CrewAI Release Notes

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

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).
• Improve custom OpenAI URLs.

Bug Fixes

• Fix null repository agent attributes.
• Fix after_llm_call hooks to prevent breaking native tool execution.
• Stop double-appending 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 the previous turn's intent when route_turn() returns falsy.
• Drain memory writes before kickoff and flow completion events.

Documentation

• Group execution hooks and document all hook contexts.
• Update documentation for execution hooks.

Contributors

@joaomdmoura, @lorenzejay, @lucasgomide, @vinibrsl

What's Changed

Features

• Pull latest LLM models dynamically in the crew wizard.
• Support inline skill definitions.
• Add generated Flow Definition authoring skill.
• Support templated Flow action inputs.
• Add text helper for flow CEL prompts.
• Add text helper to flow skill example.
• Implement message setup and feedback handling in AgentExecutor.
• Add repository agents to flow definitions.
• Define stream frame protocol for flows.
• Type tool and app in CrewDefinition.
• Repoint template commands to crewAIInc-fde org.

Bug Fixes

• Key model-catalog cache by exact API key, shorten TTL, and skip Ollama.
• Unify crewai run flow input resolution and prompt from the state schema.
• Resolve pip-audit failures for onnx 1.22.0 and nltk PYSEC-2026-597.
• Ensure we are writing version for flows.
• Include aiobotocore in the bedrock extra.
• Reject self-listening flow methods.
• Cut docs version nav from Edge so new pages aren't dropped.

Documentation

• Update language from Rules to Policies to match new dashboard changes.
• Document flow agent options.
• Add streaming docs to the navigation.
• Document Cost Limit rule type in Agent Control Plane.
• Drop CREWAI_LOG_FORMAT references from Datadog guide.

Contributors

@akaKuruma, @danielfsbarreto, @github-code-quality[bot], @joaomdmoura, @lorenzejay, @lucasgomide, @manisrinivasan2k1, @renatonitta, @vinibrsl

What's Changed

Features

• Initialize Git repositories for generated projects (#6364)
• Require explicit CrewAI project definitions (#6358)
• Open deployment page after CLI deploy (#6343)

Bug Fixes

• Fix deployment page link ID resolution (#6365)
• Fix JSON crew template rendering (#6359)
• Fix JSON crew version pin (#6342)
• Fix SSRF redirect bypass in scraping fetches (#6331)

Documentation

• Improve open source positioning in README (#6363)
• Improve coding agent setup call-to-action (#6344)
• Add snapshot and changelog for version 1.15.1a1 (#6362)

Contributors

@joaomdmoura, @lorenzejay, @oalami, @theCyberTech, @vinibrsl

What's Changed

Features

• Track conversational flow turn usage in telemetry
• Support conversational flows in the CLI TUI
• Add unified declarative flow loading
• Add declarative Flow CLI support
• Add optional if expression to each.do steps
• Add single agent action to Flow definitions
• Add crew actions to FlowDefinition
• Add inline crew definition loading
• Add each composite action to FlowDefinition
• Implement DMN mode support in crew creation and execution

Bug Fixes

• Fix owner-only permissions enforcement on credential files
• Fix JSON schema flow state kickoff inputs
• Fix symlink path traversal in skill archive extraction
• Aggregate token usage across all LLM calls
• Remove duplicated Exa tool
• Resolve JSON crew issues
• Fix JSON crew handling and enhance memory reset functionality

Documentation

• Update installation and quickstart documentation for JSON-first crew projects
• Add Datadog integration guide with importable operations dashboard
• Add "One Card per Step" Studio page
• Add snapshots and changelogs for previous versions leading to v1.15.0

Performance

• Improve crewai run startup UX
• Keep flow method progress visible for nested crews

Refactoring

• Remove StateProxy from flow state access
• Consolidate crewai run and crewai flow kickoff
• Discriminate FlowDefinition state types
• Wire config and persistence from FlowDefinition into the runtime

Contributors …