feat(diagram-engine): flex knobs (grow/align/pad) + inline rich-text labels

The expressiveness gap between engine output and hand-written XML came down
to two missing capabilities, both generic:

- Block layout inside a box: nested containers already existed, but there was
  no way to split space by weight, pin a child to an edge, or tighten padding.
  Added grow (flex-grow over the parent's leftover flow-axis space, TeX's
  glue), align (start/center/end/stretch on the cross axis) and pad
  (per-group interior padding). All three round-trip via dai_grow/dai_align/
  dai_pad markers.

- Inline rich text: labels already render HTML (html=1 on every style, esc()
  entities decode back), but the measure pass counted markup as text. The
  visibleText() strip makes autoBoxSize measure what draw.io draws: <br> is a
  line, other inline tags are invisible.

Graphviz (HTML-like table labels), D2 (grid containers + markdown-in-shape)
and TeX (box+glue) converged on exactly this design: nested boxes for block
structure, proportional glue, a small inline set for text — never full HTML.

Prompts teach the composition with a comparison-card recipe; verified by
rebuilding the CoT poster end to end in the real editor.

app/api/chat/route.ts

@@ -704,7 +704,9 @@ Example: If previous output ended with '<mxCell id="x" style="rounded=1', contin
 
 PREFER THIS over display_diagram/edit_diagram whenever the diagram's meaning is in nesting or in a fixed frame: cloud architecture, swimlane/BPMN, sequence diagrams, mind maps, org charts — AND poster-style layouts: paper summaries, cheat sheets, infographics, comparison sheets. You declare what contains what; layout, sizing, alignment and arrow routing are computed. Containers always fit their contents and siblings never overlap, so the usual layout problems cannot occur.
 
-For a POSTER (paper summary, cheat sheet): one col container as the page; a banner box as the masthead (do NOT also use set_title — the banner IS the title); a muted box for the byline; a row container holding 2-4 col containers as columns; each section is a container with role "heading" holding its items. Give each section a distinct group name — sections sharing a group share a hue, so groups are how the poster gets its colour. Use roles on boxes: callout for the core idea, good/bad for verdict pairs, metric for the headline number, muted for fine print.
+The layout model is FLEXBOX. row/col containers nest freely; a box with internal structure is an invisible col container (pad 10-14) holding smaller boxes. Three knobs: grow (columns split leftover width by weight — grow 3 / grow 2 gives a 3:2 page), align "stretch" (child fills the cross axis — headings, bars and body boxes should almost always stretch or the column looks ragged), pad (8-14 tight card, default 24 roomy section). Labels take inline HTML — <b>, <i>, <font color="#...">, <br> — so one box carries a bold keyword, a second paragraph, a coloured verdict line. Emoji in headings (💡 Core Idea) read instantly.
+
+For a POSTER (paper summary, cheat sheet): one col container as the page; a banner box as the masthead with align stretch (do NOT also use set_title — the banner IS the title); a muted box for the byline; a row container holding 2-4 col containers with grow weights as columns; each section a heading-role box + content boxes, all align stretch. Give each section a distinct group name — sections sharing a group share a hue, so groups are how the poster gets its colour. Use roles on boxes: callout for the core idea, good/bad for verdict pairs, metric for the headline number, muted for fine print. A comparison card: add_container dir=col gap=8 pad=12 grow=1 role=bad, then a bold title box, the body text, a role=bad answer bar (all align stretch), and a coloured "<font color=\\"#B85450\\"><b>✗ Often Wrong</b></font>" verdict with align start.
 
 Never write coordinates, mxCell XML, or style strings. Look AWS icon names up with search_stencils first — an invented name is rejected with suggestions.