- Question override now decays after 6 turns: after turn 6, the LLM's own
[CONTINUE] signal is respected even when questions are asked. This prevents
infinite question-ping-pong where both personas keep asking questions.
- _parse_response now accepts turn_count parameter; generate_response_with_continuation
and handle_dialogue_turn pass it through.
- Rewrote Evil Miku's conversation-mode overlay with explicit CRITICAL RULES:
ANSWER questions, engage with what she says, ask questions too, don't just
repeat dismissive one-liners. The old overlay said 'be playful-cruel' but
didn't actually tell her to participate in the conversation.
The snippet loader used wrong file paths (/app/cat/data/ instead of persona/)
causing 'Loaded 0 personality snippets' for both personas. Since the previous
commit now injects full system prompts (get_miku_system_prompt_compact and
get_evil_system_prompt) into every argument exchange, the snippet system is
redundant — all lore/lyrics/personality are already provided by the system prompts.
Created get_miku_system_prompt() and get_miku_system_prompt_compact() in
context_manager.py — mirrors get_evil_system_prompt() so both personas have
equally rich prompts with lore, lyrics, mood integration, and personality.
Previously only Evil Miku had a proper system prompt function. Regular Miku's
arguments and dialogues used a bare-bones hardcoded prompt with no lore/lyrics
— making arguments feel flat compared to normal conversation.
Changes:
- context_manager.py: added get_miku_system_prompt() (full) and
get_miku_system_prompt_compact() (lore+personality, no lyrics for tokens)
- bipolar_mode.py: both argument prompt functions now accept system_prompt
param; run_argument() builds miku_system and evil_system once and passes
them to every exchange
- persona_dialogue.py: dialogue prompts now use get_miku_system_prompt_compact()
instead of hardcoded stub, matching Evil Miku's full prompt approach
- Removed redundant hardcoded personality text from argument prompts since
the system prompts now provide it
The topic was only being injected into the initial breakthrough message via
get_argument_start_prompt(). After that, every subsequent exchange called
get_miku_argument_prompt() / get_evil_argument_prompt() which had no concept
of the topic — so both personas forgot what they were arguing about after the
first exchange and reverted to generic identity-crisis arguments.
Fix: added argument_topic parameter to both persona prompt functions and inject
it as a bold ARGUMENT THEME reminder in every single exchange. The topic block
explicitly tells the LLM to stay on-topic and not drift into generic territory.
- Removed separate 'topic' field from BipolarTriggerRequest model
- Removed topic parameter from force_trigger_argument, force_trigger_argument_from_message_id, and run_argument
- trigger_context now doubles as the argument theme: if provided by user, it becomes the topic;
if blank, a random topic is selected from the rotation pool
- Web UI: replaced two confusing fields (Context + Topic) with one clear field labeled
'What should they argue about? (optional)' with a plain-English description
- JS: removed topic field reference, context.trim() ensures empty strings aren't sent
- Added optional 'topic' field to BipolarTriggerRequest model
- Added topic parameter to force_trigger_argument and force_trigger_argument_from_message_id
- Updated run_argument to accept optional custom topic (None=random, ''=no topic, str=custom)
- Added topic input field to Web UI trigger-argument section
- Updated JS to send topic in API request body
- Custom topics bypass the random rotation system, allowing manual theme control
- Added mood-specific argument behavioral guidance: 9 moods for Evil Miku, 9 for Miku
Each mood changes argument style (e.g. cunning=chess moves, manic=chaotic, bubbly=playful deflections)
- Added personality snippet injection from Cat plugin lore/lyrics data files
40% chance per prompt to include a random lore/lyric snippet for unique material
- Added parting shot feature: 20% chance the LOSER gets a bitter final line before the winner's victory
Adds dramatic tension and prevents clean-win monotony
- Mood guidance and personality flavor injected into both argument prompts
- Changed cooldown from global (ALL channels blocked) to per-channel dict keyed by channel_id
- Added conversation streak tracker: 3 near-miss interjection scores in a row force a dialogue trigger
- Expanded topic relevance keywords: added enthusiasm/vulnerability for Evil Miku, provocation/dismissal for Miku
- Lowered keyword divisor from /3.0 to /2.0 for higher base trigger scores
- Tension rebalance: added natural decay (-0.03/turn), reduced escalation weight (0.08->0.05), increased de-escalation weight (0.06->0.08)
- Reduced momentum multiplier (1.2->1.1) and intensity multiplier (1.3->1.2)
- Added spike cooldown: if last turn tension delta >0.15, next delta halved (prevents runaway spirals)
- Added user-message interjection check in bot.py on_message() (was only checking bot's own messages)
- Added random 15% argument trigger roll on user messages in normal message flow (was only from autonomous.py)
Twitter changed the JS bundle structure from the old single-map format
(e=>e+"."+{...}[e]+"a.js") to a new two-map format
(u.u=e=>""+(({name})[e]||e)+"."+({hash})[e]+"a.js"), breaking
x-client-transaction-id generation.
This caused IndexError: list index out of range, which twscrape
interpreted as an account timeout (15-min lockout), preventing Miku
from fetching/sharing tweets.
The fix adds:
- A robust multi-pattern parser that tries known formats in order
- The _js_obj_to_dict helper from PR #303 for handling unquoted numeric
keys and scientific notation in JS object literals
- Debug logging to capture the JS snippet when ALL patterns fail,
making future breakage easier to diagnose
References:
- https://github.com/vladkens/twscrape/issues/302
- https://github.com/vladkens/twscrape/pull/303
Critical fixes:
- Add threading.Lock for all shared mutable state (override, cache, current activity)
- Atomic YAML writes (temp file + os.replace) to prevent corruption on crash
- Deep-copy cache on reads to prevent callers from mutating shared state
High-severity fixes:
- Validate entries in pick_activity_for_mood() — skip/log malformed instead of KeyError
- Log warning on unrecognized activity type fallback
- Normalize empty-string state to None (avoid 'None' display)
- release_manual_override() now uses force=True so bot always shows activity
- Add try/except in release_manual_override() to handle failures gracefully
Medium fixes:
- Remove dead 'test' mood from activities.yaml
- Validate name length (128 char Discord limit) in CRUD and manual set
- Validate streaming entries have URL in CRUD path
- Add JSON parse error handling in API routes
- on_ready preserves active manual override instead of overwriting
- Log override expiry timestamp (HH:MM:SS) for easier debugging
- exc_info=True on presence update errors for full stack traces
Low fixes:
- JS activitySetFromEntry() shows notification on parse error
- Rewrite utils/activities.py with mood energy-driven activity probability
(high-energy moods like excited/bubbly show activity ~80-85% of the time,
low-energy moods like sleepy/melancholy only ~15-25%)
- Add manual override system with 30-min auto-expiry for Web UI control
- Support all 5 Discord activity types: listening, playing, watching,
competing, streaming (with purple LIVE badge via discord.Streaming)
- Add current activity tracking (get_current_activity)
- Add force=True param to update_bot_presence for on_ready (bot.py)
- Add 4 new API routes for manual override:
GET/POST/DELETE /activities/current, POST /activities/current/auto
- Expand activities.yaml from 139 to 157 entries, adding watching,
competing, and streaming entries across 11 moods
- Update Web UI: activity type dropdown with all 5 types, conditional
URL field for streaming, 'Current Activity' override panel with
set/clear/auto controls, type-aware icons and labels
- Add 'state' field to all 139 activity entries in activities.yaml
- Songs: state shows artist (e.g. 'by kz (livetune)')
- Games: state shows genre (e.g. 'Rhythm Game', 'Sandbox', 'FPS')
- Update pick_activity_for_mood() to return 3-tuple (type, name, state)
- Update update_bot_presence() to pass state to discord.Activity()
- Add state validation in set_activities_for_mood() (optional string)
- Update Web UI editor: view shows state, edit form has state input
- State is fully optional — backward compatible, no breaking changes
The 'state' field appears as a secondary text line in Discord profile
popup, the richest display possible for bot accounts (full Rich Presence
with cover art/buttons is server-side restricted to OAuth applications).
New module that loads activities.yaml and provides:
- Weighted random activity selection per mood
- Discord presence update (Listening/Playing)
- File mtime caching for hot-reload
- Validation for CRUD operations
- Fallback for moods with no activities defined
Previously gpu_router.py had its own module-level PREFER_AMD_GPU constant
that was frozen at import time. The config API wrote to globals.PREFER_AMD_GPU
which didn't exist, so runtime GPU preference changes never took effect.
Now globals.py owns PREFER_AMD_GPU and gpu_router reads it from there.
- Backend: album storage in memory/profile_pictures/album/{uuid}/ with
original.png, cropped.png, and metadata.json per entry
- add_to_album/add_batch_to_album with efficient resource management
(vision model + face detector kept alive across batch)
- set_album_entry_as_current auto-archives current PFP before replacing
- manual/auto crop album entries without applying to Discord
- Disk usage tracking, single & bulk delete
- API: full CRUD endpoints under /profile-picture/album/*
- Frontend: collapsible album grid in tab11 with thumbnail cards,
multi-select checkboxes for bulk delete, detail panel with crop
interface (Cropper.js), description editor, set-as-current action
- profile_picture_manager.py:
- Add ORIGINAL_PATH constant; save full-res original before every crop
- Add skip_crop param to change_profile_picture() for manual crop workflow
- Add manual_crop(x,y,w,h) method with Discord avatar update + role color sync
- Add auto_crop_only() to re-run face-detection crop on stored original
- Add update_description() with Cheshire Cat declarative memory re-injection
- Add regenerate_description() via vision model
- Skip crop step if image is already at/below 512x512
- api.py:
- GET /profile-picture/image/original — serve full-res original (no-cache)
- GET /profile-picture/image/current — serve current cropped avatar (no-cache)
- POST /profile-picture/change-no-crop — acquire image, skip auto-crop
- POST /profile-picture/manual-crop — apply crop coords {x,y,width,height}
- POST /profile-picture/auto-crop — re-run intelligent crop on original
- POST /profile-picture/description — save freeform description + Cat inject
- POST /profile-picture/regenerate-description — re-generate via vision model
- GET /profile-picture/description — fetch current description text
- index.html:
- Add new tab11 '🖼️ Profile Picture Management'
- Remove PFP + role color sections from Actions tab (tab2)
- Add Cropper.js 1.6.2 via CDN for manual square crop
- Tab layout: action buttons, file upload, auto/manual crop toggle,
Cropper.js interface, side-by-side original/cropped previews,
role color management, freeform description editor, metadata box (bottom)
- Wire switchTab hook for tab11 → loadPfpTab()
- All new JS functions: pfpChangeDanbooru, pfpUploadCustom, pfpRestoreFallback,
pfpShowCropInterface, pfpApplyManualCrop, pfpApplyAutoCrop, pfpSaveDescription,
pfpRegenerateDescription, pfpRefreshPreviews, setCustomRoleColor, resetRoleColor
When Evil Mode activates, the bot's Discord account avatar is changed to evil_pfp.png.
Previously, get_persona_avatar_urls() would read this swapped avatar and pass it to
the Miku webhook, causing both webhooks to display Evil Miku's pfp.
Now caching the regular Miku CDN URL before Evil Mode changes the bot's avatar.
When Evil Mode is active, the cached URL is used instead of reading from the bot
account. Discord CDN URLs remain valid after avatar changes, so this reliably
preserves the correct pfp for both regular and Evil Miku webhooks during arguments.
- Added MIKU_NORMAL_AVATAR_URL global in bot/globals.py
- Updated get_persona_avatar_urls() to cache and return the cached URL
- Save the normal avatar URL before Evil Mode switches the bot's avatar
- Fix silent None return in analyze_image_with_vision exception handler
- Add None/empty guards after vision analysis in bot.py (image, video, GIF, Tenor)
- Route all image/video/GIF responses through Cheshire Cat pipeline (was
calling query_llama directly), enabling episodic memory storage for media
interactions and correct Last Prompt display in Web UI
- Add media_type parameter to cat_adapter.query() and forward as
discord_media_type in WebSocket payload
- Update discord_bridge plugin to read media_type from payload and inject
MEDIA NOTE into system prefix in before_agent_starts hook
- Add _extract_vision_question() helper to strip Discord mentions and bot-name
triggers from user message; pass cleaned question to vision model so specific
questions (e.g. 'what is the person wearing?') go directly to the vision model
instead of the generic 'Describe this image in detail.' fallback
- Pass user_prompt to all analyze_image_with_qwen / analyze_video_with_vision
call sites in bot.py (image, video, GIF, Tenor, embed paths)
- Fix autonomous reaction loops skipping messages that @mention the bot or have
media attachments in DMs, preventing duplicate vision model calls for images
already being processed by the main message handler
- Increase vision max_tokens: images 300->800, video/GIF 400->1000 (no VRAM
impact; KV cache is pre-allocated at model load time)
- Pre-compile 393 name variants into 4 regex patterns at module load
(was 7,300+ raw re.search() calls per message)
- Strict addressing detection using punctuation context:
START: name at beginning + punctuation (Miku, ... / みく！...)
END: comma + name at end (..., Miku / ...、ミク)
MIDDLE: commas on both sides - vocative (..., Miku, ...)
ALONE: name is the entire message (Miku! / ミクちゃん)
- Rejects mere mentions: 'I like Miku' / 'Miku is cool' no longer trigger
- Script-family-aware pattern generation (Latin, Cyrillic, Japanese)
eliminates nonsensical cross-script combos (e.g. o-みく)
- Word boundary enforcement prevents substring matches (mikumiku)
- Fixes regex 'unbalanced parenthesis' errors from old implementation
- Add comprehensive test suite (94 cases, all passing)
- discord_bridge before_agent_starts now checks evil_mode from
working_memory to load the correct personality files:
Normal: miku_lore/prompt/lyrics + /app/moods/{mood}.txt
Evil: evil_miku_lore/prompt/lyrics + /app/moods/evil/{mood}.txt
- Reads files directly instead of relying on cross-plugin working_memory
- cat_client.query() returns (response, full_prompt) tuple
- Full prompt includes system prefix + recalled memories + conversation
- API /prompt/cat returns full_prompt field
Bot was calling restore_evil_cat_state() in on_ready() before Cheshire
Cat finished booting (~25s), causing all plugin toggle API calls to fail
silently. Evil Miku plugin was left disabled and the bot used Cat's
default personality instead.
Changes:
- cat_client.py: add wait_for_ready() that polls Cat health endpoint
every 5s for up to 120s before attempting any admin API calls
- evil_mode.py: rewrite restore_evil_cat_state() with:
- wait_for_ready() gate before any plugin/model switching
- 3-second extra delay after Cat is up (plugin registry fully loaded)
- up to 3 retries on failure
- post-switch verification that the correct plugins are actually active
Also fixes helcyon model references that leaked into the container image
(cat_client.py was switching Cat's LLM to 'helcyon' which has no
llama-swap handler; reverted to correct 'darkidol' / 'llama3.1').
- Fixed missing client parameter in animated GIF webhook update path
- Added get_persona_avatar_urls() helper that returns bot's current Discord
avatar URL for Miku persona (always fresh, no cache lag)
- Pass avatar_url on every webhook.send() call in bipolar_mode.py,
persona_dialogue.py, and api.py so avatars always match current pfp
regardless of webhook cache state
#16 Timezone consistency — added TZ=Europe/Sofia to docker-compose.yml
so datetime.now() returns local time inside the container. Removed
the +3 hour hack from get_time_of_day(). All three time-of-day
consumers (autonomous_v1_legacy, moods, autonomous_engine) now
use the same correct local hour automatically.
#17 Decay truncation — replaced int() with round() in decay_events()
so a counter of 1 survives one more 15-minute cycle instead of
being immediately zeroed (round(0.841)=1 vs int(0.841)=0).
#20 Unpersisted rate limiter — _last_action_execution dict in
autonomous.py is now seeded from the engine's persisted
server_last_action on import, so restarts don't bypass the
30-second cooldown.
Note: #18 (dead config fields) was a false positive — autonomous_interval_minutes
IS used by the scheduler. #19 deferred to bipolar mode rework.
#10 Redundant coin flip in join_conversation — removed the 50% random
gate that doubled the V2 engine's own decision to act.
#11 Message-triggered actions skip _autonomous_paused — _check_and_act
and _check_and_react now bail out immediately when the autonomous
system is paused (voice session), matching the scheduled-tick path.
#12 Duplicate emoji dictionaries — removed MOOD_EMOJIS and
EVIL_MOOD_EMOJIS from globals.py (had different emojis from moods.py).
bipolar_mode.py and evil_mode.py now import the canonical dicts
from utils/moods.py so all code sees the same emojis.
#13 DM mood can spontaneously become 'asleep' — rotate_dm_mood() now
filters 'asleep' out of the candidate list since DMs have no
sleepy-to-asleep transition guard and no wakeup timer.
#15 Engage-user fallback misreports action type — log level raised to
WARNING with an explicit [engage_user->general] prefix so the
cooldown-triggered fallback is visible in logs.
#4 Sleep/mood desync — set_server_mood() now clears is_sleeping when
mood changes away from 'asleep', preventing ghost-sleep state.
#5 Race condition in _check_and_act — added per-guild asyncio.Lock so
overlapping ticks + message-triggered calls cannot fire concurrently.
#6 Class-level attrs on ServerConfig — sleepy_responses_left,
angry_wakeup_timer, and forced_angry_until are now proper dataclass
fields with defaults, so asdict()/from_dict() round-trip correctly.
Also strips unknown keys in from_dict() to survive schema changes.
#7 Persistence decay_factor crash — initialise decay_factor = 1.0
before the loop so empty-server or zero-downtime paths don't
raise NameError.
#8 Double record_action — removed the redundant call in
autonomous_tick_v2(); only _check_and_act records the action now.
#9 Engine mood desync — on_mood_change() is now called inside
set_server_mood() (single source of truth) and removed from 4
call-sites in api.py, moods.py, and server_manager wakeup task.
1. Momentum cliff at 10 messages (P0): The conversation momentum formula
had a discontinuity where the 10th message caused momentum to DROP from
0.9 to 0.5. Replaced with a smooth log1p curve that monotonically
increases (0→0→0.20→0.32→...→0.70→0.89→1.0 at 30 msgs).
2. Neutral keywords overriding all moods (P0): detect_mood_shift() checked
neutral early with generic keywords (okay, sure, hmm) that matched
almost any response, constantly resetting mood to neutral. Now: all
specific moods are scored by match count first (best-match wins),
neutral is only checked as fallback and requires 2+ keyword matches.
3. Uncancellable delayed_wakeup tasks (P0): Fire-and-forget sleep tasks
could stack and overwrite mood state after manual wake-up. Added a
centralized wakeup task registry in ServerManager with automatic
cancellation on manual wake or new sleep cycle.
- Added manual_trigger parameter to /autonomous/engage endpoint to bypass 12h cooldown
- Updated miku_engage_random_user_for_server() and miku_engage_random_user() to accept manual_trigger flag
- Modified Web UI to always send manual_trigger=true when engaging users from the UI
- Users can now manually engage the same user multiple times from web UI without cooldown restriction
- Regular autonomous schedules still respect the 12h cooldown between engagements to the same user
Changes:
- bot/api.py: Added manual_trigger parameter with string-to-boolean conversion
- bot/static/index.html: Added manual_trigger=true to engage user request
- bot/utils/autonomous_v1_legacy.py: Added manual_trigger parameter and cooldown bypass logic
- Add COPY config_manager.py to Dockerfile so it's included in the image
- Add 'config_manager' to logger COMPONENTS list to enable logging
Fixes the ModuleNotFoundError and ValueError when importing config_manager
Major changes:
- Remove unused ML libraries: torch, scikit-learn, langchain-core, langchain-text-splitters, langchain-community, faiss-cpu
- Comment out unused langchain imports in utils/core.py (only used in commented-out code)
- Keep transformers (used in persona_dialogue.py for sentiment analysis)
Results:
- Container size reduced from 14.5GB to 2.6GB
- 82% reduction (11.9GB saved)
- Bot runs correctly without errors
- All functionality preserved
Removed packages:
- torch: ~1.0-1.5GB (not used, only in soprano_to_rvc/)
- scikit-learn: ~200-300MB (not used in bot/)
- langchain-core: ~50-100MB (not used, only in commented code)
- langchain-text-splitters: ~30-50MB (not used, only in commented code)
- langchain-community: ~50-80MB (not used, only in commented code)
- faiss-cpu: ~100-200MB (not used in bot/)
This is Phase 1 of container optimization (Quick Wins).
Further optimizations possible:
- OpenCV headless (150-200MB)
- Evaluate Playwright usage (500MB-1GB)
- Alpine base image (1-1.5GB)
- Multi-stage builds (200-400MB)
Major changes:
- Add Pydantic-based configuration system (bot/config.py, bot/config_manager.py)
- Add config.yaml with all service URLs, models, and feature flags
- Fix config.yaml path resolution in Docker (check /app/config.yaml first)
- Remove Fish Audio API integration (tested feature that didn't work)
- Remove hardcoded ERROR_WEBHOOK_URL, import from config instead
- Add missing Pydantic models (LogConfigUpdateRequest, LogFilterUpdateRequest)
- Enable Cheshire Cat memory system by default (USE_CHESHIRE_CAT=true)
- Add .env.example template with all required environment variables
- Add setup.sh script for user-friendly initialization
- Update docker-compose.yml with proper env file mounting
- Update .gitignore for config files and temporary files
Config system features:
- Static configuration from config.yaml
- Runtime overrides from config_runtime.yaml
- Environment variables for secrets (.env)
- Web UI integration via config_manager
- Graceful fallback to defaults
Secrets handling:
- Move ERROR_WEBHOOK_URL from hardcoded to .env
- Add .env.example with all placeholder values
- Document all required secrets
- Fish API key and voice ID removed from .env
Documentation:
- CONFIG_README.md - Configuration system guide
- CONFIG_SYSTEM_COMPLETE.md - Implementation summary
- FISH_API_REMOVAL_COMPLETE.md - Removal record
- SECRETS_CONFIGURED.md - Secrets setup record
- BOT_STARTUP_FIX.md - Pydantic model fixes
- MIGRATION_CHECKLIST.md - Setup checklist
- WEB_UI_INTEGRATION_COMPLETE.md - Web UI config guide
- Updated readmes/README.md with new features
MOOD SYSTEM FIX:
- Mount bot/moods directory in docker-compose.yml for Cat container access
- Update miku_personality plugin to load mood descriptions from .txt files
- Add Cat logger for debugging mood loading (replaces print statements)
- Moods now dynamically loaded from working_memory instead of hardcoded neutral
- Replaced Playwright browser scraping with direct API media extraction
- Both fetch_miku_tweets() and fetch_figurine_tweets_latest() now use twscrape's built-in media info
- Reduced tweet fetching from 10-15 minutes to ~5 seconds
- Eliminated browser timeout/hanging issues
- Relaxed autonomous tweet sharing conditions:
* Increased message threshold from 10 to 20 per hour
* Reduced cooldown from 3600s to 2400s (40 minutes)
* Increased energy threshold from 50% to 70%
* Added 'silly' and 'flirty' moods to allowed sharing moods
This makes both figurine notifications and tweet sharing much more reliable and responsive.
**Critical Bug Fixes:**
1. Per-user memory isolation bug
- Changed CatAdapter from HTTP POST to WebSocket /ws/{user_id}
- User_id now comes from URL path parameter (true per-user isolation)
- Verified: Different users can't see each other's memories
2. Memory API 405 errors
- Replaced non-existent Cat endpoint calls with Qdrant direct queries
- get_memory_points(): Now uses POST /collections/{collection}/points/scroll
- delete_memory_point(): Now uses POST /collections/{collection}/points/delete
3. Memory stats showing null counts
- Reimplemented get_memory_stats() to query Qdrant directly
- Now returns accurate counts: episodic: 20, declarative: 6, procedural: 4
4. Miku couldn't see usernames
- Modified discord_bridge before_cat_reads_message hook
- Prepends [Username says:] to every message text
- LLM now knows who is texting: [Alice says:] Hello Miku!
5. Web UI Memory tab layout
- Tab9 was positioned outside .tab-container div (showed to the right)
- Moved tab9 HTML inside container, before closing divs
- Memory tab now displays below tab buttons like other tabs
**Code Changes:**
bot/utils/cat_client.py:
- Line 25: Logger name changed to 'llm' (available component)
- get_memory_stats() (lines 256-285): Query Qdrant directly via HTTP GET
- get_memory_points() (lines 275-310): Use Qdrant POST /points/scroll
- delete_memory_point() (lines 350-370): Use Qdrant POST /points/delete
cat-plugins/discord_bridge/discord_bridge.py:
- Fixed .pop() → .get() (UserMessage is Pydantic BaseModelDict)
- Added before_cat_reads_message logic to prepend [Username says:]
- Message format: [Alice says:] message content
Dockerfile.llamaswap-rocm:
- Lines 37-44: Added conditional check for UI directory
- if [ -d ui ] before npm install && npm run build
- Fixes build failure when llama-swap UI dir doesn't exist
bot/static/index.html:
- Moved tab9 from lines 1554-1688 (outside container)
- To position before container closing divs (now inside)
- Memory tab button at line 673: 🧠 Memories
**Testing & Verification:**
✅ Per-user isolation verified (Docker exec test)
✅ Memory stats showing real counts (curl test)
✅ Memory API working (facts/episodic loading)
✅ Web UI layout fixed (tab displays correctly)
✅ All 5 services running (llama-swap, llama-swap-amd, qdrant, cat, bot)
✅ Username prepending working (message context for LLM)
**Result:** All Phase 3 critical bugs fixed and verified working.
Key changes:
- CatAdapter (bot/utils/cat_client.py): WebSocket /ws/{user_id} for chat
queries instead of HTTP POST (fixes per-user memory isolation when no
API keys are configured — HTTP defaults all users to user_id='user')
- Memory management API: 8 endpoints for status, stats, facts, episodic
memories, consolidation trigger, multi-step delete with confirmation
- Web UI: Memory tab (tab9) with collection stats, fact/episodic browser,
manual consolidation trigger, and 3-step delete flow requiring exact
confirmation string
- Bot integration: Cat-first response path with query_llama fallback for
both text and embed responses, server mood detection
- Discord bridge plugin: fixed .pop() to .get() (UserMessage is a Pydantic
BaseModelDict, not a raw dict), metadata extraction via extra attributes
- Unified docker-compose: Cat + Qdrant services merged into main compose,
bot depends_on Cat healthcheck
- All plugins (discord_bridge, memory_consolidation, miku_personality)
consolidated into cat-plugins/ for volume mount
- query_llama deprecated but functional for compatibility
