda

Six scripted pi sub-agent runs (3 tool regimes × 2 models) rehearsed the
exercise; deterministic gate = solution test + approved file. Key results:
mandated CLI triples cost on the strong model (4:06 vs 0:39, PASS both);
weak model fails only under the mandate (A+Q), passes when free or optional.
Drift documented with code: scorer.updateSelection left inside the extracted
method (A+Q, C+Q). Harness in tools/rehearse; summary in
rehearsal-findings.md; per-run evidence in rehearsal-runs/; cheat sheet in
rehearse-with-agent.md corrected (lambda-typed parameters unsupported).

ideas/split-loop-with-lambda/exercise/rehearse-with-agent.md

@@ -70,5 +70,11 @@ file dropped in: it must pass deterministically.
 | introduce lambda | none — manual edit |
 | slide statement | none — manual edit |
 | extract method | `java-refactor extract` |
-| add lambda parameter | `java-refactor introduce-param` / `change-method-signature` |
+| add lambda parameter | none — manual edit (`introduce-param` / `change-method-signature` cannot introduce a lambda expression as a parameter: `introduce-param` on the lambda inlines it into the call site, referencing the private `scorer` field from outside the class → does not compile. Lambdas are only handled as rewrite *targets* — method references get converted to lambdas at call sites — never as the subject of an operation) |
 | move method to another class (step 4, not in scope) | `java-refactor move-method` (call sites not rewritten) |
+
+Rehearsal evidence (2026-09-27, see `rehearsal-findings.md`): with the CLI
+merely *available* (not mandated) plus a 6-line subcommand intro, glm-5.3-flash
+passed in 2:37 / 23 turns — using `extract` (dry-run → apply) for step 2 and
+editing manually for steps 1 and 3, with no tool-shopping detour. Mandating the
+CLI (variant A) tripled the turns of plain editing (B) on this 55-line file.