New engines start from the shared test kit (the template's tests are a
one-line EngineContractTests subclass) and the host APIs, so they don't
re-derive geometry reading, work areas or validator tolerances.
BENCH-RULES.md now forbids clocks, unseeded randomness and environment
variables from influencing placement (budgets count work; wall time only
through the host's cancellation token) and lists the kit as read-only.
Build-Engines.ps1 deploys only OpenNest.Engine.* folders, and
New-Engine.ps1 -IncludeBuildFiles copies the kit.
Co-Authored-By: Codex <noreply@openai.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Rules for the runs were being made up mid-run (git for rollback, access
to the real-part drawing archive), so each model started under a
different rule set. BENCH-RULES.md writes them down in one place, stamped
into every new engine, so all models work under the same rules:
workspace limits and no searching for other engines, git init plus
commit-per-working-state, the archive as read-only with nothing
customer-identifying kept in the (publishable) engine folder, tests may
only be added to, and what the final report must cover.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Each engine-building run started from a hand-copied scaffold (Qwen's),
which carried that engine's name and stale notes. _Template holds the
generic scaffold with a __NAME__ placeholder, and New-Engine.ps1 stamps
out a named copy. The template's starter tests go through the
benchmark's NestValidator, so a model gets a real pass/fail target
instead of a plumbing-only check; they were verified to pass against
Opus55.
Directory.Build.props now also detects when it sits in an Engines/
folder inside an OpenNest checkout, so an engine stamped there with
-IncludeBuildFiles builds without passing OpenNestRoot.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
