Skip to content

AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and support for your own .pptx templates. · by Hugo He

docs(typography): align language-aware font contracts

hugohe3b282ed1d61ff
diff --git a/skills/ppt-master/references/strategist-template.md b/skills/ppt-master/references/strategist-template.md
index 6e63c8cf..cd2b431e 100644
--- a/skills/ppt-master/references/strategist-template.md
+++ b/skills/ppt-master/references/strategist-template.md
@@ -64,7 +64,7 @@ When the communication contract conflicts with the workspace, choose and state t
> Internal note: `content_divergence` controls source reorganization; the AI-derived `template_reuse_scope` records the reused layer; `template_adherence` records whether a structured plan keeps or extends existing Layout identities.
-**Template design precedence**: User overrides win. Otherwise template colors and title/body stacks are fixed anchors, not industry defaults. Each of ≥3 Stage-2 directions still carries all six palette roles and complete font objects: repeat fixed values and vary only template-open roles. Keep declared icon and image constraints.
+**Template design precedence**: User overrides win. Otherwise template colors and title/body stacks are fixed anchors, not industry defaults. Each of ≥3 Stage-2 directions carries all six palette roles and complete fonts: repeat fixed values with `typography.fixed: true`; vary only template-open roles. Keep declared icon and image constraints.
---
diff --git a/skills/ppt-master/references/strategist.md b/skills/ppt-master/references/strategist.md
index 6a8ef644..f895744e 100644
--- a/skills/ppt-master/references/strategist.md
+++ b/skills/ppt-master/references/strategist.md
@@ -38,7 +38,7 @@ Do not force communication intent into one catalog label; Stage 1 records compos
>
> **One opt-in exception**: present the refinement line with the split-mode note ([`generate-pptx.md`](../workflows/generate-pptx.md) Step 4). Only explicit opt-in runs [`refine-spec`](../workflows/stages/refine-spec.md): write the Design Spec once, pass Gate 1, then stop before the lock for unrestricted chat revision. Never enter it unprompted.
-> **Default presentation surface — Confirm UI.** Use `<project>/confirm_ui/recommendations.stage1.json`, `.stage2.json`, and `.stage3.json` at their documented handoffs and launch per Generate Step 4. The active, unconfirmed stage may be overwritten when the user asks for a new recommendation; normal progression writes the next stage file and leaves confirmed earlier stages intact. Stage 2 carries ≥3 safe / shifted / bold `design_directions`; each bundles visual style, a six-role HEX palette, CJK + Latin heading/body typography, icons, and conditional image rendering. Immediately print the actual URL, current Stage-1 compact summary, and direct-chat fallback line required by `confirm_ui.md`; this context is not confirmation. Skip launch only for an explicit chat-only request; a chat-question tool is not a substitute. Generate Step 4 reads the final confirmed `result.json` once and retains that object for Design Spec authoring. [`confirm_ui.md`](../scripts/docs/confirm_ui.md) owns schema and lifecycle.
+> **Default presentation surface — Confirm UI.** Use `<project>/confirm_ui/recommendations.stage1.json`, `.stage2.json`, and `.stage3.json` at their documented handoffs and launch per Generate Step 4. Stage 1 writes the deck content's `primary_language` separately from UI `lang`; the server carries it forward. The active, unconfirmed stage may be overwritten when the user asks for a new recommendation; normal progression writes the next stage file and leaves confirmed earlier stages intact. Stage 2 carries ≥3 safe / shifted / bold `design_directions`; each bundles visual style, a six-role HEX palette, primary-language heading/body typography plus an English companion only for non-English decks, icons, and conditional image rendering. Immediately print the actual URL, current Stage-1 compact summary, and direct-chat fallback line required by `confirm_ui.md`; this context is not confirmation. Skip launch only for an explicit chat-only request; a chat-question tool is not a substitute. Generate Step 4 reads the final confirmed `result.json` once and retains that object for Design Spec authoring. [`confirm_ui.md`](../scripts/docs/confirm_ui.md) owns schema and lifecycle.
**Confirmed-value semantics**: confirmation preserves both the value and the owning field's semantic type. Apply the type to the affected property, not automatically to the whole object:
@@ -208,18 +208,18 @@ See [`../templates/icons/README.md`](../templates/icons/README.md) for the curre
### g. Typography Plan Confirmation (Font + Size)
-🚧 **GATE**: Read the locked preset visual-style file's §2 Typography character before recommending type. For custom, read every named `visual_style_references` file, then resolve them under `visual_style_behavior`; a novel custom uses the behavior directly. Character may come from family, weight, scale, spacing, or layout; title/body need not use different faces.
+🚧 **GATE**: Read the locked preset visual-style file's §2 Typography character before recommending type. For a custom style, first read every file in `visual_style_references` when present, then resolve their typography character under `visual_style_behavior`; a novel custom uses the behavior directly. The title carries the character; the body may remain neutral.
**Family selection**:
-- User/template typography wins. Otherwise ≥3 Stage-2 directions include safe concord and purposeful contrast; no extra font round or near-duplicate pair.
-- A category may explain candidate `note`, never replace the choice. Before Stage 2, resolve concrete `heading` / `body` `cjk`, `latin`, `css`, and positive `body_size`; `name` labels the pair and Custom fills all four faces. Repeat fixed stacks.
-- Resolve by language/target: installed/approved faces may lead; otherwise use a safe face and express character via scale, weight, spacing, color, composition. Fonts are not embedded; unavailable options are post-export Typography upgrade References after target installation, never stacks/lock.
-- Avoid near-equivalent roles such as YaHei↔PingFang, SimSun↔Songti, Arial↔Helvetica↔Segoe UI, or Times New Roman↔Times. Preview counterparts/CSS tails are not deterministic PowerPoint fallbacks.
-- **Default — language-matched safe concord (unless identity is confirmed)**: Include one approved heading/body stack—zh-CN `Microsoft YaHei` + `Arial`; zh-TW `Microsoft JhengHei` + `Arial`; ja `Meiryo` + `Arial`; ko `Malgun Gothic` + `Arial`; Latin `Arial` plus locale EA when needed. This is one candidate, not a mandate.
-- **Reference — not a constraint**: Internal recall, never Confirm UI options: neutral sans, humanist sans, editorial serif, display/expressive, mono/data. Map neutral/humanist → safe sans; editorial → safe serif; display → approved face or treated safe sans/serif; mono/data → safe Latin mono + EA companion. Use display mainly for covers/dividers/short titles and mono/data for code/data/coordinates/short labels.
+- User/template typography is authoritative. When it fixes the stacks, repeat them and set `typography.fixed: true` on every Stage-2 direction. Otherwise ≥3 directions use different concrete heading/body combinations spanning concord and contrast; no extra font round.
+- Every Stage-2 direction carries `heading` / `body` `primary`, `css`, and positive `body_size`; add `english` only when the deck's main language is not English.
+- Use concrete, target-installed PowerPoint faces. The Confirm UI font catalog supplies additional manual dropdown choices, not a recommendation whitelist.
+- Keep stacks to four families or fewer. A brand/web face may lead only after user-confirmed target installation/approved install; PPT Master does not embed fonts. Otherwise export a safe face and keep the unavailable face as Design Spec reference.
+- Avoid near-equivalent role splits such as YaHei↔PingFang, SimSun↔Songti, Arial↔Helvetica↔Segoe UI, or Times New Roman↔Times. Counterparts may aid SVG/browser preview; CSS tails are not deterministic PowerPoint fallbacks.
+- Choose by locked style and vary the axis: serif×sans, Kai/FangSong×hei, hei×song, double-serif, display×neutral, same-family weight, or sans+mono. These are recall seeds, not presets.
-**Strategist-owned role extension after confirmation**: Reuse confirmed heading/body families for recurring roles; differentiate with size, weight, color, spacing, or treatment. Add a lowercase snake_case role and exact stack only for function or confirmed visual-style/brand need (e.g. code, tabular data, brand), not recurrence alone. Keep it coherent without reopening confirmation; add one `Role rationale` only with an additional family.
+**Strategist-owned role extension after confirmation**: Confirm UI keeps the heading/body choice unchanged. While authoring the complete §IX roster and §IV typography plan, scan the actual content for recurring roles that materially need a different family for character or legibility—such as `annotation`, `footer`, `footnote`, `data`, `emphasis`, `quote`, or `code`. Add a lowercase snake_case role and exact stack only when it recurs; inherited roles and one-off garnish stay omitted. The extension must remain coherent with the confirmed heading/body system and locked visual style, and it does not reopen confirmation. Only when an additional family role is added, record one compact `Role rationale` in §IV naming the added role(s) and why; otherwise omit the line.
**Size anchors — px only**: Every authoring layer carries bare px numbers. PowerPoint's displayed pt is an export result (`px × 0.75`), never an input or confirmation value.
diff --git a/skills/ppt-master/scripts/docs/confirm_ui.md b/skills/ppt-master/scripts/docs/confirm_ui.md
index a6e92914..00281ca6 100644
--- a/skills/ppt-master/scripts/docs/confirm_ui.md
+++ b/skills/ppt-master/scripts/docs/confirm_ui.md
@@ -107,6 +107,7 @@ The AI launches Stage 1, authors the complete Stage-2 solution once from the use
{
"stage": "stage1",
"lang": "zh",
+ "primary_language": "zh-CN",
"recommend": {
"canvas": "ppt169"
},
@@ -130,7 +131,7 @@ The AI launches Stage 1, authors the complete Stage-2 solution once from the use
}
```
-All seven Stage-1 prose values may be blank and none blocks confirmation. The values shown in the boxes are editable recommendations; the submitted current values are authoritative, so clearing a box writes and retains `""`. A preservation profile may lock an open field, for example `"content_divergence": { "value": "keep source wording and page structure verbatim", "locked": true }`; the browser renders it read-only. The server carries that lock through the intermediate results and restores the value on every staged submit; the internal carry-over marker is removed from the final `result.json`.
+All seven Stage-1 prose values may be blank. `primary_language` is the deck's BCP-47 content language; `lang` is UI-only, and the server carries the former across stages. Displayed prose is editable and submitted verbatim, including `""`. A profile may lock an open field with `{ "value": "...", "locked": true }`; the browser renders it read-only, the server carries the lock, and removes its internal marker from final `result.json`.
The common paths — inform / explain / persuade / decide / align / teach / report and account / mobilize / record and hand off — appear only as help text for `communication_intent`. They are not catalog ids and must not be emitted as a `primary_job` field.
@@ -183,8 +184,8 @@ After Stage 1 is confirmed, create `recommendations.stage2.json` with the comple
} },
"typography": {
"name_zh": "微软雅黑 + Arial",
- "heading": { "cjk": "Microsoft YaHei", "latin": "Arial", "css": "sans-serif" },
- "body": { "cjk": "Microsoft YaHei", "latin": "Arial", "css": "sans-serif" },
+ "heading": { "primary": "Microsoft YaHei", "english": "Arial", "css": "sans-serif" },
+ "body": { "primary": "Microsoft YaHei", "english": "Arial", "css": "sans-serif" },
"body_size": 24
},
"image_strategy": {
@@ -230,20 +231,21 @@ After Stage 2 is confirmed, create `recommendations.stage3.json` with production
- When confirmed Stage-2 `image_usage` includes `ai`, Stage 3 sets `recommend.image_ai_path` to one of `auto` / `api` / `host-native` / `manual`. Stage 2 never asks for the acquisition mechanism while the user is still deciding the image role.
- **Color candidates carry the user-facing core `palette`**: `background`, `secondary_bg`, `primary`, `accent`, `secondary_accent`, and `body_text`. The page renders every role as a labelled swatch with its HEX value visible, and offers per-role override inputs for precise single-role edits, plus a **Custom color card with a free-text box** — the user can describe the palette in words or paste HEX values instead of filling each role; this writes `color: { "name": "custom", "custom": "<text>" }` to `result.json` for the AI to interpret. Legacy `text` is accepted as an alias for `body_text`, but new files should write `body_text`. Strategist derives secondary text, borders, state colors, and visual-style neutral tiers while writing `design_spec.md`, then projects the machine values to `spec_lock.md`; those are not user-facing confirmation choices.
- **Candidate display text may be multilingual**: color / typography candidates can provide `name_zh` / `name_en` / `name_ja` and `note_zh` / `note_en` / `note_ja`; the page falls back to legacy `name` / `note`. Labels resolve in the page language first, then fall back across the others (a `ja` page: ja → en → zh; zh/en pages keep their zh↔en fallback and try `_ja` last), so when `lang` is `ja` always include the `_ja` variants — otherwise the candidate labels render in English.
-- **Typography candidates** expose concrete CJK/Latin `heading` / `body` faces; localized `name` labels the pairing and `css` only previews. A category may explain rationale, never replace the UI choice. Custom requires all four faces and the same stacks, not category prose; a legacy prose-only result reopens these fields before final confirmation. Include topic samples. PPT baselines are `text` 20 · `balanced` 24 · `presentation` 32 px; cards preserve sizes and submit px. `delivery_purpose` remains a compatibility key.
+- **Typography candidates** use concrete heading/body `primary`; non-English decks also use `english`, while English-primary decks omit it. `cjk` / `latin` remain legacy aliases. Localized `name` labels the pair and `css` only previews. Three generated pairs differ; user/template-fixed pairs repeat only with `fixed: true`. Catalog `fonts` supplies language-filtered dropdowns plus Other without limiting recommendations; edits mark Custom and refresh the preview. Include topic samples. PPT baselines are `text` 20 · `balanced` 24 · `presentation` 32 px; cards preserve sizes and submit px.
- **Per-role size override** (parallel to color's per-role HEX override): besides `body_size`, the page exposes editable inputs for `title` / `subtitle` / `annotation`. The browser applies one documented deterministic dependency chain: `reading mode → body baseline → unpinned role sizes` (role ramp: `body ×` the §g ratios). Changing reading mode updates the body and all unpinned roles locally; changing body updates unpinned roles locally. Editing body or a role pins that value, so later reading-mode changes do not overwrite it. Font / direction-card selection preserves all current sizes. This is a browser-only state update: it performs no fetch, asks the backend to author no new recommendations, and a re-render preserves exactly what the user sees. Each role input is labelled as px and shows an approximate pt equivalent (`1px = 0.75pt`) for orientation. The final values are written to `result.json` as `typography.sizes: { "title", "subtitle", "annotation" }` in **px** — every canvas, no pt and no `sizes_pt` provenance. These confirmed values are Strategist input anchors: the completed page plan may add recurring roles, and downstream execution owns bounded per-occurrence treatment. Candidate `sizes` remain accepted for compatibility, but the fresh Stage-2 baseline is normalized through the same local ramp before first render.
- **`delivery_purpose` compatibility key / Reading mode** (enumerable, PPT only) decides where meaning is carried, not merely how large type is: `text` makes pages self-contained with complete sentences, short prose, captions, tables, and necessary detail; `balanced` shares explanation between page and presenter; `presentation` uses one idea, concise claims, and visual evidence while speech / notes carry the detail. It therefore governs page grammar, granularity, density / rhythm, and note burden. Reading-mode cards intentionally show **no px value**; the typography section owns the separately visible body / role sizes and applies any local default. It is surfaced in Stage 2 beside the visual system, separate from communication intent. `recommend.delivery_purpose` pre-selects one; `result.json` retains the key, while `spec_lock.md` uses canonical `consumption_mode`. Non-PPT canvases omit it.
- **Combined style preview** — a compact live "overall impression" strip sits just above the color section and is **sticky**: it pins under the topbar so it stays visible while the user scrolls through the color / icon / typography sections, keeping the picking controls and their combined effect on screen together. It applies the currently selected color palette **and** typography (heading sample in `primary` over `background`, body sample in `body_text`, an `accent` bar, a `secondary_bg` chip) and repaints on every color / HEX-override / font / `body_size` change. It does not replace the per-candidate swatches or font samples (those stay for picking); it is deliberately an abstract style chip, **not** a slide-layout preview — page layout preview remains the live-preview server's job (Step 6). No schema field; it derives entirely from the existing color + typography selections.
- **Generated-image direction** appears only for `image_usage: ai`: up to three preset cards plus one full-width AI custom proposal. Custom has no preset dropdown; selection makes it editable and submits `rendering: "custom"` + `behavior`. If that behavior uses catalog renderings, it visibly names their exact ids; Strategist retains that confirmed basis as optional `image_rendering_references` in `spec_lock.md`. A genuinely novel behavior produces no reference row. The live preview follows the selection. No image palette is written; deck colors remain authoritative, and legacy `image_strategy.palette` is ignored.
-- **`design_directions`** is the canonical Stage-2 spectrum: ≥3 safe / shifted / bold bundles with localized copy, style, icons, conditional image strategy, complete CJK/Latin typography, and HEX `background`, `secondary_bg`, `primary`, `accent`, `secondary_accent`, `body_text`. Selection applies the bundle; component controls override it. `result.json` stores components, not a direction id.
+- **`design_directions`** is the canonical Stage-2 spectrum: ≥3 safe / shifted / bold bundles with localized copy, style, icons, conditional image strategy, complete language-aware typography, and HEX `background`, `secondary_bg`, `primary`, `accent`, `secondary_accent`, `body_text`. Selection applies the bundle; component controls override it. `result.json` stores components, not a direction id.
- `recommend.generation_mode` and `refine_spec` mirror [`generate-pptx`](../../workflows/generate-pptx.md) Step 4. `split` / `true` are explicit opt-ins. Refinement adds no UI stage: after Gate 1 it stops before the lock for unrestricted chat revision until approval.
- `content_divergence` is a **free-text** Stage-1 source-treatment field. Blank means a balanced default; facts stay sourced at every level. Strategist consumes it while authoring §IX and records it in `design_spec.md §I`; it is not written to `spec_lock.md`. Beautify sends `{ "value": "keep source wording and page structure verbatim", "locked": true }`, so the UI displays it read-only and the server restores it on every staged submit. Template-fill does not use this confirmation flow and does not surface it.
-- `lang` is a soft default (`zh` / `en` / `ja` — the page UI supports all three); an explicit user language choice in the page (persisted to `localStorage`) wins.
+- `lang` is the soft UI-language default (`zh` / `en` / `ja`); the persisted user choice wins. It never sets `primary_language`.
### Output — `result.json` (written on submit, read by the AI)
```json
{
+ "primary_language": "zh-CN",
"canvas": "ppt169",
"page_count": "12-15",
"audience": "...",
@@ -258,7 +260,7 @@ After Stage 2 is confirmed, create `recommendations.stage3.json` with production
"visual_style": "swiss-minimal",
"color": { "name": "...", "palette": { "background": "#...", "secondary_bg": "#...", "primary": "#...", "accent": "#...", "secondary_accent": "#...", "body_text": "#..." } },
"icons": "tabler-outline",
- "typography": { "name": "...", "heading": { "cjk": "...", "latin": "...", "css": "..." }, "body": { "cjk": "...", "latin": "...", "css": "..." }, "body_size": 24, "body_size_unit": "px", "sizes": { "title": 42, "subtitle": 32, "annotation": 18 } },
+ "typography": { "name": "...", "heading": { "primary": "...", "english": "...", "css": "..." }, "body": { "primary": "...", "english": "...", "css": "..." }, "body_size": 24, "body_size_unit": "px", "sizes": { "title": 42, "subtitle": 32, "annotation": 18 } },
"delivery_purpose": "balanced",
"formula_policy": "mixed",
"image_usage": ["ai", "provided"],
diff --git a/skills/ppt-master/scripts/prompt_audit_manifest.json b/skills/ppt-master/scripts/prompt_audit_manifest.json
index 1fbf7258..d12e1b35 100644
--- a/skills/ppt-master/scripts/prompt_audit_manifest.json
+++ b/skills/ppt-master/scripts/prompt_audit_manifest.json
@@ -31,7 +31,7 @@
"skills/ppt-master/references/strategist.md": 14225,
"skills/ppt-master/references/strategist-image.md": 2500,
"skills/ppt-master/references/strategist-template.md": 2100,
- "skills/ppt-master/templates/design_spec_reference.md": 3250,
+ "skills/ppt-master/templates/design_spec_reference.md": 3275,
"skills/ppt-master/templates/spec_lock_reference.md": 2375,
"skills/ppt-master/workflows/generate-pptx.md": 13775,
"skills/ppt-master/workflows/stages/apply-template-workspace.md": 1800
diff --git a/skills/ppt-master/templates/design_spec_reference.md b/skills/ppt-master/templates/design_spec_reference.md
index 87c8007c..615f1a67 100644
--- a/skills/ppt-master/templates/design_spec_reference.md
+++ b/skills/ppt-master/templates/design_spec_reference.md
@@ -93,7 +93,7 @@ Use these exact subsections and field shapes:
### Font Plan
-| Role | Character (Reference) | Chinese | English | Fallback tail |
+| Role | Character (Reference) | Primary | English if non-English | Fallback tail |
| --- | --- | --- | --- | --- |
| Title | <category/modifier> | <family> | <family> | <fallback> |
| Body | <category/modifier> | <family> | <family> | <fallback> |
diff --git a/skills/ppt-master/templates/scaffolds/design_spec.md b/skills/ppt-master/templates/scaffolds/design_spec.md
index f2909ba0..7c8e086a 100644
--- a/skills/ppt-master/templates/scaffolds/design_spec.md
+++ b/skills/ppt-master/templates/scaffolds/design_spec.md
@@ -58,7 +58,7 @@
### Font Plan
-| Role | Character (Reference) | Chinese | English | Fallback tail |
+| Role | Character (Reference) | Primary | English if non-English | Fallback tail |
| --- | --- | --- | --- | --- |
| Title | [fill] | [fill] | [fill] | [fill] |
| Body | [fill] | [fill] | [fill] | [fill] |
diff --git a/skills/ppt-master/workflows/profiles/beautify-pptx.md b/skills/ppt-master/workflows/profiles/beautify-pptx.md
index 656e0695..d6cc644b 100644
--- a/skills/ppt-master/workflows/profiles/beautify-pptx.md
+++ b/skills/ppt-master/workflows/profiles/beautify-pptx.md
@@ -167,8 +167,11 @@ This step has two halves:
Use the three `<project_path>/confirm_ui/recommendations.stageN.json` files at the same staged handoffs as [`generate-pptx`](../generate-pptx.md) Step 4 and launch the same confirm server. The active, unconfirmed stage may be overwritten for a requested regeneration; normal progression leaves confirmed earlier stages intact. Do **not** hide fields: seed **every** targeted-confirmation field with the inherited / source-derived default so the user sees the recommendation and keeps the place to change it. Schema → [`scripts/docs/confirm_ui.md`](../../scripts/docs/confirm_ui.md).
+The typography rows below show the non-English shape; omit `english` for an English source.
+
```json
{
+ "primary_language": "<source main language>",
"recommend": {
"canvas": "<step3-canvas-id>",
"mode": "briefing",
@@ -190,16 +193,16 @@ Use the three `<project_path>/confirm_ui/recommendations.stageN.json` files at t
{ "name_zh": "备选配色 A", "name_en": "Alternative palette A", "name_ja": "代替配色A", "palette": { "background": "#...", "secondary_bg": "#...", "primary": "#...", "accent": "#...", "secondary_accent": "#...", "body_text": "#..." } }
] },
"typography": { "selected": 0, "candidates": [
- { "name_zh": "复刻源 PPT(推荐)", "name_en": "Source replica (recommended)", "name_ja": "元PPTを再現(推奨)", "heading": { "cjk": "...", "latin": "...", "css": "<PPT-safe stack>" }, "body": { "cjk": "...", "latin": "...", "css": "<PPT-safe stack>" }, "body_size": <dominant observed.sizes_pt × 4/3, as px> },
- { "name_zh": "实际字体(observed)", "name_en": "Observed fonts", "name_ja": "実際のフォント(observed)", "heading": { "cjk": "...", "latin": "...", "css": "<PPT-safe stack>" }, "body": { "cjk": "...", "latin": "...", "css": "<PPT-safe stack>" }, "body_size": <dominant observed.sizes_pt × 4/3, as px> },
- { "name_zh": "备选字体 A", "name_en": "Alternative pairing A", "name_ja": "代替ペアリングA", "heading": { "cjk": "...", "latin": "...", "css": "<PPT-safe stack>" }, "body": { "cjk": "...", "latin": "...", "css": "<PPT-safe stack>" }, "body_size": <canvas-appropriate baseline> }
+ { "name_zh": "复刻源 PPT(推荐)", "name_en": "Source replica (recommended)", "name_ja": "元PPTを再現(推奨)", "heading": { "primary": "...", "english": "...", "css": "<PPT-safe stack>" }, "body": { "primary": "...", "english": "...", "css": "<PPT-safe stack>" }, "body_size": <dominant observed.sizes_pt × 4/3, as px> },
+ { "name_zh": "备选字体 A", "name_en": "Alternative pairing A", "name_ja": "代替ペアリングA", "heading": { "primary": "...", "english": "...", "css": "<PPT-safe stack>" }, "body": { "primary": "...", "english": "...", "css": "<PPT-safe stack>" }, "body_size": <canvas-appropriate baseline> },
+ { "name_zh": "备选字体 B", "name_en": "Alternative pairing B", "name_ja": "代替ペアリングB", "heading": { "primary": "...", "english": "...", "css": "<PPT-safe stack>" }, "body": { "primary": "...", "english": "...", "css": "<PPT-safe stack>" }, "body_size": <canvas-appropriate baseline> }
] }
}
```
- **Recommend keep, allow override**: pre-fill the open communication contract from the source's apparent audience and purpose, preserving composite purposes in prose; also pre-fill canvas / mode / visual style / icons / image strategy with the source-faithful default (canvas = Step 3 format, mode = `briefing`, image_usage = `provided`). The purpose examples are hints, never a `primary_job` selector. Beautify's only true non-choices are frozen text and strict 1:1 page count (changing either means routing to the main pipeline). Seed `content_divergence` to verbatim preservation with `locked: true`; the Confirm UI renders it read-only and the server restores the locked value on every staged submit. A request to reshape wording or page structure routes to the main pipeline instead of weakening this profile.
- **Our recommendation is the pre-selected default = the source replica**: for color and typography, author **several candidates** like the from-scratch flow. The pre-selected default (`selected: 0`, the first card) is what beautify recommends — the candidate that **best replicates the source deck's style** (the truest reading of `theme` / `observed`). Replicate-by-default.
-- **Judge the other alternatives exactly as the from-scratch flow does — fonts as much as colors**: don't invent a beautify-specific rule. Author each non-replica candidate with the **same content-driven judgment the Strategist uses when generating from scratch** (color §e, typography §g), applied to the material this project provides — the source document's content and subject, the company's own theme colors, and any brand signal. Pick the palette **and** the font pairing by what fits *this* deck's content; fonts are chosen by content fit, not just defaulted to a safe face. Reach **≥3 candidates total** (PPT-safe stacks; the same creative-choice rule used elsewhere) so a user who departs from the replica still lands on a considered, content-fitting direction — depart-by-choice.
+- **Judge the other alternatives exactly as the from-scratch flow does — fonts as much as colors**: don't invent a beautify-specific rule. Author each non-replica candidate with the **same content-driven judgment the Strategist uses when generating from scratch** (color §e, typography §g), applied to the material this project provides — the source document's content and subject, the company's own theme colors, and any brand signal. Pick the palette **and** the font pairing by what fits *this* deck's content; fonts are chosen by content fit, not just defaulted to a safe face. Reach **≥3 candidates total with distinct heading/body combinations** (PPT-safe stacks; the same creative-choice rule used elsewhere) so a user who departs from the replica still lands on a considered, content-fitting direction. `primary` always follows the source deck's main language; include `english` only when that language is not English.
- **`body_size` is the load-bearing field, and the replica follows the source's own size**: seed the replica candidate's `body_size` from the source's actual body size — take the dominant `observed.sizes_pt` value (the most frequent run-level size, the **body proxy**) and **convert it to px (`× 4/3`)** before seeding, since the system is px-only and the source measures in pt: a source 20pt body becomes `26.67`px, so the replica renders at the source's true size (seeding the bare `20` as px would shrink it ~25% — the pt-as-px trap). Whichever source value you land on below (observed mode, or `theme.sizes.body`) gets the same `× 4/3` conversion. The confirm page (and chat fallback) then writes that px to `result.json` (`body_size`) **directly — no further conversion, no `body_size_pt` provenance** (pt never enters the contract). The "most frequent = body" read is a proxy, not a guarantee — `observed.sizes_pt` counts every explicit run size (titles, captions, footnotes, chart/label text included, no placeholder-type resolution), so a deck dense with small labels can let a caption size outrank true body; cross-check the proxy against the page's actual body blocks and the sanity range below before trusting it, and prefer the size the body paragraphs visibly render at over the raw mode when the two disagree. Fall back to `theme.sizes.body` (the declared placeholder size) when `observed.sizes_pt` is empty, and to a PPT consumption-mode baseline (`text` 20 / `balanced` 24 / `presentation` 32 px — one fixed value per mode) only when neither is present. Note `theme.sizes.body` is the master `bodyStyle` **level-1 declared default** — a coarse value that commonly **over-reads** the real body density (decks often render body at a deeper outline level or override it smaller), so when you land on this fallback treat it as an upper-ish guess and run it through the sanity check below, never as a precise body size. `theme.sizes.body_levels` and `layout_sizes_pt` are **reference context, not extra fallback tiers**: consult them to judge a saner body value when the deck is theme-driven (`observed` empty) — e.g. a deeper `body_levels` entry or a `layout_sizes_pt` hint may read truer than level-1 — but do not auto-seed from them; the seed chain stays `observed → theme.sizes.body → consumption-mode baseline`, and a theme-driven deck whose body size genuinely can't be pinned cleanly is exactly the case the sanity check is for. The canvas hint stays a **sanity range**, not the seed: if the source's own size lands far outside it (a dense source doc reads tiny on a projection canvas), surface that to the user rather than silently snapping — the replica recommendation is the source's size, the user confirms or overrides. Non-replica alternatives may use the consumption-mode baseline. This is what prevents the deck from exporting at an unintentionally small size while still honoring the source.
Run Generate Step 4's confirmation orchestration unchanged, including its