- Tabs wrap to multiple rows instead of overflowing
- Reduced tab padding for compact fit
- Stats bar items wrap to 2 rows on narrow panels
- Activity log and diagnostics text wraps instead of overflowing
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace hover/click expand with native resize: vertical.
User can drag the bottom edge to resize between 30px and 400px.
Always scrollable.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Main tab gets "Memory Extraction" header with "Automatic" checkbox
- "Select all" moved inline with "Character Attachments" header
- New charMemory_sectionHeader CSS for label + control on same line
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Activity Log labeled and always visible below tab content
- Diagnostics moved from Main tab to permanent pane at bottom
- Main tab now only has Extract Now and View/Edit buttons
- Click activity log to expand, hover also works
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
SillyTavern's popup dialog centers content by default, causing
bullets and card text to appear centered instead of left-aligned.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add settings migration from old consolidationPrompt to new
per-preset consolidationPrompts system. Update changelog with
all consolidation UX improvements for v1.3.0.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Shows last 3 log entries always visible below tabs, expandable
on click for more history. Uses max-height transition for smooth
expand/collapse.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Consolidated blocks now display as clean read-only cards with numbered
theme headers. Pencil icon toggles individual blocks into edit mode
with text inputs, delete buttons, and add memory/block controls. Dialog
toolbar includes expandable prompt viewer matching the Consolidate tab.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace hidden textarea + Custom option with <details> disclosure
showing the editable prompt for each strategy. Restore Default button
appears when a preset has been customized.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- escapeHtml() now escapes quotes for safe use in attribute values
- Remove duplicate countBlocksBullets (identical to existing countMemories)
- Disable editor inputs during re-run LLM call to prevent lost edits
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Each consolidated memory is now an editable card with text inputs instead
of raw text with <memory> tags. Supports add/delete bullets and blocks.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add box-sizing to consolidation editor textarea
- Bump version to 1.3.0
- Update changelog with new consolidation features
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Verbose log entries (prompts, responses) now render as collapsible
<details> sections with the first line as summary. Full content is
in a pre-formatted block with scroll, so it doesn't flood the log.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Replace default extraction prompt with higher-quality version: AVOID list
(sexual mechanics, temporary states, dialogue), FOCUS categories, past
tense rule, consolidation/fact-checking rules, better examples
- Bump default responseLength from 500 to 800
- Add minCooldownMinutes setting (default 10, range 0-30) to prevent
rapid-fire extractions; manual extractions bypass cooldown
- Combine Activity Log + Diagnostics into single tabbed drawer
- Expand stats bar from 2 to 4 items: file, memory count, extraction
progress (msgs/interval), cooldown timer with auto-refresh
- Fix stats bar showing stale count after Clear All Memories
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add collapsible Activity Log panel that shows timestamped events:
chat switches, extraction state, message collection, LLM responses
- Fix bug where lastExtractedIndex advanced even when LLM returned
NO_NEW_MEMORIES, preventing subsequent manual extraction from
processing messages on a switched-to chat
- Now only advance lastExtractedIndex when memories are actually saved;
always reset messagesSinceExtraction to prevent re-trigger loops
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Refactor collectRecentMessages/extractMemories to accept optional endIndex
- Add brain button on character messages to extract memories up to that point
- Add bookmark button on all messages to pin text as memory without LLM
- Show subtle brain indicator on messages already processed by extraction
- Update indicators on chat switch and after extraction completes
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Switch from ## Memory N headers to <memory chat="..." date="..."> tag blocks
with individual bullet parsing. Memory manager now shows grouped extraction
cards with per-bullet edit/delete controls. Stats bar simplified to file name
and total bullet count. Diagnostics panel shows vectorization status.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Rename extension header from CharMemory to Character Memory
- Add always-visible stats bar showing active file, memory count, and
extraction progress
- Flatten Memory Status sub-drawer so controls are immediately visible
- Merge Advanced section into Settings with separator dividers
- Rename buttons: Manage Memories → View / Edit, Reset → Clear All
Memories (moved to Settings with danger styling)
- Add tooltips, helper text styling, and separator/danger-button CSS
- Call updateStatusDisplay after consolidation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Memories now stored as numbered `## Memory N` entries with timestamps
- Auto-migrates existing flat-text memories to structured format
- "Manage Memories" popup with edit/delete per entry (replaces "View Memories")
- "Consolidate" button and `/consolidate-memories` slash command to merge duplicates via LLM
- Extraction now splits LLM output on `---` separators into individual entries
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Automatically extracts structured character memories from chat and stores
them in character-scoped Data Bank files for vector retrieval.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
