mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-07-03 06:08:15 +00:00
* 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>
149 lines
5.2 KiB
Plaintext
149 lines
5.2 KiB
Plaintext
---
|
|
title: Reasoning
|
|
description: "Aprenda como habilitar e usar o reasoning do agente para aprimorar a execução de tarefas."
|
|
icon: brain
|
|
mode: "wide"
|
|
---
|
|
|
|
## Visão Geral
|
|
|
|
O reasoning do agente é um recurso que permite que agentes reflitam sobre uma tarefa e criem um plano antes da execução. Isso ajuda os agentes a abordarem tarefas de forma mais metódica e garante que estejam preparados para realizar o trabalho atribuído.
|
|
|
|
## Uso
|
|
|
|
Para habilitar o reasoning para um agente, basta definir `reasoning=True` ao criar o agente:
|
|
|
|
```python
|
|
from crewai import Agent
|
|
|
|
analista = Agent(
|
|
role="Analista de Dados",
|
|
goal="Analisar dados e fornecer insights",
|
|
backstory="Você é um analista de dados especialista.",
|
|
reasoning=True,
|
|
max_reasoning_attempts=3 # Opcional: Defina um limite de tentativas de reasoning
|
|
)
|
|
```
|
|
|
|
## Como Funciona
|
|
|
|
Quando o reasoning está habilitado, antes de executar uma tarefa, o agente irá:
|
|
|
|
1. Refletir sobre a tarefa e criar um plano detalhado
|
|
2. Avaliar se está pronto para executar a tarefa
|
|
3. Refinar o plano conforme necessário até estar pronto ou até o limite de max_reasoning_attempts ser atingido
|
|
4. Inserir o plano de reasoning na descrição da tarefa antes da execução
|
|
|
|
Esse processo ajuda o agente a dividir tarefas complexas em etapas gerenciáveis e identificar potenciais desafios antes de começar.
|
|
|
|
## Opções de Configuração
|
|
|
|
<ParamField body="reasoning" type="bool" default="False">
|
|
Ativa ou desativa o reasoning
|
|
</ParamField>
|
|
|
|
<ParamField body="max_reasoning_attempts" type="int" default="None">
|
|
Número máximo de tentativas para refinar o plano antes de prosseguir com a execução. Se None (padrão), o agente continuará refinando até que esteja pronto.
|
|
</ParamField>
|
|
|
|
## Exemplo
|
|
|
|
Aqui está um exemplo completo:
|
|
|
|
```python
|
|
from crewai import Agent, Task, Crew
|
|
|
|
# Create an agent with reasoning enabled
|
|
analista = Agent(
|
|
role="Analista de Dados",
|
|
goal="Analisar dados e fornecer insights",
|
|
backstory="Você é um analista de dados especialista.",
|
|
reasoning=True,
|
|
max_reasoning_attempts=3 # Opcional: Defina um limite de tentativas de reasoning
|
|
)
|
|
|
|
# Create a task
|
|
analysis_task = Task(
|
|
description="Analise os dados de vendas fornecidos e identifique as principais tendências.",
|
|
expected_output="Um relatório destacando as 3 principais tendências de vendas.",
|
|
agent=analista
|
|
)
|
|
|
|
# Create a crew and run the task
|
|
crew = Crew(agents=[analista], tasks=[analysis_task])
|
|
result = crew.kickoff()
|
|
|
|
print(result)
|
|
```
|
|
|
|
## Tratamento de Erros
|
|
|
|
O processo de reasoning foi projetado para ser robusto, com tratamento de erros integrado. Se ocorrer um erro durante o reasoning, o agente prosseguirá com a execução da tarefa sem o plano de reasoning. Isso garante que as tarefas ainda possam ser executadas mesmo que o processo de reasoning falhe.
|
|
|
|
Veja como lidar com possíveis erros no seu código:
|
|
|
|
```python
|
|
from crewai import Agent, Task
|
|
import logging
|
|
|
|
# Set up logging to capture any reasoning errors
|
|
logging.basicConfig(level=logging.INFO)
|
|
|
|
# Create an agent with reasoning enabled
|
|
agent = Agent(
|
|
role="Analista de Dados",
|
|
goal="Analisar dados e fornecer insights",
|
|
reasoning=True,
|
|
max_reasoning_attempts=3
|
|
)
|
|
|
|
# Create a task
|
|
task = Task(
|
|
description="Analise os dados de vendas fornecidos e identifique as principais tendências.",
|
|
expected_output="Um relatório destacando as 3 principais tendências de vendas.",
|
|
agent=agent
|
|
)
|
|
|
|
# Execute the task
|
|
# If an error occurs during reasoning, it will be logged and execution will continue
|
|
result = agent.execute_task(task)
|
|
```
|
|
|
|
## Exemplo de Saída de reasoning
|
|
|
|
Veja um exemplo de como pode ser um plano de reasoning para uma tarefa de análise de dados:
|
|
|
|
```
|
|
Task: Analise os dados de vendas fornecidos e identifique as principais tendências.
|
|
|
|
Reasoning Plan:
|
|
I'll analyze the sales data to identify the top 3 trends.
|
|
|
|
1. Understanding of the task:
|
|
I need to analyze sales data to identify key trends that would be valuable for business decision-making.
|
|
|
|
2. Key steps I'll take:
|
|
- First, I'll examine the data structure to understand what fields are available
|
|
- Then I'll perform exploratory data analysis to identify patterns
|
|
- Next, I'll analyze sales by time periods to identify temporal trends
|
|
- I'll also analyze sales by product categories and customer segments
|
|
- Finally, I'll identify the top 3 most significant trends
|
|
|
|
3. Approach to challenges:
|
|
- If the data has missing values, I'll decide whether to fill or filter them
|
|
- If the data has outliers, I'll investigate whether they're valid data points or errors
|
|
- If trends aren't immediately obvious, I'll apply statistical methods to uncover patterns
|
|
|
|
4. Use of available tools:
|
|
- I'll use data analysis tools to explore and visualize the data
|
|
- I'll use statistical tools to identify significant patterns
|
|
- I'll use knowledge retrieval to access relevant information about sales analysis
|
|
|
|
5. Expected outcome:
|
|
A concise report highlighting the top 3 sales trends with supporting evidence from the data.
|
|
|
|
READY: I am ready to execute the task.
|
|
```
|
|
|
|
Esse plano de reasoning ajuda o agente a organizar sua abordagem para a tarefa, considerar possíveis desafios e garantir que entregará o resultado esperado.
|