odoo_client.attach_call_artifacts posts the transcript to the lead's chatter
(readable in place) and attaches transcript_<sid>.txt + the stereo call WAV.
bot.py wires it post-call: extract_and_record now returns the Odoo ref
(persisted_to), the in-call tool path stamps it too, the audiobuffer handler
records the saved WAV path, and the attach runs in a thread after the lead
lands (brief wait for the async WAV write; failures only log — the lead is
already safe). Verified e2e against db1: create -> attach -> verify -> delete.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Reliability drill finding: xmlrpc.client has no default timeout, and the call
slot is released only after run_agent returns (which awaits post-call
persistence). A hung -- not refused -- Odoo would block forever; two hung
persists would leave the phone line permanently at capacity ("busy") until a
restart. All XML-RPC round-trips now use a 15s socket timeout
(ODOO_TIMEOUT_SECS), http and https transports both covered.
Drilled: black-hole address fails cleanly at the timeout; real auth unaffected.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
A caller asking if their already-purchased frames were ready got railroaded
through the booking script and hung up. AVA had no path for requests it can't do
on the phone.
- Prompt: classify intent first — question (answer it), can't-do request (take
name + a one-line note, confirm callback number, promise a staff callback;
never force booking questions), or booking (the ordered steps).
- extract.py: request_type = appointment | callback | none. Callback gate needs
a name or a request note. Records kind.
- practice.py / odoo_client.py: callbacks write a "📞 Callback request" lead
(name, callback number, what they need) instead of an appointment card.
Verified the classifier: frames-status -> callback, booking -> appointment,
pure question -> none.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- Reason visibility: the reason WAS extracted ("disintegrated eyes") but only
lived in the Odoo description note. Add it to the post-call log line and to
the Odoo lead title so it's visible at a glance.
- Latency: split the timing — Whisper is ~0.1s, latency is LLM-side. The ~3s
tail was cold model reloads after Ollama's keep-alive expired. server.py now
warms + pins the model on startup (keep_alive=-1, ollama ps UNTIL=Forever),
removing cold first-turn stalls. Whisper size left alone (not the bottleneck).
- CLAUDE.md: insurance rule (never suggest/guess the plan), latency note.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
In-call (system prompt + per-call calendar injection):
- Gather full name (prompt asks for last name if only first given).
- Confirm the caller-ID number; if declined, use the number the caller gives.
- Ask for and LOG insurance only — never promise/confirm/deny coverage or
treatment based on it; staff verify on callback.
- Validate the requested date against an injected 45-day calendar (recomputed
per call since the server is long-running). Push back on impossible/mismatched
dates, e.g. "Monday lands on the sixth — would you like that date?".
- AGENT_NAME=AVA; 4s grace pause before hang-up (HANGUP_DELAY_SECS).
Logging (post-call extraction -> Odoo):
- Extract full name, phone_confirmed, chosen callback (caller-ID or alternate),
insurance, reason, and preferred time annotated with a resolved YYYY-MM-DD
date (today's date is fed to the extractor).
- odoo_client: insurance row on the lead note (log only — staff verify).
.gitignore: ignore rotated avc_run.log* files.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
