fix: move CREATE INDEX in vector_store after ALTER TABLE migration

fix: move CREATE INDEX statements after ALTER TABLE migration in memory_store schema to prevent UndefinedColumnError on startup

refactor: centralise all magic numbers into config.py driven by env vars

feat: bi-temporal supersession, scope isolation, configurable threshold, benchmark adapter

Rebrand to Kaal — rename from Chronos OS, add Logo component with serif seal design, swap all Hexagon icons for Logo

Switch agent to GPT OSS 120B — officially recommended Cerebras model for tool-calling agents

Fix Cerebras model ID to llama3.1-70b as 3.3 was deprecated

Switch primary heavy agent model from GLM 4.7 to blazing fast Llama 3.3 70B on Cerebras

Fix router hanging on rate limits by setting max_retries=0 to force instant fallback

Update pricing to premium B2B SaaS tiers: /mo Builder and /mo Scale

Update heavy pipeline to use zai-glm-4.7 and update dashboard display

Revert to Llama 3.3 70B to fix API crash with DeepSeek V3.2

Update DeepSeek model to use explicit cerebras endpoint string

Update heavy pipeline to use DeepSeek V3.2 for optimal reasoning and MoE efficiency

Update heavy pipeline to use GPT-OSS 20B for high efficiency and low token burn

Revert heavy pipeline to Qwen 3 235B on Cerebras

Prioritize Cerebras API over Groq in LLM router for higher limits and speed

Fix: cast agent max_results to integer and cleanup debug logging

CRITICAL FIX: Escape JSON braces in SVO prompt - root cause of 0 events bug

Debug: add step-by-step tracing to SVO parser

Force Docker cache bust v9 + add startup version marker to confirm new code

Fix: Convert all Python to LF line endings + add .gitattributes to prevent CRLF on Linux Docker

Fix: Bulletproof SVO JSON extraction - remove response_format, add 6-layer JSON recovery for Groq output

Fix: Correct LLM router and docs to properly attribute Llama to Groq and Qwen to Cerebras

Auto-retry models on high traffic rate limits

Stability: Groq primary for reasoning + Robust JSON SVO parsing with retries

Fix model ID: Use qwen-3-235b-a22b-instruct-2507 for Cerebras reasoning

Fix: Update LangChain 0.3 imports for ChatLiteLLM

Hotfix: change blocking model async await to a background task so Render port scanner doesn't timeout

Migrate to Vercel Next.js UI Frontend, prune 10x SVO model overhead payload

Migrate: SQLite+ChromaDB → Neon PostgreSQL+pgvector (persistent cloud storage)

10x Code Quality: Fix crash bug, cache LLM singletons, optimize batch inserts, purge stale references

Refactor: Implement LiteLLM Mixture of Agents Orchestration

Initial commit for Chronos OS MVP