Fetching metadata from the HF Docker repository...
Ctrl+K
- content Deploy: chapters-as-corpus restructure + analyze-input/direct-teaching skills + unified scratch (6 fields) + explicit BASE_DIR shell hint
- core Session-recovery propagated from socratic: hidden gr.Textbox (#recovery-payload) + Gradio .then(js=...) chains write/clear localStorage; on_submit_initial / on_end_session yield JSON events on their CONFIRM yields. RECOVERY_HEAD adds modal styling + window.__SOC_RECOVERY helpers; storage key explanatory_session_v1. TUTORIAL_HEAD walkthrough guard early-returns when localStorage carries an unfinished session so welcome doesn't overlap the recovery modal. on_recover_session rebuilds chatbot/cache/logger via SessionLogger.from_dict (now restores dominant_framework). HF file lookup loose-matches /{sid}_*.json within this Space's mode_prefix.
- data Session-recovery propagated from socratic: hidden gr.Textbox (#recovery-payload) + Gradio .then(js=...) chains write/clear localStorage; on_submit_initial / on_end_session yield JSON events on their CONFIRM yields. RECOVERY_HEAD adds modal styling + window.__SOC_RECOVERY helpers; storage key explanatory_session_v1. TUTORIAL_HEAD walkthrough guard early-returns when localStorage carries an unfinished session so welcome doesn't overlap the recovery modal. on_recover_session rebuilds chatbot/cache/logger via SessionLogger.from_dict (now restores dominant_framework). HF file lookup loose-matches /{sid}_*.json within this Space's mode_prefix.
- prompts STEP 1 framework detection: full reasoning-mode diagnosis with refined mixed-drafts rule. STEP 1 replaces keyword indicator lists with (a) identify load-bearing reasoning move, (b) 3 diagnostic questions in order (predicted outcomes / principles regardless of outcomes / character of an actor), (c) topic-vs-load decoupling table, (d) 'remove the lens' verification test. Mixed drafts rule: NOT a hard consequence default. Instead, pick the participant's CORE argument by explicit emphasis markers ('the most important reason' / 'perhaps for me' / 'the thing that is most ethically questionable is X') (highest priority), argumentative weight, then 'remove the lens' decisive test. Consequence is last-resort fallback only. Tested against pilot Kantian argument 5/5 correctly → duty_rights. Other downstream sections (essay, plan, hooks) unchanged.
- tests Deploy: PROBE_OPENING / FOLLOW_UP rewrite. Manager directive switches from flat ≤25-word strings to structured T's — T1 PROBE_OPENING has 4 fields (issue, anchor, missing_move, direction) at sub-probe start; FOLLOW_UPs have only direction. Hard rule: direction must be idea-level analytical guidance, not polished prose. Main agent renders PROBE_OPENING as natural-language analytical guidance (no rigid 'To strengthen this part... For example, ...' template). Engaging-default mid-probe becomes a FOLLOW_UP extension (strict mode: if manager has no FOLLOW_UP, bot does a light conversational pass with no teaching invention). Transition-due Block 1 simplified to brief credit/ack; Block 2 renders new sub-probe PROBE_OPENING. Global ban on 'For example, [polished declarative sentence]'.
- tutorial_images UI parity with socratic/socratic-frame: (1) hide Gradio Chatbot top chrome via show_label=False + CSS for share/clear/delete/trash; (2) strip the '# Case: ...' H1 from the initial chatbot message via display-only CASE_TEXT_DISPLAY (full CASE_TEXT still passed to LLM via stream_turn); (3) hide the left yellow feedback-hint column (guide-col visible=False) so chatbot expands left, and drop the bottom-row mirror column so chat-row (scale=3) + action-col (scale=2) align under chatbot + right-col above.
- 1.87 kB UI parity with socratic/socratic-frame: (1) hide Gradio Chatbot top chrome via show_label=False + CSS for share/clear/delete/trash; (2) strip the '# Case: ...' H1 from the initial chatbot message via display-only CASE_TEXT_DISPLAY (full CASE_TEXT still passed to LLM via stream_turn); (3) hide the left yellow feedback-hint column (guide-col visible=False) so chatbot expands left, and drop the bottom-row mirror column so chat-row (scale=3) + action-col (scale=2) align under chatbot + right-col above.
- 2.46 kB Deploy: chapters-as-corpus restructure + analyze-input/direct-teaching skills + unified scratch (6 fields) + explicit BASE_DIR shell hint
- 13.4 kB Deploy: chapters-as-corpus restructure + analyze-input/direct-teaching skills + unified scratch (6 fields) + explicit BASE_DIR shell hint
- 121 kB STEP 1 framework detection rewritten from keyword-matching to reasoning-mode diagnosis. Previous prompt used indicator keyword lists ('right to X', 'consent', 'privacy' → duty_rights, etc.), which would misclassify drafts that mention a topic but argue through a different framework. New STEP 1 asks the LLM to (a) identify the load-bearing reasoning move, (b) ask 3 diagnostic questions in order (predicted outcomes / principles regardless of outcomes / character of an actor), (c) apply a topic-vs-load decoupling table, (d) verify via 'remove the lens' test. Mixed drafts hard-default to consequence. Regression tested in socratic_frame (8/8 cases including 1 synthetic privacy+consequence, 4 pilot consequence+privacy, 3 pilot duty_rights+privacy). Other downstream sections (essay generation, discussion plan, hooks) unchanged.
- 2.27 kB Rename condition + mode_prefix to *-ca to match local folder rename. hf_dataset unchanged (legacy data stays in same dataset under new subfolder).
- 88 Bytes Deploy: chapters-as-corpus restructure + analyze-input/direct-teaching skills + unified scratch (6 fields) + explicit BASE_DIR shell hint