* refactor(desktop): split clarify-tool.tsx into a clarify/ folder
Pure moves, no behaviour change. Parsing, the question-card core
(shell, choice rows, question block), the delivery watchdog, and each
pending/settled card get their own file so the core can be reused.
* feat(clarify): one questions[] shape with per-question status and one outcome
The clarify tool now takes only questions=[{question, choices?, multi_select?}].
A wrong shape is a tool error that names the right one, so a model that
sends the old top-level question/choices corrects itself on the next call.
Every result has the same shape on every surface: each response carries
status (answered, skipped, unanswered) with user_response null unless
answered, and the result carries one outcome (submitted, cancelled,
timed_out, undelivered) plus an optional surface-written notice. The
timeout and cancel sentences that used to pose as the user's answer are
gone, and the compressor reads status instead of matching their prefixes.
The callback contract is callback(questions) -> {answers, outcome, notice?}
(None = skipped, missing qid = unanswered). tui_gateway settles a batch the
same way for the last lock, a cancel, an interrupt and the deadline, and
clarify.lock keeps a null answer as a skip. A multi-select answer that is
not a JSON array counts as one typed ("Other") answer. The tool-row preview
reads the first question.
* feat(clarify): every surface asks through the one question card
CLI: the batch panel is the only panel; Enter on an empty field skips a
question, Ctrl+C cancels and keeps the locked answers, the deadline returns
timed_out. -q and -z return undelivered with a no-user notice.
Ink TUI: the single-question prompt is gone; the card supports multi-select
(Space or a digit toggles, Enter locks, typed Other text joins the picks),
an empty submit skips, Esc cancels, and "Batch" names are dropped.
Desktop: the single-question card is deleted and its keyboard handling moved
into the one card (arrows, letters and digits, auto-advance, Enter picks then
confirms). Confirm enables at one answer; blank questions lock null; Skip and
a composer message cancel; the settled card shows No answer for unanswered
questions. The bots room card follows the same contract.
Messaging: one card per question with a "Reply skip to skip" line in every
locale; timeouts and delivery failures map to timed_out and undelivered.
* fix(clarify): cancelled for a released messaging card, labels win over the skip word
A prose reply to a messaging choice card, /new and session end released
the wait with "", which read as timed_out. They now resolve with a
CANCELLED marker and the tool gets outcome cancelled.
A typed reply that matches a choice label ("Skip") now resolves to that
choice; the skip word applies only when no choice matches.
The bots room card sends the picked labels as they are; the tool already
strips the recommendation label. Unused OUTCOMES and a new docstring and
comment are removed.
* fix(tui): re-editing a multi-select answer keeps its picks
The Ink card stored a multi-select answer as display text ("A, B"), so
revisiting the question put the whole string into Other and re-locked it
as one item. The answers map now keeps the raw JSON array, the card
restores the picks on revisit, and only the display lines format it.
Comments that earlier edits reworded are restored to their original
words, minus the phrases the change made wrong. The compute-host clarify
lock accepts None for a skipped question.
* test(clarify): align three checks with the one-answer confirm and the regenerated keys
The desktop Cmd+Enter test now expects a send with one answer (the blank
question locks null), the compressor test expects the single-answer summary
the code gives, and locales/_keys.desktop.json is regenerated for the
removed and added clarify strings.
* test(tui): the one-question card header is singular
5.6 KiB
Port Notes — baoyu-comic
Ported from JimLiu/baoyu-skills v1.56.1.
Changes from upstream
SKILL.md adaptations
| Change | Upstream | Hermes |
|---|---|---|
| Metadata namespace | openclaw |
hermes (with tags + homepage) |
| Trigger | Slash commands / CLI flags | Natural language skill matching |
| User config | EXTEND.md file (project/user/XDG paths) | Removed — not part of Hermes infra |
| User prompts | AskUserQuestion (batched) |
clarify tool (batched, up to 5 questions) |
| Image generation | baoyu-imagine (Bun/TypeScript, supports --ref) |
image_generate — prompt-only, returns a URL; no reference image input; agent must download the URL to the output directory |
| PDF assembly | scripts/merge-to-pdf.ts (Bun + pdf-lib) |
Removed — the PDF merge step is out of scope for this port; pages are delivered as PNGs only |
| Platform support | Linux/macOS/Windows/WSL/PowerShell | Linux/macOS only |
| File operations | Generic instructions | Hermes file tools (write_file, read_file) |
Structural removals
references/config/directory (removed entirely):first-time-setup.md— blocking first-time setup flow for EXTEND.mdpreferences-schema.md— EXTEND.md YAML schemawatermark-guide.md— watermark config (tied to EXTEND.md)
scripts/directory (removed entirely): upstream'smerge-to-pdf.tsdepended onpdf-lib, which is not declared anywhere in the Hermes repo. Rather than add a new dependency, the port drops PDF assembly and delivers per-page PNGs.- Workflow Step 8 (Merge to PDF) removed from
workflow.md; Step 9 (Completion report) renumbered to Step 8. - Workflow Step 1.1 — "Load Preferences (EXTEND.md)" section removed from
workflow.md; steps 1.2/1.3 renumbered to 1.1/1.2. - Generic "User Input Tools" and "Image Generation Tools" preambles — SKILL.md no longer lists fallback rules for multiple possible tools; it references
clarifyandimage_generatedirectly.
Image generation strategy changes
image_generate's schema accepts only prompt and aspect_ratio (landscape | portrait | square). Upstream's reference-image flow (--ref characters.png for character consistency, plus user-supplied refs for style/palette/scene) does not map to this tool, so the workflow was restructured:
- Character sheet PNG is still generated for multi-page comics, but it is repositioned as a human-facing review artifact (for visual verification) and a reference for later regenerations / manual prompt edits. Page prompts themselves are built from the text descriptions in
characters/characters.md(embedded inline during Step 5).image_generatenever sees the PNG as a visual input. - User-supplied reference images are reduced to
style/palette/scenetrait extraction — traits are embedded in the prompt body; the image files themselves are kept only for provenance underrefs/. - Page prompts now mandate that character descriptions are embedded inline (copied from
characters/characters.md) — this is the only mechanism left to enforce cross-page character consistency. - Download step — after every
image_generatecall, the returned URL is fetched to disk (e.g.,curl -fsSL "<url>" -o <target>.png) and verified before the workflow advances.
SKILL.md reductions
- CLI option columns (
--art,--tone,--layout,--aspect,--lang,--ref,--storyboard-only,--prompts-only,--images-only,--regenerate) converted to plain-English option descriptions. - Preset files (
presets/*.md) andohmsha-guide.md:`--style X`/`--art X --tone Y`shorthand rewritten toart=X, tone=Y+ natural-language references. partial-workflows.md: per-skill slash command invocations rewritten as user-intent cues; PDF-related outputs removed.auto-selection.md: priority order dropped the EXTEND.md tier.analysis-framework.md: language-priority comment updated (user option → conversation → source).
File naming convention
Source content pasted by the user is saved as source-{slug}.md, where {slug} is the kebab-case topic slug used for the output directory. Backups follow the same pattern with a -backup-YYYYMMDD-HHMMSS suffix. SKILL.md and workflow.md now agree on this single convention.
What was preserved verbatim
- All 6 art-style definitions (
references/art-styles/) - All 7 tone definitions (
references/tones/) - All 7 layout definitions (
references/layouts/) - Core templates:
character-template.md,storyboard-template.md,base-prompt.md - Preset bodies (only the first few intro lines adapted; special rules unchanged)
- Author, version, homepage attribution
Syncing with upstream
To pull upstream updates:
# Compare versions
curl -sL https://raw.githubusercontent.com/JimLiu/baoyu-skills/main/skills/baoyu-comic/SKILL.md | head -5
# Look for the version: line
# Diff a reference file
diff <(curl -sL https://raw.githubusercontent.com/JimLiu/baoyu-skills/main/skills/baoyu-comic/references/art-styles/manga.md) \
references/art-styles/manga.md
Art-style, tone, and layout reference files can usually be overwritten directly (they're upstream-verbatim). SKILL.md, references/workflow.md, references/partial-workflows.md, references/auto-selection.md, references/analysis-framework.md, references/ohmsha-guide.md, and references/presets/*.md must be manually merged since they contain Hermes-specific adaptations.
If upstream adds a Hermes-compatible PDF merge step (no extra npm deps), restore scripts/ and reintroduce Step 8 in workflow.md.