Skip to content

Latest commit

 

History

History
530 lines (362 loc) · 16.6 KB

File metadata and controls

530 lines (362 loc) · 16.6 KB

Changelog

All notable changes to this project will be documented in this file.

The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.

Fixed

  • 👷(ci) pull the MinIO images from quay.io instead of Docker Hub
  • 🐛(ci) fix the CHANGELOG check failing when a pull request is opened
  • 🐛(back) replace whitenoise with servestatic for async-capable serving

0.0.24 - 2026-09-08

Fixed

  • 🐛(front) fix translation hide source

0.0.23 - 2026-09-07

Added

  • 💄(settings) move analytics settings to general
  • 📈(posthog) track projects, Docs export, summarization and co2 footprint
  • 👷(ci) audit GitHub Actions workflows with zizmor on push and pull request
  • 🔒️(back) throttle conversation and project creation per user
  • 🚸(front) explain the wait when a creation rate limit is reached

Changed

  • ⬆️(back) migrate to pydantic-ai 2.x
  • 🏗️(front) migrate the frontend from Next.js to Vite and React Router
  • 🏗️(front) rename frontend build var from the NEXT_PUBLIC_ prefix to VITE_
  • 💬(back) rewrite the default agent instructions and tool descriptions
  • 💄(front) correct icon Docs button
  • ♻️(back) use httpx as the single HTTP client for outbound calls
  • ⬆️(back) update django, pypdf, sqlparse and pydantic-settings
  • 🔒️(ci) pin CI actions and installed packages to immutable versions
  • ⚡️(ci) run e2e tests in parallel across browsers and shards
  • ✨(back) sort conversations by stored size in the admin list
  • 🚸(back) show 200 conversations per admin list page for bulk actions
  • ♻️(back) split the settings module into per-domain configuration mixins
  • ⬆️(chat) upgrade the Vercel AI SDK from v4 to v5

Fixed

  • 🐛(front) fix the frontend dev container failing to start
  • 🐛(back) read the OIDC_CREATE_USER setting from its documented env var

Removed

  • 🔥(back) remove the unused Albert web search manager and its tool
  • 🔥(back) remove the unused RAG_WEB_SEARCH_PROMPT_UPDATE setting
  • 🔥(back) remove the unused Tavily web search tool
  • 🔥(back) remove the activation code gate, keeping past records for history
  • 🔥(back) remove the unused text streaming protocol

0.0.22 - 2026-08-10

Added

  • ✨(conversation) summarize messages

Changed

  • ⚡️(back) add users to the Brevo follow-up list only at signup
  • ✨(back) list conversation files on the admin conversation page
  • ⚡️(back) speed up the admin conversation list page
  • ♻️(back) parse PDFs through the current Albert OCR endpoint
  • ⬆️(dependencies) update dependencies and pin CVE-affected packages

Removed

  • 🔥(back) remove the unused Albert RAG document search module

0.0.21 - 2026-07-28

Changed

  • ⬆️(dependencies) update pypdf and next

Fixed

  • 🐛(back) align Albert RAG document upload and search with the current API

0.0.20 - 2026-07-23

Added

  • 💄(front) add tooltip co2
  • ✨(back) add slide deck generation tool
  • ✨(back) add model fallback mechanism
  • ✨(back) add celery for running background tasks
  • 🧱(helm) add celery worker and beat deployments
  • ✨(front) add "Edit in Docs" action to export a message to Docs
  • 🔒(back) guard parsing against decompression bombs and oversized PDFs

Changed

  • ♻️(back) split chat views and replace hardcoded strings with constants
  • 💄(front) change 404 illustration
  • ✨(back) process project files asynchronously with indexing state
  • ⚡️(back) process conversation files asynchronously off the request worker
  • ⬆️(dependencies) update dependencies and pin CVE-affected packages
  • ♻️(front) consolidate input chat banners into a reusable component
  • ⬆️(dependencies) drop unused pydantic-ai extras
  • 💬(back) use a generic localised timestamped title for Docs exports
  • ⬆️(front) pin sharp to a libvips patched against GHSA-f88m-g3jw-g9cj

Fixed

  • 🐛(front) prevent app crash for users without a full name or email
  • 🐛(front) refresh the conversation title in the collapsed left panel

Removed

  • 🔥(back) remove the Find RAG backend and its FIND_API_* settings

0.0.19 - 2026-06-24

Changed

  • 🔧(dependencies) bump backend to Python 3.14 and update pinned dependencies
  • ⬆️(dependencies) update front and mail dependencies
  • ♻️(front) source the home documentation link from config
  • 💄(front) use "L'Assistant" as the default product name

Fixed

  • 🐛(front) keep the app open when using the contact link
  • 💄(front) use semantic warning color for banner icon
  • ✨(back) handle 404 during deletion as successful de-indexing

0.0.18 - 2026-06-12

Added

  • ✨(back) add cron job to poll Albert models health
  • ✨(back) de-index inactive collections and reindex in conversation
  • ✨(back) rate-limit chat with a model-health-aware token cooldown
  • ✨(backend) add sliding window history processor
  • ✨(banner) add dynamic health banners
  • ✨(frontend) display specific error when document parsing fails

Changed

  • 🧱(helm) bump chart to v0.0.6
  • 🚸(front) replace help button with a dropdown menu
  • 🔒️(back) restrict sign-in to users with an allowed OIDC role
  • ♻️(back) rename model health status "orange" to "yellow"
  • 🚸(front) explain the attachment size limit when an upload fails

Fixed

  • 🐛(helm) stop job pods from matching the backend disruption budget
  • 🐛(front) use the browser language for the default UI on first load
  • 💄(settings modal) updated the settings modal size

0.0.17 - 2026-06-02

Added

  • ✨(maintenance) add maintenance mode

Changed

  • 🔒️(front) disable yarn install scripts in docker build
  • ⬆️(dependencies) update back and front dependencies
  • 🚸(back) improve chat admin filtering, search and display columns

Fixed

  • 🐛(backend) remove user list endpoint

Added

  • ✨(frontend): display specific error when LLM provider is down

0.0.16 - 2026-05-21

Added

  • ✨(sources) add source panel
  • ✨(onboarding) add onboarding modal
  • ✨(back) add ODT parsing support
  • ✨(back) add self-documentation tool
  • ✅(front) add tests for SourceItem component
  • ✨(documents) make document context hybrid
  • 🐛(fix) add prevent_url_hallucination instruction to ConversationAgent
  • ✨(projects) handle project files for RAG search
  • ✨(banner) configurable banner with level, title, content and start/end

Changed

  • ✨(settings) new settings modal
  • ✨(front) allow typing while LLM is generating a response
  • 🐛(fix) source links should open a new tab
  • 💄(ui) codeblock light mode
  • ⬆️(dependencies) update back and front dependencies
  • 💄(ui) new header
  • ✨(back) add debug mode setup for local development
  • ⬆️(dependencies) update pydanticai and related dependencies
  • ⚙️(back) get carbon data from albert api provider
  • ✨(tools): update descriptions
  • ✨(auth) add silent OIDC login
  • ⬆️(back) upgrade lxml and pypdf
  • ✨(back) set allow_smart_web_search to False for all users
  • ✨(back) make allow_conversation_analytics user setting readonly in admin
  • 🚸(front) switch to new conversation when creating a project

Fixed

  • 💬(onboarding) fix wording step 1 img
  • 🐛(fix) new conversation in project button max size
  • 💄(ui) little fix margin top
  • 💄(ui) review ui for part of the project
  • 🐛(fix) Fix streaming crash with OpenAI-compatible APIs
  • 🐛(fix) strip thinking part for models without reasoning support
  • ✨(dev) setup Tilt for local development
  • 🐛(front) project modal now respects document-upload feature flag
  • 🐛(back) self-doc tool no longer triggers on generic or document questions
  • 🐛(backend) improve url hallucination instruction

0.0.15 - 2026-03-31

Added

  • ✨(back) add projects with custom LLM instructions
  • ✨(front) projects management UI
  • 🥚(front) add April Fools day prank

Changed

  • ⬆️(dependencies) upgrade Next.js 15 to 16, upgrade python dependencies
  • ✨(front) rich text copy for Word/Docs paste

Fixed

  • 🐛(back) add missing color option for project colors
  • 💄(project) ui fix project
  • 💄(ui) ui fix button css
  • 💄(ui) ui fix model selector css

0.0.14 - 2026-03-11

Added

  • ✨(user) allow disabling automatic internet search
  • ✨(search) add searchModal and modify leftPanel
  • ✨(waffle) hide the waffle if not fr theme
  • ✨(front) allow pasting an attachment from clipboard
  • ✨(array) temporarily adjust array

Changed

  • ⚡️(front) optimize streaming markdown rendering performance
  • ⬆️(back) update pydantic-ai
  • ♻️(chat) refactor AIAgentService for readability and maintainability
  • 🚸(oidc) ignore case when fallback on email #281
  • ⬆️(back) update pillow, django-pydantic-field, pypdf
  • ♻️(front) migrate from ESLint 8 to ESLint 9 flat config
  • ⬆️(back) update django and pypdf

Fixed

  • 💚(docker) vendor mime.types file instead of fetching from Apache SVN
  • 🚑️(back) fix mime type for pptx
  • 🐛(front) fix math formulas and carousel translations
  • 🐛(helm) reverse liveness and readiness for backend deployment
  • 🐛(front) fix dark mode styling on chat messages
  • 🐛(front) fixed inverted toast for setting changes

0.0.13 - 2026-02-09

Added

  • 💄(front) ui fix : update ui-kit
  • ✨(front) add persistent darkmode
  • ✨(front) add ui kit #240
  • 🧱(files) allow to use S3 storage without external access #849
  • ✨(backend) add FindRagBackend #209
  • ⬆️(back) update dependencies
  • ✨(back) use adaptive parsing for pdf documents

Changed

  • 💄(darkmode) change color feedback button
  • 🏗️(back) migrate to uv
  • ♻️(front) optimize syntax highlighting bundle size

Fixed

  • 🐛(back) cast collection Ids to API expected types

0.0.12 - 2026-01-27

Fixed

  • ⚡️(front) performance improvements on chat input
  • 💄(front) i18n and standardize pdf parsing display

Removed

  • 🔥(chat) consider PDF documents as other kind of documents #234

0.0.11 - 2026-01-16

Changed

  • 📦️(front) update react
  • ✨(chat) generate and edit conversation title

Fixed

  • 🐛(e2e) fix test-e2e-chromium
  • 🐛(back) fix system prompt compatibility with self-hosted models #200
  • ⚰️(back) remove dead code and unused files
  • 🐛(back) prevent tool call timeouts

Removed

  • 🔥(chat) remove thinking part from frontend #227

0.0.10 - 2025-12-15

Added

  • ✨(front) add retry button

Fixed

  • 🐛(front) fix long user messages
  • 🐛(front) fix "Maximum update depth exceeded" error in Chat component
  • 🐛(front) fix parsing documents display
  • 🐛(front) fix opacity input in error
  • 🐛(front) resolve React hydration errors
  • 🚑️(user) allow longer short names #182

0.0.9 - 2025-11-17

Added

  • ✨(front) add code copy button
  • ✨(RAG) add generic collection RAG tools #159

Fixed

  • 🔊(langfuse) enable tracing with redacted content #162

0.0.8 - 2025-11-10

Fixed

  • 🦺(front) Fix send prohibited file types
  • 🐛(front) fix target blank links in chat #103
  • 🚑️(posthog) pass str instead of UUID for user PK #134
  • ⚡️(web-search) keep running when tool call fails #137
  • ✨(summarize): new summarize tool integration #78

Removed

  • 🔥(posthog) remove posthog middleware for async mode fix #146

0.0.7 - 2025-10-28

Fixed

  • 🚑️(posthog) fix the posthog middleware for async mode #133

0.0.6 - 2025-10-28

Fixed

  • 🚑️(stats) fix tracking id in upload event #130

0.0.5 - 2025-10-27

Fixed

  • 🚑️(drag-drop) fix the rejection display on Safari #127

0.0.4 - 2025-10-27

Added

  • ♿️(a11y) improve accessibility #135
  • 🌐(i18n) add dutch language #117

Changed

  • ⚡️(asgi) use uvicorn to serve backend #121

Fixed

  • 🐛(front) fix mobile source
  • 🐛(attachments) reject the whole drag&drop if unsupported formats #123

0.0.3 - 2025-10-21

Fixed

  • 🚑️(web-search) fix missing argument in RAG backend #116

0.0.2 - 2025-10-21

Added

  • ✨(front) add drag'n drop file
  • ✨(activation-codes) register users also on Brevo #98
  • 📈(posthog) add sub field to tracking #95

Changed

  • 🔧(front) change links feedback tchap + settings popup
  • 🐛(front) code activation fix session end #93
  • 💬(wording) error page wording #102
  • ⚡️(web-search) allow to override returned chunks #107
  • 🐛(activation-codes) create contact in brevo before add to list #108
  • ⚗️(summarization) add system prompt to handle tool #112

0.0.1 - 2025-10-19

Changed

  • 🎨(front) activation page footer
  • 👷(front) change size small modal
  • 🎨(front) retour ui global
  • 👷(front) fix button scrollDown
  • 💥(front) disable input when error occurred
  • 👷(front) fix scroll
  • 🐛(front) fix left panel status + fix scroll
  • 🐛(llm) add is_active field and persist chat preference
  • ✨(frontend) add LLM selection in chat input #53
  • 🎨(front) fix width chat container
  • 🎨(front) fix width chat container #55
  • 🐛(front) fix button search web on new conversation
  • 🎨(front) improvement search input scroll
  • ✨(404) fix front 404 page
  • ✅(chat) add frontend feature flags #29
  • 🎨(front) change list attachment in chat
  • 🎨(front) move emplacement for attachment
  • 🎨(ui) retour ui sources files
  • ✨(ui) fix retour global ui
  • 🐛(fix) broken staging css
  • 🎨(alpha) adjustment for alpha version
  • ✨(ui) delete flex message
  • ✅(front) add enabled/disabled conversation analysis
  • 🎨(front) amelioration chat ux
  • 🎨(front) global layout modification
  • ✨(front) global layout UI
  • ♻️(chat) rewrite backend using Pydantic AI SDK #4
  • 🗃️(chat) enforce messages stored JSON format #6
  • 🐛(chat) UI messages must have a unique identifier #6
  • ✨(llm) allow configuration from JSON file #22
  • 💥(agent) replace routing w/ tool calls #40
  • 🧱(storage) upload the user documents into S3 #86

Added

  • 🎉(conversations) bootstrap backend & frontend #1
  • ✨(web-search) add RAG capability to do web search #7
  • ✨(chat) add document RAG on document uploaded by user #8
  • ✨(backend) allow use to stop conversation streaming #14
  • 🐛(agent) add the current date in the system prompt #18
  • ✨(backend) add feature flags from posthog #13
  • ✨(user) allow to use conversation data for analytics #23
  • ✨(chat) enforce response in user language #24
  • 📈(langfuse) add light instrumentation #26
  • 🚑️(agent) allow Mistral w/ vLLM & tools #36
  • ✨(web-search) add Brave search tool #47
  • ✨(models) add mistral support & customization #51
  • 🐛(web-search) add summarization to Brave results #58
  • ✨(langfuse) allow user to score messages from LLM #6
  • ✨(onboarding) add activation code logic for launch #62
  • 💄(chat) add code highlighting for LLM responses #67
  • 🔧(evals) add run_evals management command