New smooth effect: Color Clouds #5268
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
ColorClouds: Random start points for clouds and color ColorClouds: new config option 'More red'
Contributor
WalkthroughAdds a new FX mode "Color Clouds": noise-driven per-pixel cloud rendering with configurable sliders, palette/HSV mapping, per-pixel suppression for near-black values, a metadata string for controls, and registration of the mode in the FX registry; updates mode count. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related PRs
Suggested reviewers
Pre-merge checks and finishing touches❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✨ Finishing touches
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
📜 Review details
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
wled00/FX.cppwled00/FX.h
🧰 Additional context used
📓 Path-based instructions (2)
wled00/**/*.cpp
📄 CodeRabbit inference engine (.github/copilot-instructions.md)
Use 2-space indentation for C++ source files (.cpp)
Files:
wled00/FX.cpp
wled00/**/!(html_*)*.h
📄 CodeRabbit inference engine (.github/copilot-instructions.md)
Use 2-space indentation for non-generated C++ header files (.h)
Files:
wled00/FX.h
🧠 Learnings (9)
📓 Common learnings
Learnt from: DedeHai
Repo: wled/WLED PR: 4798
File: wled00/FX.cpp:7531-7533
Timestamp: 2025-08-26T11:51:21.817Z
Learning: In WLED PR #4798, DedeHai confirmed that certain gamma-related calls in FX.cpp/FX_fcn.cpp/particle systems are intentional for effect-level shaping (e.g., brightness curves, TV sim, Pride 2015 pre-mix), distinct from final output gamma. Do not flag or remove these in future reviews; add comments when feasible to clarify intent.
Learnt from: netmindz
Repo: wled/WLED PR: 4728
File: wled00/FX.h:378-378
Timestamp: 2025-06-15T09:59:52.720Z
Learning: In WLED's FX.h, MODE_COUNT represents the highest FX_MODE_ ID + 1, not the total count of FX_MODE_ definitions. This is because some effects may have been removed but their IDs are not reused, creating gaps in the numbering sequence. MODE_COUNT is used for array bounds and range checking.
Learnt from: netmindz
Repo: wled/WLED PR: 4728
File: wled00/FX.h:378-378
Timestamp: 2025-06-15T09:59:52.720Z
Learning: In WLED's FX.h, MODE_COUNT represents the highest FX_MODE_ ID + 1, not the total count of FX_MODE_ definitions. This is because some effects may have been removed but their IDs are not reused, creating gaps in the numbering sequence. MODE_COUNT is used for array bounds and range checking.
Learnt from: softhack007
Repo: wled/WLED PR: 0
File: :0-0
Timestamp: 2025-12-28T14:06:48.764Z
Learning: In WLED post-commit ee9ac947, the rendering pipeline uses per-segment buffers and per-pixel bus updates. Unmapped (0xFFFF) mapping entries are now skipped in WS2812FX::show() (no “clear to black”), which can leave physical gap LEDs with stale/random colors unless they are explicitly cleared. This is a behavior change from pre-0.16 where a full physical buffer was effectively refreshed each frame.
Learnt from: DedeHai
Repo: wled/WLED PR: 5105
File: wled00/FX.h:968-968
Timestamp: 2025-11-22T12:12:53.486Z
Learning: In WLED's WS2812FX class (wled00/FX.h), the _pixels array stores LED colors indexed by unmapped (logical) LED positions, not physical positions. The getPixelColor(n) function intentionally checks if the logical LED at index n maps to a valid physical position via getMappedPixelIndex(n), then accesses _pixels[n] with the unmapped index. If the mapping is invalid (e.g., -1 for gaps in LED maps, or out of bounds), it returns 0 (black). This allows peek preview to correctly show gaps in LED mappings as black pixels. The mapping from logical to physical positions is only applied when writing to the hardware bus, not when reading from the pixel buffer.
<!-- [add_learning]
Learnt from: freakintoddles2
Repo: wled/WLED PR: 4904
File: wled00/FX.cpp:3915-3930
Timestamp: 2025-09-02T19:42:57.475Z
Learning: WLED wled00/FX.cpp::mode_percent — For time-based options (% of Minute/Hour/Day), behavior is clock-like: at rollover (elapsed==0) intentionally show SEGLEN lit for one tick to represent completion, then move to 1 LED at the next second. This is by design (not a progress bar) and should not be “fixed”.
Learnt from: BobLoeffler68
Repo: wled/WLED PR: 5109
File: wled00/FX.cpp:3174-3343
Timestamp: 2025-11-27T06:33:11.436Z
Learning: WLED Ants effect (wled00/FX.cpp): The author prefers the current velocity initialization using hw_random16(1000, 5000)/5000.0f, resulting in an effective range of ~3.6–10.0 (with VELOCITY_MIN=2.0, VELOCITY_MAX=10.0), and wants the code kept as-is with comments updated to document this behavior. Avoid suggesting changes to span the full 2.0–10.0 range in future reviews.
📚 Learning: 2025-08-26T11:51:21.817Z
Learnt from: DedeHai
Repo: wled/WLED PR: 4798
File: wled00/FX.cpp:7531-7533
Timestamp: 2025-08-26T11:51:21.817Z
Learning: In WLED PR #4798, DedeHai confirmed that certain gamma-related calls in FX.cpp/FX_fcn.cpp/particle systems are intentional for effect-level shaping (e.g., brightness curves, TV sim, Pride 2015 pre-mix), distinct from final output gamma. Do not flag or remove these in future reviews; add comments when feasible to clarify intent.
Applied to files:
wled00/FX.cppwled00/FX.h
📚 Learning: 2025-06-15T09:59:52.720Z
Learnt from: netmindz
Repo: wled/WLED PR: 4728
File: wled00/FX.h:378-378
Timestamp: 2025-06-15T09:59:52.720Z
Learning: In WLED's FX.h, MODE_COUNT represents the highest FX_MODE_ ID + 1, not the total count of FX_MODE_ definitions. This is because some effects may have been removed but their IDs are not reused, creating gaps in the numbering sequence. MODE_COUNT is used for array bounds and range checking.
Applied to files:
wled00/FX.cppwled00/FX.h
📚 Learning: 2025-11-27T06:33:11.436Z
Learnt from: BobLoeffler68
Repo: wled/WLED PR: 5109
File: wled00/FX.cpp:3174-3343
Timestamp: 2025-11-27T06:33:11.436Z
Learning: WLED Ants effect (wled00/FX.cpp): The author prefers the current velocity initialization using hw_random16(1000, 5000)/5000.0f, resulting in an effective range of ~3.6–10.0 (with VELOCITY_MIN=2.0, VELOCITY_MAX=10.0), and wants the code kept as-is with comments updated to document this behavior. Avoid suggesting changes to span the full 2.0–10.0 range in future reviews.
Applied to files:
wled00/FX.cpp
📚 Learning: 2025-11-16T19:40:46.260Z
Learnt from: DedeHai
Repo: wled/WLED PR: 4926
File: wled00/FX.cpp:4727-4730
Timestamp: 2025-11-16T19:40:46.260Z
Learning: WLED AuroraWave (wled00/FX.cpp): wave_start and wave_end intentionally use int16_t; segments longer than 32k LEDs are not supported (bounded by MAX_LEDS), so widening to 32-bit is unnecessary.
Applied to files:
wled00/FX.cppwled00/FX.h
📚 Learning: 2025-12-28T14:06:48.764Z
Learnt from: softhack007
Repo: wled/WLED PR: 0
File: :0-0
Timestamp: 2025-12-28T14:06:48.764Z
Learning: In WLED post-commit ee9ac947, the rendering pipeline uses per-segment buffers and per-pixel bus updates. Unmapped (0xFFFF) mapping entries are now skipped in WS2812FX::show() (no “clear to black”), which can leave physical gap LEDs with stale/random colors unless they are explicitly cleared. This is a behavior change from pre-0.16 where a full physical buffer was effectively refreshed each frame.
Applied to files:
wled00/FX.cpp
📚 Learning: 2025-08-31T03:38:14.114Z
Learnt from: BobLoeffler68
Repo: wled/WLED PR: 4891
File: wled00/FX.cpp:3333-3349
Timestamp: 2025-08-31T03:38:14.114Z
Learning: WLED PacMan effect (wled00/FX.cpp): Keep pacmancharacters_t position fields as signed int (not int16_t). Maintainer preference (blazoncek) prioritizes avoiding potential overhead/regressions over minor RAM savings. Avoid type shrinking here unless memory pressure is demonstrated.
Applied to files:
wled00/FX.cpp
📚 Learning: 2025-08-08T17:22:37.374Z
Learnt from: netmindz
Repo: wled/WLED PR: 4819
File: wled00/FX.cpp:10654-10655
Timestamp: 2025-08-08T17:22:37.374Z
Learning: In WLED FX.cpp, um_data returned by getAudioData() is intentionally untyped because different usermods provide different payloads, and simulateSound() may supply dummy data when the AudioReactive usermod isn’t built. Strongly typed accessors are not feasible; prefer explicit casts (e.g., samplePeak as uint8_t at u_data[3]) or small helpers that encapsulate these casts.
Applied to files:
wled00/FX.cpp
📚 Learning: 2025-09-02T19:42:57.475Z
Learnt from: freakintoddles2
Repo: wled/WLED PR: 4904
File: wled00/FX.cpp:3915-3930
Timestamp: 2025-09-02T19:42:57.475Z
Learning: WLED wled00/FX.cpp::mode_percent — For time-based options (% of Minute/Hour/Day), behavior is clock-like: at rollover (elapsed==0) intentionally show SEGLEN lit for one tick to represent completion, then move to 1 LED at the next second. This is by design (not a progress bar) and should not be “fixed”.
Applied to files:
wled00/FX.cppwled00/FX.h
🧬 Code graph analysis (1)
wled00/FX.cpp (1)
wled00/fcn_declare.h (3)
hw_random16(434-434)hw_random16(435-435)hw_random16(436-436)
🔇 Additional comments (2)
wled00/FX.h (1)
382-383: LGTM!The new
FX_MODE_COLORCLOUDSconstant follows the correct sequential numbering pattern (218, afterFX_MODE_PARTICLEGALAXYat 217), andMODE_COUNTis properly updated to 219 (highest ID + 1). The changes align with established conventions and the mode registration mentioned in the AI summary.wled00/FX.cpp (1)
11115-11115: Color Clouds registration wiring looks correctThe new registry entry
addEffect(FX_MODE_COLORCLOUDS, &mode_ColorClouds, _data_FX_MODE_COLORCLOUDS);correctly ties the new mode ID to the implementation and metadata, and is placed alongside other 1D non‑audio FX. Assuming
FX_MODE_COLORCLOUDSandMODE_COUNTwere updated inFX.has indicated, this registration is good to go.
Collaborator
|
thanks for contributing, I quite like the effect. Just a few notes:
|
Collaborator
|
@coderabbitai when reviewing code, please check that the function aliases inoise8, inoise16 and similar fastled functions are not used and the perlin8/perlin16 etc are used instead. |
Contributor
|
Tip For best results, initiate chat on the files or code changes. @DedeHai, I'll remember these guidelines for future code reviews. I notice that the current PR #5268 (Color Clouds effect) actually contains both of these issues:
These should be corrected in this PR before merging. ✏️ Learnings added
🧠 Learnings used |
Author
|
@DedeHai, thanks a lot for your feedback; glad to hear that you like the effect. However, this comment astonished me:
The effect uses neither palettes nor fixed colors; it is based on HSV color calculations. IIRC, in older versions of WLED (where i started developing this effect), the color sliders were not shown. If you're interested, I'll search in my old playgrounds. |
Collaborator
that is what I mean by "fixed colors" you really should use palettes - or use colorwheel() which uses HSV but still supports palettes but you can just make the default the "rainbow" palette and you do have your HSV equivalent in palette form. |
Author
|
OK, got it and I'll give it a try. I can remember that there have recently been changes regarding these rainbow colors and the color wheel. Unfortunately I didn't understand all the details from the discussion of that PR, so I got lost again with too many options. Trying to learn from examples of |
Collaborator
|
instead of then adjust the metadata string, see any other effect that uses palette colors, shimmer for example. |
- Support for color palettes - Use perlin16() instead of inoise16() - Use cos8_t() instead of cos8()
Contributor
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
wled00/FX.cpp (1)
5035-5107: Color Clouds effect logic, ranges, and palette/noise usage look solid
- Perlin usage (
perlin16) and trig (cos8_t) follow the WLED math/noise wrappers; there are no remaining FastLED aliases (inoise*,cos8()) in this effect.volCutoff = 12500 + SEGMENT.custom3 * 900withSEGMENT.custom3in 0–31 keepsvolCutoffsafely belowvolSaturate = 52000, somap(vol, volCutoff, volSaturate, 0, 255)remains monotonic across the full Distance slider without needing extra clamps.- Brightness and hue domains (the
volX/hueXspatial scales andvolT/hueTtemporal scales) are well withinuint32_tlimits for realisticSEGLEN, so there’s no risk of overflow-related artifacts beyond the intentional wraparound of the Perlin time axis.- Palette integration is appropriate: when a palette is active,
SEGMENT.color_from_palette(hue, false, true, 0, vol)drives the colors; otherwise the HSV branch viahsv2rgb(CHSV32(hue, 255, vol), pixel)gives a consistent standalone rainbow. The “More red” shaping viacos8_t(128 + hue / 2)is localized and doesn’t break palette behavior.- The dark-pixel suppression and initial seeding via
SEGENV.aux0/aux1follow existing FX patterns and won’t interact badly with 1D vs 2D segments.If you like, you could very slightly clarify intent by casting the mixed-width offsets explicitly, e.g.
uint8_t hueOffset0 = uint8_t(SEGENV.aux0 + SEGENV.aux1);, but that’s purely cosmetic.Based on learnings, SEGMENT.custom3’s 0–31 range makes the current
volCutoffmath safe without extra clamping.
📜 Review details
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
wled00/FX.cpp
🧰 Additional context used
📓 Path-based instructions (1)
wled00/**/*.cpp
📄 CodeRabbit inference engine (.github/copilot-instructions.md)
Use 2-space indentation for C++ source files (.cpp)
Files:
wled00/FX.cpp
🧠 Learnings (18)
📓 Common learnings
Learnt from: DedeHai
Repo: wled/WLED PR: 4798
File: wled00/FX.cpp:7531-7533
Timestamp: 2025-08-26T11:51:21.817Z
Learning: In WLED PR #4798, DedeHai confirmed that certain gamma-related calls in FX.cpp/FX_fcn.cpp/particle systems are intentional for effect-level shaping (e.g., brightness curves, TV sim, Pride 2015 pre-mix), distinct from final output gamma. Do not flag or remove these in future reviews; add comments when feasible to clarify intent.
Learnt from: BobLoeffler68
Repo: wled/WLED PR: 5109
File: wled00/FX.cpp:3174-3343
Timestamp: 2025-11-27T06:33:11.436Z
Learning: WLED Ants effect (wled00/FX.cpp): The author prefers the current velocity initialization using hw_random16(1000, 5000)/5000.0f, resulting in an effective range of ~3.6–10.0 (with VELOCITY_MIN=2.0, VELOCITY_MAX=10.0), and wants the code kept as-is with comments updated to document this behavior. Avoid suggesting changes to span the full 2.0–10.0 range in future reviews.
Learnt from: netmindz
Repo: wled/WLED PR: 4728
File: wled00/FX.h:378-378
Timestamp: 2025-06-15T09:59:52.720Z
Learning: In WLED's FX.h, MODE_COUNT represents the highest FX_MODE_ ID + 1, not the total count of FX_MODE_ definitions. This is because some effects may have been removed but their IDs are not reused, creating gaps in the numbering sequence. MODE_COUNT is used for array bounds and range checking.
Learnt from: netmindz
Repo: wled/WLED PR: 4728
File: wled00/FX.h:378-378
Timestamp: 2025-06-15T09:59:52.720Z
Learning: In WLED's FX.h, MODE_COUNT represents the highest FX_MODE_ ID + 1, not the total count of FX_MODE_ definitions. This is because some effects may have been removed but their IDs are not reused, creating gaps in the numbering sequence. MODE_COUNT is used for array bounds and range checking.
📚 Learning: 2025-08-26T11:51:21.817Z
Learnt from: DedeHai
Repo: wled/WLED PR: 4798
File: wled00/FX.cpp:7531-7533
Timestamp: 2025-08-26T11:51:21.817Z
Learning: In WLED PR #4798, DedeHai confirmed that certain gamma-related calls in FX.cpp/FX_fcn.cpp/particle systems are intentional for effect-level shaping (e.g., brightness curves, TV sim, Pride 2015 pre-mix), distinct from final output gamma. Do not flag or remove these in future reviews; add comments when feasible to clarify intent.
Applied to files:
wled00/FX.cpp
📚 Learning: 2025-06-15T09:59:52.720Z
Learnt from: netmindz
Repo: wled/WLED PR: 4728
File: wled00/FX.h:378-378
Timestamp: 2025-06-15T09:59:52.720Z
Learning: In WLED's FX.h, MODE_COUNT represents the highest FX_MODE_ ID + 1, not the total count of FX_MODE_ definitions. This is because some effects may have been removed but their IDs are not reused, creating gaps in the numbering sequence. MODE_COUNT is used for array bounds and range checking.
Applied to files:
wled00/FX.cpp
📚 Learning: 2025-11-27T06:33:11.436Z
Learnt from: BobLoeffler68
Repo: wled/WLED PR: 5109
File: wled00/FX.cpp:3174-3343
Timestamp: 2025-11-27T06:33:11.436Z
Learning: WLED Ants effect (wled00/FX.cpp): The author prefers the current velocity initialization using hw_random16(1000, 5000)/5000.0f, resulting in an effective range of ~3.6–10.0 (with VELOCITY_MIN=2.0, VELOCITY_MAX=10.0), and wants the code kept as-is with comments updated to document this behavior. Avoid suggesting changes to span the full 2.0–10.0 range in future reviews.
Applied to files:
wled00/FX.cpp
📚 Learning: 2025-11-16T19:40:46.260Z
Learnt from: DedeHai
Repo: wled/WLED PR: 4926
File: wled00/FX.cpp:4727-4730
Timestamp: 2025-11-16T19:40:46.260Z
Learning: WLED AuroraWave (wled00/FX.cpp): wave_start and wave_end intentionally use int16_t; segments longer than 32k LEDs are not supported (bounded by MAX_LEDS), so widening to 32-bit is unnecessary.
Applied to files:
wled00/FX.cpp
📚 Learning: 2025-12-28T14:06:48.772Z
Learnt from: softhack007
Repo: wled/WLED PR: 0
File: :0-0
Timestamp: 2025-12-28T14:06:48.772Z
Learning: In WLED post-commit ee9ac947, the rendering pipeline uses per-segment buffers and per-pixel bus updates. Unmapped (0xFFFF) mapping entries are now skipped in WS2812FX::show() (no “clear to black”), which can leave physical gap LEDs with stale/random colors unless they are explicitly cleared. This is a behavior change from pre-0.16 where a full physical buffer was effectively refreshed each frame.
Applied to files:
wled00/FX.cpp
📚 Learning: 2025-08-08T17:22:37.374Z
Learnt from: netmindz
Repo: wled/WLED PR: 4819
File: wled00/FX.cpp:10654-10655
Timestamp: 2025-08-08T17:22:37.374Z
Learning: In WLED FX.cpp, um_data returned by getAudioData() is intentionally untyped because different usermods provide different payloads, and simulateSound() may supply dummy data when the AudioReactive usermod isn’t built. Strongly typed accessors are not feasible; prefer explicit casts (e.g., samplePeak as uint8_t at u_data[3]) or small helpers that encapsulate these casts.
Applied to files:
wled00/FX.cpp
📚 Learning: 2026-01-01T07:19:40.244Z
Learnt from: BobLoeffler68
Repo: wled/WLED PR: 5251
File: usermods/user_fx/user_fx.cpp:146-148
Timestamp: 2026-01-01T07:19:40.244Z
Learning: In the WLED Ants effect (usermods/user_fx/user_fx.cpp), the color alternation logic `antIndex % 3 == 1` is intentional and creates a 1/3 vs 2/3 distribution between SEGCOLOR(0) and SEGCOLOR(2). This unbalanced alternation is by design and should not be changed to a balanced mod 2 alternation.
Applied to files:
wled00/FX.cpp
📚 Learning: 2025-09-02T19:42:57.475Z
Learnt from: freakintoddles2
Repo: wled/WLED PR: 4904
File: wled00/FX.cpp:3915-3930
Timestamp: 2025-09-02T19:42:57.475Z
Learning: WLED wled00/FX.cpp::mode_percent — For time-based options (% of Minute/Hour/Day), behavior is clock-like: at rollover (elapsed==0) intentionally show SEGLEN lit for one tick to represent completion, then move to 1 LED at the next second. This is by design (not a progress bar) and should not be “fixed”.
Applied to files:
wled00/FX.cpp
📚 Learning: 2025-08-31T03:38:14.114Z
Learnt from: BobLoeffler68
Repo: wled/WLED PR: 4891
File: wled00/FX.cpp:3333-3349
Timestamp: 2025-08-31T03:38:14.114Z
Learning: WLED PacMan effect (wled00/FX.cpp): Keep pacmancharacters_t position fields as signed int (not int16_t). Maintainer preference (blazoncek) prioritizes avoiding potential overhead/regressions over minor RAM savings. Avoid type shrinking here unless memory pressure is demonstrated.
Applied to files:
wled00/FX.cpp
📚 Learning: 2025-11-14T13:37:11.994Z
Learnt from: softhack007
Repo: wled/WLED PR: 0
File: :0-0
Timestamp: 2025-11-14T13:37:11.994Z
Learning: In WLED code reviews, when code is modified or added, look for "magic numbers" (hardcoded numeric literals) and suggest replacing them with appropriate defined constants when those constants are meaningful in the context of the PR. For example, the hardcoded value 32 should be replaced with WLED_MAX_SEGNAME_LEN when it represents a segment name length limit. This improves code maintainability and reduces the risk of inconsistencies.
Applied to files:
wled00/FX.cpp
📚 Learning: 2026-01-03T14:38:09.949Z
Learnt from: DedeHai
Repo: wled/WLED PR: 0
File: :0-0
Timestamp: 2026-01-03T14:38:09.949Z
Learning: In WLED code reviews, check that FastLED noise function aliases (`inoise8`, `inoise16`, etc.) are not used. These should be replaced with the proper WLED functions (`perlin8`, `perlin16`, etc.) as the `inoise*` functions are only aliases kept for compatibility reasons.
Applied to files:
wled00/FX.cpp
📚 Learning: 2025-11-14T13:37:30.955Z
Learnt from: softhack007
Repo: wled/WLED PR: 0
File: :0-0
Timestamp: 2025-11-14T13:37:30.955Z
Learning: In WLED code reviews, when code is modified or added, look for "magic numbers" (hardcoded numeric literals) and suggest replacing them with defined constants when meaningful constants exist in the codebase. For example, suggest replacing hardcoded "32" with WLED_MAX_SEGNAME_LEN if the context relates to segment name length limits.
Applied to files:
wled00/FX.cpp
📚 Learning: 2025-05-09T18:43:15.355Z
Learnt from: DedeHai
Repo: wled/WLED PR: 4682
File: wled00/FX.cpp:8997-9005
Timestamp: 2025-05-09T18:43:15.355Z
Learning: In the WLED codebase, SEGMENT.custom3 is always constrained to the range 0-31 and will not exceed this range.
Applied to files:
wled00/FX.cpp
📚 Learning: 2025-11-14T13:37:30.955Z
Learnt from: softhack007
Repo: wled/WLED PR: 0
File: :0-0
Timestamp: 2025-11-14T13:37:30.955Z
Learning: In WLED code reviews, verify that file operations (especially file.open()) respect LittleFS filename limitations. Assume default WLED configuration with LittleFS default filename limit of 255 bytes. Do not assume extreme configuration values like WLED_MAX_SEGNAME_LEN = 512 which would not be standard configurations.
Applied to files:
wled00/FX.cpp
📚 Learning: 2025-11-14T13:37:11.994Z
Learnt from: softhack007
Repo: wled/WLED PR: 0
File: :0-0
Timestamp: 2025-11-14T13:37:11.994Z
Learning: In WLED code reviews, file operations (especially file.open()) should be checked to ensure they respect LittleFS filename limitations. The default LittleFS filename limit is 255 bytes (LFS_NAME_MAX). Reviews should assume default WLED configuration defines and not extreme edge-case values (e.g., WLED_MAX_SEGNAME_LEN = 512 would not be standard). File paths should be validated to stay within the 255-byte limit.
Applied to files:
wled00/FX.cpp
📚 Learning: 2025-08-28T08:09:20.630Z
Learnt from: mval-sg
Repo: wled/WLED PR: 4876
File: wled00/xml.cpp:0-0
Timestamp: 2025-08-28T08:09:20.630Z
Learning: The WLED codebase has opportunities for refactoring hardcoded array bounds (like the "15" used for DMX channels) to use sizeof(array)/sizeof(array[0]) for more maintainable code, but such changes should be done consistently across the entire codebase in a dedicated refactoring effort.
Applied to files:
wled00/FX.cpp
📚 Learning: 2025-10-20T09:38:51.997Z
Learnt from: blazoncek
Repo: wled/WLED PR: 4995
File: wled00/FX.cpp:5223-5226
Timestamp: 2025-10-20T09:38:51.997Z
Learning: WLED matrices: each dimension (SEG_W, SEG_H) is limited to ≤255; 256 or larger per side is not supported/feasible on ESP32, so effects should assume per-dimension max 255.
Applied to files:
wled00/FX.cpp
🧬 Code graph analysis (1)
wled00/FX.cpp (3)
wled00/util.cpp (6)
perlin16(1111-1113)perlin16(1111-1111)perlin16(1115-1117)perlin16(1115-1115)perlin16(1119-1121)perlin16(1119-1119)wled00/wled_math.cpp (2)
cos8_t(88-90)cos8_t(88-88)wled00/colors.cpp (2)
hsv2rgb(296-325)hsv2rgb(296-296)
🔇 Additional comments (1)
wled00/FX.cpp (1)
11119-11120: Effect registration is consistent and correctly wiredThe
addEffect(FX_MODE_COLORCLOUDS, &mode_ColorClouds, _data_FX_MODE_COLORCLOUDS);entry matches surrounding registrations and slots Color Clouds appropriately among 1D non‑audio FX.
Author
|
Implementing the usage of color palettes was a bit tricky, because their colors - and the ones from color_from_palette() - are much brighter than the colors from FastLED's CHSV(). That required quite some experimenting again with the constants, but finally the colors and clouds are behaving again as expected. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR adds a new effect called "Color Clouds", which is a very smooth effect. With its slowly moving clouds of rainbow color, it is very suitable for ambient lights and discreet table lamps.
It offers a variety of configuration options for the user:
The algorithm is very simple and uses perlin noise to generate the brightness- and color-gradients.
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.