m3taversal 66bc742979 feat: full transcript archival + SOURCE:/CLAIM: inline tags ... Transcript system: - All messages in all chats captured to chat_transcripts store - 1-hour dump job writes per-chat JSON to /opt/teleo-eval/transcripts/ - Includes internal reasoning (KB matches, searches, learnings) - Transcripts accumulate over session (no clear on dump) - Per-chat directories: transcripts/{chat-slug}/{date-hour}.json Inline contribution tags: - SOURCE: creates inbox source file with verbatim user content - CLAIM: creates draft claim file attributed to contributor - Both strip tag from displayed response - Full user message preserved verbatim (Rio decides context, can't alter) Also: multi-URL processing (up to 5 per message) Pentagon-Agent: Epimetheus <3D35839A-7722-4740-B93D-51157F7D5E70>		2026-03-25 13:35:10 +00:00
..
bot.py	feat: full transcript archival + SOURCE:/CLAIM: inline tags	2026-03-25 13:35:10 +00:00
kb_retrieval.py	fix: decision record body cap 2K → 8K — proposals were truncating mid-text	2026-03-24 16:18:08 +00:00
market_data.py	epimetheus: sync VPS-deployed code to repo — Mar 18-20 reliability + features	2026-03-20 20:17:27 +00:00
teleo-telegram.service	epimetheus: source archive restructure — inbox/queue + inbox/archive/{domain} + inbox/null-result	2026-03-18 11:50:04 +00:00
worktree_lock.py	epimetheus: sync VPS-deployed code to repo — Mar 18-20 reliability + features	2026-03-20 20:17:27 +00:00
x_client.py	epimetheus: fix article content parsing — contents[] array, not text field	2026-03-23 15:30:59 +00:00
x_search.py	epimetheus: direct tweet lookup via /tweets?tweet_ids= endpoint	2026-03-23 15:17:11 +00:00