Bug Fixes & Improvements

[valentinfrlch]

v1.5.2 Release Notes

⚠️ Please read the breaking changes before updating!

This update includes bug fixes and performance improvements.

Contributors

A huge thank you to our contributors @TheRealFalseReality, @bekdan1988, @alemuro, and everyone who helped test the pre-release versions!

⚠️ Breaking Changes

In our previous release (1.5.1), we moved snapshots to /config/media/llmvision/snapshots. This change caused issues for some users who were using other integrations that depend on the /media directory. As a result, the snapshots directory is moving again to /media/llmvision/snapshots.

What this means for you:

• Existing snapshots will automatically migrate to the new location when you restart after upgrading to 1.5.2.
• Remove the media folder configuration that you may have added to your configuration.yaml

  homeassistant:
    media_dirs:
      llmvision: /config/media/llmvision # Remove this line
      media: /media # Remove this line

• If you have any custom automations that use snapshots, update your template to:
  {{ response.key_frame.replace('/media','/media/local') }}
• If you use the Timeline Card, make sure to update it as well!

I apologize for any inconvenience this causes!

Integration

🌐 Languages

• Support for Hungarian language: Added 🇭🇺 Hungarian translations. (by @bekdan1988)
• Support for Catalan language: Added Catalan translations. (by @alemuro)

🔧 Improvements & Fixes

• Improved keyframe selection: Keyframe should now show the detected object more reliably. (by @valentinfrlch)
• Timeline events not deleted: Fixed a bug that caused events not being deleted properly. (by @valentinfrlch)
• Anthropic fix: Fixed an issue that caused validation to fail for the Anthropic provider. (Cannot create Anthropic provider – always “Invalid API key” #475) (by @valentinfrlch)
• Reduced image pipeline latency: Frames are now stored directly in memory instead of in a temporary directory. This reduces disk wear and reduces latency caused by I/O operations. It also fixes a race condition when running multiple actions in parallel. (Parallel video analyzer actions failing #505, VideoAnalyzer: FFmpeg failed with return code 183 doesn't trigger a retry #510) (by @valentinfrlch)
• Moved Timeline snapshots: Snapshots are now stored securely behind Home Assistant authentication in /media. LLM Vision will attempt to migrate your previously captured snapshots to the new folder. (by @valentinfrlch)
• System Prompts: System prompts are now injected as actual system messages for every provider, which should improve their effectiveness. Also try out the updated default system and title prompts. (by @valentinfrlch)
• max_tokens now optional: max_tokens is now an optional parameter. Newer models use tokens for reasoning, which could result in empty responses if max_tokens was set too low. (by @valentinfrlch)

Blueprint

Make sure to update the blueprint by re-importing it!

A huge thank you to @TheRealFalseReality for maintaining the blueprint!

🔧 Improvements & Fixes

• New media folder: Updated all key_frame paths to match new media path. (by @TheRealFalseReality)

---

This discussion was created from the release Bug Fixes & Improvements.

[pluusla]

Thank you for the update!

Unfortunately, I’m still unable to re-import the blueprint. I keep getting the following error message:

[546294708832] Error handling message: mapping values are not allowed here in "<unicode string>", line 124, column 68: ... er of tokens to generate. **Note: Newer and reasoning models may ... ^

Do you have any idea what might be causing this YAML parsing issue?

[yarafie]

Took a quick look at it and that line 124 needs to be between quotes.

description: Maximum number of tokens to generate. Note: Newer and reasoning models may require significantly more tokens. At least 5000 is recommended.

needs to be

description: "Maximum number of tokens to generate. Note: Newer and reasoning models may require significantly more tokens. At least 5000 is recommended."

[TheRealFalseReality]

Oh wow, dunno how that slipped past me. I pushed the fix.

[valentinfrlch]

That might have been my fault. I simply copy pasted the beta into the main blueprint. Thanks for fixing it so quickly @TheRealFalseReality!

[Anto79-ops]

hello, does the blueprint prompt support templating, like sensor states?

thanks

[TheRealFalseReality]

It does

[TheRealFalseReality]

Well, it should, I have not tested that yet. Please let me know if it works

[Anto79-ops]

sorry, I ended making an automation for what I needed and not use the blueprint in this case.

[ziptbm]

Can the documentation be updated to properly show how this should be configured correctly with Open WebUI given the changes?

I made changes at v1.5.1 to make it work and it was, but now I've tried to revert and been unable to undo what I did previously. I need more time to dig into it, but I haven't yet figured out how to what the configuration was two builds ago so it works again. I'm getting errors like:

"couldn't generate content. Check logs for details."

And in the logs I'm getting "Login attempt or request with invalid authentication from 10.0.2.20 (10.0.2.20). Requested URL: '/media/local/llmvision/snapshots/9d77ad4d-0.jpg"

This is what's in my configuration.yaml and I have updated the BP and reloaded the connections to Open WebUI to make sure it still works.

homeassistant:
  customize: !include customize.yaml
  allowlist_external_dirs: 
    - /config
    - /media
#  media_dirs:
#    llmvision: /config/media/llmvision

[justfalter]

@valentinfrlch Thank you very much for the continued work on this project!

I should say that I almost clicked upgrade without reading the release notes, as the version bump from 1.5.1 to 1.5.2 initially led me to believe the update contained inconsequential bug-fixes.

I wonder if you are familiar with semantic versioning (semver) at all? As a software engineer, As a software engineer, I have found semver be extremely useful for communicating the impact of individual releases, whether they be breaking changes, new features, or bug fixes. At the end of the day, a major-version bump for breaking changes signal to users that they should carefully read release notes before upgrading and help reduce user complaints about xyz HA addon/extension/etc "suddenly breaking for no reason".

From the semver.org website:

Given a version number MAJOR.MINOR.PATCH, increment the:

1. MAJOR version when you make incompatible API changes
2. MINOR version when you add functionality in a backward compatible manner
3. PATCH version when you make backward compatible bug fixes
   Additional labels for pre-release and build metadata are available as extensions to the MAJOR.MINOR.PATCH format.

Thank you again for your efforts on this project!

[valentinfrlch]

Thanks for the feedback! I thought I was, but clearly I’ve misunderstood some part. I’ll pay closer attention going forward!