McRitchie Studio

Two-repo feature, sequenced on a gem publish. (1) studio-engine#8 — adds Studio::Enumeral + create_studio_enumerals + bumps 0.9.0; review, then PUBLISH 0.9.0 to RubyGems (approval-gated). (2) mcritchie#157 (DRAFT) — /pokemon type-badge coloring + seed + post_deploy_cmd 'bin/rails enumerals:seed'; Gemfile is at ~>0.9 but lock still 0.8.0, so after 0.9.0 publishes run 'bundle update studio-engine', un-draft, then review/merge. Local proof (engine path-override): 26 runs/164 assertions/0 fail; live /pokemon all 436 badges colored, ranking poison=100 -> dark=1800. turf-monster untouched (adopts later via gem). Worktrees: mcritchie .worktrees/enumeral-colors (port 3006), engine /Users/alex/projects/.worktrees/studio-engine-enumeral-colors.

Scope grew (same branch/PRs): (a) each type now has an emoji (Studio::Enumeral metadata; engine adds #emoji + emoji_map — 0.9.0), shown on /pokemon badges; (b) Pokemon#signature_color = least-common type's color (highest rank) now tints the task MASCOT AVATAR ring (board+detail) and the bin/statusline ⊙<mascot> handle (truecolor from devops.mascot_color, stamped by Task#assign_mascot, carried via bin/task + bin/agent-worktree). Also fixed a latent statusline read_ctx field-shift on empty middle fields (US-separator). All local: 90+ tests 0 fail; /pokemon live :3006.

Excluded from rel (2026-06-24 QA release). CI fully red: Gemfile requires studio-engine (~> 0.9) but Gemfile.lock still pins 0.8.0, and frozen/deployment bundle refuses to update because studio-engine 0.9.0 (the Enumeral gem) is not published to RubyGems. Ordering: publish studio-engine 0.9.0 (eng#8) first, then bundle update studio-engine in mcr#157 to relock 0.9.0, push, confirm CI green + un-draft. Then resubmit.

Dependency block CLEARED. (1) Published studio-engine 0.9.0 to RubyGems (operator-assigned lane) + tagged v0.9.0 + merged eng#8 to engine release. (2) mcr#157: bundle update -> lock pins 0.9.0; verified 64 tests green vs the PUBLISHED gem (no path override). (3) Root cause of CI-not-running was ALSO a merge conflict with release (20 commits ahead) -> merged release in, resolved bin/task (kept new marker_mascot resolver + my mascot_color) + db/schema.rb (regenerated, version 20260624053010). (4) PR un-drafted, now MERGEABLE; CI GREEN on f958353 (scan_ruby/scan_js/lint/test all pass, run 28113065092). Ready for Avi review.

Review cascade: carl[deep] APPROVE (gem 0.9.0 lock clean, migration matches engine reference, model sound, turf unaffected, seed correctly narrow via enumerals:seed); shannon[heavy/UI] BLOCK.

shannon[heavy]: acceptance #7 partial miss — stage_agents_helper.rb:271 (stage_timeline) builds MascotAgent without color:, so the mascot on the /tasks/:id consolidated timeline shows the name-palette color while the build board shows the type (signature) color — same mascot, two colors. REQUIRED: add color: mascot.signature_color at line 271 (and line 162 for consistency; harmless there but align). Add a regression test asserting the consolidated-timeline mascot avatar carries the type color (mirror the build-board test). Non-blocking (defer): text-white low-contrast on light type colors (Electric/Ice/Steel/Fairy/Flying). Everything else approved.

Block resolved (9d262fb): color: mascot.signature_color added to all 4 MascotAgent.new sites (271 stage_timeline + 162 + the 2 already-correct), so the consolidated timeline mascot matches the build board. Regression test RED->GREEN (name-palette #3B82F6 -> signature #6F35FC); target suites 133 runs 0F. dor-check ✓. carl[deep] APPROVE stands. Merge-gated on CI test green.