Devin AI d1e094b22f Fix #6089: Widen litellm dependency constraint to >=1.84.0,<2 ...

The litellm extra was pinned to >=1.83.7,<1.84, but all versions in
that range have transitive dependency conflicts with crewAI's core
requirements:
- litellm 1.83.7 pins python-dotenv==1.0.1 (crewAI needs >=1.2.2)
- litellm 1.83.8 pins openai==2.24.0 (crewAI needs >=2.30.0)
- litellm 1.83.14 pins openai==2.24.0

litellm 1.84.0+ relaxes these to openai>=2.20.0,<3 and
python-dotenv>=1.0.0,<2, which are compatible with crewAI's bounds.

Adds regression tests verifying the dependency bounds stay compatible.

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

2026-06-09 17:15:01 +00:00

..

a2a

chore(crewai): drop self-explanatory comments

2026-05-26 10:23:33 -07:00

agents

Lorenze/fix/file input not working reliably (#6020)

2026-06-02 17:14:51 -07:00

cassettes

Lorenze/feat/conversational flows (#5896)

2026-06-03 11:53:16 -07:00

cli

chore(crewai): drop self-explanatory comments

2026-05-26 10:23:33 -07:00

config

Release/v1.0.0 (#3618)

2025-10-20 14:10:19 -07:00

crew

feat: async crew support

2025-12-04 16:53:19 -05:00

events

feat(otel): surface real finish_reason + sampling params + response.id on LLM events (#5945)

2026-06-05 07:23:38 -04:00

experimental

refactor(skills): move Skills Repository to experimental + CREWAI_EXPERIMENTAL gate

2026-05-28 09:38:10 -07:00

hooks

chore(crewai): drop self-explanatory comments

2026-05-26 10:23:33 -07:00

knowledge

feat(storage): pluggable default backends for memory, knowledge, rag, flow (#6079)

2026-06-08 21:14:13 -05:00

llms

feat(otel): surface real finish_reason + sampling params + response.id on LLM events (#5945)

2026-06-05 07:23:38 -04:00

mcp

feat: enhance StdioTransport to prevent environment variable leakage (#5506)

2026-05-27 13:38:25 -07:00

memory

feat(storage): pluggable default backends for memory, knowledge, rag, flow (#6079)

2026-06-08 21:14:13 -05:00

pipeline

chore: restructure test env, cassettes, and conftest; fix flaky tests

2025-11-29 16:55:24 -05:00

project

fix: hash callback args correctly to ensure caching works

2025-11-05 07:19:09 -05:00

rag

feat(storage): pluggable default backends for memory, knowledge, rag, flow (#6079)

2026-06-08 21:14:13 -05:00

security

chore(crewai): drop self-explanatory comments

2026-05-26 10:23:33 -07:00

skills

refactor(skills): move Skills Repository to experimental + CREWAI_EXPERIMENTAL gate

2026-05-28 09:38:10 -07:00

storage

New Unified Memory System (#4420)

2026-02-13 21:34:37 -03:00

task

fix(task): use acall for output conversion in async paths

2026-05-04 18:42:12 +08:00

telemetry

chore(crewai): drop self-explanatory comments

2026-05-26 10:23:33 -07:00

tools

Lorenze/fix/file input not working reliably (#6020)

2026-06-02 17:14:51 -07:00

tracing

Lorenze/feat/conversational flows (#5896)

2026-06-03 11:53:16 -07:00

utilities

feat(lock_store): make locking backend overridable (#6015)

2026-06-04 13:28:31 -05:00

__init__.py

Release/v1.0.0 (#3618)

2025-10-20 14:10:19 -07:00

test_agent_multimodal.py

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

test_async_human_feedback.py

Build FlowDefinition from Flow DSL metadata (#6017)

2026-06-03 18:02:56 -03:00

test_callback.py

chore(crewai): drop self-explanatory comments

2026-05-26 10:23:33 -07:00

test_checkpoint_cli.py

refactor: extract CLI into standalone crewai-cli package

2026-05-06 20:46:46 +08:00

test_checkpoint.py

chore(crewai): drop self-explanatory comments

2026-05-26 10:23:33 -07:00

test_context.py

Lorenze/imp/native tool calling (#4258)

2026-01-22 17:44:03 -08:00

test_crew_multimodal.py

Fix structured output leaks in tool-calling loops (#5897)

2026-05-27 13:20:53 -07:00

test_crew_thread_safety.py

Release/v1.0.0 (#3618)

2025-10-20 14:10:19 -07:00

test_crew.py

Add crew trained agents file support (#6012)

2026-06-02 09:38:34 -07:00

test_custom_llm.py

chore(crewai): drop self-explanatory comments

2026-05-26 10:23:33 -07:00

test_event_record.py

chore(crewai): drop self-explanatory comments

2026-05-26 10:23:33 -07:00

test_flow_ask.py

chore(crewai): drop self-explanatory comments

2026-05-26 10:23:33 -07:00

test_flow_conversation.py

Migrate @listen/@router runtime to read from FlowDefinition (#6084)

2026-06-09 09:40:30 -07:00

test_flow_default_override.py

chore(crewai): drop self-explanatory comments

2026-05-26 10:23:33 -07:00

test_flow_definition.py

Migrate @listen/@router runtime to read from FlowDefinition (#6084)

2026-06-09 09:40:30 -07:00

test_flow_human_input_integration.py

chore(crewai): drop self-explanatory comments

2026-05-26 10:23:33 -07:00

test_flow_multimodal.py

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_flow_persistence_factory.py

feat(storage): pluggable default backends for memory, knowledge, rag, flow (#6079)

2026-06-08 21:14:13 -05:00

test_flow_persistence.py

chore(crewai): drop self-explanatory comments

2026-05-26 10:23:33 -07:00

test_flow_resumability_regression.py

Release/v1.0.0 (#3618)

2025-10-20 14:10:19 -07:00

test_flow_visualization.py

Build FlowDefinition from Flow DSL metadata (#6017)

2026-06-03 18:02:56 -03:00

test_flow.py

Migrate @listen/@router runtime to read from FlowDefinition (#6084)

2026-06-09 09:40:30 -07:00

test_guardrail_serialization.py

fix: serialize guardrail callables as null for JSON checkpointing

2026-04-28 14:57:49 +08:00

test_hallucination_guardrail.py

Release/v1.0.0 (#3618)

2025-10-20 14:10:19 -07:00

test_human_feedback_decorator.py

Migrate @listen/@router runtime to read from FlowDefinition (#6084)

2026-06-09 09:40:30 -07:00

test_human_feedback_integration.py

Build FlowDefinition from Flow DSL metadata (#6017)

2026-06-03 18:02:56 -03:00

test_imports.py

Release/v1.0.0 (#3618)

2025-10-20 14:10:19 -07:00

test_litellm_dependency_compat.py

Fix #6089: Widen litellm dependency constraint to >=1.84.0,<2

2026-06-09 17:15:01 +00:00

test_llm_streaming_finish_reason.py

feat(otel): surface real finish_reason + sampling params + response.id on LLM events (#5945)

2026-06-05 07:23:38 -04:00

test_llm.py

chore(crewai): drop self-explanatory comments

2026-05-26 10:23:33 -07:00

test_markdown_task.py

Release/v1.0.0 (#3618)

2025-10-20 14:10:19 -07:00

test_multimodal_validation.py

Release/v1.0.0 (#3618)

2025-10-20 14:10:19 -07:00

test_project.py

chore(crewai): drop self-explanatory comments

2026-05-26 10:23:33 -07:00

test_streaming_integration.py

chore: restructure test env, cassettes, and conftest; fix flaky tests

2025-11-29 16:55:24 -05:00

test_streaming.py

chore(crewai): drop self-explanatory comments

2026-05-26 10:23:33 -07:00

test_task_guardrails.py

chore(crewai): drop self-explanatory comments

2026-05-26 10:23:33 -07:00

test_task.py

chore(crewai): drop self-explanatory comments

2026-05-26 10:23:33 -07:00

utils.py

fix: add GPT-5 and o-series to multimodal vision prefixes (#5183)

2026-04-01 18:08:37 -03:00