Skip to content

Releases: tvcnet/social-toolkit

v4.9.0 - Modular Architecture

21 Mar 20:54
@tvcnet tvcnet
v4.9.0
92b69db

Choose a tag to compare

View all tags
v4.9.0 - Modular Architecture Latest
Latest

This release modularizes the TVCNet Social Toolkit architecture for better maintainability and performance.

Highlights

  • Consolidated Platform Registry: Added TST_PLATFORMS to tst-config.js for single-source-of-truth configuration.
    • AI Service Call Dispatcher: Unified the AI provider calls into a single dispatcher method.
    • History & Schedule Modules: Extracted post history and content calendar management into dedicated domain modules.
    • Sanitized Activity Logs: Fixed Alpine.js duplicate key issues by re-keying logs at load-time.
Assets 2
Loading

v4.7.8 - Critical Prompt Construction Fix

21 Mar 00:08
@tvcnet tvcnet
v4.7.8
d3a564b

Choose a tag to compare

View all tags
v4.7.8 - Critical Prompt Construction Fix

Fixed

  • Critical Prompt Construction Bug: Fixed a destructuring mismatch in buildPrompt() where platform was always undefined (the Alpine component uses selectedPlatform). This caused the entire structured prompt - 5 W's, platform guide, tone, length, image context, and character limit rules - to be skipped, sending only a generic fallback string to the AI. Most visibly, when photos were attached, the AI would generate posts based solely on the image with no text context.

Impact

This fix restores the full prompt pipeline for all four AI providers (Claude, OpenAI, Gemini, Ollama). Posts will now correctly incorporate all user inputs, platform-specific writing guides, and image context instructions.

Loading

v4.7.7 - Multimodal Vision, Bug Fixes & Code Quality

20 Mar 00:17
@tvcnet tvcnet
v4.7.7
39c68c3

Choose a tag to compare

View all tags
v4.7.7 - Multimodal Vision, Bug Fixes & Code Quality

What's New in v4.7.7

Multimodal (Vision) AI Support

All four AI providers (Claude, OpenAI, Gemini, Ollama) now officially support sending uploaded images alongside the text prompt. When photos are uploaded, the prompt engine automatically injects visual analysis instructions - enabling more visually relevant, engaging posts.

Polishing UX Transparency

When a generated post exceeds a platform's character limit and requires a second API pass, the loading message now explicitly shows "Polishing text to fit platform limits..." instead of random loading phrases, giving users clear transparency about the delay.

Code Quality Improvements

  • Namespaced Utilities: Consolidated loose global functions (tstStripLinks, tstStripMarkdown, tstSanitize) into a modular TST_Utils namespace object.
    • Declarative Alpine.js Keyboard Shortcuts: Replaced imperative document.addEventListener bindings with idiomatic @keydown directives on the <body> element, fixing an invalid .cmd modifier.
    • Escape Key Enhancement: Escape now cascades - closing the Settings modal first, then the Help modal.

Bug Fixes

  • Critical: Prompt Length Instruction Bug - Fixed a bug where the AI was never receiving the "CONCISE", "BALANCED", or "DEEP DIVE" content length instruction due to destructuring length instead of contentLength.
    • Word Count Edge Case - Fixed wordCount calculation where empty/whitespace-only responses displayed "1 word" instead of "0 words".

Files Changed (8)

tvcnet-social-toolkit.html, social-toolkit.js, tst-utils.js, tst-services.js, tst-content.js, tst-config.js, CHANGELOG.md, README.md

Loading

v4.7.6: Documentation & Asset Synchronization

18 Mar 23:57
@tvcnet tvcnet
v4.7.6
9715033

Choose a tag to compare

View all tags
v4.7.6: Documentation & Asset Synchronization

This release synchronizes the project versioning, updates asset cache-busting, and refines the platform help documentation. Includes new 'Post Directly' indicators and footer link updates.

Loading