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>
No more shared org-level document search for unauthenticated users.
DocumentRAG.search() now returns empty if no API key provided.
Explicit !ai search command tells users to connect first.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The _md_to_html method was missing horizontal rule conversion, so ---
rendered as literal dashes. Now converts to <hr/> and strips adjacent
<br/> tags for clean spacing.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
System prompt now strictly forbids #/##/### headings and --- rules.
Uses **bold** for section titles instead, with no blank lines between
title and content, to eliminate excessive whitespace in Element.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- System prompt now requires inline source links next to each claim
instead of a separate "Quellen:" section at the bottom
- Use bold for sub-headings instead of ## to reduce padding/whitespace
- Limit horizontal rules for tighter message layout
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Format search results as markdown links: [Title](URL)
- System prompt now requires a "Quellen:/Sources:" section with
clickable links whenever web_search is used
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The text bot had no websearch capability while the voice agent did.
Added Brave Search integration as a web_search tool so the bot can
answer questions about current events and look up information.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The auto-detect language + translation menu was misidentifying regular
German messages and blocking normal responses. Bot now simply responds
in whatever language the user writes in, per updated system prompt.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Bare variable references in environment: override env_file values
with the host shell value (empty). SENTRY_DSN is already loaded
via env_file: .env, so the explicit references were zeroing it out.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
