## Linear ticket
https://linear.app/chatwoot/issue/CW-7187/voice-calls-followup-tasks
## Description
Improvements to the WhatsApp voice-calling experience plus a cheaper,
more accurate audio-transcription model.
- First-time callers now get a real name. An inbound WhatsApp call
creates the contact from the caller's WhatsApp profile name instead of
the bare phone number.
- Clear, consistent call attribution. Call bubbles show a unified
"Handled by {agent}"
- Cleaner call widget. The dismiss (✕) button is shown only for incoming
calls
- WhatsApp calling for manual inboxes. voice_calling_supported? now
covers any whatsapp_cloud inbox
- Transcription: whisper-1 → gpt-4o-mini-transcribe.
## Type of change
- [ ] New feature (non-breaking change which adds functionality)
## Checklist:
- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [ ] My changes generate no new warnings
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged and published in downstream
modules
## Description
This is the first PR in a series of PRs for Introducing unread counts in
the sidebar for inboxes and labels.
In this PR:
* Added the unread store, counter and builder modules
* Added redis keys for unread count management
* Added specs for all 3 modules, some specs are for testing enterprise
only feature like specific roles and permissions which are added in the
respective enterprise folder itself.
**Note**
None of this changes affect anything else and nothing is wired to
existing modules.
Issue:
https://linear.app/chatwoot/issue/CW-6851/support-unread-conversation-counts
## Type of change
Please delete options that are not relevant.
- [ ] Bug fix (non-breaking change which fixes an issue)
- [x] New feature (non-breaking change which adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality not to work as expected)
- [ ] This change requires a documentation update
## How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration.
## Checklist:
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [ ] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged and published in downstream
modules
---------
Co-authored-by: Sojan Jose <sojan@pepalo.com>
Stop the onboarding flow from writing the user's company website into
`accounts.domain`. That column is reserved for the inbound email domain
used to construct reply-to addresses (`reply+<uuid>@<domain>`), and
silently overloading it from onboarding was breaking email continuity
for accounts whose domain MX didn't point at Chatwoot's inbound —
customer replies were going to an unreachable address.
The website value now lives in `custom_attributes.website`, which is
what the rest of the app already treats as the "company website" field.
Adds the server-side flow that turns Meta WhatsApp Cloud Calling
webhooks into Chatwoot Calls, conversations, voice_call message bubbles,
and ActionCable broadcasts. Stacked on top of #14312 (PR-2 — provider
methods); intentionally does not include the HTTP controller, routes, or
frontend (those land in PR-4 and PR-9).
## Closes
- Part of the WhatsApp Cloud Calling rollout. Linear: TBD
## What changed
**Webhook routing**
- `app/jobs/webhooks/whatsapp_events_job.rb` — append
`prepend_mod_with('Webhooks::WhatsappEventsJob')` so EE can extend it
without forking.
- `enterprise/app/jobs/enterprise/webhooks/whatsapp_events_job.rb` (new)
— overlay that prepends `handle_message_events` to intercept `field:
'calls'` payloads (route to `Whatsapp::IncomingCallService`) and
`interactive.call_permission_reply` messages (route to
`Whatsapp::CallPermissionReplyService`); falls through with `super` for
regular messages.
**Services**
- `enterprise/app/services/whatsapp/incoming_call_service.rb` (new) —
gated on `provider_config['calling_enabled']`; processes `connect`
(creates inbound call via `Voice::InboundCallBuilder` or transitions an
existing outbound call to `in_progress`) and `terminate` events; updates
conversation `additional_attributes` and broadcasts
`voice_call.incoming`/`voice_call.outbound_connected`/`voice_call.ended`.
- `enterprise/app/services/whatsapp/call_permission_reply_service.rb`
(new) — handles WhatsApp interactive `call_permission_reply` replies;
clears the conversation's `call_permission_requested_at` flag and
broadcasts `voice_call.permission_granted` so the agent UI can re-enable
the call button.
**Builder/model adjustments**
- `enterprise/app/services/voice/inbound_call_builder.rb` —
provider-agnostic; accepts `provider:` and `extra_meta:` kwargs, drops
`account:` (now derived from `inbox.account` to keep the param count
under rubocop's ceiling without disabling cops), uses digits-only
`source_id` for WhatsApp ContactInbox (validation requires
`^\d{1,15}\z`), skips Twilio-only `conference_sid` for non-Twilio
providers.
- `enterprise/app/services/voice/call_message_builder.rb` — adds
`create!`/`update_status!` API and `CALL_TO_VOICE_STATUS` map; uses
direct `Message.create!` (bypasses `Messages::MessageBuilder`'s
incoming-on-non-Api-inbox guard, which would otherwise reject the system
bubble); content is `'WhatsApp Call'` for WhatsApp and `'Voice Call'`
for Twilio. Backwards-compatible `perform!` retained for the existing
Twilio call sites.
- `enterprise/app/models/call.rb` — adds `default_ice_servers` (driven
by `VOICE_CALL_STUN_URLS` env), `direction_label` alias for the
`inbound`/`outbound` strings the FE expects, and
`ringing?`/`in_progress?`/`terminal?` predicates used throughout the
pipeline.
**Outgoing-channel guard**
- `app/services/base/send_on_channel_service.rb` — extends
`invalid_message?` to skip messages with `content_type == 'voice_call'`.
Without this, agent-initiated outbound calls (PR-4) would deliver
\"WhatsApp Call\" as a text message to the contact every time.
**Twilio call-site update**
- `enterprise/app/controllers/twilio/voice_controller.rb` — drops the
now-redundant `account: current_account` kwarg from the
`Voice::InboundCallBuilder.perform!` call.
**Tests**
- New: `spec/enterprise/services/whatsapp/incoming_call_service_spec.rb`
(5 examples — calling-disabled, inbound connect, outbound connect,
terminate completed, terminate no-answer, unknown event).
- New:
`spec/enterprise/services/whatsapp/call_permission_reply_service_spec.rb`
(3 examples — accept, reject, calling-disabled).
- Updated: `spec/enterprise/services/voice/inbound_call_builder_spec.rb`
and `spec/enterprise/controllers/twilio/voice_controller_spec.rb` to
drop the `account:` kwarg from call expectations.
## How to test
In `rails console` against an account with a WhatsApp inbox where
`provider_config['calling_enabled']` is true:
```ruby
inbox = Inbox.find(<id>)
params = { calls: [{ id: 'wacid_test', from: '15550001111', event: 'connect',
session: { sdp: 'v=0...', sdp_type: 'offer' } }] }
Whatsapp::IncomingCallService.new(inbox: inbox, params: params).perform
# => Conversation + Call (status: 'ringing', provider: 'whatsapp') + voice_call message bubble
# => ActionCable broadcasts `voice_call.incoming` to the assignee or account-wide
# Then terminate it:
Whatsapp::IncomingCallService.new(inbox: inbox,
params: { calls: [{ id: 'wacid_test', event: 'terminate', duration: 0, terminate_reason: 'no_answer' }] }
).perform
# => Call status flips to 'no_answer', message bubble updates, `voice_call.ended` broadcast fires
```
End-to-end browser flow (Meta → cable → UI) requires the controller from
PR-4 and the frontend from PR-9.
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When a new account finishes onboarding we want to land them on a
dashboard with a working web widget already configured, branded, named,
and assigned to them, instead of an empty inbox list. This PR adds the
services that produce that widget. **No user-visible change yet:** the
services are dormant until the trigger and background job are wired up
in the follow-up PR.
## Context
Milestone 1 added `Account::BrandingEnrichmentJob`, which calls
context.dev during signup and stores brand data on
`account.custom_attributes['brand_info']`, plus the new onboarding form
that captures `domain`, `name`, `industry`, etc. Milestone 2 starts
using that data, and the first thing we want is a web widget
materialized automatically. Splitting the service layer from the
orchestration plumbing (Redis key, `onboarding_step` extension,
controller wiring, ActionCable) keeps this diff focused and lets the
LLM/widget logic merge independently.
## How to test
Run against an existing account that already has `brand_info` populated.
```ruby
account = Account.find(<account_id>)
user = account.administrators.first
inbox = WidgetCreationService.new(account, user).perform
inbox.channel.widget_color # color from brand_info, or '#1f93ff'
inbox.channel.welcome_title # brand_info[:title], or account.name
inbox.channel.welcome_tagline # LLM tagline (Enterprise + system key set),
# else brand_info[:slogan]/[:description]/nil
inbox.inbox_members.pluck(:user_id)
```
Toggle `InstallationConfig['CAPTAIN_OPEN_AI_API_KEY']` to flip between
LLM and brand-text tagline paths. To verify failure isolation, raise
inside `Captain::Llm::WidgetTaglineService#perform` and confirm widget
creation still succeeds with the fallback tagline.
## Linear Ticket
-
https://linear.app/chatwoot/issue/CW-6875/captain-credits-3-bugs-in-stripe-subscription-lifecycle-cancel-ratchet
## Description
Fixes Captain credit settlement on subscription cancellation. Previously
`limits['captain_responses']` and `captain_responses_usage` were left in
their pre-cancellation state, which caused incorrect credit totals when
a customer re-subscribed. Cancellation now settles the monthly allotment
(preserving any remaining topup) and resets the usage counter.
## Type of change
- [ ] Bug fix (non-breaking change which fixes an issue)
## How Has This Been Tested?
1. Set up an account subscribed to a paid plan (e.g. Startups) so
`limits['captain_responses']` reflects the plan allotment.
2. Fire `customer.subscription.deleted` for that account's Stripe
customer. Confirm the limits.
3. Fire `customer.subscription.updated` re-subscribing to the paid plan.
Confirm the limits.
4. Repeat cancel → re-subscribe several times;
## Checklist:
- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [ ] My changes generate no new warnings
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged and published in downstream
modules
# Pull Request Template
## Description
Captain (v1) makes false promises by saying it will handoff but doesn't.
This happens due to an exact string match comparison and the prompt
gives the model a lot of responsibilities:
- identity
- what to respond
- obey custom instructions
- decide on tool calls
This PR decouples responsibility, the core prompt responds, and an
additional llm call evaluates if handoff was needed or not after that
message.
## Type of change
- [x] Bug fix (non-breaking change which fixes an issue)
## How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration.
Locally
## Checklist:
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [x] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] Any dependent changes have been merged and published in downstream
modules
Two production-grade fixes to the existing audio transcription service.
**Independent of the WhatsApp Calling work** — these affect every audio
attachment that goes through Whisper (voice notes, call recordings,
voicemails, etc.).
## Closes
- [PLA-151 — PR-5: Recording Upload + Transcription
Pipeline](https://linear.app/chatwoot/issue/PLA-151/pr-5-recording-upload-transcription-pipeline)
## Why this is needed
### 1. Whisper rejects payloads larger than 25 MB
OpenAI's [Whisper
API](https://platform.openai.com/docs/guides/speech-to-text) hard-caps
file uploads at 25 MB. Long audio recordings — voice notes from chatty
contacts, ~70+ min Opus call recordings — currently hit OpenAI with the
full payload and 413 (\`Payload Too Large\`). The job retries via the
existing \`Faraday::BadRequestError\` discard path, but the agent still
sees a transcription failure for an attachment we knew was too big up
front.
This PR adds a pre-flight \`audio_too_large?\` check via the blob's
\`byte_size\` and returns a controlled error without hitting OpenAI. The
audio attachment is preserved (agents can still listen), only the
transcription is skipped.
### 2. Whisper hallucinates on silence at non-zero temperature
At \`temperature: 0.4\` (the previous value), Whisper produces
well-documented hallucinated repeats on silence and near-silent segments
— e.g. \`Oh, dear. Oh, dear. Oh, dear.\` filling the transcript. This
shows up in real recordings whenever there's a hold or quiet moment.
\`temperature: 0.0\` matches OpenAI's recommended default for
transcription and eliminates the spirals.
Reference:
[openai/whisper#928](https://github.com/openai/whisper/discussions/928),
[openai-python#1010](https://github.com/openai/openai-python/issues/1010).
## Are WhatsApp call recordings already handled?
Yes — by the existing pipeline, **before this PR**:
\`\`\`
Browser MediaRecorder → upload_recording (PR-4)
→ @call.message.attachments.create!(file_type: :audio, ...)
→ Enterprise::Concerns::Attachment#enqueue_audio_transcription
(after_create_commit hook)
→ Messages::AudioTranscriptionJob.perform_later(attachment.id)
→ Messages::AudioTranscriptionService → Whisper
\`\`\`
The \`after_create_commit\` hook already fires for every audio
attachment regardless of source. PR-4's \`upload_recording\` endpoint
creates the attachment; the existing job/service take it from there. No
new wiring needed.
This PR just makes the existing service more robust:
- Calls longer than ~70 min (Opus 48 kbps) no longer 413 against OpenAI
- Quiet recordings no longer produce hallucinated transcripts
## How to test
\`\`\`ruby
# In rails console with a real audio attachment:
service = Messages::AudioTranscriptionService.new(Attachment.audio.last)
# Normal-sized audio: unchanged behaviour
service.perform # => { success: true, transcriptions: ... }
# Large audio: new guard returns error instead of 413-ing OpenAI
allow(attachment.file.blob).to
receive(:byte_size).and_return(30.megabytes)
service.perform # => { error: 'Audio too large for Whisper' }
\`\`\`
Existing transcription specs cover the happy path; one new spec
exercises the byte-limit guard.
## Risk
Low. Both changes are pre-flight guards or parameter values — they
reduce the surface of OpenAI calls that can fail. Failure to transcribe
is already non-fatal (the audio attachment is preserved either way).
When an inbound voice call ends, the conversation bubble now (1) renders
an inline audio player as soon as Twilio finishes the recording and (2)
shows the call duration alongside "Call ended" so the agent gets the
at-a-glance summary without opening the recording.
Fixes
https://linear.app/chatwoot/issue/PLA-118/feat-recordings-on-calls-should-be-attached-on-the-conversation
and
https://linear.app/chatwoot/issue/PLA-119/duration-of-the-call-is-not-visible-on-the-chat-bubble
## How to test
1. Set up a Twilio voice inbox and trigger an inbound call.
2. Answer the call from an agent, talk for a few seconds, then hang up.
3. As soon as the call ends, the bubble should read **"Call ended —
0:NN"** (where NN is the call duration in seconds).
4. Wait a few seconds for Twilio to finish processing the recording
(usually <30s after hangup).
5. The same bubble should now show an inline audio player below the
duration. Press play; the recording should be audible.
6. Refresh the page — both the duration and the player should still be
there.
7. End a second call on the same conversation — its bubble should get
its own duration + player, independent of the first.
---------
Co-authored-by: Muhsin <12408980+muhsin-k@users.noreply.github.com>
Adds the Meta WhatsApp Cloud API surface needed for browser-based
calling. This is the second slice of the WhatsApp calling feature,
sitting on top of `feat/voice-call-model-wiring` and consumed by later
PRs (incoming-webhook pipeline, call service, frontend).
This PR ships only the provider-level HTTP wrapper and one error class.
It is feature-flag-free and does not change any user-visible behaviour
on its own — without later PRs, no caller invokes these methods.
## Linear
-
https://linear.app/chatwoot/issue/PLA-148/pr-2-meta-cloud-api-provider-methods
## What changed
- Add `Whatsapp::Providers::WhatsappCloudCallMethods`
(`enterprise/app/services/whatsapp/providers/whatsapp_cloud_call_methods.rb`)
wrapping six Meta endpoints:
- `pre_accept_call`, `accept_call`, `reject_call`, `terminate_call` —
`POST /{phone_id}/calls` with the relevant action payload.
- `send_call_permission_request` — `POST /{phone_id}/messages`
interactive `call_permission_request`.
- `initiate_call` — `POST /{phone_id}/calls` with `audio`/`offer`
session.
- Prepend the module into `Whatsapp::Providers::WhatsappCloudService`
only if defined, so OSS continues to work without the enterprise
overlay.
- Add `Voice::CallErrors::NoCallPermission`
(`enterprise/lib/voice/call_errors.rb`) — raised when Meta returns error
code `138006` from `initiate_call`. The remaining call-service errors
(`NotRinging`, `AlreadyAccepted`, `CallFailed`) will land with PR-4.
## How to test
There is no UI in this PR. Smoke-test from a Rails console with a
WhatsApp inbox configured for calling:
```ruby
inbox = Inbox.find(<id>)
svc = inbox.channel.provider_service
svc.respond_to?(:initiate_call) # => true
svc.respond_to?(:send_call_permission_request) # => true
# Optional live calls (require a real phone + Meta call-permission opt-in):
svc.send_call_permission_request('15551234567')
svc.initiate_call('15551234567', '<sdp_offer>')
```
Failure path: `initiate_call` against a contact who has not granted call
permission should raise `Voice::CallErrors::NoCallPermission` with
Meta's user-facing message.
Twilio voice now uses first-class `Call` records as the source of truth
for call state, instead of storing it on
`conversation.additional_attributes` and `conversation.identifier`. Each
call gets its own record, its own `voice_call` bubble matched by
`call_sid`, and its own conference name keyed off `Call.id`. Multiple
calls on the same conversation (for `lock_to_single_conversation`
inboxes) now work correctly, and the conversation card stays in sync
with the real latest message.
Fixes https://linear.app/chatwoot/issue/PLA-121/lock-to-single-thread
---------
Co-authored-by: Muhsin <12408980+muhsin-k@users.noreply.github.com>
# Pull Request Template
## Description
- Wires up Controllers to auto-sync job
- adds plan based sync schedule
- a scheduler that runs every hour to check syncable documents
- guards the whole feature behind feature flag by reclaiming
`twilio_content_templates`
- Adds a global and account level cap on how many documents to enqueue
to prevent sudden burst at first run
- some refactor to simplify code
- specs
Fixes # (issue)
## Type of change
- [x] New feature (non-breaking change which adds functionality)
## How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration.
specs and locally
## Checklist:
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [x] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] Any dependent changes have been merged and published in downstream
modules
Voice calling is now a capability on the existing TwilioSms rather than
a separate Voice model. A single Twilio phone number handles both SMS
and voice calls through one inbox.
Fixes
https://linear.app/chatwoot/issue/CW-6683/add-voice-calling-as-a-capability-on-twilio-sms-channel
and https://linear.app/chatwoot/issue/PLA-120/add-the-support-for-sms
**What changed**
- Replaced Channel::Voice with voice_enabled flag on Channel::TwilioSms
- Added voice_enabled, twiml_app_sid, api_key_secret columns to
channel_twilio_sms table
- Dropped channel_voice table (no production data)
- All voice logic lives in Enterprise layer via
prepend_mod_with('Channel::TwilioSms')
- Added Voice settings tab on Twilio SMS inbox settings to
enable/disable voice
- Validates Twilio number voice capability before provisioning
- Teardown service cleans up TwiML app and credentials when voice is
disabled
- Frontend voice detection uses isVoiceCallEnabled() /
getVoiceCallProvider() helpers — extensible to future providers
- Gated by channel_voice feature flag
**How to test**
1. Enable feature flag:
Account.find(<id>).enable_features('channel_voice')
2. Create voice inbox: Inboxes → Voice tile → enter Twilio credentials →
verify incoming/outgoing calls and SMS work
3. Enable voice on existing SMS inbox: Inboxes → select Twilio SMS inbox
→ Voice tab → toggle on → provide API key credentials → verify calls
work
4. Disable voice: Voice tab → toggle off → verify TwiML app is deleted,
credentials cleared, SMS still works
5. Re-enable voice: Toggle on again → must provide api_key_secret again
→ new TwiML app provisioned
---------
Co-authored-by: Muhsin <12408980+muhsin-k@users.noreply.github.com>
# Pull Request Template
## Description
- Fetch main content only from Firecrawl, exclude some tags to remove
boilerplate
- Prompt changes for FAQ generation
## Type of change
Please delete options that are not relevant.
- [x] Bug fix (non-breaking change which fixes an issue)
## How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration.
tested locally
## Checklist:
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [x] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] Any dependent changes have been merged and published in downstream
modules
Adds the ability to translate help center articles to other languages using Captain's LLM infrastructure. Translated articles are created as drafts linked to the source article.
Fixes
https://linear.app/chatwoot/issue/CW-6901/translate-article-to-another-language
**How to test**
1. Navigate to Help Center → Articles for a portal with multiple locales
2. Click the three-dot menu on any article → "Translate"
3. Select a target language and category → click Translate
4. Switch to the target locale — the translated article appears as a
draft
5. Try translating the same article again — a warning shows the existing
translation with a link to open it in a new tab
6. Click "Overwrite and translate" to replace the existing translation
https://github.com/user-attachments/assets/1d2e991b-f0ac-403a-bcc1-2181b5731ea4
## Linear ticket
https://linear.app/chatwoot/issue/CW-6834/billing-upgrade-didnt-work
## Description
A `customer.subscription.updated` Stripe webhook for account 76162
returned 200 OK but did not persist the new `subscribed_quantity`. Root
cause: a race condition between the webhook handler and
`increment_response_usage` (Captain usage counter), both doing
read-modify-write on the `custom_attributes` JSONB column. The webhook
wrote `quantity: 6`, then a concurrent `save` from
`increment_response_usage` overwrote the entire hash with stale data —
restoring `quantity: 5`.
Fix: use atomic `jsonb_set` so usage counter updates only touch the
single key they care about, instead of rewriting the whole
`custom_attributes` hash. `increment_custom_attribute` also performs the
increment in SQL, making concurrent increments correct as well.
## Type of change
- [x] Bug fix (non-breaking change which fixes an issue)
## How Has This Been Tested?
- New regression spec in `handle_stripe_event_service_spec.rb` that
simulates concurrent webhook + `increment_response_usage` and asserts
both `subscribed_quantity` and `captain_responses_usage` survive
- Existing account, billing, captain, and topup specs all pass locally
## Checklist:
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [x] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged and published in downstream
modules
HandoffTool changes conversation status but only posts a private note.
ResponseBuilderJob now detects the tool flag and creates the public
handoff message that was previously only shown in V1.
# Pull Request Template
## Description
Captain V2 was silently forwarding conversations to humans without
showing a handoff message to the customer. The conversation appeared to
just stop
responding.
Root cause: In V2, HandoffTool calls bot_handoff! during agent
execution, which changes conversation status from pending to open. By
the time control returns
to ResponseBuilderJob#process_response, the conversation_pending? guard
returns early - skipping create_handoff_message entirely. The V1 flow
didn't have this
problem because AssistantChatService just returns a string token
(conversation_handoff) and lets ResponseBuilderJob handle everything.
What changed:
1. AgentRunnerService now surfaces the handoff_tool_called flag (already
tracked internally for usage metadata) in its response hash.
2. ResponseBuilderJob#handoff_requested? detects handoffs from both V1
(response token) and V2 (tool flag).
3. ResponseBuilderJob#process_response checks handoff_requested? before
the conversation_pending? guard, so V2 handoffs are processed even when
the status has
already changed.
4. ResponseBuilderJob#process_action('handoff') captures
conversation_pending? before calling bot_handoff! and uses that snapshot
to guard both bot_handoff!
and the OOO message - preventing double-execution when V2's HandoffTool
already ran them.
New V2 handoff flow:
AgentRunnerService
→ agent calls HandoffTool (creates private note, calls bot_handoff!)
→ returns response with handoff_tool_called: true
ResponseBuilderJob#process_response
→ handoff_requested? detects the flag
→ process_action('handoff')
→ create_handoff_message (public message for customer)
→ bot_handoff! skipped (conversation_pending? is false)
→ OOO skipped (conversation_pending? is false)
Fixes#13881
## Type of change
Please delete options that are not relevant.
- [x] Bug fix (non-breaking change which fixes an issue)
- [ ] New feature (non-breaking change which adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality not to work as expected)
- [ ] This change requires a documentation update
## How Has This Been Tested?
- Update existing response_builder_job_spec.rb covering the V2 handoff
path, V2 normal response path, and V1 regression
- Updated existing agent_runner_service_spec.rb expectations for the new
handoff_tool_called key and added a context for when the flag is true
## Checklist:
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [ ] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] Any dependent changes have been merged and published in downstream
modules
---------
Co-authored-by: Aakash Bakhle <48802744+aakashb95@users.noreply.github.com>
Co-authored-by: aakashb95 <aakashbakhle@gmail.com>
## Account branding enrichment during signup
This PR does the following
### Replace Firecrawl with Context.dev
Switches the enterprise brand lookup from Firecrawl to Context.dev for
better data quality, built-in caching, and automatic filtering of
free/disposable email providers. The service interface changes from URL
to email input to match Context.dev's email endpoint. OSS still falls
back to basic HTML scraping with a normalized output shape across both
paths.
The enterprise path intentionally does not fall back to HTML scraping on
failure — speed matters more than completeness. We want the user on the
editable onboarding form fast, and a slow fallback scrape is worse than
letting them fill it in.
Requires `CONTEXT_DEV_API_KEY` in Super Admin → App Config. Without it,
falls back to OSS HTML scraping.
### Add job to enrich account details
After account creation, `Account::BrandingEnrichmentJob` looks up the
signup email and pre-fills the account name, colors, logos, social
links, and industry into `custom_attributes['brand_info']`.
The job signals completion via a short-lived Redis key (30s TTL) + an
ActionCable broadcast (`account.enrichment_completed`). The Redis key
lets the frontend distinguish "still running" from "finished with no
results."
## Description
Two improvements to Agent Capacity Policy:
**1. Support exclusion via zero conversation limit**
Allow `conversation_limit` to be `0` on inbox capacity limits. Agents
with a zero limit are excluded from auto-assignment for that inbox while
remaining members for manual assignment.
**2. Fix exclusion rules duration input**
- Default changed from `10` to `null` so time-based exclusion isn't
applied unless explicitly set.
- Minimum lowered from 10 to 1 minute.
- `DurationInput` updated to handle `null` values correctly.
## Type of change
Please delete options that are not relevant.
- [ ] Bug fix (non-breaking change which fixes an issue)
- [ ] New feature (non-breaking change which adds functionality)
## How Has This Been Tested?
- Added model and capacity service specs for zero-limit exclusion
behavior.
- Tested manually via UI flows
## Checklist:
- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [ ] My changes generate no new warnings
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged and published in downstream
modules
---------
Co-authored-by: Muhsin Keloth <muhsinkeramam@gmail.com>
Adds `WebsiteBrandingService` (OSS) with an Enterprise override using
Firecrawl v2 to extract branding and business data from a URL for
onboarding auto-fill.
OSS version uses HTTParty + Nokogiri to extract:
- Business name (og:site_name or title)
- Language (html lang)
- Favicon
- Social links from `<a>` tags
Enterprise version makes a single Firecrawl call to fetch:
- Structured JSON (name, language, industry via LLM)
- Branding (favicon, primary color)
- Page links
Falls back to OSS if Firecrawl is unavailable or fails.
Social handles (WhatsApp, Facebook, Instagram, Telegram, TikTok, LINE)
are parsed deterministically via a shared `SocialLinkParser`.
> We use links for socials, since the LLM extraction was unreliable,
mostly returned empty, and hallucinated in some rare scenarios
## How to test
```ruby
# OSS (no Firecrawl key needed)
WebsiteBrandingService.new('chatwoot.com').perform
# Enterprise (requires CAPTAIN_FIRECRAWL_API_KEY)
WebsiteBrandingService.new('notion.so').perform
WebsiteBrandingService.new('postman.com').perform
```
Verify the returned hash includes business_name, language,
industry_category, social_handles, and branding with
favicon/primary_color.
<img width="908" height="393" alt="image"
src="https://github.com/user-attachments/assets/e3696887-d366-485a-89a0-8e1a9698a788"
/>
## Description
When a customer downgrades from Enterprise to Business, they may retain
unused Stripe credit balance. During an AI credits topup,
Stripe::Invoice.finalize_invoice auto-applies that credit balance to the
invoice. If the credit balance fully covers the invoice amount, Stripe
marks it as paid immediately upon finalization. Calling
Stripe::Invoice.pay on an already-paid invoice throws an error, breaking
the topup flow.
This fix retrieves the invoice status after finalization and skips the
pay call if Stripe has already settled it via credits.
## Type of change
Please delete options that are not relevant.
- [ ] Bug fix (non-breaking change which fixes an issue)
## How Has This Been Tested?
Tested against Stripe test mode with the following scenarios:
- Full credit balance payment: Customer has enough Stripe credit balance
to cover the entire invoice. Invoice is marked paid after
finalize_invoice — pay is correctly skipped. Credits are fulfilled
successfully.
- Partial credit balance payment: Customer has some Stripe credit
balance but not enough to cover the full amount. Invoice remains open
after finalization — pay is called and charges the remaining amount to
the default payment method. Credits are fulfilled successfully.
- Zero credit balance (normal payment): Customer has no Stripe credit
balance. Invoice remains open after finalization — pay charges the full
amount. Credits are fulfilled successfully.
## Checklist:
- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [ ] My changes generate no new warnings
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged and published in downstream
modules
This change blocks Help Center access for default/Hacker-plan accounts
and closes the downgrade gap that could leave `help_center` enabled
after a subscription falls back to the default cloud plan.
Fixes: none
Closes: none
## Why
Default-plan accounts should not be able to access the Help Center, but
the downgrade fallback path only reset the plan name and did not
reconcile premium feature flags. That meant some accounts could keep
`help_center` enabled even after landing back on the Hacker/default
plan.
## What this change does
- blocks Help Center portal and article access for default/Hacker-plan
accounts
- reconciles premium feature flags when a subscription falls back to the
default cloud plan, so `help_center` is disabled immediately instead of
waiting for a later webhook
- preserves existing account `custom_attributes` during Stripe customer
recreation instead of overwriting them
- adds Enterprise coverage for the default-plan access checks on hosted
and custom-domain Help Center routes
- fixes the public access check to use the resolved portal object so
blocked requests return the intended response instead of raising an
error
## Validation
1. Create or use an account on the default/Hacker cloud plan with an
active portal.
2. Visit the portal home page and a published article on both the
Chatwoot-hosted URL and a configured custom domain.
3. Confirm the Help Center is blocked for that account.
4. Downgrade a paid account back to the default/Hacker plan through the
Stripe webhook flow.
5. Confirm `help_center` is disabled right after the downgrade fallback
is processed and the account can no longer access the Help Center.
---------
Co-authored-by: Muhsin Keloth <muhsinkeramam@gmail.com>
Co-authored-by: Sojan Jose <sojan@pepalo.com>
# Pull Request Template
## Description
Captain v1 does not have access to contact attributes. Added a toggle to
let user choose if they want contact information available to Captain.
## Type of change
- [x] Bug fix (non-breaking change which fixes an issue)
## How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration.
Specs and locally
<img width="1924" height="740" alt="CleanShot 2026-03-19 at 18 48 19@2x"
src="https://github.com/user-attachments/assets/353cfeaa-cd58-40eb-89e7-d660a1dc1185"
/>
![Uploading CleanShot 2026-03-19 at 18.53.26@2x.png…]()
## Checklist:
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [x] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] Any dependent changes have been merged and published in downstream
modules
## Description
This PR optimizes message queries by explicitly filtering with
`account_id` so the database can use the existing indexes more
efficiently.
Changes:
- Add `account_id` to message query filters to improve index
utilization.
- Update `last_incoming_message` query to include `account_id`.
- Avoid unnecessary preloading of `contact_inboxes` where it is not
required.
- Update specs to ensure `account_id` is set correctly in
message-related tests.
These changes reduce query cost and improve performance for message
lookups, especially on large accounts.
---------
Co-authored-by: Pranav <pranav@chatwoot.com>
Extract and pass image attachments from the latest user message to the
runner,
excluding the last user message from the context for processing.
Fixes#13588
# Pull Request Template
## Description
Adds image support to captain v2
## Type of change
Please delete options that are not relevant.
- [x] Bug fix (non-breaking change which fixes an issue)
## How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration.
specs and local testing
<img width="754" height="1008" alt="image"
src="https://github.com/user-attachments/assets/914cbc2c-9d30-42d0-87d4-9e5430845c87"
/>
langfuse also shows media correctly with the instrumentation code:
<img width="1800" height="1260" alt="image"
src="https://github.com/user-attachments/assets/ce0f5fa6-b1a5-42ec-a213-9a82b1751037"
/>
## Checklist:
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [x] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] Any dependent changes have been merged and published in downstream
modules
---------
Co-authored-by: Shivam Mishra <scm.mymail@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
# Pull Request Template
## Description
Adds channel type to Captain assistant traces in Langfuse
## Type of change
- [x] New feature (non-breaking change which adds functionality)
## How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration.
<img width="906" height="672" alt="image"
src="https://github.com/user-attachments/assets/224cee95-56aa-4672-8f74-0c0052251db9"
/>
<img width="908" height="611" alt="image"
src="https://github.com/user-attachments/assets/ddd8ef0d-47c1-450c-a09f-27e82a34d04d"
/>
## Checklist:
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [x] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] Any dependent changes have been merged and published in downstream
modules
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
## How to reproduce
In Chatwoot Cloud, mark an account for deletion from account settings
while the account has an active Stripe subscription. Before this change,
deletion marking did not explicitly mark subscriptions to stop renewing
at period end.
## What changed
This PR adds `Enterprise::Billing::CancelCloudSubscriptionsService` and
calls it from the delete action path in
`Enterprise::Api::V1::AccountsController`. The service lists only active
Stripe subscriptions for the customer and sets `cancel_at_period_end:
true` when needed. The account deletion schedule remains unchanged
(existing static 7-day behavior), and Stripe deleted-event fallback
behavior remains unchanged.
## How this was tested
Added and updated specs:
-
`spec/enterprise/services/enterprise/billing/cancel_cloud_subscriptions_service_spec.rb`
-
`spec/enterprise/controllers/enterprise/api/v1/accounts_controller_spec.rb`
Executed:
- `bundle exec rspec
spec/enterprise/services/enterprise/billing/cancel_cloud_subscriptions_service_spec.rb`
- `bundle exec rspec
spec/enterprise/controllers/enterprise/api/v1/accounts_controller_spec.rb:363`
# Pull Request Template
## Description
## Type of change
typo fix
## How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration.
## Checklist:
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [x] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] Any dependent changes have been merged and published in downstream
modules
# Pull Request Template
## Description
Instruments captain v2
## Type of change
- [x] New feature (non-breaking change which adds functionality)
## How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration.
Local testing:
<img width="864" height="510" alt="image"
src="https://github.com/user-attachments/assets/855ebce5-e8b8-4d22-b0bb-0d413769a6ab"
/>
## Checklist:
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [x] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] Any dependent changes have been merged and published in downstream
modules
---------
Co-authored-by: Shivam Mishra <scm.mymail@gmail.com>
## Summary
This PR reduces duplicate failure noise for audio transcription jobs
that fail with permanent HTTP 400 responses, and fixes a file-format
edge case causing intermittent 400s.
Sentry issue: [CHATWOOT-99E /
6660541334](https://chatwoot-p3.sentry.io/issues/6660541334/)
## Confirmed root cause
For some attachments, the stored filename had no extension (example:
`speech`, content type `audio/mpeg`).
When the temporary transcription upload file was created without an
extension, OpenAI returned:
`Unrecognized file format` (HTTP 400).
## Scope of changes
1. `Messages::AudioTranscriptionJob`
- Keeps `discard_on Faraday::BadRequestError` to avoid retry storms on
permanent request errors.
- Adds explicit Rails warning logs for discarded jobs with
attachment/job/status context.
2. `Messages::AudioTranscriptionService`
- Keeps guaranteed temp file cleanup via `ensure`.
- Ensures temp upload files include an extension when the original
filename has none, derived from blob `content_type`.
- This addresses intermittent failures like extensionless `audio/mpeg`
files.
## Reproduction
Enable audio transcription for an account and process an audio
attachment whose stored filename has no extension (for example `speech`)
but valid audio content type (`audio/mpeg`).
Before this fix, OpenAI transcription could return HTTP 400
`Unrecognized file format` for that attachment while similar attachments
with extensions succeeded.
## Testing
Ran:
`bundle exec rubocop
enterprise/app/jobs/messages/audio_transcription_job.rb
enterprise/app/services/messages/audio_transcription_service.rb`
Result: both modified files pass lint with no offenses.
## Linear Ticket:
https://linear.app/chatwoot/issue/CW-6081/review-feedback
## Description
Assignment V2 Service Enhancements
- Enable Assignment V2 on plan upgrade
- Fix UI issue with fair distribution policy display
- Add advanced assignment feature flag and enhance Assignment V2
capabilities
## Type of change
- [ ] Bug fix (non-breaking change which fixes an issue)
## How Has This Been Tested?
This has been tested using the UI.
## Checklist:
- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [ ] My changes generate no new warnings
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged and published in downstream
modules
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> **Medium Risk**
> Changes auto-assignment execution paths, rate limiting defaults, and
feature-flag gating (including premium plan behavior), which could
affect which conversations get assigned and when. UI rewires inbox
settings and policy flows, so regressions are possible around
navigation/linking and feature visibility.
>
> **Overview**
> **Adds a new premium `advanced_assignment` feature flag** and uses it
to gate capacity/balanced assignment features in the UI (sidebar entry,
settings routes, assignment-policy landing cards) and backend
(Enterprise balanced selector + capacity filtering).
`advanced_assignment` is marked premium, included in Business plan
entitlements, and auto-synced in Enterprise accounts when
`assignment_v2` is toggled.
>
> **Improves Assignment V2 policy UX** by adding an inbox-level
“Conversation Assignment” section (behind `assignment_v2`) that can
link/unlink an assignment policy, navigate to create/edit policy flows
with `inboxId` query context, and show an inbox-link prompt after
creating a policy. The policy form now defaults to enabled, disables the
`balanced` option with a premium badge/message when unavailable, and
inbox lists support click-to-navigate.
>
> **Tightens/adjusts auto-assignment behavior**: bulk assignment now
requires `inbox.enable_auto_assignment?`, conversation ordering uses the
attached `assignment_policy` priority, and rate limiting uses
`assignment_policy` config with an infinite default limit while still
tracking assignments. Tests and i18n strings are updated accordingly.
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
23bc03bf75ee4376071e4d7fc7cd564c601d33d7. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
---------
Co-authored-by: Pranav <pranav@chatwoot.com>
Co-authored-by: iamsivin <iamsivin@gmail.com>
Co-authored-by: Muhsin Keloth <muhsinkeramam@gmail.com>
Co-authored-by: Shivam Mishra <scm.mymail@gmail.com>
The index is already added in production.
Adds a new reporting API that returns conversation counts grouped by
channel type and first response time buckets (0-1h, 1-4h, 4-8h, 8-24h,
24h+).
- GET /api/v2/accounts/:id/reports/first_response_time_distribution
- Uses SQL aggregation to handle large datasets efficiently
- Adds composite index on reporting_events for query performance
Tested on production workload.
Request: GET
`/api/v2/accounts/1/reports/first_response_time_distribution?since=<since>&until=<until>`
Response payload:
```
{
"Channel::WebWidget": {
"0-1h": 120,
"1-4h": 85,
"4-8h": 32,
"8-24h": 12,
"24h+": 3
},
"Channel::Email": {
"0-1h": 12,
"1-4h": 28,
"4-8h": 45,
"8-24h": 35,
"24h+": 10
},
"Channel::FacebookPage": {
"0-1h": 50,
"1-4h": 30,
"4-8h": 15,
"8-24h": 8,
"24h+": 2
}
}
```
---------
Co-authored-by: Muhsin Keloth <muhsinkeramam@gmail.com>
# Pull Request Template
## Description
Fixes # (issue)
When we migrated to RubyLLM, images weren't being sent properly in
RubyLLM format to the model, so it did not understand images.
## Type of change
Please delete options that are not relevant.
- [x] Bug fix (non-breaking change which fixes an issue)
## How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration.
specs + local testing
Current behaviour on staging:
<img width="772" height="1012" alt="image"
src="https://github.com/user-attachments/assets/7b7d360f-dea4-48af-b20b-ee4c98a38a85"
/>
local testing with fix:
<img width="792" height="1216" alt="image"
src="https://github.com/user-attachments/assets/5ef82452-015e-4bda-a68f-884d00acb014"
/>
## Checklist:
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [x] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] Any dependent changes have been merged and published in downstream
modules
---------
Co-authored-by: Sojan Jose <sojan@pepalo.com>
## Description
- Replaces Stripe Checkout session flow with direct card charging for AI
credit top-ups
- Adds a two-step confirmation modal (select package → confirm purchase)
for better UX
- Creates Stripe invoice directly and charges the customer's default
payment method immediately
## Type of change
- [ ] New feature (non-breaking change which adds functionality)
## How Has This Been Tested?
- Using the specs
- UI manual test cases
<img width="945" height="580" alt="image"
src="https://github.com/user-attachments/assets/52bdad46-cd0e-4927-b13f-54c6b6353bcc"
/>
<img width="945" height="580" alt="image"
src="https://github.com/user-attachments/assets/231bc7e9-41ac-440d-a93d-cba45a4d3e3e"
/>
## Checklist:
- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [ ] My changes generate no new warnings
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged and published in downstream
modules
---------
Co-authored-by: Shivam Mishra <scm.mymail@gmail.com>
We’ve been watching Sidekiq workers climb from ~600 MB at boot to
1.4–1.5 GB after an hour whenever attachment-heavy jobs run. This PR is
an experiment to curb that growth by streaming attachments instead of
loading the whole blob into Ruby: reply-mailer inline attachments,
Telegram uploads, and audio transcriptions now read/write in chunks. If
this keeps RSS stable in production we’ll keep it; otherwise we’ll roll
it back and keep digging
