Add adaptive router research section

Clarify bandit selection score labels

Refresh admin UI styling

Gate bandit rewards by signal consumers

Add intent strategy mapping safeguards

Align strategy formats with MVP1 model

Implement DB-first strategy format flow

Research tab: add RL family-tree categorization primer (umbrella -> bandit -> contextual [we are here] / full RL -> RLHF), the one-question axis table, and plain-language where-we-fit. Makes the taxonomy understandable to anyone

Research tab: add Who-uses-what industry usage table (Yahoo/Netflix/Spotify/MS/Google/Meta/LLM labs -> method -> use case) in Industry-context section

Research tab: add prominent Our-unique-approach banner — the bandit x agent-memory x critic fusion (with why each piece is needed)

Research tab: add Which-method-when guide (greedy/UCB/Thompson/contextual/contextual-TS/dueling/RLHF) with problem statement + when-to-use + fit-for-us, a 4-step decision flow, and contextual-TS + TS-tutorial + Chapelle&Li papers. Clarifies we are not UCB-only and the correct method per sub-problem

Add dedicated Research admin tab: validated paper library (foundations->RLHF frontier), Now->Goal flow diagram with data+formula per stage, evolution roadmap to the RLHF preference-brain goal. Move research out of UCB Formula tab (now a focused tuner)

UCB tab: plain-English paper summaries, why-classics-are-old note, and a Recent research (2018-2021) section (NeuralUCB, Neural Thompson, Beyond-UCB, IDS)

Add UCB research basis + paper links and conclusion to the UCB Formula admin tab

Record unmapped-intent suggestions + surface backlog in Admin

Restore warm Claude Desktop palette (was reverted to teal/blue)

Add admin-token auth, security/streaming tests, DB design doc

Unify admin + analytics chrome via shared app-shell stylesheet

Add instruction_quality dashboard — the missing signal consumer

Signal Rules: show LIVE reward numbers from reward_scale config

Add 25-signal catalog (15 atomic + 10 composite) with full UI CRUD

Strategy Performance: rename Cells -> Situations + add column legend

Add UserAutocomplete to admin tabs — fixes filter-by-name

Add Bandit State admin tab — per-user inspection of UCB cells + per-cell reset

Initial commit — APE Modulor for HF Spaces deploy