[docs] Neutral comments: drop self-promotion framing; describe behaviour, not the model

[ux] Simplify intake credit to 'Made by @helmo for the … Hackathon'

[ux] Move credit to the intake screen only; LinkedIn/HF as logo-icons

[ux] Add discreet credit footer (LinkedIn, Hugging Face, hackathon tag)

[ux] Hide stray 'processing' overlay on recommendation card actions

[assess] Agentic guard against junk/jailbreak input; tidy economic UX

[fix] Give Ollama a real context window (root cause); deterministic weak-check

[fix] Treat chatbot-greeting assessments as weak (use grounded fallback)

[fix] Robust assessment + 2-3 recs + documents progress

[assess] Remove web search entirely (prompt, code, module, test, env)

[fix] Economic recommendations follow the profile, not a hardcoded Gulf list

[fix] Hide doubled 'processing' spinner; never leak @@END / metadata

[fix] Choice controls never toggle visibility; non-signatories not asylum dests

[ux] Permanent fix: reveal controls in a separate round-trip; localise chrome

[ux] Reveal choices in one frame; make assessment always substantive

[ux] Reliably reveal every choice control (fix docs options)

[assess] Honest handling of economic (non-protection) cases

[ux] Show multi-select options instantly (no extra Continue)

[ux] Keep the top nav fixed in place across screen transitions

[ux] Make all phase screens fill the shell at the same width

[ux] Consistent screen width — all phases use 1180px

[ux] Widen the intake screen (was too narrow / mobile-looking)

[ux] Trim site-bar nav + redundant intake tagline

[ux] Trust note: drop the unenforced consent clause

[brand+ux] Rebrand to Fugee, render markdown, branded detailed documents

[assessment] Disable web search; guarantee visible grounded reasoning

[agentic] Ground assessment in UNHCR guidelines via a RAG tool

[fix] CheckboxGroup reveal lag, proceed-button label, LGBTQ legal correctness

[assessment] Don't auto-jump to recommendations — let the person read first

[interview] Restore persecution categories + fix CheckboxGroup reveal lag

[interview] Conditional questions, agentic correction loop, bold review labels

[agentic] LLM labeled review summary, eligibility-aware assessment, control fix

[agentic] Port pi loop hooks + LLM-drafted editable (Word) documents

[fix] Fully-scripted multilingual interview (no LLM) + remove walkthrough chrome

[ui] Mockup chrome: site-bar, per-phase headers, wider layout

[fix] Deterministic slot-filling interview (agentic flow, consistent UI)

[T049-T055 + UX] Phase 5 documents + single-model + responder/UX fixes

[T044-T048 + data] Phase 4 recommendations + real UNHCR stats integration

[T035-T043] Phase 3 — situation assessment (reasoning stream + real tools)

[T030-T034] Phase 2 — intake screen + language selection + theming

[T017-T029] Phase 1 — agent loop + interview core

[T011+] Env config: uv venv, .env loader, remote Ollama host + model

[T001-T016] Phase 0 — project setup: agent loop, state machine, Gradio skeleton