iachat/enterprise/app/models
Rodribm10 b457e84c2f fix(captain): route embeddings to legacy OpenAI + retry transient errors
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>
2026-04-22 17:42:31 -03:00
..
captain fix(captain): route embeddings to legacy OpenAI + retry transient errors 2026-04-22 17:42:31 -03:00
channel feat(enterprise): add voice conference API (#13064) 2025-12-15 15:11:59 -08:00
concerns feat(lifecycle): inject concierge context into Captain orchestrator prompt 2026-04-15 09:25:16 -03:00
enterprise feat: bypass user limit validation to allow unlimited agents 2026-02-25 21:40:18 -03:00
account_saml_settings.rb feat: update users on SAML setup and destroy [CW-2958][CW-5612] (#12346) 2025-09-15 21:20:22 +05:30
agent_capacity_policy.rb feat: Add agent capacity controllers (#12200) 2025-08-26 19:12:58 -07:00
applied_sla.rb Chore/merge upstream 4.8.0 (#150) 2025-11-19 16:25:58 -03:00
article_embedding.rb feat: legacy features to ruby llm (#12994) 2025-12-11 14:17:28 +05:30
captain_inbox.rb chore(style): fix rubocop offenses and update typing indicators 2026-02-25 15:06:58 -03:00
company.rb chore(style): fix rubocop offenses and update typing indicators 2026-02-25 15:06:58 -03:00
copilot_message.rb feat: Update UI for Copilot (#11561) 2025-06-02 22:02:03 -05:00
copilot_thread.rb feat: Add support for more tool, standardize copilot chat service (#11560) 2025-05-23 01:07:07 -07:00
custom_role.rb feat: Add APIs to manage custom roles in Chatwoot (#9995) 2024-08-23 17:18:28 +05:30
inbox_capacity_limit.rb feat: Add agent capacity controllers (#12200) 2025-08-26 19:12:58 -07:00
sla_event.rb feat: Conversation API to return applied_sla and sla_events (#9174) 2024-04-01 23:30:07 +05:30
sla_policy.rb fix: Prevent SLA deletion timeouts by moving to async job (#12944) 2025-12-10 12:28:47 +05:30