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

[deploy] Modal-hosted Ollama backend + remote auth headers

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

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

[docs] Brand the Word (.docx) output to match the PDF template

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

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

[docs] Bundle Inter + Fraunces locally — offline PDF generation

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

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

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

[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)

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

[T006] Loop: gracefully degrade when model rejects `think` param

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