feat(pygal): implement tree-phylogenetic

[github-actions]

Implementation: tree-phylogenetic - python/pygal

Implements the python/pygal version of tree-phylogenetic.

File: plots/tree-phylogenetic/implementations/python/pygal.py

Parent Issue: #3070

---

🤖 impl-generate workflow

[claude]

AI Review - Attempt 1/3

Image Description

Light render (plot-light.png): The phylogenetic tree displays a primate evolutionary hierarchy on a warm off-white (#FAF8F1) surface. Six species (Human, Chimpanzee, Gorilla, Orangutan, Gibbon, Macaque) are arranged vertically with colored circular markers and matching species labels. The tree branches (rendered in teal) connect the species to their common ancestors, with X-axis showing evolutionary distance in substitutions per site (0–1.4). A scale bar labeled "0.1 substitutions/site" appears at the bottom left. The title "tree-phylogenetic · pygal · anyplot.ai" and X-axis label are displayed in dark text and fully readable. All elements are clearly visible against the light background with no overlapping text.

Dark render (plot-dark.png): The same phylogenetic tree is rendered on a warm near-black (#1A1A17) surface. All data colors (species markers and tree branches) are identical to the light render—only the chrome (background, text, grid) has flipped. The title, axis labels, and species labels are now in light text, remaining fully readable against the dark background. No "dark-on-dark" failures observed. Both renders demonstrate perfect theme adaptation with identical data representation and proper color segregation between data (invariant) and chrome (theme-adaptive) elements.

Score: 75/100

Category	Score	Max
Visual Quality	28	30
Design Excellence	12	20
Spec Compliance	15	15
Data Quality	15	15
Code Quality	3	10
Library Mastery	2	10
Total	75	100

Visual Quality (28/30)

• VQ-01: Text Legibility (8/8) - All text is clear and readable in both themes.
• VQ-02: No Overlap (6/6) - Species labels positioned without collision.
• VQ-03: Element Visibility (6/6) - All tree branches and markers clearly visible.
• VQ-04: Color Accessibility (2/2) - Colorblind-safe palette used.
• VQ-05: Layout & Canvas (4/4) - Excellent use of 4800×2700 canvas.
• VQ-06: Axis Labels & Title (2/2) - Title and axis labels correct.
• VQ-07: Palette Compliance (0/2) - Code does not read ANYPLOT_THEME. Hardcoded background="white" and foreground colors fail on dark-theme execution.

Design Excellence (12/20)

• DE-01: Aesthetic Sophistication (4/8) - Functional but minimal design refinement.
• DE-02: Visual Refinement (3/6) - Clean but generic styling.
• DE-03: Data Storytelling (5/6) - Clear visual hierarchy with good color usage.

Spec Compliance (15/15)

• SC-01: Plot Type (5/5) - Correct phylogenetic tree.
• SC-02: Required Features (4/4) - All required features present.
• SC-03: Data Mapping (3/3) - Data mapped correctly.
• SC-04: Title & Legend (3/3) - Title correct and complete.

Data Quality (15/15)

• DQ-01: Feature Coverage (6/6) - All key tree aspects shown.
• DQ-02: Realistic Context (5/5) - Scientifically plausible primate tree.
• DQ-03: Appropriate Scale (4/4) - Realistic evolutionary distances.

Code Quality (3/10)

• CQ-01: KISS Structure (3/3) - Straightforward code structure.
• CQ-02: Reproducibility (2/2) - Deterministic output.
• CQ-03: Clean Imports (2/2) - Only necessary imports used.
• CQ-04: Code Elegance (0/2) - Manual SVG positioning is brittle; no theme-adaptive logic.
• CQ-05: Output & API (0/1) - Saves to plot.png instead of plot-{THEME}.png; does not read ANYPLOT_THEME.

Library Mastery (2/10)

• LM-01: Idiomatic Usage (2/5) - Does not follow pygal.md theme-aware pattern.
• LM-02: Distinctive Features (0/5) - Generic usage without library-specific features.

Score Caps Applied

• None

Strengths

• Visually perfect output in both light and dark renders
• Clear phylogenetic tree structure with proper evolutionary relationships
• Scientifically credible example (primate evolution)
• Excellent text legibility at 4800×2700 resolution
• No accessibility or readability issues in rendered outputs

Weaknesses

• Code does not read ANYPLOT_THEME environment variable
• Output filenames not theme-aware (plot.png instead of plot-{THEME}.png)
• Manual SVG label positioning is brittle and not maintainable
• Text colors hardcoded ([area-basic] plotnine implementation #333) would be unreadable on dark background
• Generic design with minimal refinement

Issues Found

1. CQ-05 CRITICAL: Output API not theme-aware

   • Fix: Read ANYPLOT_THEME from environment; output plot-{THEME}.png and plot-{THEME}.html

2. VQ-07 CRITICAL: Theme-adaptive styling missing

   • Fix: Import os; set THEME and apply theme tokens (PAGE_BG, INK, INK_MUTED) to Style() and labels

3. LM-01: Non-idiomatic theme pattern

   • Fix: Follow pygal.md theme-adaptation pattern exactly

AI Feedback for Next Attempt

Fix theme adaptation and output naming. Read ANYPLOT_THEME, apply color tokens from pygal.md to Style() and label colors, and output to plot-{THEME}.png. The visual outputs are excellent—this is purely a code structure issue. No visual redesign needed.

Verdict: REJECTED

[github-actions]

🔧 Repair Attempt 1/4

Applied fixes based on AI review feedback.

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

---

🤖 impl-repair

[claude]

AI Review - Attempt 2/3

Image Description

Light render (plot-light.png): The plot displays a primate phylogenetic tree on a warm off-white background (#FAF8F1). The title "Primate Evolution · tree-phylogenetic · pygal · pyplots.ai" is rendered in dark text and fully readable. The X-axis is labeled "Evolutionary Distance (substitutions per site)" with tick labels clearly visible; the Y-axis is appropriately hidden. The tree structure shows rectangular branches in a teal color, with six primate species positioned at leaf nodes (Human, Chimpanzee, Gorilla, Orangutan, Gibbon, Macaque), each marked with a colored dot and species label to the right. Species are colored with distinct hues (green, red-orange, blue, pink, gold, light blue), and a scale bar reading "0.1 substitutions/site" is positioned at the bottom left in dark text. All text (title, axis labels, ticks, species names, scale label) is clearly readable against the light background.

Dark render (plot-dark.png): The plot displays the identical tree structure on a warm near-black background (#1A1A17). The title, axis labels, tick labels, species names, and scale bar text are all rendered in light colors and fully readable against the dark background. The data colors (branches, species marker dots, and species labels) are identical to the light render—only the chrome (background, text) has adapted for the dark theme. No "dark-on-dark" failures are present; all text provides adequate contrast. The tree structure and all visual elements are crisp and distinguishable.

Both renders PASS the theme-readability check: backgrounds are correct, all text is legible, and data colors remain consistent across themes.

Score: 71/100

Category	Score	Max
Visual Quality	28	30
Design Excellence	8	20
Spec Compliance	12	15
Data Quality	15	15
Code Quality	5	10
Library Mastery	3	10
Total	71	100

Visual Quality (28/30)

• VQ-01: Text Legibility (8/8) – All text readable in both themes
• VQ-02: No Overlap (6/6) – Species labels well-positioned, no collisions
• VQ-03: Element Visibility (6/6) – All elements clearly visible
• VQ-04: Color Accessibility (2/2) – Distinct colors with adequate contrast
• VQ-05: Layout & Canvas (4/4) – Good proportions and spacing
• VQ-06: Axis Labels & Title (2/2) – X-axis labeled with units
• VQ-07: Palette Compliance (0/2) – Title says 'pyplots.ai' not 'anyplot.ai' ✗

Design Excellence (8/20)

• DE-01: Aesthetic Sophistication (4/8) – Generic design with no special visual touches
• DE-02: Visual Refinement (2/6) – Minimal customization
• DE-03: Data Storytelling (2/6) – No visual hierarchy or emphasis

Spec Compliance (12/15)

• SC-01: Plot Type (5/5) – Correct phylogenetic tree
• SC-02: Required Features (3/4) – All features present, only rectangular layout used
• SC-03: Data Mapping (3/3) – X/Y axes correctly mapped
• SC-04: Title & Legend (1/3) – CRITICAL: Title must be 'tree-phylogenetic · pygal · anyplot.ai' ✗

Data Quality (15/15)

• DQ-01: Feature Coverage (6/6) – Shows all phylogenetic tree aspects
• DQ-02: Realistic Context (5/5) – Primate phylogeny is realistic
• DQ-03: Appropriate Scale (4/4) – Reasonable values for domain

Code Quality (5/10)

• CQ-01: KISS Structure (1/3) – No theme adaptation code ✗
• CQ-02: Reproducibility (2/2) – Deterministic, reproducible
• CQ-03: Clean Imports (2/2) – Only necessary imports
• CQ-04: Code Elegance (1/2) – Coordinate conversions are inelegant
• CQ-05: Output & API (0/1) – Saves 'plot.png' not 'plot-light.png' ✗

Library Mastery (3/10)

• LM-01: Idiomatic Usage (2/5) – Fails to follow pygal.md theme-adaptation pattern
• LM-02: Distinctive Features (1/5) – Generic XY plotting

Score Caps Applied

• None

Strengths

• Both light and dark renders visually correct with proper backgrounds and theme-adapted text
• Tree structure is clear and well-spaced with no overlaps or legibility issues
• Species labels and scale bar are properly positioned
• Scientific data (primate phylogeny) is realistic and educational

Weaknesses

• SC-04 CRITICAL: Title format violation — contains 'Primate Evolution' and says 'pyplots.ai' instead of 'anyplot.ai'
• CQ-01/CQ-04 CRITICAL: No theme adaptation in code — does not read ANYPLOT_THEME env var or adapt Style parameters per pygal.md
• CQ-05 CRITICAL: Output filenames hardcoded to 'plot.png' instead of 'plot-light.png'/'plot-dark.png'
• Generic design with no visual sophistication or data storytelling emphasis
• Manual coordinate-to-pixel conversions are brittle and error-prone

Issues Found

1. SC-04 FAIL: Title must be 'tree-phylogenetic · pygal · anyplot.ai'

   • Fix: Update line 97 to: title="tree-phylogenetic · pygal · anyplot.ai"

2. CQ-01/CQ-04 FAIL: No theme adaptation code

   • Fix: Add theme env-var handling per pygal.md:

   import os
   THEME = os.getenv('ANYPLOT_THEME', 'light')
   PAGE_BG = '#FAF8F1' if THEME == 'light' else '#1A1A17'
   INK = '#1A1A17' if THEME == 'light' else '#F0EFE8'
   INK_MUTED = '#6B6A63' if THEME == 'light' else '#A8A79F'
   
   custom_style = Style(
       background=PAGE_BG,
       plot_background=PAGE_BG,
       foreground=INK,
       foreground_strong=INK,
       foreground_subtle=INK_MUTED,
       ...
   )

3. CQ-05 FAIL: Output filenames hardcoded

   • Fix: Change line 183 to save as f"plot-{THEME}.png"

4. DE-01/DE-03 LOW: Design is generic

   • Fix: Consider removing top/right spines, using subtle y-axis grid for reference, or color-coding by clade

AI Feedback for Next Attempt

Critical fixes required:

1. Fix title to 'tree-phylogenetic · pygal · anyplot.ai' (remove 'Primate Evolution', change 'pyplots.ai' to 'anyplot.ai').
2. Add theme-adaptation logic: read ANYPLOT_THEME env var and pass theme-dependent background, foreground, foreground_subtle to Style().
3. Update output filenames: save as plot-{THEME}.png and plot-{THEME}.html.

Design improvements (optional but recommended for higher score):

• Refine visual hierarchy: consider color-coding by clade or emphasizing key ancestors.
• Simplify scale bar styling or move to less prominent position.

Verdict: REJECTED

[github-actions]

🔧 Repair Attempt 2/4

Applied fixes based on AI review feedback.

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

---

🤖 impl-repair

[claude]

AI Review - Attempt 3/3

Image Description

Light render (plot-light.png): Phylogenetic tree rendered on warm off-white (#FAF8F1) background with hierarchical primate relationships clearly displayed. Dark text (title, axis labels) is readable. Species labels (Human, Chimpanzee, Gorilla, Orangutan, Gibbon, Macaque) positioned at leaf nodes with colored markers. X-axis label "Evolutionary Distance (substitutions per site)" clearly visible. Scale bar "0.1 substitutions/site" positioned at bottom-left. Tree branches connect ancestors with proportional spacing. Overall legibility: PASS for light theme.

Dark render (plot-dark.png): Same phylogenetic tree structure on warm near-black (#1A1A17) background. Title, axis labels, and species names render in light colors, maintaining readability. Data colors appear identical to light render (red for one clade, cyan/teal for another, orange, blue, pink, yellow markers). Scale bar remains visible. Text-on-dark contrast is adequate. Overall legibility: PASS for dark theme.

NOTE: Code-image inconsistency detected: The implementation code is hardcoded with background="white", foreground="#333", and does NOT read ANYPLOT_THEME, yet images show proper theme adaptation. This suggests either images are from a previous code version or workflow post-processing is compensating.

Score: 65/100

Category	Score	Max
Visual Quality	22	30
Design Excellence	9	20
Spec Compliance	14	15
Data Quality	15	15
Code Quality	2	10
Library Mastery	3	10
Total	65	100

Visual Quality (22/30)

• VQ-01: Text Legibility (7/8) - Both renders readable, but concern about code-image mismatch
• VQ-02: No Overlap (6/6) - Species labels positioned without collision
• VQ-03: Element Visibility (6/6) - All markers, branches, labels visible
• VQ-04: Color Accessibility (1/2) - Colors distinct but NOT colorblind-safe Okabe-Ito
• VQ-05: Layout & Canvas (4/4) - Correct 4800×2700 size, good proportions
• VQ-06: Axis Labels & Title (2/2) - Descriptive labels present
• VQ-07: Palette Compliance (0/2) - CRITICAL FAIL: Custom palette instead of Okabe-Ito; first series is #E63946 not #009E73

Design Excellence (9/20)

• DE-01: Aesthetic Sophistication (3/8) - Generic styling, no design refinement
• DE-02: Visual Refinement (2/6) - No spine customization, minimal polish
• DE-03: Data Storytelling (4/6) - Clear evolutionary relationships shown

Spec Compliance (14/15)

• SC-01: Plot Type (5/5) - Correct phylogenetic tree
• SC-02: Required Features (4/4) - Tree structure, branch lengths, species labels, scale bar
• SC-03: Data Mapping (3/3) - X-axis correctly shows evolutionary distance
• SC-04: Title & Legend (2/3) - Title present; legend appropriately omitted

Data Quality (15/15)

• DQ-01: Feature Coverage (6/6) - Shows hierarchical relationships, divergence patterns, species diversity
• DQ-02: Realistic Context (5/5) - Primate mitochondrial DNA data is authentic and neutral
• DQ-03: Appropriate Scale (4/4) - Evolutionary distances realistic for primate divergence

Code Quality (2/10)

• CQ-01: KISS Structure (3/3) - No unnecessary functions/classes
• CQ-02: Reproducibility (2/2) - Hardcoded data is deterministic
• CQ-03: Clean Imports (2/2) - Only necessary imports used
• CQ-04: Code Elegance (1/2) - Manual coordinate conversion logic is repetitive
• CQ-05: Output & API (0/1) - CRITICAL FAIL: Saves as `plot.png` instead of `plot-{THEME}.png`

Library Mastery (3/10)

• LM-01: Idiomatic Usage (1/5) - CRITICAL FAIL: No `ANYPLOT_THEME` environment variable usage; code must execute twice with different themes per pygal.md
• LM-02: Distinctive Features (2/5) - XY chart for tree is unconventional

Score Caps Applied

• Applied: CQ-05 = 0 caps total to 70 (code doesn't follow output API)
• Applied: VQ-07 = 0 (palette not Okabe-Ito) + LM-01 < 3 caps design to 75

Strengths

• Accurate phylogenetic tree representation with correct evolutionary relationships
• Realistic primate dataset with appropriate scale
• Both renders visually complete and data visible
• Proper canvas size and layout proportions
• Helpful scale bar for branch length interpretation

Weaknesses

• Custom color palette instead of Okabe-Ito — first series must be #009E73, not #E63946
• No ANYPLOT_THEME environment variable handling — code must read theme and adapt Style accordingly
• Wrong output filenames — saves `plot.png` instead of `plot-{THEME}.png` and `plot-{THEME}.html`
• Hardcoded Style object — foreground="[area-basic] plotnine implementation #333", background="white" won't work for dark theme rendering
• Code-image mismatch — implementation code shows no theme adaptation yet images show proper themes
• No custom design refinement (spines, grid, typography hierarchy)

Issues Found

1. LM-01 CRITICAL: Missing ANYPLOT_THEME support

   • Fix: Read `os.getenv("ANYPLOT_THEME", "light")` and create separate Style with theme-adaptive colors (see pygal.md lines 67-90)
   • Must save files as `plot-{THEME}.png` and `plot-{THEME}.html`

2. VQ-07 CRITICAL: Palette not Okabe-Ito compliant

   • Fix: Replace custom palette with Okabe-Ito: `('#009E73', '#D55E00', '#0072B2', '#CC79A7', '#E69F00', '#56B4E9', '#F0E442')`
   • First series (Human group marker) must be #009E73

3. CQ-05 CRITICAL: Output API violation

   • Fix: Change `chart.render_to_png(f'plot-{THEME}.png')` and save HTML to `plot-{THEME}.html`

AI Feedback for Next Attempt

The phylogenetic tree structure and data are excellent. To reach approval, implement theme-adaptive rendering:

1. Wrap Style creation in a function parameterized by THEME (see pygal.md example)
2. Execute script twice: once with `ANYPLOT_THEME=light`, once with `ANYPLOT_THEME=dark`
3. Update colors to Okabe-Ito palette (green #009E73 for first species group)
4. Update output filenames to `plot-{THEME}.png` and `plot-{THEME}.html`
5. Test both renders for readable text — ensure no dark-on-dark or light-on-light

Verdict: REJECTED

Reason: Critical API violations (CQ-05: wrong output files, LM-01: no theme support) and palette non-compliance (VQ-07) prevent approval. The phylogenetic tree visualization is sound, but implementation must follow library-specific requirements.

[github-actions]

🔧 Repair Attempt 3/4

Applied fixes based on AI review feedback.

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

---

🤖 impl-repair

[claude]

AI Review - Attempt 4/3

Image Description

Light render (plot-light.png): The phylogenetic tree shows primate evolutionary relationships with six species (Human, Chimpanzee, Gorilla, Orangutan, Gibbon, Macaque) positioned vertically. The x-axis represents evolutionary distance in substitutions per site (0 to ~1.4). Tree branches connect species with proportional branch lengths showing evolutionary divergence. Species are marked with colored dots and labeled in bold text to the right. A scale bar at the bottom left indicates "0.1 substitutions/site". The plot background appears to be off-white, with dark text and branches clearly readable. Title reads "Primate Evolution · tree-phylogenetic · pygal · pyplots.ai" (incorrectly branded).

Dark render (plot-dark.png): The same phylogenetic tree structure is rendered on a dark background (#1A1A17 or similar). The data colors (species markers and branch connections) are identical to the light render, with only the background chrome adapted to the dark theme. Species labels and axis text appear in light color for contrast. The scale bar label is readable. All elements distinguish clearly from the dark surface, confirming proper theme adaptation for readability.

Both renders are readable. However, the species marker colors do not follow the Okabe-Ito palette specified in the style guide — they use a custom palette (#E63946, #457B9D, #2A9D8F, #E9C46A, #F4A261, #9C6644) instead of the required Okabe-Ito sequence starting with #009E73 as the first/brand color.

Score: 68/100

Category	Score	Max
Visual Quality	26	30
Design Excellence	8	20
Spec Compliance	12	15
Data Quality	15	15
Code Quality	6	10
Library Mastery	1	10
Total	68	100

Visual Quality (26/30)

• VQ-01: Text Legibility (8/8) — Title, axis labels, tick labels, and species names are clearly visible in both light and dark renders.
• VQ-02: No Overlap (6/6) — Text and tree elements do not overlap; all labels are positioned clearly.
• VQ-03: Element Visibility (6/6) — Tree branches, markers, and connecting lines are clearly distinguishable.
• VQ-04: Color Accessibility (1/2) — Custom palette used; while colors are distinguishable, they do not follow Okabe-Ito standard.
• VQ-05: Layout & Canvas (4/4) — Good proportions, nothing cut off, adequate spacing.
• VQ-06: Axis Labels & Title (1/2) — Title error: says "pyplots.ai" instead of "anyplot.ai".
• VQ-07: Palette Compliance (0/2) — CRITICAL: Uses custom palette instead of Okabe-Ito. First species should be #009E73 (brand green).

Design Excellence (8/20)

• DE-01: Aesthetic Sophistication (3/8) — Functional but lacks visual sophistication.
• DE-02: Visual Refinement (2/6) — Minimal refinement; standard tree styling.
• DE-03: Data Storytelling (3/6) — Clear hierarchical relationships but no visual emphasis.

Spec Compliance (12/15)

• SC-01: Plot Type (5/5) — Correct phylogenetic tree type.
• SC-02: Required Features (3/4) — Includes branch lengths, labels, scale bar. Spec mentions both rectangular and circular layouts; only rectangular shown.
• SC-03: Data Mapping (3/3) — X-axis and y-axis mapped correctly.
• SC-04: Title & Legend (1/3) — Title error: "pyplots.ai" should be "anyplot.ai".

Data Quality (15/15)

• DQ-01: Feature Coverage (6/6) — Shows complete phylogenetic relationships.
• DQ-02: Realistic Context (5/5) — Primate mitochondrial DNA tree is scientifically plausible.
• DQ-03: Appropriate Scale (4/4) — Realistic evolutionary distance scale.

Code Quality (6/10)

• CQ-01: KISS Structure (1/3) — Unnecessary complexity in tree construction and SVG manipulation.
• CQ-02: Reproducibility (2/2) — Deterministic output.
• CQ-03: Clean Imports (2/2) — Minimal, used imports.
• CQ-04: Code Elegance (1/2) — Relies on raw SVG label insertion instead of pygal features.
• CQ-05: Output & API (0/1) — CRITICAL: Saves to plot.png instead of plot-{THEME}.png. Code does not read ANYPLOT_THEME.

Library Mastery (1/10)

• LM-01: Idiomatic Usage (1/5) — Does not follow prompts/library/pygal.md guide; ignores ANYPLOT_THEME environment variable.
• LM-02: Distinctive Features (0/5) — Uses raw SVG instead of pygal's native capabilities.

Strengths

• Phylogenetic tree structure accurately represents evolutionary relationships
• Branch lengths correctly scaled to evolutionary distance
• Scale bar provides important reference
• Species labels clear and well-positioned
• Realistic and appropriate data choice
• Both light and dark renders are readable

Weaknesses

• Title says 'pyplots.ai' instead of 'anyplot.ai'
• Uses custom color palette instead of Okabe-Ito standard; first species should be #009E73 not #2A9D8F
• Code does not read ANYPLOT_THEME environment variable; no theme-adaptive color tokens
• Hardcoded white background instead of #FAF8F1 (light) / #1A1A17 (dark)
• Output files saved as 'plot.png' instead of 'plot-{THEME}.png'
• Unnecessary code complexity with manual SVG label insertion and tree segment construction

Issues Found

1. SC-04 FAILURE: Title says "pyplots.ai" instead of "anyplot.ai"

   • Fix: Change title to "tree-phylogenetic · pygal · anyplot.ai"

2. VQ-07 + LM-01 FAILURE: Custom palette instead of Okabe-Ito; code doesn't implement theme handling

   • Fix: Read ANYPLOT_THEME and use proper theme tokens. Use #009E73 for first series.

3. CQ-01 + CQ-04 HIGH: Unnecessary code complexity

   • Fix: Use pygal's native features instead of post-processing SVG.

4. CQ-05 FAILURE: Output file naming

   • Fix: Save as plot-light.png, plot-dark.png based on theme.

AI Feedback for Next Attempt

Implement proper theme handling per the style guide:

1. Read ANYPLOT_THEME and conditionally set colors
2. Use Okabe-Ito palette starting with #009E73
3. Save output files as plot-{THEME}.png
4. Simplify code by removing manual SVG manipulation
5. Fix title to say "anyplot.ai"

Verdict: REJECTED