Switch from Rust-side HKDF (KDF_HKDF=1) to Python-side HKDF derivation
with raw key mode (KDF_RAW=0). This eliminates potential HKDF implementation
mismatches between Rust FFI and Element Call JS that caused video frame
decryption failures (audio worked, video showed 8x8 garbage frames).
Changes:
- Add _derive_and_set_key() helper that pre-derives HKDF then calls set_key()
- Set key_derivation_function=KDF_RAW (proto 0 = no Rust-side derivation)
- Replace all direct set_key() calls with _derive_and_set_key()
- Add per-track diagnostic logging (audio vs video)
- Add frame size check in look_at_screen (detect E2EE failure early)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
8x8 frames are encrypted garbage from E2EE video decryption failure.
Skip frames < 64x64 to avoid sending black/noise images to the LLM.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
1. Text bot can now capture video frames from active call when user
types vision-related queries ("siehst du meinen bildschirm", etc.)
2. Voice transcript injected into text bot context during active calls
3. Text messages injected into voice transcript with [typed in chat] prefix
4. Bot text replies injected back into voice transcript
This enables seamless context sharing between voice calls and text chat.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Video tracks (camera + screen share) were never getting E2EE keys set
via set_key() because the condition on track_subscribed only matched
audio tracks (kind==1). This caused DEC_FAILED for all video frames,
making look_at_screen return encrypted garbage or fail entirely.
Also added track source logging to distinguish camera vs screen share.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add HTTPS instruction to system prompt so LLM never generates http:// links.
Fix bare matrixhost.eu/settings references to use full https:// URLs.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add scheduled messages/reminders system:
- New scheduled_messages table in memory-service with CRUD endpoints
- schedule_message, list_reminders, cancel_reminder tools for the bot
- Background scheduler loop (30s) sends due reminders automatically
- Supports one-time, daily, weekly, weekdays, monthly repeat patterns
Make article URL handling non-blocking:
- Show 3 options (discuss, text summary, audio) instead of forcing audio wizard
- Default to passing article context to AI if user just keeps chatting
- New AWAITING_LANGUAGE state for cleaner audio flow FSM
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Integrates _ensure_cross_signing() into Bot.start() flow. On first run, generates
and uploads cross-signing keys, then signs the bot device. On subsequent restarts,
detects existing cross-signatures and skips. Seeds persisted for device recovery.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Allows the bot to paginate back up to 500 messages in a room
to find specific content, beyond the default 10-message context window.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Route ~90% of simple chat to claude-haiku (4x cheaper), escalate to
claude-sonnet for code blocks, long messages, technical keywords,
multimodal, and explicit requests. Sentry tags track model_used,
escalation_reason, and token usage breadcrumbs.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Make user_id required on all request models with field validators
- Always include user_id in WHERE clause for chunk queries (prevents cross-user data leak)
- Add bearer token auth on all endpoints except /health
- Add composite index on (user_id, room_id) for conversation_chunks
- Bot: guard query_chunks with sender check, pass room_id, send auth token
- Docker: pass MEMORY_SERVICE_TOKEN to both bot and memory-service
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Per-user Fernet encryption for fact/chunk_text/summary fields
- Postgres RLS with memory_app restricted role
- SSL for memory-db connections
- Data migration script (migrate_encrypt.py)
- DB migration (migrate_rls.sql)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Scanned passport PDFs have completely garbled OCR text that makes
the LLM think they're not passports, even though the AI-generated
title and summary correctly identify them. Added explicit instruction
to trust title/summary fields.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When doc_context is available, limit history to just 4 messages (2 exchanges)
to prevent stale answer patterns from overriding fresh document search results.
Without RAG results, keep 10 messages for normal conversation context.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The AI reply often contains full document content (passport details, etc.)
which the memory extraction LLM incorrectly stores as user facts. Limiting
to 200 chars avoids including document content while keeping the gist.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
30 messages of "only one passport" history overwhelmed fresh RAG results.
Reducing to 10 messages (5 exchanges) provides enough conversation context
without letting stale patterns dominate.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Two changes:
1. Reorder messages: doc_context now placed RIGHT BEFORE the user message
(after chat history), so fresh search results override historical patterns
where the bot repeatedly said "only one passport"
2. Strengthen doc_context instructions: explicitly tell LLM that fresh search
results override chat history, and to list ALL matching documents
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The memory extraction prompt was extracting facts from RAG search results
(e.g., passport holder names) and storing them as if they were facts about
the user. Added explicit instruction to only extract facts the user directly
states about themselves.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
With only 3 results, passport queries often miss family members since
all passport files have similar low relevance scores. Increasing to 10
ensures all related documents are included in LLM context.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Raise VAD thresholds (activation 0.65→0.75, min speech 0.4→0.6s,
min silence 0.55→0.65s) to reduce false triggers from background noise
- Add "focus on latest message" instruction to all prompts (voice + text)
- Add "greet and wait" behavior for new conversations instead of auto-continuing
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add rag_key_manager.py: stores encryption key in private E2EE room
- Bot loads key from Matrix on startup, injects into RAG via portal proxy
- No plaintext key on disk (removed RAG_ENCRYPTION_KEY from .env)
- Pass owner_id (matrix_user_id) to RAG search for user isolation
- Stronger format_context instructions for source link rendering
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
DocumentRAG class now prefers local RAG endpoint (RAG_ENDPOINT env var)
over central portal API. When RAG_ENDPOINT is set, searches go to the
customer VM encrypted RAG service on localhost:8765. Falls back to
portal API for unmigrated customers.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When v2 API returns 401 (scope mismatch with classic OAuth tokens),
fall back to v1 REST API which accepts classic scopes. Also provides
clear error message asking user to re-authorize if both fail.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Switch from /wiki/rest/api/content to /wiki/api/v2/pages.
V2 requires space ID instead of key, so resolve via /api/v2/spaces first.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Video track kind is 2 (not 0) in LiveKit Python SDK — camera was never captured
- Replace broken confluence_collab.create_page import with direct REST API call
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Remove all !ai command handling (help, models, set-model, search, etc)
- Remove legacy user_keys system (WildFiles API key storage)
- Remove docs connect/disconnect commands
- Bot now responds to all DM messages and @mentions naturally
- Settings managed exclusively via matrixhost.eu portal
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Remove WILDFILES_BASE_URL and WILDFILES_ORG env vars
- Rename _wildfiles_org_cache to _documents_cache
- Update _has_documents() to use provider=documents
- Remove "wildfiles connect" command alias (keep "docs connect")
- Remove WILDFILES env vars from docker-compose.yml
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
DocumentRAG now calls MatrixHost /api/bot/documents/search instead of
the WildFiles API. Removes device auth flow and legacy org provisioning.
Bot authenticates via existing BOT_API_KEY pattern.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Connect the Matrix AI bot to customer WildFiles orgs via the MatrixHost
portal API instead of requiring manual !ai wildfiles connect. The bot
now auto-resolves the user document org on every message, enabling
seamless RAG document search for all MatrixHost customers.
- Add _get_wildfiles_org() with portal API lookup and session cache
- Update DocumentRAG.search() to accept org_slug (no API key needed)
- Add DocumentRAG.get_org_stats() for org-based stats
- Update context building to use portal org lookup with legacy fallback
- Add !ai docs connect/disconnect aliases
- Rebrand all user-facing messages from WildFiles to Documents
- !ai wildfiles connect now checks portal first, shows auto-connect msg
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When browse_url fails with DNS resolution error (common with STT-misrecognized
domain names like "klicksports" instead of "clicksports"), automatically try a
web search to find the correct domain and retry. Applied to both text and voice bot.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add semantic search over past conversations alongside existing memory facts.
New conversation_chunks table stores user-assistant exchanges with LLM-generated
summaries embedded for retrieval. Bot queries chunks on each message and injects
relevant past conversations into the system prompt. New exchanges are indexed
automatically after each bot response.
Memory-service: /chunks/store, /chunks/query, /chunks/bulk-store endpoints
Bot: chunk query + formatting, live indexing via asyncio.gather with memory extraction
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Both bots can now fetch and read web pages via browse_url tool.
Uses httpx + BeautifulSoup to extract clean text from HTML.
Complements existing web_search (Brave) with full page reading.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
