p-o-claude re-measured their own source after our (b) finding and sent
back the root cause. It generalizes past them, including to us.
The counting error: their --bundle surface is four sites, not three
(run.py:554 default=None, run_s10.py:46 has a fixture default,
hitl.py:290 append/no default, contracts.py:81 required field).
Verified here against their tree, not their report.
The same blind spot in our own work: we greped both PO repos for the
installation-root signature (expanduser|Path.home|.claude/), got 0 hits,
and reported "no default". The grep was sound; the inference was wider
than it supported. Enumerating declarations instead surfaces one neither
side had reported — portfolio-optimiser's simulation.py:48
_default_bundle_dir() -> shared_root()/examples/bygg-energi-mikro, used
at simulation.py:293. Both PO repos carry a fixture-shaped default, not
just p-o-claude.
The headline is unchanged and survives contact: a fixture default aimed
at golden bytes creates no installation root and is not user-owned
second-brain state. Still one installation against three
non-installations; STEG 5 stays descriptive; §8 untouched. What changed
is the support — "caller-supplied with no default" was too strong, and
the accurate claim is the narrower one the grep actually proved: no
installation root anywhere in either src/.
Citations now pinned to commits rather than lines (PO 9e149c6, POC
bf50d2c) — portfolio-optimiser landed 8+ commits the same day and
already invalidated run.py:653, now run.py:679.
Verified: suite 73/73; check-versions 11 OK · 0 WARN · 0 ERROR.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CPHvLhn2U3j2XD3Cn8zeYa