@sleepy_panda_srl/portulan 0.2.0 → 0.4.0

package/evals/ab/personas/implementer.md

@@ -0,0 +1,22 @@
+# implementer — acquired routing comparison
+
+Host: 2.1.321 (Claude Code). Concrete model: claude-sonnet-5-5.
+
+A uses the shipped inherited model and undeclared child effort (observed high). B requests medium through the native child tool. Each case has one attempt per arm.
+
+| Arm | Semantic passes | Observed cost index | Cold-normalized cost index |
+|---|---:|---:|---:|
+| A | 3/3 | 254184.55 | 435042.30 |
+| B | 3/3 | 249066.45 | 429923.05 |
+
+Medium wins this observed corpus: **yes**. The shipped policy remains inherited model, undeclared effort, instruction floor retained and five-minute cache lifetime.
+
+These are three observations, not a reliability estimate. A result on this concrete model does not establish medium effort for other inherited models. Cost indexes use the frozen declared vector, include parent and child requests, and are not subscription bills. First-request input is normalized separately in each fresh parent and child context.
+
+| Case | A | B |
+|---|---|---|
+| implementer-lower-bound | PASS | PASS |
+| implementer-dedup | PASS | PASS |
+| implementer-containment | PASS | PASS |
+
+The common acquisition record accounts for both mechanism probes and discloses the one retained-answer decoder repair after the first outcome. The original failed decode score and the repaired score are both retained; that child was never rerun.