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/rehearsal-runs/B/time.txt

@@ -0,0 +1,23 @@
+	Command being timed: "timeout -k 15 600 pi -p -a --session-dir /tmp/rehearsal/runs/B/session --name rehearsal-B Read AGENTS.md in this directory and execute the refactoring task it describes. Run mvn -q test after each change. When done, stop and report the final diff of LongRangeForecasts.java."
+	User time (seconds): 15.30
+	System time (seconds): 1.08
+	Percent of CPU this job got: 41%
+	Elapsed (wall clock) time (h:mm:ss or m:ss): 0:39.35
+	Average shared text size (kbytes): 0
+	Average unshared data size (kbytes): 0
+	Average stack size (kbytes): 0
+	Average total size (kbytes): 0
+	Maximum resident set size (kbytes): 249312
+	Average resident set size (kbytes): 0
+	Major (requiring I/O) page faults: 0
+	Minor (reclaiming a frame) page faults: 332026
+	Voluntary context switches: 28517
+	Involuntary context switches: 935
+	Swaps: 0
+	File system inputs: 0
+	File system outputs: 1624
+	Socket messages sent: 0
+	Socket messages received: 0
+	Signals delivered: 0
+	Page size (bytes): 4096
+	Exit status: 0