Files
crewAI/docs/edge/pt-BR/tools/integration/overview.mdx
Lucas Gomide a237ebabba feat: adopt directory-based docs versioning with Edge channel (#6202)
* feat: adopt directory-based docs versioning with Edge channel

Switch docs.crewai.com from navigation-only versioning (every version
selector entry rendered the same docs/<lang>/* source files) to
Mintlify's directory-based versioning so each version selector entry
renders its own snapshot. Add an "Edge" channel under docs/edge/<lang>/*
that always reflects main HEAD for unreleased work, eliminating
pre-release leakage onto frozen release labels. External links to
canonical /<lang>/* URLs are preserved via wildcard redirects that
always land on the current default version.

Layout:
- docs/edge/<lang>/*         rolling source (you edit here)
- docs/edge/enterprise-api.*.yaml
- docs/v<X.Y.Z>/<lang>/*     frozen, immutable snapshots
- docs/v<X.Y.Z>/enterprise-api.*.yaml
- docs/images/               shared, append-only
- docs/docs.json             nav + redirects

URLs follow the Mintlify-idiomatic shape: /edge/<lang>/<page> for
Edge, /v<X.Y.Z>/<lang>/<page> for every frozen snapshot. The wildcard
redirects /<lang>/:slug* -> /<default>/<lang>/:slug* keep stale links
working, and every freeze rewrites them (plus all per-section/per-page
redirects) so destinations always resolve to the current default
without depending on a second redirect hop.

Release flow integration (devtools release):
- New module crewai_devtools.docs_versioning.freeze() materialises
  docs/v<X.Y.Z>/ from docs/edge/, rewrites openapi: refs inside the
  snapshot, inserts the version into every language block in
  docs.json, and refreshes all redirect destinations.
- _update_docs_and_create_pr() in cli.py now calls that freeze during
  Phase 2 of devtools release. Edge changelogs are updated first (so
  the snapshot freeze picks them up), then the snapshot is staged
  alongside docs.json, branched as docs/freeze-v<X.Y.Z>, and the PR
  is titled [docs-freeze] docs: snapshot and changelog for v<X.Y.Z>
  — the title prefix the new CI guard reads.
- The PR still gates tag, GitHub release, PyPI publish, and the
  enterprise release as before; no new PRs are added.
- Pre-releases (1.X.YaN, 1.X.YbN, ...) skip the snapshot — they ride
  Edge — and the docs PR title omits the [docs-freeze] prefix.
- docs_check (AI-generated docs scaffolding) writes to
  docs/edge/<lang>/* so newly-generated unreleased docs land in Edge
  and never accidentally touch a frozen snapshot.

Migration scripts (one-shot):
- scripts/docs/freeze_historical_versions.py reconstructs all 16
  historical snapshots (v1.10.0 .. v1.14.7) from git tags via
  git archive | tar, rewriting openapi: MDX refs so each snapshot
  reads its own enterprise-api YAML rather than the live one.
- scripts/docs/prefix_version_paths.py one-shot-migrates docs.json:
  rewrites every page path in 16 versioned blocks to point under
  docs/v<X.Y.Z>/, inserts a new Edge entry per language, tags
  v1.14.7 as Latest (default), prunes pages whose target file
  doesn't exist in the snapshot (e.g. docs/ar/ didn't exist before
  v1.12.0), and writes the wildcard + per-section redirects.
- scripts/docs/freeze_current_edge.py is now a thin CLI wrapper
  around docs_versioning.freeze for manual one-off freezes (e.g.
  retroactively snapshotting a forgotten release).

CI guards (.github/workflows/docs-snapshots.yml):
- Frozen snapshots under docs/v[0-9]*/ are immutable; only PRs whose
  title contains [docs-freeze] (i.e. release-cut PRs generated by
  devtools release or the manual wrapper) may modify them.
- Images under docs/images/ are append-only since snapshots share a
  single image directory. Deleting or renaming an image breaks every
  historical snapshot that still references it.

Restored docs/images/crewai-otel-export.png from PR #3673; it was
deleted in PR #4908 but v1.10.0 / v1.10.1 snapshots still reference
it. Restoring instead of editing the snapshots preserves historical
rendering fidelity and validates the new append-only rule
retroactively.

Tests:
- lib/devtools/tests/test_docs_versioning.py covers the freeze: file
  copy, openapi rewrite, version insertion, default demotion, redirect
  upserts, per-section redirect rewriting, idempotency, and invalid
  inputs.

Verified locally with mintlify broken-links: 0 broken links across
the full site (Edge + 16 frozen versions, 4 locales).

AGENTS.md (repo root) is the contributor guide for the new model;
RELEASING.md is the release-cut runbook; README's Contribution
section links to both.

Co-authored-by: Cursor <cursoragent@cursor.com>

* style: resolve linter issues

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-17 11:56:59 -04:00

73 lines
3.3 KiB
Plaintext

---
title: "Visão Geral"
description: "Conecte agentes CrewAI com automações externas e serviços de IA gerenciados"
icon: "plug"
mode: "wide"
---
As ferramentas de integração permitem que seus agentes deleguem trabalho para outras plataformas de automação e serviços de IA gerenciados. Use-as quando o fluxo precisar invocar uma automação já publicada no CrewAI Platform ou quando for necessário direcionar tarefas para provedores especializados, como Amazon Bedrock.
## **Ferramentas Disponíveis**
<CardGroup cols={2}>
<Card title="Ferramenta de Execução de Automação CrewAI" icon="robot" href="/pt-BR/tools/integration/crewaiautomationtool">
Invoque automações ativas do CrewAI Platform, envie entradas personalizadas e acompanhe o resultado diretamente do seu agente.
</Card>
<Card title="Ferramenta Bedrock Invoke Agent" icon="aws" href="/pt-BR/tools/integration/bedrockinvokeagenttool">
Acesse agentes do Amazon Bedrock a partir das suas crews, reutilize guardrails existentes da AWS e traga as respostas de volta ao fluxo atual.
</Card>
</CardGroup>
## **Casos de Uso Comuns**
- **Encadear automações**: Inicie uma automação do CrewAI a partir de outra crew ou flow
- **Hand-off corporativo**: Direcione tarefas para agentes Bedrock que já incorporam políticas e guardrails internos
- **Workflows híbridos**: Combine o raciocínio do CrewAI com sistemas externos que expõem APIs de agente
- **Tarefas demoradas**: Faça polling de automações externas e mescle o resultado final na execução atual
## **Exemplo de Início Rápido**
```python
from crewai import Agent, Task, Crew
from crewai_tools import InvokeCrewAIAutomationTool
from crewai_tools.aws.bedrock.agents.invoke_agent_tool import BedrockInvokeAgentTool
# Automação externa
analysis_automation = InvokeCrewAIAutomationTool(
crew_api_url="https://analysis-crew.acme.crewai.com",
crew_bearer_token="YOUR_BEARER_TOKEN",
crew_name="Analysis Automation",
crew_description="Executa o pipeline de análise em produção",
)
# Agente gerenciado no Bedrock
knowledge_router = BedrockInvokeAgentTool(
agent_id="bedrock-agent-id",
agent_alias_id="prod",
)
automation_strategist = Agent(
role="Estrategista de Automação",
goal="Orquestrar automações externas e resumir os resultados",
backstory="Você coordena fluxos corporativos e sabe quando delegar tarefas a serviços especializados.",
tools=[analysis_automation, knowledge_router],
verbose=True,
)
execute_playbook = Task(
description="Execute a automação de análise e peça ao agente Bedrock pontos principais para a diretoria.",
agent=automation_strategist,
)
Crew(agents=[automation_strategist], tasks=[execute_playbook]).kickoff()
```
## **Boas Práticas**
- **Proteja credenciais**: Armazene tokens e chaves de API em variáveis de ambiente ou no gerenciador de segredos
- **Planeje a latência**: Automações externas podem levar mais tempo — configure intervalos e timeouts adequados
- **Reutilize sessões**: Agentes Bedrock aceitam IDs de sessão para manter contexto entre chamadas
- **Valide respostas**: Normalize a saída remota (JSON, texto, códigos de status) antes de enviá-la a etapas seguintes
- **Monitore o uso**: Acompanhe logs no CrewAI Platform ou no AWS CloudWatch para evitar estouros de quota e falhas