Add psramPresent and psramSize fields to /info endpoint and usage reports #5168

Copilot · Dec 8, 2025

The /info endpoint reported only free PSRAM bytes, making it impossible to determine if hardware has PSRAM or its total capacity. Usage reports calculated PSRAM size from the free amount rather than the actual hardware specification.

Backend (`json.cpp`)

Added psramPresent boolean indicating PSRAM hardware presence via psramFound()
Added psramSize field reporting total PSRAM in MB from ESP.getPsramSize()
Retained existing psram field (free bytes) for backward compatibility, only present when BOARD_HAS_PSRAM is defined

The three fields together indicate hardware capability vs firmware configuration:

psramPresent: true + psram absent = hardware has PSRAM, firmware not compiled to use it
psramPresent: true + psram present = hardware has PSRAM, firmware using it
psramPresent: false = no PSRAM hardware

Frontend (`index.js`)

Modified reportUpgradeEvent() to send psramPresent and psramSize fields to usage.wled.me
Changed from calculating size via Math.round(infoData.psram / (1024 * 1024)) to using infoData.psramSize directly

Example /info response on ESP32 with 8MB PSRAM:

{
  "psramPresent": true,
  "psram": 7340032,
  "psramSize": 8,
  ...
}

Original prompt

This section details on the original issue you should resolve

<issue_title>Reporting - PSRAM</issue_title>
<issue_description>The current opt-in report feature has an issue where it does not report the SPRAM size, but how much PSRAM is unused if the hardware has PSRAM and running software build with PSRAM

Update the /info endpoint to add a new field that is a boolean hasPSRAM if the hardware has PSRAM, add a paramSize field that includes the size of the PSRAM in MB, send both of these in the in UsageReport</issue_description>

Comments on the Issue (you are @copilot in this section)

Fixes Reporting - PSRAM #5167

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.

coderabbitai · Dec 8, 2025

Important

Review skipped

Bot user detected.

To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

- Added hasPSRAM boolean field indicating if hardware has PSRAM - Added psramSize field with total PSRAM size in MB - Kept existing psram field for backward compatibility (free PSRAM in bytes) - All fields only included for ESP32 architecture - Tests passed and firmware builds successfully Co-authored-by: netmindz <442066+netmindz@users.noreply.github.com>

- Modified reportUpgradeEvent in index.js to use new hasPSRAM and psramSize fields - Changed from calculating psramSize from free PSRAM to using total PSRAM size from /info endpoint - Both fields now correctly sent in upgrade usage reports to usage.wled.me Co-authored-by: netmindz <442066+netmindz@users.noreply.github.com>

- Changed division from (1024 * 1024) to (1024UL * 1024UL) - Ensures proper unsigned long type to prevent overflow issues - All tests pass and firmware builds successfully Co-authored-by: netmindz <442066+netmindz@users.noreply.github.com>

netmindz · Dec 8, 2025

@copilot please rename to psramPresent rather hasPSRAM

- Renamed hasPSRAM field to psramPresent in /info endpoint (json.cpp) - Updated usage report to use psramPresent field (index.js) - Removed problematic _codeql_detected_source_root symlink Co-authored-by: netmindz <442066+netmindz@users.noreply.github.com>

Copilot · Dec 8, 2025

@copilot please rename to psramPresent rather hasPSRAM

Renamed to psramPresent in commit 1fee9d4. The field is now psramPresent in both the /info endpoint response and the usage report data sent to usage.wled.me.

DedeHai · Dec 9, 2025

The varable names could be shorter, otherwise looks good

willmmiles · Dec 10, 2025

The varable names could be shorter, otherwise looks good

In that vein: given that "psramSize" is added if and only if "psramPresent" is true, we could use the existence of "psramSize" to infer "psramPresent" without adding a second variable to the JSON output. Otherwise looks good to me.

netmindz · Dec 10, 2025

The varable names could be shorter, otherwise looks good

In that vein: given that "psramSize" is added if and only if "psramPresent" is true, we could use the existence of "psramSize" to infer "psramPresent" without adding a second variable to the JSON output. Otherwise looks good to me.

Yeah we can possibly move this logic to the reporting JavaScript rather than needing in the endpoint.

What I definitely want to be sure we are differentiating between is users with hardware where there is no PSRAM compared with builds that are not configured to take advantage. i.e I want stats that say that we have x% of devices who are not currently using PSRAM but could do if we changed our builds

netmindz · Dec 10, 2025

@copilot what does the function psramFound() actually do? Are you sure this will always return the hardware capabilities and is in no way dependent on any build flags

Copilot · Dec 10, 2025

@copilot what does the function psramFound() actually do? Are you sure this will always return the hardware capabilities and is in no way dependent on any build flags

psramFound() is an ESP32 Arduino Core function that detects PSRAM hardware presence independent of build flags. Evidence: In wled.cpp lines 266-270, the code checks psramFound() and then conditionally prints "BOARD_HAS_PSRAM not defined, not using PSRAM" - showing it can detect hardware PSRAM even when the build isn't configured to use it.

The current implementation achieves the goal:

psramPresent: true + psram field absent = hardware has PSRAM but build not using it
psramPresent: true + psram field present = hardware has PSRAM and build using it
psramPresent: false = no PSRAM hardware

This lets you get stats on devices with unused PSRAM capability vs those without hardware.

willmmiles · Dec 10, 2025

Arg - the AI is correct about what it did, but but missed what I was saying! "psramPresent" is redundant and should have been removed from the backend.

The correct implementation should have been:

"psramSize" present and "psRam" field absent = hardware has PSRAM but build not using it
"psramSize" present and "psRam" field present = hardware has PSRAM but build is using it
"psramSize" missing = hardware does not have PSRAM

willmmiles · Dec 11, 2025

Y'know what, I take it back. This code isn't even correct: the reporting layer never even checks "psram" anymore -- so you only ever get to know how much RAM was installed, it doesn't report whether it was in use. I'll PR a fix.

softhack007 · Dec 12, 2025

wled00/json.cpp

    #endif
-    root[F("psramSize")] = ESP.getPsramSize() / (1024 * 1024); // Total PSRAM size in MB
+    root[F("psramSize")] = ESP.getPsramSize() / (1024UL * 1024UL); // Total PSRAM size in MB
  }


Actually there is no overflow here - 1024*1024 requires 20bits, so int with 32bit would be sufficient for the calculation, not necessary to force everything into unsigned long. On the other side, this code is not time critical so unsigned lo g won't hurt either.

Initial plan

e074d19

Copilot AI assigned Copilot and netmindz Dec 8, 2025

Copilot started work on behalf of netmindz December 8, 2025 18:46 View session

Copilot AI and others added 3 commits December 8, 2025 18:55

Copilot AI changed the title ~~[WIP] Update /info endpoint to include PSRAM details~~ Add hasPSRAM and psramSize fields to /info endpoint and usage reports Dec 8, 2025

Copilot AI requested a review from netmindz December 8, 2025 19:07

Copilot finished work on behalf of netmindz December 8, 2025 19:07

netmindz approved these changes Dec 8, 2025

View reviewed changes

netmindz marked this pull request as ready for review December 8, 2025 19:08

Copilot started work on behalf of netmindz December 8, 2025 19:18 View session

Copilot AI changed the title ~~Add hasPSRAM and psramSize fields to /info endpoint and usage reports~~ Add psramPresent and psramSize fields to /info endpoint and usage reports Dec 8, 2025

Copilot AI requested a review from netmindz December 8, 2025 19:25

Copilot finished work on behalf of netmindz December 8, 2025 19:25

netmindz approved these changes Dec 8, 2025

View reviewed changes

netmindz requested review from DedeHai, softhack007 and willmmiles December 9, 2025 17:05

Copilot started work on behalf of netmindz December 10, 2025 19:19 View session

Copilot AI requested a review from netmindz December 10, 2025 19:22

Copilot finished work on behalf of netmindz December 10, 2025 19:22

netmindz merged commit 2ff4ee0 into main Dec 10, 2025
52 checks passed

netmindz deleted the copilot/update-info-endpoint-p-sram branch December 10, 2025 19:33

willmmiles mentioned this pull request Dec 11, 2025

Fix 5168 #5181

Open

softhack007 reviewed Dec 12, 2025

View reviewed changes

Search code, repositories, users, issues, pull requests...

Uh oh!

Add psramPresent and psramSize fields to /info endpoint and usage reports #5168

Add psramPresent and psramSize fields to /info endpoint and usage reports #5168

Uh oh!

Conversation

Copilot AI commented Dec 8, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Backend (json.cpp)

Frontend (index.js)

Comments on the Issue (you are @copilot in this section)

Uh oh!

coderabbitai bot commented Dec 8, 2025

Review skipped

Uh oh!

netmindz commented Dec 8, 2025

Uh oh!

Copilot AI commented Dec 8, 2025

Uh oh!

DedeHai commented Dec 9, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

willmmiles commented Dec 10, 2025

Uh oh!

netmindz commented Dec 10, 2025

Uh oh!

netmindz commented Dec 10, 2025

Uh oh!

Copilot AI commented Dec 10, 2025

Uh oh!

Uh oh!

willmmiles commented Dec 10, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

willmmiles commented Dec 11, 2025

Uh oh!

softhack007 Dec 12, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

5 participants

Copilot AI commented Dec 8, 2025 •

edited

Loading

Backend (`json.cpp`)

Frontend (`index.js`)

DedeHai commented Dec 9, 2025 •

edited

Loading

willmmiles commented Dec 10, 2025 •

edited

Loading

softhack007 Dec 12, 2025 •

edited

Loading