Generation density was inconsistent — some runs shipped a full dashboard,
others stopped at a header + four stat cards + a two-row table. A vision-less
model cannot use the get_screenshot completeness check (it never sees the
render), so it declared done on a coherent-but-sparse skeleton. Add a text-based
completeness bar it CAN follow: tables need >=6 realistic rows, a dashboard needs
its full section set (stats + primary table + a secondary section), and every
list/card carries varied data.
An already-row shell whose sidebar hugs its content (height=fit_content) is
only as tall as its nav, so a space_between / fill_container footer inside it has
no room to sink and floats mid-page (measured: a 260x532 sidebar in a 260x1234
row stranded the profile card 700px above the bottom). ensure_split_shell_is_row
now also promotes the sidebar of an ALREADY-horizontal shell to fill_container
height, not just the freshly-flipped case.
A fill_container block keeps min-size 0 so a fixed sibling gets its space, but
that lets it shrink below its fit_content text — the text then overflows into
the next column (measured: a 260px sidebar schedule row painted the client name
over the appointment time). Add a geometry-driven pass: when a text resolves
wider than its parent block, constrain it (width fill_container + textGrowth
fixed-width) so it wraps inside instead of overflowing.
The design-loop prompt teaches the G(...) image-fill op but never required
using it, so a model built avatar/photo frames and left them as empty colored
squares. Add a hard rule: every avatar, photo, thumbnail, hero, or logo slot
must get an image fill via G(id, "search", "<subject>") in the same batch
that creates the frame.
Add a dashboard domain skill and teach models to emit an imagePrompt alongside
imageSearchQuery so a configured generation model produces a rich image while
stock search stays the fallback.
When a generation profile is configured, generate images from the node-bound
prompt; otherwise search stock placeholders. Both paths keep the prompt/query on
the node so it can be re-generated or re-searched later.
The OpenAI-compat tool-loop body never sent the reasoning-off field, so a GLM/
MiniMax reasoning model spent its whole per-turn budget on hidden reasoning and
truncated the design mid-op. Send thinking:{type:disabled} for those models in
the loop body (matching the single-shot path) and raise the per-turn output
budget for headroom.
Resolve real layout geometry to correct table-column overflow and collapsed
fill-container heights, iterating until stable. Add whole-root passes: sidebar
app-shell reshape + content eviction + split-shell row layout, table column
gap/regroup, footer sink, surface discipline, scaffold padding. The design-loop
finalize backstop runs these once at loop end and injects background-contrasting
fills for fill-less text. run.rs: continue past a failed subtask and compute
zero-content before cleanup.
Add a parent-by-reference program DSL and an executable-script protocol with
best-effort per-line parsing, so a truncated or malformed line drops only that
op instead of the whole design. Route protocol selection in prompt/subagent and
normalize flex keywords in parse. Registers the new modules in lib.
Map Figma/flex auto-layout field names (layoutMode/direction/itemSpacing/
strokeWeight and nested {type,gap,padding} / {Horizontal:{…}} layout objects)
onto the flat schema, recover image src from url/source aliases, normalize
textGrowth/sizing keywords, and quote bareword DSL values — so a single
unfamiliar spelling no longer drops the whole node or op.
Reads a program file, runs it through op_mcp::batch_design_snapshot, applies, saves
the .op (postProcess off = raw structure) — the headless harness for benchmarking
the program-DSL path vs flat JSONL across weak models.
OPENPENCIL_PROGRAM_GEN makes the sub-agent emit a batch_design program
(binding=I(parent,{...})) instead of flat _parent JSONL; nesting by captured
binding makes weak-model row decomposition / header-only tables near-inexpressible.
Runs the existing op_mcp executor to a section forest. Gated to the full first
attempt; drops the conflicting jsonl-format skill so PROGRAM_FORMAT governs alone.
split_operations now groups by operation-start grammar + bracket depth (not a
quote/bracket state machine), so a stray unbalanced quote can no longer swallow
following operations. parse_json_arg gains lenient repairs for fused close-quote+
comma, missing opening quote on a string value, and unclosed trailing brackets;
normalize_node_shape drops an empty stroke (0-length PenStroke) instead of failing
the whole node. +5 regression tests (369 pass).
Weak models emit a table as a header row followed by FLAT row-indexed sibling
cells (R1 Client Cell, R1 Visit, …, R2 Client Cell, …) that render stacked
vertically with full-width status bars. table_repair::regroup_flat_table_rows
groups them into Table→Row→Cell with header-aligned column widths. Detection is
narrow and never guesses (adversarial review caught heuristic-header /
chunk-of-N over-firing on toolbars/feeds): it requires an explicit table header
AND every cell to carry an R{n} row index, aborting on any ragged/ambiguous run.
ReplaceSubtree allocates a fresh root id, so the structural restructures
(app_shell + table_repair) ran via a new apply_root_transform helper that
returns the current root id; run_cleanup_passes threads it into the subsequent
per-root passes instead of the stale id (which they'd otherwise no-op on).
Weak models emit a desktop dashboard's sidebar either as a full-width band on a
vertical root or crammed into a horizontal row with every section — both render
broken (the removed bespoke scaffold used to pre-build the two-column root).
app_shell::reshape_sidebar_to_app_shell detects a sidebar dashboard and rewrites
it to a horizontal [sidebar(260) | content-column(fill)] shell, run in the shared
cleanup::run_cleanup_passes finalize point (covers orchestrator + agentic loop).
A layout==vertical|none guard on fix_horizontal_overflow stops it re-widening the
narrowed sidebar. Detection is hardened (strong sidebar token + structural
dashboard-content gate) against restaurant/landing/top-nav/mobile/multi-screen
false-positives; 14 unit + 1 integration test, verified end-to-end via op-smoke.
classify_intent matched only creation verbs, so a noun-phrase request like
"Luxury webapp for managing barbershop clients" fell through to the weak chat
loop instead of the orchestrator. Add product/app nouns (webapp/web app/website/
app for/mobile app/admin panel/saas + 网站/网页/小程序/后台) to DESIGN_KEYWORDS.
Reasoning models (glm-5.x / minimax) burn their whole token budget on hidden
<think> and emit an empty design when thinking is left on (glm-5.2: thinking≈30k,
text=0). design_turn_thinking_mode forces ThinkingMode::Disabled for any model
whose profile is thinking_disabled, applied across all design-capable paths —
the design-agent loop, the builtin tool-executing chat loop, and sub-agent
spawns. Claude (thinking productive) keeps the chat default.
A clipped frame with an explicit numeric height now honours that height and
clips overflow (layout_repair no longer lets the root grow to content), matching
Pencil's fixed-height artboards. Status-bar shell strokes are suppressed in the
scene path (width-independent) so they don't paint a stray black frame, and
legacy .op path nodes remap geometry→d so authored paths aren't dropped.
Bundle 11 OFL design-font TTFs and register them with jian-skia at startup so
--render-shots reproduces Pencil's glyph metrics without system fonts.
OPENPENCIL_RENDER_MARGIN tightens the export crop to match Pencil export_nodes
(no frame), and OPENPENCIL_DUMP_LAYOUT prints every node's computed rect as JSONL
to diff our layout against Pencil snapshot_layout element-for-element. Bumps
vendor/jian to the bundled-font + Auto=no-wrap render-parity commits.
Data verdict (copy-pencil-verdict.md): weak-model M3 quality comes entirely from the
SEQUENTIAL deterministic core (manifest element-builders + role-resolver + post-passes
+ finalize), exercised at concurrency=1. The 3 scaffold strategies / mode-rotation /
per-subtask retry ladder are removable complexity not paid for by M3. Collapsed to a
single sequential path; concurrent (perf-only) folds to sequential; dashboard folds into
the generic path (cleanup_desktop_dashboard already handles sparse rows). Kept the
deterministic core 100% intact + BufferDocSink/clamp_concurrency (spawn_agents) + the
dashboard normalizer trio (feeds plan_normalize). M3 gate held within noise (50%→ the one
flip re-ran 2/3 PASS; 7/8 prompts identical; no new failures from removed code).
Pencil's slot-component pattern uses an empty styled master (slot:[...] + zero children)
with the instance supplying content via its own inline children. expand_ref only
populated children from the master, dropping instance content → empty shell → blank
white circle in converted templates. Now falls back to instance children (remapped)
when the master has none. Fixes converted-template stat-card rendering + composed-ref
content. +2 ref_resolve tests +1 variables_resolve nested-token regression guard.
- #41: collapse chevron renders through IconButton so it shows the ghost
button-hover wash instead of only swapping the icon color
- #42: send/stop share one circle slot (toggle in place); footer cluster
sits snug with no reserved stop gap; hit-test routes streaming->stop else send
- #43: example cards stay clickable without a connected model (clicking one
fills the input; sending still requires a model)
- tab close glyph shows only while the tab is hovered (inset still reserved
on the active tab so the title doesn't reflow)
Built-in design generation now runs as an agentic MCP tool-loop (reusing the
agent-rs BuiltInProvider), gated behind OPENPENCIL_DESIGN_AGENT_LOOP / the
Settings experimental toggle; the orchestrator stays the default.
- design-agent system prompt + in-process design toolset (parity-locked with
the MCP surface) + flag-gated Intent::Design routing
- spawn_agents execution as sequential sub-loops + live creation-mode badges
(per-agent glow + 'N/M designing...' header)
- new MCP tools: get_guidelines, ToolSearch, get_screenshot, get_editor_state,
export_nodes, spawn_agents; style-guide local audit
- #27 AI panel restyle: rounded tool cards + green check-rings, gray user
bubbles, model-pill bottom toolbar, header, empty-state pills, the
PARALLEL AGENTS (agent_team_size) 1x-6x chip dropdown
- multi-chat tabs: ChatSessions model (Deref-to-active) + tab row UI
(switch / close / + / Cmd+T) with each run bound to its tab
Large checkpoint commit spanning the working tree (Rust shell crates).
On natural completion the design-turn teardown now calls
agent_indicators::finish_if_epoch instead of end_if_epoch: the already
queued reveals keep playing at the queue cadence and the whole overlay
(cursor + borders) clears itself once the last one lands, so the tail of
a slow 160ms stream is no longer snapped away mid-reveal.
A user stop / abort still tears down immediately via end_if_epoch, so a
cancelled generation does not keep animating. Wired across the
orchestrator run guard, the web design session, the host-core
DesignSession drop, and the desktop sub-agent / design-loop teardown.
Updates the desktop lifecycle tests to match: the frame-clear test now
drives past the drain window before asserting the overlay cleared, and a
shared registry test-lock serializes reveal-streaming turns against the
exact animation-deadline assertion (the registry is process-global).
Each agent gets an arrow cursor that flies between the nodes it places
along the reveal schedule, arriving as each node scale-pops in; the
element currently being placed carries a breathing border. Replaces the
old dashed-border reveal fade (canvas_agent_overlay removed).
Reveal cadence is slowed to a uniform 160ms queue and retained for the
whole run, so the cursor parks on the last placement between streamed
chunks instead of fading out. Splits agent_indicators tests into a
sibling file to stay under the 800-line cap.
The WASM bundle build (#56) and op-web-sdk bundle workflows install binaryen
via apt, which on the ubuntu runner is v108 (2022) — too old for rustc 1.94's
wasm feature set. It lacks the --enable-bulk-memory-opt flag (the original
'Unknown option' failure) AND cannot validate the memory.copy/fill opcodes
rustc now emits, so wasm-opt rejects the bundle with 'all used features should
be allowed'. Download a pinned binaryen version_123 release (matches the local
dev toolchain) and prepend it to PATH. Verified locally: the full
check-wasm-bundle.sh pipeline passes with binaryen 123 against a fresh
rustc-1.94 wasm build.
