crewAI

v1.15.3 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 10d AI Agents & Assistants

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agents ai ai-agents aiagentframework llms

Summary

AI summary

Add organization ID to PlusAPI client, introduce step interception points, and enable declarative flows in the TUI.

Changes in this release

Type	Severity	Summary	CVE
Feature
Feature	Low	Add organization ID parameter to PlusAPI client Add organization ID parameter to PlusAPI client Source: llm_adapter@2026-07-16 Confidence: high	—
Feature	Low	Add step interception points and rework execution hooks documentation around @on Add step interception points and rework execution hooks documentation around @on Source: llm_adapter@2026-07-16 Confidence: high	—
Feature	Low	Wire execution-boundary interception points Wire execution-boundary interception points Source: llm_adapter@2026-07-16 Confidence: high	—
Feature	Low	Add generic interception-hook dispatcher Add generic interception-hook dispatcher Source: llm_adapter@2026-07-16 Confidence: high	—
Feature	Low	Run declarative flows on the TUI (headless terminal fallback) Run declarative flows on the TUI (headless terminal fallback) Source: llm_adapter@2026-07-16 Confidence: high	—
Bugfix
Bugfix	Medium	Sync kickoff-completed event with OUTPUT hook result Sync kickoff-completed event with OUTPUT hook result Source: llm_adapter@2026-07-16 Confidence: high	—
Bugfix	Medium	Fix null repository agent attributes Fix null repository agent attributes Source: llm_adapter@2026-07-16 Confidence: high	—
Bugfix	Medium	Ensure after_llm_call hooks do not break native tool execution Ensure after_llm_call hooks do not break native tool execution Source: llm_adapter@2026-07-16 Confidence: high	—
Bugfix	Medium	Avoid double-append of the turn reply when a handler trims history Avoid double-append of the turn reply when a handler trims history Source: llm_adapter@2026-07-16 Confidence: high	—
Bugfix	Medium	Make tool-result caching opt-in instead of on by default Make tool-result caching opt-in instead of on by default Source: llm_adapter@2026-07-16 Confidence: high	—
Bugfix	Low	Stop rewriting the authored tool description at construction Stop rewriting the authored tool description at construction Source: granite4.1:30b@2026-07-16-audit Confidence: low	—
Bugfix	Low	Expose token usage under both names on agent and crew results Expose token usage under both names on agent and crew results Source: granite4.1:30b@2026-07-16-audit Confidence: low	—
Bugfix	Low	Report per-call usage metrics on kickoff results Report per-call usage metrics on kickoff results Source: granite4.1:30b@2026-07-16-audit Confidence: low	—
Bugfix	Low	Stop replaying previous turn's intent when route_turn() returns falsy Stop replaying previous turn's intent when route_turn() returns falsy Source: granite4.1:30b@2026-07-16-audit Confidence: low	—

Full changelog

What's Changed

Features

Add organization ID parameter to PlusAPI client
Add step interception points and rework execution hooks documentation around @on
Wire execution-boundary interception points
Add generic interception-hook dispatcher
Run declarative flows on the TUI (headless terminal fallback)

Bug Fixes

Sync kickoff-completed event with OUTPUT hook result
Fix null repository agent attributes
Ensure after_llm_call hooks do not break native tool execution
Avoid double-append of the turn reply when a handler trims history
Make tool-result caching opt-in instead of on by default
Stop rewriting the authored tool description at construction
Expose token usage under both names on agent and crew results
Report per-call usage metrics on kickoff results
Stop replaying previous turn's intent when route_turn() returns falsy

Documentation

Update execution hooks grouping and document all hook contexts

Contributors

@joaomdmoura, @lorenzejay, @lucasgomide, @vinibrsl

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track crewAI

Get notified when new releases ship.

About crewAI

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

All releases →