fix: magi_clarify now emits magi_done (prevent UI freeze), Caspar R1 3-attempt retry, all join(timeout=5)->30

feat: parse and forward debate_rounds from frontend to run_magi

feat: add debate_rounds param (1-round or 2-round), fix dynamic rounds selection

feat: 2-round debate + PE upgrade + token limits expanded

fix: CASPAR all modes use background thread + keepalive to prevent Nginx timeout

fix: raise all agent max_tokens to 32000 (DeepSeek/Grok/Claude), remove artificial output token limits

fix: max_tokens 8000->16000 to prevent CASPAR truncation; fix mode routing for admission probability queries

fix: replace SSE comment ping with real data events (magi_keepalive), reduce interval to 5s to prevent Nginx proxy_read_timeout cutting Caspar stream and causing missing magi_verdict

feat: activate ps_distillation_kb_v4 RAG + add essay_review mode

fix: add UChicago/MIT/Stanford hardcoded round rules + dynamic mode UI labels

fix: stream Caspar content delta + local accumulation + remove double-buffering

fix: use async generator for true SSE streaming (no buffering)

feat: upgrade Caspar system prompts (planning+evaluation) - remove word limit, require full MAZE data citation, detailed school list, deep strategy

feat: upgrade Caspar system prompts (planning+evaluation) - remove word limit, require full MAZE data citation, detailed school list, deep strategy

feat: upgrade Caspar system prompts (planning+evaluation) - remove word limit, require full MAZE data citation, detailed school list, deep strategy

feat: upgrade Caspar system prompts (planning+evaluation) - remove word limit, require full MAZE data citation, detailed school list, deep strategy

fix: replace _drain_queue with _drain_queue_with_keepalive - prevent Nginx idle timeout during Balthasar/Melchior calls (root cause of Agent 3 not showing)

fix: add magi_done event to all modes; prevent spurious terminated error display

P1 Grok Judge: KB fact-consistency audit after Caspar in planning mode + P0-1/P0-2 prompt upgrades

P0: KB policy audit in Balthasar + round decision micro-scaffold in Caspar (Claude Opus 4.7 recommendation)

fix: Caspar keep-alive - _stream_claude_et_with_keepalive in all 4 modes, prevents HF Space idle timeout

fix: universal system-level MAZE data injection for all 6 agents (evaluation+planning)

feat: Universal dual-track fusion injector - all modes/agents now fuse Agentic Tool data + pretrained knowledge via _dispatch_stream + _call_claude_et hooks

fix: dual-track prompt engineering - force MELCHIOR to fuse Agentic Tool data + pretrained knowledge in evaluation+planning modes

feat: add Agentic Tool Prefetch (方案A) - MAZE/school data fetched before 3-agent deliberation in evaluation+planning modes

feat: upgrade Caspar system prompts (planning+evaluation) - remove word limit, require full MAZE data citation, detailed school list, deep strategy

fix: Claude max_tokens 8000→16000, budget_tokens 4000→6000 to fix Caspar truncation

feat: upgrade Caspar system prompts (planning+evaluation) - remove word limit, require full MAZE data citation, detailed school list, deep strategy

feat: upgrade Caspar system prompts (planning+evaluation) - remove word limit, require full MAZE data citation, detailed school list, deep strategy

fix: 消除 planning/arbiter system prompt 中「你女儿/你孩子」幻觉——改为第三方称谓禁令

fix: scrollIntoView null error in doQA, PDF button now works correctly

fix: scrollIntoView null error in doQA, PDF button now works correctly

fix: scrollIntoView null error in doQA, PDF button now works correctly

fix: scrollIntoView null error in doQA, PDF button now works correctly

fix: scrollIntoView null error in doQA, PDF button now works correctly

feat: add one-click PDF download for full consultation records (jsPDF, all 3 panels)

feat: add one-click PDF download for full consultation records (jsPDF, all 3 panels)

feat: Grok Multi-Agent review - upgrade planning mode MAZE analysis

update app.py

update app.py

update requirements.txt

update app.py

update agent/magi_system.py

update agent/magi_system.py

update app.py

update agent/magi_system.py

update agent/magi_system.py

update data/maze_cases_v2.parquet

update agent/magi_system.py

feat: remove all KB retrieval limits - return all matching results