feat(plotly): implement line-parametric

[github-actions]

Implementation: line-parametric - plotly

Implements the plotly version of line-parametric.

File: plots/line-parametric/implementations/plotly.py

Parent Issue: #4424

---

🤖 impl-generate workflow

[claude]

AI Review - Attempt 1/3

Image Description

The plot displays two subplots side by side on a white background. Left subplot: a Lissajous figure (x=sin(3t), y=sin(2t)) rendered as a continuous curve with a color gradient transitioning from Python Blue (#306998) at t=0 to coral/red (#E4573A) at t=2π. The curve self-intersects multiple times forming the characteristic figure-eight-like pattern within [-1,1] bounds. Start point marked with a blue circle and "t = 0" label, end point marked with a red square and "t = 2π" label — both at the origin (0,0), causing label overlap. Right subplot: an Archimedean spiral (x=t·cos(t), y=t·sin(t)) with the same color gradient from t=0 to t=4π, expanding outward. Start marked with blue circle near origin, end with red square at the rightmost extent. Both subplots have equal aspect ratio, subtle gray gridlines, zero lines, and axis labels "x(t)" and "y(t)". Subplot titles display the parametric equations. Main title reads "line-parametric · plotly · pyplots.ai".

Score: 80/100

Category	Score	Max
Visual Quality	24	30
Design Excellence	13	20
Spec Compliance	15	15
Data Quality	14	15
Code Quality	10	10
Library Mastery	4	10
Total	80	100

Visual Quality (24/30)

• VQ-01: Text Legibility (8/8) — All font sizes explicitly set: title 28, subplot titles 20, axis labels 22, ticks 18, marker text 16. All clearly readable.
• VQ-02: No Overlap (3/6) — On the Lissajous plot, start (t=0) and end (t=2π) markers overlap at the origin (0,0) since sin(3·2π)=0 and sin(2·2π)=0. Both labels and markers stack on top of each other, partially obscuring text.
• VQ-03: Element Visibility (5/6) — Line width 3.5 is good, markers size 14 with white outlines are visible. Color gradient is clear. Slightly thick for the Lissajous self-intersections.
• VQ-04: Color Accessibility (4/4) — Blue-to-coral gradient is colorblind-safe, provides good contrast on white background.
• VQ-05: Layout & Canvas (3/4) — Good use of space with two subplots, but the spiral subplot has asymmetric whitespace due to the spiral extending primarily rightward.
• VQ-06: Axis Labels & Title (1/2) — Labels "x(t)" and "y(t)" are descriptive for parametric notation but lack physical context or units. Acceptable for mathematical curves but not fully descriptive.

Design Excellence (13/20)

• DE-01: Aesthetic Sophistication (5/8) — Custom blue-to-coral gradient is intentional and visually appealing. plotly_white template provides clean look. Marker styling with white outlines adds polish. Above defaults but not publication-level.
• DE-02: Visual Refinement (4/6) — Subtle grid (8% opacity), styled zero lines (15% opacity), explicit axis line colors (30% opacity). Good attention to detail on grid hierarchy. White background is clean.
• DE-03: Data Storytelling (4/6) — Color gradient effectively communicates direction of traversal. Start/end markers with labels create a narrative of parameter progression. Subplot titles explain the equations. Viewer understands the parameterization story.

Spec Compliance (15/15)

• SC-01: Plot Type (5/5) — Correct parametric curve plot with two different curve types.
• SC-02: Required Features (4/4) — Equal aspect ratio (scaleanchor) ✓, color gradient for direction ✓, two curves (Lissajous + spiral) ✓, start/end markers ✓, sufficient point density (1000 points) ✓.
• SC-03: Data Mapping (3/3) — x(t) and y(t) correctly computed and mapped to axes. All data visible.
• SC-04: Title & Legend (3/3) — Title "line-parametric · plotly · pyplots.ai" in correct format. No legend needed (color gradient replaces it), which is appropriate.

Data Quality (14/15)

• DQ-01: Feature Coverage (5/6) — Shows self-intersecting closed curve (Lissajous) and open expanding curve (spiral). Good variety but could include a third curve type for richer demonstration.
• DQ-02: Realistic Context (5/5) — Real mathematical/physics curves: Lissajous figures from signal analysis, Archimedean spirals from nature/engineering. Equations clearly labeled.
• DQ-03: Appropriate Scale (4/4) — Mathematically correct: Lissajous bounded [-1,1], spiral grows proportional to t. Values are exact.

Code Quality (10/10)

• CQ-01: KISS Structure (3/3) — Clean imports → data → plot → save flow. Loop for segments is appropriate.
• CQ-02: Reproducibility (2/2) — Fully deterministic (trigonometric functions, no randomness).
• CQ-03: Clean Imports (2/2) — All imports used: numpy, go, make_subplots.
• CQ-04: Code Elegance (2/2) — Segment loop is clean and appropriate for color gradients. No over-engineering.
• CQ-05: Output & API (1/1) — Saves as plot.png with correct dimensions (1600×900 scale=3 = 4800×2700). Also saves HTML.

Library Mastery (4/10)

• LM-01: Idiomatic Usage (3/5) — Uses go.Scatter and make_subplots correctly. However, manually creating 160 scatter traces for color gradients is verbose; could use a single trace with marker color mapping or plotly's built-in colorscale capabilities.
• LM-02: Distinctive Features (1/5) — Does not leverage plotly-specific features like continuous colorscales on lines, animation frames for parameter sweeps, or hover data showing t values. The HTML export is nice but the core visualization is generic.

Score Caps Applied

• None

Strengths

• Full spec compliance with all required features (equal aspect ratio, color gradient, two curves, start/end markers)
• Excellent code quality with clean, deterministic, well-structured code
• Good design choices: custom blue-to-coral gradient, subtle grid hierarchy, clean white template
• Subplot titles clearly explain the parametric equations
• Color gradient effectively communicates traversal direction

Weaknesses

• Start/end marker labels overlap at origin (0,0) on the Lissajous curve since both t=0 and t=2π map to the same point
• Library mastery is low: 160 individual scatter traces for color gradients instead of using plotly's native colorscale capabilities
• No hover information leveraging plotly's interactivity (t values, coordinates)

Issues Found

1. VQ-02 MEDIUM: Start and end labels overlap at origin on Lissajous figure
   • Fix: Offset the end marker label position (e.g., "bottom right" instead of "bottom left") or add a slight positional offset to separate the markers
2. LM-01 LOW: Manual segment traces instead of native colorscale
   • Fix: Consider using a single trace with line=dict(color=t, colorscale=...) or marker-based color mapping for cleaner plotly usage
3. LM-02 LOW: Does not leverage plotly's distinctive interactive features
   • Fix: Add customdata with t values and hover template showing parameter values at each point

AI Feedback for Next Attempt

Fix the overlapping start/end labels on the Lissajous curve by adjusting text positions or adding offsets — both points map to (0,0). Improve library mastery by using plotly's native colorscale for line coloring instead of 160 separate traces, and add hover templates showing the parameter t value at each point to leverage plotly's interactivity strengths.

Verdict: REJECTED

[github-actions]

🔧 Repair Attempt 1/3

Applied fixes based on AI review feedback.

Status: Repair completed, re-triggering review...

---

🤖 impl-repair

[claude]

AI Review - Attempt 2/3

Image Description

The plot displays two side-by-side parametric curves on a white background. The main title reads "line-parametric · plotly · pyplots.ai" centered at the top. The left panel shows a Lissajous figure (x = sin(3t), y = sin(2t)) — a classic self-intersecting closed curve with looping figure-eight-like shape. The right panel shows an Archimedean Spiral (x = t·cos(t), y = t·sin(t)) expanding outward from the origin. Both curves use a custom color gradient transitioning from deep Python Blue (t=0) to coral/red (t=max), with vertical colorbars labeled "Parameter t" showing π-based tick values. Start markers (blue circles) and end markers (red/coral squares) are labeled on each curve. Axes are labeled "x(t) — horizontal position" and "y(t) — vertical position" with subtle gray gridlines and zero lines. Equal aspect ratios are maintained for both panels.

Score: 85/100

Category	Score	Max
Visual Quality	27	30
Design Excellence	12	20
Spec Compliance	15	15
Data Quality	14	15
Code Quality	10	10
Library Mastery	7	10
Total	85	100

Visual Quality (27/30)

• VQ-01: Text Legibility (8/8) — All font sizes explicitly set: title 28pt, axis labels 22pt, ticks 18pt, subplot titles 20pt, annotation text 16pt. All perfectly readable.
• VQ-02: No Overlap (5/6) — On the Lissajous curve, start and end points are both near the origin, causing "Start (t = 0)" and "End (t = 2π)" labels to be in close proximity. Positioning offsets (top-right vs bottom-left) help but don't fully resolve the crowding.
• VQ-03: Element Visibility (5/6) — Marker size 5 with 2000 points creates visible curves. The color gradient makes the path easy to follow. However, using mode="markers" rather than lines means thin gaps appear between points at some sections.
• VQ-04: Color Accessibility (4/4) — Custom blue-to-coral colorscale avoids red-green issues. Good contrast against white background.
• VQ-05: Layout & Canvas (3/4) — Good two-panel layout. Equal aspect ratio constraint makes the Lissajous subplot narrower than the spiral. Right colorbar's "Parameter t" title is slightly cramped against the canvas edge.
• VQ-06: Axis Labels & Title (2/2) — Descriptive labels "x(t) — horizontal position" and "y(t) — vertical position" are appropriate for mathematical parametric curves.

Design Excellence (12/20)

• DE-01: Aesthetic Sophistication (5/8) — Custom colorscale from Python Blue to coral, plotly_white template, equation-annotated subplot titles, and matched start/end markers with distinct shapes. Above defaults but not publication-exceptional.
• DE-02: Visual Refinement (4/6) — Subtle grid at 0.08 opacity, zero lines at 0.15, axis lines at 0.3 opacity. Good whitespace. Colorbar ticks use π notation. Some further refinement possible.
• DE-03: Data Storytelling (3/6) — Color gradient conveys direction of parametric traversal. Start/end markers with labels guide the viewer. Subplot titles include equations. However, there's no strong focal point or emphasis hierarchy between the two curves.

Spec Compliance (15/15)

• SC-01: Plot Type (5/5) — Correct parametric curve plot with two curves traced as functions of parameter t.
• SC-02: Required Features (4/4) — Equal aspect ratio ✓, color gradient for t direction ✓, two example curves (Lissajous + spiral) ✓, start/end markers labeled ✓, 2000 points for smooth rendering ✓.
• SC-03: Data Mapping (3/3) — X/Y correctly computed from parametric equations. Axes show full data range with scaleanchor for equal aspect.
• SC-04: Title & Legend (3/3) — Title "line-parametric · plotly · pyplots.ai" in correct format. No legend needed (colorbars serve as the color reference for each subplot).

Data Quality (14/15)

• DQ-01: Feature Coverage (6/6) — Two distinct parametric curve types: Lissajous (closed, self-intersecting) and Archimedean spiral (open, expanding). Demonstrates looping, self-intersection, and unbounded growth.
• DQ-02: Realistic Context (4/5) — Classic mathematical curves well-known in physics and engineering. Plausible and neutral, though inherently mathematical/abstract rather than applied real-world context.
• DQ-03: Appropriate Scale (4/4) — Parameter ranges are standard: [0, 2π] for Lissajous, [0, 4π] for spiral. Output values are sensible for the equations.

Code Quality (10/10)

• CQ-01: KISS Structure (3/3) — Clean Imports → Data → Plot → Save structure with no functions or classes.
• CQ-02: Reproducibility (2/2) — Fully deterministic: trigonometric functions on linspace, no randomness.
• CQ-03: Clean Imports (2/2) — All three imports used: numpy, plotly.graph_objects, make_subplots.
• CQ-04: Code Elegance (2/2) — Clean, well-organized. Some repetition in start/end markers is inherent to the two-panel layout.
• CQ-05: Output & API (1/1) — Saves as plot.png with correct 1600×900 scale=3 dimensions. Also exports HTML.

Library Mastery (7/10)

• LM-01: Idiomatic Usage (4/5) — Good use of go.Scatter with marker colorscale, make_subplots, customdata with hovertemplate, and scaleanchor for aspect ratio. Could leverage plotly.express or more advanced layout features.
• LM-02: Distinctive Features (3/5) — Hover tooltips via hovertemplate+customdata, HTML export, and interactive colorbars are Plotly-distinctive. Could push further with animations or range sliders.

Score Caps Applied

• None

Strengths

• Full spec compliance with both required curve types and all visual features (color gradient, start/end markers, equal aspect)
• Custom colorscale with π-notation colorbar ticks demonstrates attention to mathematical detail
• Clean, well-structured code with deterministic data and proper output format
• Interactive features (hover tooltips with parameter values, HTML export) leverage Plotly's strengths

Weaknesses

• Start/end labels on Lissajous are crowded near the origin since both points coincide
• Using mode="markers" instead of lines creates thin gaps between points; a line trace with color segments would be smoother
• Design excellence could be elevated with stronger visual hierarchy between the two panels
• Right colorbar title slightly cramped against canvas edge

Issues Found

1. VQ-02 MINOR: Start/end labels overlap near origin on Lissajous curve
   • Fix: Use annotations with arrows pointing to the markers, positioned further away, or offset one label more aggressively
2. VQ-03 MINOR: Marker-based rendering instead of line segments causes visual gaps
   • Fix: Consider using smaller, denser markers or a segmented line approach for smoother appearance
3. DE-01 MODERATE: Aesthetic sophistication is good but not exceptional
   • Fix: Add more visual polish — consider a background gradient, more refined marker styling, or annotation callouts for key curve properties
4. DE-03 MODERATE: Limited data storytelling and visual hierarchy
   • Fix: Create emphasis through size contrast, highlight self-intersection points on Lissajous, or annotate mathematical properties (e.g., frequency ratio 3:2)

AI Feedback for Next Attempt

To reach 90+: (1) Fix the start/end label crowding on the Lissajous by using arrow annotations positioned further from the origin. (2) Consider adding a line trace underneath the markers for smoother curve rendering, or use smaller more densely packed markers. (3) Enhance data storytelling by highlighting notable features like self-intersection points on the Lissajous or annotating the frequency ratio. (4) Increase right margin slightly to prevent colorbar title cramping. (5) Consider making one panel the visual focal point (e.g., larger or more prominently styled) to create hierarchy.

Verdict: REJECTED

[github-actions]

🔧 Repair Attempt 2/3

Applied fixes based on AI review feedback.

Status: Repair completed, re-triggering review...

---

🤖 impl-repair

[claude]

AI Review - Attempt 3/3

Image Description

The plot displays two side-by-side subplots on a light blue-gray background (plotly_white template). The left subplot shows a Lissajous figure (x = sin(3t), y = sin(2t)) — a closed, self-intersecting curve with three horizontal lobes and two vertical lobes. The right subplot shows an Archimedean spiral (x = t·cos(t), y = t·sin(t)) — an open, expanding spiral making about two full turns. Both curves use a continuous color gradient mapped to parameter t, transitioning from deep blue (t=0) through teal and olive to coral/red (t=max). Each subplot has a vertical colorbar on the right showing the parameter t scale with tick labels in π notation. Start points are marked with blue circles and "Start (t = 0)" annotations with arrow connectors; end points are marked with coral/red squares and corresponding "End" annotations. The main title reads "line-parametric · plotly · pyplots.ai" centered at the top. Each subplot has a bold subtitle with the curve name and an italic line showing the parametric equation and a brief description. Axes are labeled x(t) and y(t). A "Reset View" button appears at the bottom center. The grid is very subtle, with visible zero lines.

Score: 88/100

Category	Score	Max
Visual Quality	27	30
Design Excellence	14	20
Spec Compliance	15	15
Data Quality	14	15
Code Quality	10	10
Library Mastery	8	10
Total	88	100

Visual Quality (27/30)

• VQ-01: Text Legibility (8/8) — All font sizes explicitly set: title 28pt, axis titles 22pt, tick fonts 18pt, subplot titles 18pt, annotations 16pt, colorbar title 18pt, colorbar ticks 16pt. All clearly readable.
• VQ-02: No Overlap (6/6) — Start/end annotations use arrow offsets to avoid collision. No text overlaps observed.
• VQ-03: Element Visibility (5/6) — Markers at size 6 with 2000 points create a solid-looking colored line effect. Works well for gradient visualization but appears slightly chunky in places. Start/end markers at size 16 are clearly visible.
• VQ-04: Color Accessibility (4/4) — Custom colorscale from blue through teal/olive to coral. Perceptually reasonable progression, not reliant on red-green distinction.
• VQ-05: Layout & Canvas (3/4) — Two subplots fill the canvas well with equal aspect ratio. The first colorbar at x=0.42 (between subplots) creates some visual crowding. Margins are reasonable overall.
• VQ-06: Axis Labels & Title (1/2) — Labels "x(t)" and "y(t)" are mathematically conventional for parametric curves but lack descriptive context or units.

Design Excellence (14/20)

• DE-01: Aesthetic Sophistication (6/8) — Custom 6-stop colorscale, styled annotations with borders and semi-transparent backgrounds, HTML-formatted subtitles, custom background color. Clearly above library defaults with intentional design choices.
• DE-02: Visual Refinement (4/6) — plotly_white template provides clean base. Grid at 0.06 opacity is very subtle. Zeroline distinguished at different opacity. Custom background color. Good whitespace management.
• DE-03: Data Storytelling (4/6) — The side-by-side layout of a closed/self-intersecting curve vs. an open/expanding curve creates meaningful contrast. Descriptive subtitles with equation and characterization guide the viewer. Color gradient and start/end markers show directionality and progression.

Spec Compliance (15/15)

• SC-01: Plot Type (5/5) — Correct parametric curve plot with two distinct curve types as specified.
• SC-02: Required Features (4/4) — Equal aspect ratio via scaleanchor ✓, color gradient along curve ✓, two example curves (Lissajous + spiral) ✓, start/end markers with labels ✓, sufficient point density (2000 points) ✓.
• SC-03: Data Mapping (3/3) — x(t) and y(t) correctly computed from parametric equations. Axes display full range of data.
• SC-04: Title & Legend (3/3) — Title follows exact format "line-parametric · plotly · pyplots.ai". Curves identified by subplot titles (no legend needed for separate subplots).

Data Quality (14/15)

• DQ-01: Feature Coverage (6/6) — Shows two contrasting parametric curve types: Lissajous (closed, self-intersecting, bounded) and Archimedean spiral (open, expanding, unbounded). Demonstrates loops, self-intersections, and expanding radius.
• DQ-02: Realistic Context (4/5) — Lissajous figures and Archimedean spirals are real mathematical curves with applications in signal analysis, antenna design, and physics. Context is educational/scientific but inherently mathematical rather than a concrete real-world scenario.
• DQ-03: Appropriate Scale (4/4) — Lissajous correctly bounded in [-1, 1], spiral expanding proportionally with t. Parameter ranges appropriate for each curve type.

Code Quality (10/10)

• CQ-01: KISS Structure (3/3) — Follows Imports → Data → Plot → Save structure. No functions or classes defined.
• CQ-02: Reproducibility (2/2) — Fully deterministic — trigonometric functions with no random components.
• CQ-03: Clean Imports (2/2) — All three imports used: numpy, go, make_subplots.
• CQ-04: Code Elegance (2/2) — Loop with tuple unpacking for the two curves reduces duplication. Reset View button is a legitimate Plotly interactive feature. Appropriate complexity.
• CQ-05: Output & API (1/1) — Saves as plot.png with correct dimensions (1600×900, scale=3). Also exports HTML for interactivity.

Library Mastery (8/10)

• LM-01: Idiomatic Usage (4/5) — Good use of graph_objects API: make_subplots, go.Scatter, annotations, colorbars with custom tick labels, scaleanchor for aspect ratio. Marker-based gradient is a common Plotly pattern for continuous color on lines.
• LM-02: Distinctive Features (4/5) — Leverages several Plotly-distinctive features: updatemenus for Reset View button, hovertemplate with customdata, HTML export via write_html, HTML-formatted text in titles/annotations. These are features unique to Plotly's interactive ecosystem.

Score Caps Applied

• None — no cap conditions triggered.

Strengths

• Full spec compliance with all required features (two curves, color gradient, start/end markers, equal aspect ratio)
• Custom colorscale with professional blue-to-coral progression creates visual appeal
• Excellent use of Plotly-specific features (hovertemplate, updatemenus, HTML export, HTML-formatted text)
• Clean, well-structured code with effective loop to reduce duplication
• Thoughtful data storytelling through contrasting curve types with descriptive subtitles

Weaknesses

• Colorbar between subplots (x=0.42) creates slight visual crowding in the center
• Marker-based gradient approach produces a slightly chunky appearance rather than a smooth line
• Axis labels "x(t)"/"y(t)" could be more descriptive

Issues Found

1. VQ-05 MINOR: First colorbar positioned between subplots creates visual crowding
   • Fix: Adjust colorbar placement or use a single shared colorbar
2. VQ-03 MINOR: Marker size 6 with 2000 points creates slightly chunky appearance
   • Fix: Reduce marker size to 3-4 or increase point count for smoother appearance

AI Feedback for Next Attempt

Strong implementation at 88/100. The main areas preventing a 90+ score are minor visual polish issues: the inter-subplot colorbar crowding and the marker-based line rendering. Consider using a single shared colorbar or repositioning, and reducing marker size for smoother curves. The design excellence is solid with the custom palette and storytelling — pushing DE-01 to 7-8 would require even more refined typography and layout polish.

Verdict: REJECTED

[github-actions]

🔧 Repair Attempt 3/3

Applied fixes based on AI review feedback.

Status: Repair completed, re-triggering review...

---

🤖 impl-repair

[claude]

AI Review - Attempt 3/3

Image Description

The plot displays two side-by-side subplots on a light background with the plotly_white template. The main title "line-parametric · plotly · pyplots.ai" is centered at the top in dark gray. The left subplot shows a Lissajous figure (x = sin(3t), y = sin(2t)) — a closed, self-intersecting curve with three horizontal lobes. The right subplot shows an Archimedean spiral (x = t·cos(t), y = t·sin(t)) expanding outward from the origin over about two full turns. Both curves use a continuous color gradient from deep Python Blue (t=0) through teal and olive-green to coral/red (t=max), rendered as overlapping line segments. Each subplot has a vertical colorbar with π-notation tick labels ("0", "π/2", "π", etc.) and the title "Parameter t (rad)". Start points are marked with blue circles and annotated "Start (t = 0)" with arrow connectors; end points are marked with coral squares and annotated "End (t = 2π/4π)". Both subplots have bold titles with italic equation subtitles describing each curve's character. Axes are labeled "Horizontal Position x(t)" and "Vertical Position y(t)" with subtle gridlines and zero lines. A "Reset View" button sits at the bottom center.

Score: 87/100

Category	Score	Max
Visual Quality	28	30
Design Excellence	14	20
Spec Compliance	15	15
Data Quality	14	15
Code Quality	8	10
Library Mastery	8	10
Total	87	100

Visual Quality (28/30)

• VQ-01: Text Legibility (8/8) — All font sizes explicitly set: title 28pt, axis titles 22pt, tick fonts 18pt, subplot titles 18pt, annotations 16pt, colorbar title 18pt, colorbar ticks 16pt. All clearly readable at output resolution.
• VQ-02: No Overlap (6/6) — Start/end annotations on Lissajous use offset arrows (ax=55,ay=-45 vs ax=-55,ay=45) to separate labels despite both points mapping near the origin. No text collisions observed.
• VQ-03: Element Visibility (5/6) — Line segments at width 3.5 create a smooth-looking gradient curve. Start/end markers at size 16 with white outlines are clearly visible. Minor: the segmented approach produces very slight visual artifacts at segment boundaries in some areas.
• VQ-04: Color Accessibility (4/4) — Custom 6-stop colorscale from blue through teal/olive to coral is colorblind-safe. Good contrast against white background. Not reliant on red-green distinction.
• VQ-05: Layout & Canvas (3/4) — Two subplots fill canvas well with equal aspect ratio via scaleanchor. However, the first colorbar positioned at x=0.44 (between subplots) creates slight visual crowding in the center region.
• VQ-06: Axis Labels & Title (2/2) — "Horizontal Position x(t)" and "Vertical Position y(t)" are descriptive. No physical units needed for dimensionless mathematical curves.

Design Excellence (14/20)

• DE-01: Aesthetic Sophistication (6/8) — Custom 6-stop colorscale (blue→teal→olive→coral), HTML-formatted subtitles with bold name and italic equation, styled annotations with semi-transparent backgrounds and color-matched borders, distinct marker shapes (circle vs square). Clearly above library defaults with intentional design choices.
• DE-02: Visual Refinement (4/6) — plotly_white template as clean base. Grid at 0.05 opacity is very subtle. Zeroline distinguished at 0.15 opacity. Custom background color rgba(248,249,252,1). Axis lines at 0.18 opacity. Good whitespace via margins. Could push further with more nuanced spacing.
• DE-03: Data Storytelling (4/6) — Side-by-side layout of closed/self-intersecting vs. open/expanding curve creates meaningful mathematical contrast. Descriptive subtitles characterize each curve ("closed, self-intersecting" vs "open, expanding outward"). Color gradient and start/end markers show direction of traversal. Good hierarchy but no focal point emphasis between panels.

Spec Compliance (15/15)

• SC-01: Plot Type (5/5) — Correct parametric curve plot with x(t), y(t) traced as functions of parameter t.
• SC-02: Required Features (4/4) — Equal aspect ratio via scaleanchor ✓, color gradient for direction ✓, two example curves (Lissajous + spiral) ✓, start/end markers labeled ✓, 2000 points for smooth rendering ✓.
• SC-03: Data Mapping (3/3) — x(t) and y(t) correctly computed from parametric equations. Axes display full data range.
• SC-04: Title & Legend (3/3) — Title "line-parametric · plotly · pyplots.ai" in correct format. Curves identified by subplot titles; no legend needed.

Data Quality (14/15)

• DQ-01: Feature Coverage (6/6) — Two contrasting parametric curve types: Lissajous (closed, self-intersecting, bounded) and Archimedean spiral (open, expanding, unbounded). Demonstrates looping, self-intersection, and expanding radius.
• DQ-02: Realistic Context (4/5) — Lissajous figures and Archimedean spirals are well-known mathematical curves with real applications in signal analysis, antenna design, and physics. Neutral, educational context but inherently mathematical rather than an applied real-world scenario.
• DQ-03: Appropriate Scale (4/4) — Lissajous correctly bounded in [-1, 1]. Spiral expanding proportionally with t up to 4π. Parameter ranges are standard for each curve type.

Code Quality (8/10)

• CQ-01: KISS Structure (2/3) — Overall flow follows Imports → Data → Plot → Save, but defines a helper function interpolate_color() (lines 35-46), violating the "no functions/classes" guideline.
• CQ-02: Reproducibility (2/2) — Fully deterministic: trigonometric functions on linspace, no random components.
• CQ-03: Clean Imports (2/2) — All three imports used: numpy, plotly.graph_objects, make_subplots.
• CQ-04: Code Elegance (1/2) — The manual color interpolation function and 200-segment loop approach is verbose but necessary given Plotly's lack of native line color gradients. The Reset View button is a legitimate Plotly feature. Slightly over-engineered overall.
• CQ-05: Output & API (1/1) — Saves as plot.png with correct dimensions (1600×900, scale=3 = 4800×2700). Also exports HTML for interactivity.

Library Mastery (8/10)

• LM-01: Idiomatic Usage (4/5) — Good use of graph_objects: make_subplots, go.Scatter, add_annotation, colorbars with custom π-notation ticks, scaleanchor for equal aspect ratio, hovertemplate with customdata. The segmented line approach is a common Plotly workaround for line color gradients.
• LM-02: Distinctive Features (4/5) — Leverages several Plotly-distinctive features: updatemenus for Reset View button, hovertemplate with customdata for interactive tooltips, write_html for interactive export, HTML-formatted text in titles/annotations. These features are unique to Plotly's interactive ecosystem.

Score Caps Applied

• None — no cap conditions triggered.

Strengths

• Full spec compliance with all required features (two curves, color gradient, equal aspect ratio, start/end markers)
• Custom 6-stop colorscale with professional blue-to-coral progression
• Excellent use of Plotly-specific features (hovertemplate, updatemenus, HTML export, HTML-formatted text)
• Well-resolved start/end label overlap on Lissajous via directional arrow offsets
• Descriptive subtitles with equation and curve characterization create good storytelling

Weaknesses

• Helper function interpolate_color() violates KISS structure guideline
• Inter-subplot colorbar (x=0.44) creates slight visual crowding in the center
• Segmented line approach with 200 segments per curve is verbose (400+ traces total)

Issues Found

1. CQ-01 MINOR: Helper function interpolate_color() defined instead of inline logic
   • Fix: Inline the color computation or use a lookup approach without a function definition
2. VQ-05 MINOR: First colorbar positioned between subplots creates visual crowding
   • Fix: Use a single shared colorbar or reposition closer to the subplot
3. CQ-04 MINOR: 200-segment approach creates 400+ traces which is verbose
   • Fix: Could reduce segment count or explore alternative gradient approaches

AI Feedback for Next Attempt

Solid implementation at 87/100 on attempt 3. The main gaps preventing 90+ are: (1) the helper function violates KISS — inline the color interpolation or use a simpler approach, (2) the inter-subplot colorbar creates slight crowding, and (3) design excellence could be pushed higher with stronger visual hierarchy between panels. The spec compliance, data quality, and library mastery are all strong.

Verdict: REJECTED