Knowledge base: fold the embedding provider base URL into the snippet
fingerprint so re-pointing the provider triggers a reindex even when the
model name is unchanged. Reject empty knowledge base content. Cap
concurrent background snippet embeds at 4 and tie embedding work to the
app lifecycle context. Reindex when the embedding base URL changes, not
just the model or dimensions.
Prompt injection: neutralize << >> block delimiters in snippets,
transcripts, subjects, and contact fields so untrusted content can't
forge a boundary the model relies on.
OTP: set the verified flag inside the Lua match script so verification
is atomic. Only count codes that were actually emailed toward the resend
cap, and check the cap before sending instead of incrementing up front.
Tools: fetch only the enabled tools among the allowed IDs, and route all
registrations through one helper so custom tools can't shadow built-ins.
Agent queue: hand a dropped response job off to a human instead of
leaving the conversation assigned to the assistant with no reply.
Also let GetAllConversationMessages return every message when limit is
non-positive, populate admin forms without triggering validation, and
default the copilot name to Juno.
The AI agent and embedding goroutines only stopped on ctx cancellation.
main() never waited for them, so a worker mid-reply could still hit the
database after db.Close() ran.
Give both AI managers a Close() that stops accepting new work and waits for
in-flight workers, matching the existing webhook/sla shutdown pattern. Wire
aiAgent.Close() and ai.Close() into main's shutdown right after the HTTP
server stops, so in-flight work finishes while its dependencies are still up
and before the database closes. Queued-but-unstarted jobs are dropped since
ctx is already cancelled - shutdown stays fast instead of grinding through a
backlog of slow AI calls.
Custom tools can now require a verified contact before they run. This gives tools a trustworthy signal about who the customer is without relying on DMARC or the JWT login.
ai_tools gets a requires_verification column, defaulting to true (fail-closed). A flagged tool is blocked in httpTool.Execute until the conversation is verified, and every tool call now carries an X-Libredesk-Contact-Verified header so tool authors can tell an OTP-verified contact from a self-claimed one.
The AI agent gets three native tools: send_email_verification emails a 6-digit code out of band, check_email_verification confirms it, and set_contact_email lets an anonymous visitor add an email to send the code to. Codes and the verified window live in Redis, scoped per conversation, with attempt and resend caps. JWT livechat contacts stay trusted without OTP; email contacts and visitors verify by code.
The tool admin form gets a "require verified contact" toggle (default on) with a confirm dialog when turning it off.
Tool auth used to be a single header/value pair. It is now a list of
headers, each value encrypted at rest and masked in the API. Editing a
tool keeps an untouched (masked) value's existing secret, matched by
header name. Covered with unit tests.
Agent tuning: a full agent run is now capped (90s for livechat since the
customer is watching, 3min for email), the per-provider-call timeout
drops 90s to 60s with 2 retries, and default worker_count goes 2 to 10
for burst headroom. Idle workers are free; the run cap is what protects
the pool.
Also adds help text and placeholders across the AI admin pages.
Move the webhook SSRF guard into a shared internal/ssrf package and wire it
into every place the server fetches an admin-set URL: webhooks, OIDC discovery,
the AI provider base URL, and custom AI tool calls. Add a global [ssrf] config
block, off by default with an allowed_cidrs bypass, so single-tenant self-hosters
keep reaching internal hosts while multi-tenant or hosted deploys can turn it on.
The old [webhook] allowed_hosts key is still read for backward compat and folds
into the guard.
Medium (title + short body):
add WIP autonomous AI agent
New internal/aiagent package runs AI assistants that reply to customers
on conversations assigned to them, grounded on a knowledge base. Also mines
resolved conversations for FAQ suggestions. Adds admin UI and the v2.7.0
schema. Still work in progress.
Convs and messages now push the full list-row payload to perm-authorized agents on create/assign/message, so livechat returning customers bubble up instantly without waiting for the timer refresh. Background list refresh bumped 30s -> 60s as a drift safety net.
- New meta JSONB field in CSAT responses to capture random adhoc data as that might be needed for custom CSAT pages.
- Add support prefilled rating for csat pages picked from query param
- Refactor widget.js.
- Fix possible race conditions in inbox reload logic.
- Reload only the updated inbox when an inbox is updated / created not all.
- Retain last inbox while navigatin back from admin -> inbox
- Translate web template pass i18n dependency
- Fix colors in menu card
- Show update description if avaialble in AppUpdate component
- Remvoe i18n from settings as i18n and settings depend on each other to load initial lang.
- Clear inbox password as the update SQL query now returns the config.
- Fetch agents and inboxes from the store instead of directly fetching using axios instance.
feat: Add HTTP utility functions for trusted origin checks
feat: Implement typing status broadcasting for live chat clients and agents.
feat: Add support for signed URLs in media manager
fix: Update database migration to handle duplicate visitors with same email address.
feat: Add conversation subscription and typing message models for WebSocket communication
feat: Implement conversation subscription management in WebSocket hub this is used for broadcasting typing indicator.
feat: Revamp widget JavaScript to improve mobile responsiveness and show unread messages if any.
- new vue app for serving live chat widget, created subdirectories inside frontend dir `main` and `widget`
- vite changes for both main app and widget app.
- new backend live chat channel
- apis for live chat widget
- single table stores acitivites against entities, actors, timestamps, ip addresses and activity description.
- admin page to view, sort and filter activity logs.
- new `activity_logs:manage` permission
Abhinav Raut