Devin AI a395a5cde1 feat: Add prompt caching support for AWS Bedrock and Anthropic models ...

- Add enable_prompt_caching and cache_control parameters to LLM class
- Implement cache_control formatting for Anthropic models via LiteLLM
- Add helper method to detect prompt caching support for different providers
- Create comprehensive tests covering all prompt caching functionality
- Add example demonstrating usage with kickoff_for_each and kickoff_async
- Supports OpenAI, Anthropic, Bedrock, and Deepseek providers
- Enables cost optimization for workflows with repetitive context

Addresses issue #3535 for prompt caching support in CrewAI

Co-Authored-By: João <joao@crewai.com>

2025-09-18 20:21:50 +00:00

..

agents

fix: handle model parameter in OpenAI adapter initialization (#3510)

2025-09-12 17:31:53 -04:00

cli

chore: bump CrewAI version to 0.186.1 and update dependencies in CLI templates (#3499)

2025-09-10 17:01:19 -07:00

crews

Brandon/cre 19 workflows (#1347)

2024-09-27 12:11:17 -03:00

events

Lorenze/ephemeral trace ask (#3530)

2025-09-18 10:17:34 -07:00

experimental

refactor: Move events module to crewai.events (#3425)

2025-09-02 10:06:42 -04:00

flow

Lorenze/ephemeral trace ask (#3530)

2025-09-18 10:17:34 -07:00

knowledge

refactor: unify rag storage with instance-specific client support (#3455)

2025-09-17 14:46:54 -04:00

llms

chore: modernize LLM interface typing and add constants (#3483)

2025-09-10 08:30:49 -04:00

memory

refactor: unify rag storage with instance-specific client support (#3455)

2025-09-17 14:46:54 -04:00

project

fix: support to define MPC connection timeout on CrewBase instance (#3465)

2025-09-10 09:58:46 -04:00

rag

refactor: unify rag storage with instance-specific client support (#3455)

2025-09-17 14:46:54 -04:00

security

chore: modernize security module typing (#3469)

2025-09-08 11:52:59 -04:00

tasks

chore: enhance typing and documentation in tasks module (#3467)

2025-09-08 11:42:23 -04:00

telemetry

chore: refactor telemetry module with utility functions and modern typing (#3485)

2025-09-10 09:18:21 -04:00

tools

Lorenze/fix tool call twice (#3495)

2025-09-10 15:20:21 -07:00

translations

improviong reasoning prompt

2025-05-25 15:24:59 -07:00

types

chore: update typing in types module to Python 3.10+ syntax (#3482)

2025-09-10 09:07:36 -04:00

utilities

refactor: unify rag storage with instance-specific client support (#3455)

2025-09-17 14:46:54 -04:00

__init__.py

chore: bump CrewAI version to 0.186.1 and update dependencies in CLI templates (#3499)

2025-09-10 17:01:19 -07:00

agent.py

refactor: Move events module to crewai.events (#3425)

2025-09-02 10:06:42 -04:00

context.py

feat: add thread-safe platform context management (#3502)

2025-09-11 17:32:51 -04:00

crew.py

Lorenze/ephemeral trace ask (#3530)

2025-09-18 10:17:34 -07:00

lite_agent.py

refactor: Move events module to crewai.events (#3425)

2025-09-02 10:06:42 -04:00

llm.py

feat: Add prompt caching support for AWS Bedrock and Anthropic models

2025-09-18 20:21:50 +00:00

process.py

Hierarchical process (#206)

2024-02-02 13:56:35 -03:00

task.py

refactor: Move events module to crewai.events (#3425)

2025-09-02 10:06:42 -04:00