The v1 /wiki/rest/api/content/{id} endpoint returns 410 Gone.
Switch to /wiki/api/v2/pages/{id} with body-format=storage parameter.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add AtlassianClient class: fetches per-user OAuth tokens from portal,
calls Jira and Confluence REST APIs on behalf of users
- Add 7 Atlassian tools: confluence_search, confluence_read_page,
jira_search, jira_get_issue, jira_create_issue, jira_add_comment,
jira_transition
- Replace single LLM call with agentic loop (max 5 iterations)
that feeds tool results back to the model
- Add PORTAL_URL and BOT_API_KEY env vars to docker-compose
- Update system prompt with Atlassian tool guidance
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Single source of truth at christian/confluence-collab.git — eliminates stale copy drift.
Dockerfile COPY unchanged, works identically with submodule.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace inline regex section parser in voice.py with confluence_collab
library (BS4 parsing, 409 conflict retry). Bot now loads section outline
into LLM context when Confluence links are detected.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Three issues fixed:
1. Confluence URLs were detected but content never fetched - now reads
the actual page via API so the LLM can work with it
2. Room document context (PDFs, Confluence, images) was stored but never
passed to the text LLM - now included as system message
3. Conversation history increased from 10 to 30 messages for better
context in collaborative sessions
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Voice bot can now see the users camera or screen share when asked.
Captures a single frame, encodes as JPEG, sends to Sonnet vision
with full context (transcript + document). Triggered by phrases like
schau mal, siehst du das, can you see this.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
"bist du dir sicher" / "are you sure" / "stimmt das wirklich" now also
trigger Opus escalation for fact-checking the previous answer.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Sonnet can now escalate complex questions to Opus via a function tool,
same pattern as search_web and read_confluence_page. Full context
(transcript + document) is passed automatically. Triggered by user
phrases like "denk genauer nach" / "think harder" or when Sonnet is
unsure about complex analysis.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When a voice call ends and a document was loaded in the room, the bot
now analyzes the transcript for document-specific changes/corrections
and posts them as a structured "Dokument-Aenderungen" message. Returns
nothing if no document changes were discussed.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Confluence tools default to active page from room context — no more
asking user for page_id
- Prompt allows roleplay/mock interviews when document context present
- Explicit instruction not to ask for page_id
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Short links like /wiki/x/AQDbAw are resolved via redirect to get numeric
page ID. Also adds CONFLUENCE_* env var declarations to bot.py module level.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Enable realtime Confluence page editing during Element Call voice sessions.
- Add read_confluence_page and update_confluence_page function tools
- Detect Confluence URLs shared in Matrix rooms, store page ID for voice context
- Section-level updates via heading match + version-incremented PUT
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add RoomEncryptedFile handler for PDFs/docs in encrypted rooms
- Tell summary LLM not to include headings (prevents duplicate)
- Strip <br/> after block elements in _md_to_html
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Generalize PDF-only voice context to support all document types:
- Rename _room_pdf_context → _room_document_context (list-based, 5 cap)
- Handle .docx (python-docx), .txt, .md, .csv, .json, .xml, .html, .yaml, .log
- Store AI image descriptions for voice context
- Multi-document context building with type labels and per-type truncation
- _respond_with_ai now returns reply text for caller use
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Pass PDF document context from room to voice session so the voice LLM
can answer questions about uploaded PDFs. Persist call transcripts and
post an LLM-generated summary to the room when the call ends.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Store user timezone as [PREF:timezone] in memory service
- Query timezone preference on session start, override default
- Add set_user_timezone tool so bot learns timezone from conversation
- On time-relevant questions, bot asks if user is still at stored location
- Seeded Europe/Nicosia for @christian.gick:agiliton.eu
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Bot now knows the user's timezone (Europe/Berlin default) and which
LLM model it's running on, so it can answer questions about both.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Removing the blocking wait entirely caused DEC_FAILED - the rotated key
had not arrived via nio sync before the pipeline started. Restore a short
3s wait (down from 10s) which is enough for nio to deliver the rotated key.
Also fix on_mute/on_unmute arg order (participant, publication - not reversed).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Replace _extract_voice_memories with _store_voice_exchange
- Store raw "User: ... / Assistant: ..." pairs directly
- No LLM call needed — faster, cheaper, no lost context
- Load as "Frühere Gespräche" with full thread context
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
flash_v2_5 had audible compression artifacts. multilingual_v2 has higher
fidelity while speed=1.15 via VoiceSettings still gives snappier delivery.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Model: eleven_multilingual_v2 → eleven_flash_v2_5 (lower latency)
- Speed: 1.15x via VoiceSettings
- Stability/similarity tuned for natural German speech
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
EC rotates encryption key when bot joins LiveKit room. The rotated
key arrives via Matrix sync 3-5s later. Previous 2s wait was too
short - DEC_FAILED before new key arrived.
Extended wait to 10s. Added logging to bot.py to trace why late
key events were not being processed.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The HKDF sed patch in Dockerfile was wrong — it swapped salt/info
based on incorrect analysis of minified JS. The original Rust FFI
parameters are correct: salt="LKFrameEncryptionKey", info=[0;128].
Also removed Python-side HMAC pre-ratcheting of keys. Element Call
uses explicit key rotation via Matrix events, not HMAC ratcheting.
Added diagnostic logging to trace exact key bytes during E2EE setup.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
EC JS SDK uses: salt=Uint8Array(8), info=encode("LKFrameEncryptionKey")
Rust FFI used: salt=ratchet_salt, info=[0u8;128]
The salt and info parameters were swapped, causing DEC_FAILED on every
call. This patch fixes the Rust HKDF derivation in the Dockerfile
before cargo build.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Allows disabling E2EE for diagnostic purposes. When disabled, bot
connects to LiveKit without frame encryption.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Inline E2EE options had 3 wrong values vs Element Call JS SDK:
- failure_tolerance=-1 (infinite, hid all DEC_FAILED) → 10
- key_ring_size=16 (too small, keys overflow) → 256
- ratchet_window_size=16 (wrong) → 10
Now uses _build_e2ee_options() which was already correct but never called.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
ElevenLabs scribe_v2_realtime also produces non-asterisk artifacts like
"Untertitel: ARD Text im Auftrag von Funk (2017)" from TV/radio audio.
Add pattern matching for subtitle metadata, copyright notices, and
parenthetical/bracketed annotations.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace Jack Marlowe (slow/raw) with Robert Ranger (deep/natural) for
a more pleasant conversational voice assistant experience.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace broken _VoiceAgent stt_node override with _NoiseFilterAgent that uses
on_user_turn_completed() + StopResponse. This operates downstream of VAD+STT
so no backpressure risk to the audio pipeline.
When ElevenLabs scribe_v2_realtime produces *Störgeräusche* etc., the agent
now silently suppresses them before the LLM responds. The prompt-based filter
is kept as defense-in-depth.
Fixes: MAT-41
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The _count_frames coroutine created a second rtc.AudioStream on the caller's
audio track, competing with AgentSession's internal pipeline for event loop
time. Under load, this caused VAD to miss speech → user_state stuck on "away".
- Remove _count_frames AudioStream (debugging artifact)
- Add VAD state diagnostics (speaking count, away duration)
- Add VAD watchdog: warns if user_state=away >30s (MAT-40 detection)
Fixes: MAT-40
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
