Defer thinking indicators until backend reports selected advisors

Stream selected advisors so thinking indicators only show the chosen 3

Restore header advisor dropdown and honor active_advisor selection in chat-stream.

Wire LLM failover for the BrainForge Cybersecurity endpoint

Fix LLM chat startup and polish cybersecurity advisor UI.

Restore cybersecurity user profile UX and personalize advisor responses

Add Cybersecurity Advisor Canvas on FEAT_CybersecurityCanvas

Enhance LaTeX editing capabilities in Canvas

Refactor Canvas components and enhance user experience

Enhance Canvas sidebar and deliverables functionality

Enhance deliverables functionality and UI

Merge remote-tracking branch 'origin/main' into feat/Canvas-Upgrades

Enhance UI and functionality across components

Draft 1

Draft 1

Add User Guide (#53)

Support Voice Interaction (#32)

UI: sidebar redesign + chat header signout cleanup (#56)

Add Neon AI Branding (#15)

Fix bug around chat deletion (#54)

Feat/persona avatars (#43)

Fix/dup first message (#44)

Feat/advisor tools (#38)

Feat/vllm endpoints (#36)

Stream LLM Responses (#18)

Refactor chat UI layout (#19)

fix: correct home navigation logout and improve Home button (#11)

Add configuration support (#3)

add footer

fix conflicting css rules

Merge pull request #78 from sohank-17/sohank-fix_responses

fix canvas button

fix state management

Response formatting fix

bug fix

update canvas

canvas code

add code and props for canvas

update environment variables

fix data mismatch

fix document session id error

bug fixes

add document auth

mobile layout fixes

update sidebar props

update mobile toggle

fix response formatting

add chat specific context

change advisors info

fix export bug