Starstruk Logo MarkStarstruk

v3.5.0

DocumindHQ/documindv3.5.0May 28, 2026by assafelovic

AI Summary

A massive update introducing new AI models and retrievers, alongside critical bug fixes for LLM output parsing, configuration handling, and token limits to support modern long-output models.

Key Highlights

  • Added ModelsLab image generation provider and OpenAlex retriever.
  • Fixed NameError for STRATEGIC_LLM and resolved import issues in websocket manager.
  • Added support for custom Mistral-compatible endpoints via MISTRAL_BASE_URL.
  • Increased max_tokens cap from 32k to 200k for modern long-output models.
  • Added LLM cost change analysis and tracking for Anthropic usage.

New Features

  • ModelsLab image generation provider
  • OpenAlex retriever
  • Agent Discovery Protocol manifest endpoint

Full Release Notes

Massive update across the stack with critical bug fixes and performance improvements including addition to new models and retrievers. Thanks to the amazing community for pushing this!

## What's Changed
* feat: add ModelsLab image generation provider by @adhikjoshi in https://github.com/assafelovic/gpt-researcher/pull/1647
* fix: NameError when STRATEGIC_LLM lacks colon separator (#1673) by @sudabg in https://github.com/assafelovic/gpt-researcher/pull/1679
* fix: properly resolve report_type imports in websocket_manager and re… by @varadfromeast in https://github.com/assafelovic/gpt-researcher/pull/1740
* Fix: resolve unhashable dict error in detailed report context deduplication by @3mk4yl in https://github.com/assafelovic/gpt-researcher/pull/1700
* Add Codex CLI plugin manifest by @internet-dot in https://github.com/assafelovic/gpt-researcher/pull/1721
* fix: eliminate process-level env pollution from MCP retriever setup by @octo-patch in https://github.com/assafelovic/gpt-researcher/pull/1742
* feat(cli): generate filename from LLM and add YAML frontmatter for re… by @VVjwell in https://github.com/assafelovic/gpt-researcher/pull/1743
* feat: add OpenAlex retriever by @CuiweiG in https://github.com/assafelovic/gpt-researcher/pull/1748
* feat(server): add Agent Discovery Protocol manifest endpoint by @zhao0112 in https://github.com/assafelovic/gpt-researcher/pull/1749
* fix: truncate document content to prevent embedding token limit errors by @octo-patch in https://github.com/assafelovic/gpt-researcher/pull/1750
* fix: support MISTRAL_BASE_URL env var for custom Mistral-compatible endpoints by @octo-patch in https://github.com/assafelovic/gpt-researcher/pull/1754
* Add LLM cost change analysis to CI by @Jwrede in https://github.com/assafelovic/gpt-researcher/pull/1761
* chore: fix some typos across codebase by @box4wangjing in https://github.com/assafelovic/gpt-researcher/pull/1768
* Limit multi-agent human plan revisions by @CalibratedGhosts in https://github.com/assafelovic/gpt-researcher/pull/1769
* fix(deep_research): parse LLM output with json_repair + regex fallback by @RomainROCH in https://github.com/assafelovic/gpt-researcher/pull/1773
* fix(llm): raise max_tokens cap from 32k to 200k for modern long-output models by @RomainROCH in https://github.com/assafelovic/gpt-researcher/pull/1775
* Fix incorrect config file path in Chinese README by @wesssI in https://github.com/assafelovic/gpt-researcher/pull/1779
* fix(retrieval): send Brave snippets to scraper by @RomainROCH in https://github.com/assafelovic/gpt-researcher/pull/1780
* feat(cost): track Anthropic usage from native metadata by @RomainROCH in https://github.com/assafelovic/gpt-researcher/pull/1781

## New Contributors
* @adhikjoshi made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/1647
* @sudabg made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/1679
* @varadfromeast made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/1740
* @3mk4yl made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/1700
* @internet-dot made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/1721
* @VVjwell made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/1743
* @CuiweiG made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/1748
* @zhao0112 made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/1749
* @Jwrede made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/1761
* @box4wangjing made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/1768
* @CalibratedGhosts made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/1769
* @RomainROCH made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/1773
* @wesssI made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/1779

**Full Changelog**: https://github.com/assafelovic/gpt-researcher/compare/v3.4.4...v3.5.0