feat: implement study actions#122
Open
longobucco wants to merge 5 commits into
Open
Conversation
longobucco
commented
Jun 11, 2026
longobucco
commented
Collaborator
- QVAC query.js/server.js: add preserveMarkdown and enableThinking options to generateFromContext/streamFromContext; skip _stripMarkdown for structured study output; omit /nothink only for DERIVE to enable Qwen3 chain-of-thought
- study_service: add _stream_generate, stream_dispatch with SSE keepalive, semantic cache (shared key with dispatch), separate 120s httpx client for generation, per-action enableThinking (DERIVE only), ORAL/COMPARE system prompt hardening with explicit label and dimension enforcement
- study_api: POST /study/stream SSE endpoint with asyncio.wait_for keepalive and X-Accel-Buffering header; per-user JWT rate limit key in rate_limit.py
- study.ts: sendStudyActionStream consuming SSE with citations sentinel parsing
- OutputPane: streaming path for EXPLAIN/SUMMARIZE/DERIVE/COMPARE/OPEN_QUESTIONS, action-streaming message type filtered from localStorage persistence, onActionResult parity between streaming and buffered paths
- StudyOutput: remarkGfm on all ReactMarkdown, robust oral parser with multi-label regex, OralQuestionCard idle/submitted/revealed phases, quiz split regex handles Q1:/Q1. variants, quiz explanation extracted and shown after reveal, retrieval-failed banner
- remark-gfm@3.0.1 added to apps/web dependencies
added 5 commits
June 11, 2026 12:21
- QVAC query.js/server.js: add preserveMarkdown and enableThinking options to generateFromContext/streamFromContext; skip _stripMarkdown for structured study output; omit /nothink only for DERIVE to enable Qwen3 chain-of-thought - study_service: add _stream_generate, stream_dispatch with SSE keepalive, semantic cache (shared key with dispatch), separate 120s httpx client for generation, per-action enableThinking (DERIVE only), ORAL/COMPARE system prompt hardening with explicit label and dimension enforcement - study_api: POST /study/stream SSE endpoint with asyncio.wait_for keepalive and X-Accel-Buffering header; per-user JWT rate limit key in rate_limit.py - study.ts: sendStudyActionStream consuming SSE with citations sentinel parsing - OutputPane: streaming path for EXPLAIN/SUMMARIZE/DERIVE/COMPARE/OPEN_QUESTIONS, action-streaming message type filtered from localStorage persistence, onActionResult parity between streaming and buffered paths - StudyOutput: remarkGfm on all ReactMarkdown, robust oral parser with multi-label regex, OralQuestionCard idle/submitted/revealed phases, quiz split regex handles Q1:/Q1. variants, quiz explanation extracted and shown after reveal, retrieval-failed banner - remark-gfm@3.0.1 added to apps/web dependencies
…cading course deletion
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.