Acrescenta valor 'openai_hermes_gateway' ao CAPTAIN_LLM_PROVIDER, sem mexer
nas opções existentes (openai_api e openai_codex_oauth continuam intactos).
Quando ativado, o Captain chama o Hermes Agent rodando em modo gateway HTTP
local (CAPTAIN_HERMES_GATEWAY_URL, default http://host.docker.internal:9877).
O Hermes faz o roteamento multi-modelo (Codex/Anthropic/Gemini) usando o
OAuth dele em ~/.hermes/auth.json — o Captain não precisa fazer OAuth direto.
Configs novas em installation_config.yml:
- CAPTAIN_HERMES_GATEWAY_URL — URL do gateway (default host.docker.internal:9877)
- CAPTAIN_HERMES_GATEWAY_MODEL — modelo no formato <provider>/<model>
- CAPTAIN_HERMES_GATEWAY_API_KEY — opcional, dummy se gateway local não exige
Embeddings e Files API continuam apontando pra OpenAI tradicional via
legacy_openai_settings — Hermes Gateway não expõe esses endpoints.
Specs cobrem: dummy key, custom api_key override, custom model, defaults,
trailing slash strip, light_model por provider, hermes_gateway? predicate.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Anon key não tinha permissão de INSERT em reserva_hotel.unidades — RLS
exige authenticated + tenant_member, não atendido. POST direto falhava
sem feedback útil.
Solução: RPC reserva_hotel.provision_unidade(...) com SECURITY DEFINER
que faz upsert idempotente bypassando RLS, com validações de tenant +
marca dentro da função. EXECUTE granted to anon.
Service agora chama /rpc/provision_unidade em vez de POST /unidades.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Hook after_commit on:create no Captain::Unit dispara
ProvisionUnitInSupabaseJob, que upserta a unit em reserva_hotel.unidades
via Supabase REST (UNIQUE on tenant_id+chatwoot_unit_id) e grava IDs no
Captain::Unit (supabase_unit_id, supabase_tenant_id, supabase_marca_id).
Sem isso, criar nova unidade no painel Pix não habilitava roleta — a row
no Supabase ficava ausente e OfferService caía em "tenant não resolvido".
Inclui rake captain:reprovision_unit_in_supabase[id] + provision_all
pra reconciliação manual e migration retroativa.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Resolve duas camadas de problema identificadas em teste end-to-end:
1. Embeddings falhavam com HTTP 404 (/codex/v1/embeddings não existe).
Solução: Captain::Llm::EmbeddingService sempre usa OpenAI tradicional
via Llm::Config.with_api_key(legacy_settings). ProviderConfig expõe
legacy_openai_settings pra isso.
2. Servidor Codex ocasionalmente responde com response.failed +
code=server_error (instabilidade transitória). Client agora retenta
até 2x com backoff exponencial (0.5s, 1.5s) em erros retryable:
HTTP 5xx, server_error no response.failed, ou stream inacabado.
Outras correções nesta etapa:
- Scenario#agent_model: em modo Codex, ignora CAPTAIN_OPEN_AI_MODEL_SCENARIO
(que pode ter gpt-4o legado) e usa ProviderConfig.model.
- ExtractionService/ContradictionCheckerService/TranslateQueryService:
trocam constantes hardcoded gpt-4o-mini/gpt-4.1-nano por
ProviderConfig.light_model (respeitando o provider ativo).
- ProviderConfig.DEFAULT_CODEX_MODEL agora é gpt-5.2 (reconhecido pelo
RubyLLM; gpt-5.4 não está no catalog do gem).
Validado ponta-a-ponta: WhatsApp → Chatwoot → Jasmine → handoff Daniela
→ faq_lookup com embedding OK → resposta com preços corretos.
Docs em docs/captain-codex-oauth.md.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adiciona o toggle openai_api | openai_codex_oauth. Por padrão mantém
comportamento legado (API key OpenAI tradicional). Quando mudamos pra
openai_codex_oauth, os clientes (RubyLLM + Agents gem) passam a
apontar para o proxy interno em http://localhost:3000/codex,
configurável via CAPTAIN_CODEX_PROXY_URL.
- Captain::Llm::ProviderConfig: single source of truth de api_key,
api_base e model, baseado em CAPTAIN_LLM_PROVIDER
- config/initializers/ai_agents.rb refatorado
- lib/llm/config.rb refatorado
- 8 specs do ProviderConfig passando
- Fallback seguro: api_key dummy ('codex-oauth') quando usando proxy
(o proxy ignora Authorization e usa OAuth interno)
NÃO mexe no Llm::LegacyBaseOpenAiService (PDF/Files API). Esse
continua sempre na API tradicional porque o endpoint Codex não
expõe Files API.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Codex endpoint retorna HTTP 400 "Instructions are required" quando o
campo vem ausente. Agora sempre incluímos o campo — string com espaço
quando não há system message no request.
Validado end-to-end: curl → /codex/v1/chat/completions → proxy traduz
→ Codex devolve streaming SSE → proxy agrega → JSON Chat Completions.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- RetentionSummaryBadge in the "Previous conversations" sidebar:
tiered status (First contact / Active / Recurring / Sleeping /
At risk / Inactive) + counts of interactions, one-shots, Pix.
- Retention tab in Captain Reports: KpiCards, FlowCard, CohortMatrix
(12x13 heatmap with CSV export).
- Five new filters on the contacts list: recurring, last interaction,
days since, interactions count, reservations paid.
- Full pt_BR + en i18n under CAPTAIN_REPORTS.RETENTION.*
- Spec for InteractionCalculatorService covering gap behavior,
one-shot classification, internal-label exclusion, multi-conversation
grouping across the 30h window.
- Docs: docs/captain-retention-indicators.md with business rules,
column reference, endpoint shape, and backup SQL queries.
Consolida o trabalho desta branch de abril/2026 em um bloco pronto pra
testar em staging antes do merge pra main.
## Correções de memória semântica
- ExtractionService: Princípio Zero + Regra de Ouro (ação consumada vs intenção).
- Cenário Daniela_Reservas: Passo 0 de classificação (consulta/intenção/fora).
## Roleta da Sorte (end-to-end)
- Schema Supabase + 7 RPCs atômicas (server-side, idempotentes).
- Services: Offer, Redeem, WeeklyReport.
- Jobs: OfferRouletteJob (hook em ConfirmationService após Pix pago),
NotifyRevealed + Scheduler de fallback.
- Tool manual GenerateRoletaLinkTool + endpoint público /roleta/notify.
- Dashboard /captain/roleta com Resgate + Relatório + anomaly detection.
## Cenário Reclamacoes_Ouvidoria
- Triagem P1-P4, framework LAST, Three-level listening, Self-check.
- Sem compensação material, detecção de cliente frustrado eleva prioridade.
## Analytics
- Funil de conversão /captain/funnel: 5 etapas via regex, zero LLM.
- Detector de churn via ChurnOutreach* (cron dias úteis 10h-17h BRT).
## Trabalho pré-existente incluído
- Captain Executive Reports (ceo_digest, mattermost_delivery).
- get_reserva_preco_tool, Lifecycle ajustes, Reservations UI polimentos.
## Outros
- .gitignore: patterns pra credenciais.
- Migrations de scenarios idempotentes.
- i18n completa pt_BR+en pra roleta/funnel.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Problema observado em teste real 2026-04-19 11:24:
usuário forneceu suíte+data+hora pra Daniela. Em vez de chamar
generate_pix, Daniela chamou handoff_to_jasmine. Jasmine respondeu
"Vou te transferir pra Daniela..." — mentira, a conversa ficou
parada com a Jasmine.
Sequência dentro de UM único run:
jasmine.handoff_to_daniela_reservas_agent
-> daniela.handoff_to_jasmine (!)
-> jasmine responde "vou te transferir..."
O prompt da Daniela tem "🚨 NUNCA FAÇA HANDOFF DE VOLTA PRA JASMINE"
mas o LLM ignora a proibição quando a ferramenta está registrada.
A única solução robusta é não registrar a ferramenta.
Historicamente tivemos medo de remover a back-edge porque sem ela
a Daniela (quando confusa) ficava em loop chamando faq_lookup —
incidente que queimou créditos reais. Esse medo não vale mais:
commit f3f8a8d5c adicionou TOOL_LOOP_THRESHOLD=3 +
MAX_TURNS_PER_MESSAGE=15 que disparam bot_handoff automático em
qualquer loop de tool. A proteção contra runaway existe por
OUTRA via agora, então podemos remover a back-edge com segurança.
Efeito esperado:
- scenario termina a resposta sozinho (sem ping-pong)
- scenario confuso/em loop -> rate limit corta -> humano recebe
Memory: atualizado feedback_never_touch_captain_without_safety_caps.md
refletindo a nova invariante.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Três camadas de proteção contra runaway token burn no AgentRunnerService:
1. MAX_TURNS_PER_MESSAGE = 15
Cap dentro de uma única chamada run(). Já estava aplicado;
agora extraído como constante nomeada.
2. MAX_TURNS_PER_CONVERSATION = 30
Cap ao longo da vida da conversa. Contador em
conversation.custom_attributes['captain_turn_count']. Ao atingir,
dispara bot_handoff automático e responde com mensagem de
transferência pra humano.
3. TOOL_LOOP_THRESHOLD = 3
Detecta a mesma (tool_name, args) invocada 3+ vezes no resultado
de um único run (sintoma do loop faq_lookup que queimou tokens
em 2026-04-19). Ao detectar: dispara bot_handoff e aborta o turno.
trigger_bot_handoff! aciona conversation.bot_handoff! quando
disponível, removendo a conversa do pipeline automático.
Motivação: dois incidentes reais de queima de crédito OpenAI em
2026-04-19. Ver memory/feedback_never_touch_captain_without_safety_caps.md
pras invariantes completas.
Tests atualizados: mock_result agora stuba :messages (usado pelo
novo tool_loop_detected?) e max_turns esperado é 15.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
User feedback revealed a fundamental design issue: the memory model was
accumulating contradictory "Prefere X" facts because a single choice was
being treated as a permanent preference. Result: 3 different
"Prefere suite X" entries coexisting, all at 90% confidence, with
reservation patterns over time (2hrs, 4hrs, pernoite) all claiming to be
the customer's "preferred" duration.
Corrections:
1. ExtractionService prompt — preferencia now requires EXPLICIT
declaration words ("prefiro", "gosto mais de", "sempre escolho",
"adoro", "favorita"). A mere choice in one conversation is NO LONGER
extracted as preferencia — instead it goes to padrao_comportamental
WITH THE DATE in the content (e.g. "Reservou Alexa para pernoite em
23/05/2026"). This makes memory temporal and auditable instead of
imposing fake consistency.
2. Reference date is passed to the LLM prompt via the latest message
timestamp, used as the anchor date the LLM must embed in every
padrao_comportamental content.
3. ContradictionCheckerService — dual threshold:
- cosine < 0.15 → auto-supersede without LLM (pure duplicate)
- 0.15 to 0.6 → ask LLM if contradicts, supersede if yes
- > 0.6 → ignore, unrelated facts
Previously only the middle band existed, so near-duplicate facts like
two "aniversário 23/05" entries or three "prefere suite X" entries
were never cleaned up.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Also fixes double-scheduling bug in scheduler_spec and delivery_spec caused by
after_create_commit hook firing while rules already exist — reservation is now
created before rules in setup so the hook finds nothing to schedule.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Orchestrates guards → render (Liquid) → send pipeline for one delivery.
Handles skip, reschedule, sent, failed states and re-enqueues on reschedule.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Implement guards following the same pass/reschedule/too_stale pattern as QuietHours.
Also fix belongs_to :conversation on Delivery to use class_name: '::Conversation' to avoid namespace resolution failure inside Captain::Lifecycle module.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Pure function mapping reservation events to timestamps; used by Scheduler (T9) to compute fire_at.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
## 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`
