Commit History

  1. fix: normalize search_volume (int→str), relevance (float→int), competition (lower→Title), post_count (int→str) for LongCat API responses

    3ef98d0
  2. fix: add catch-all viral_hashtags mapping at end of cross_map_fields to catch hashtags set by platform-specific mappers

    2680851
  3. fix: add generic cross-map fields (core_keywords, viral_hashtags, strategy_tips, content_titles) to all platform response models so they survive FastAPI's response_model filter

    91c8715
  4. fix: add Pinterest cross-maps for core_keywords, content_titles, hashtags, strategy_tips

    504cc76
  5. fix: handle model returning dict instead of list for tweet_threads/post_drafts/post_ideas/video_concepts

    468fc59
  6. feat: Add LinkedIn API posting + enhanced analyzer + schema

    639b959
  7. feat: Add LongCat API as primary model with Qwen fallback + cross-map fix

    249b12a
  8. fix: Add Instagram cross-maps for hashtag_sets/captions/content_ideas

    43bad80
  9. fix: Run cross-map after defaults so LLM-sparse responses still get mapped

    0054399
  10. fix: Add core_keywords and related_phrases cross-mapping from tags/video_titles

    2eb9ab6
  11. fix: Cross-map platform keys to generic keys for frontend template

    ae74dac
  12. fix: Improve prompts to return JSON object, add error for list response

    5b10e71
  13. fix: Add error message when LLM returns list instead of dict

    a4fce70
  14. fix: Escape curly braces in f-string causing Invalid format specifier

    c19bbb8
  15. fix: Guard against LLM returning JSON array instead of object

    2cf0f7b
  16. fix: Add missing validate_and_fill_data_defaults function

    758a047
  17. fix: Catch normalize/validate errors, hide raw JSON parse errors againe

    e22a390
  18. fix: Catch normalize/validate errors, hide raw JSON parse errors

    4a774c4
  19. feat: Multi-platform batch generation + simple UI⁠

    91bd745
  20. feat: Simple HTML frontend with section copy buttons⁠

    a1f2a19
  21. fix: Handle missing correction fields + ResponseValidationError

    c4fea6f
  22. feat: Add Grammar Correction API v2.1.0⁠

    ff08af5

  1. fix: Add normalize_response to handle model output format mismatches⁠

    e1cb6ad
  2. perf: Reduce max_new_tokens 1500→800, cut output by 50% for faster CPU inference⁠

    b0fb0e7
  3. fix: Raise HTTPException for unexpected errors instead of returning invalid dict⁠

    0ca65c8
  4. feat: Add 3-tier quantization with auto hardware detection⁠

    efb4fe4
  5. fix: Simplify prompts for 0.5B model reliability + resilient error handling⁠

    6e467d1

  1. feat: Add multi-platform social media analysis with 7 platform-specific endpoints⁠

    38098b4

  1. Add GPU Setup Cheat Sheet for RTX 4050

    30aa031
  2. Add documentation for running on RTX 4050 6GB

    2caec2a
  3. Update docs to reflect Qwen-0.5B Local CPU architecture

    bb2afa9
  4. Add Schema Validation Safety Net: Auto-fill missing JSON fields with defaults

    c31af39
  5. Fix JSON Crash: Lower Temp to 0.3 + Enhance Repair Logic + Add Error Fallback

    fdbd75a
  6. Switch to Qwen-0.5B (Nano) for instant speed and 100% stability

    f169fdd
  7. Optimize for Speed: 30 Keywords / 1500 Tokens to stop Local CPU Timeout

    99776a0
  8. Reduce to 50 keywords to prevent CPU Timeout (Internal Server Error)

    4d779c6
  9. Scale up to 150 keywords using Local Inference

    9a256bc
  10. Migrate to Local Inference (Qwen-1.5B) to permanently bypass API limits: Re-added Torch/Transformers

    50196f5
  11. Switch to SmolLM2 (HF Native) to resolve provider support issues

    e7e750b
  12. Switch to Qwen-1.5B (Lightweight) to fix all API limits

    24ee997
  13. Switch to Google Gemma-2-9B-IT for dependable serverless support

    ddcd3d9
  14. Fix NameError and Switch to Phi-3-Mini to bypass 402 Payment Limits

    3509502
  15. Fix truncation error: Reduce to 50 keywords + JSON repair logic

    7252943
  16. Increase keyword limit to 150 and max_tokens to 8000

    394498e
  17. Extend output: 10 keywords/hashtags + add Content Titles

    e8267ad
  18. Update docs with A-Z guide for Qwen Model

    d68c4e0
  19. Update prompts for stronger SEO data extraction

    3d17470
  20. Switch to Qwen/Qwen2.5-7B-Instruct for reliable availability

    1b66ca1
  21. Switch to Zephyr-7B-Beta for Chat API compatibility

    ad41aff
  22. Fix API method: Use chat_completion for Mistral Instruct

    d877e39