Reported News
CrewAI 1.15.38 makes gpt-6-luna the default model everywhere
CrewAI 1.15.38, published November 8, 2026 on GitHub, lists as its first feature: "Make gpt-6-luna crewAI's default model everywhere."
- Changes reported
- 5
- listed below, each from a source we read
- We tested
- Not tested yet
- reported from sources; we did not run it ourselves
- Gaps we flag
- 3
- things we could not verify
- Sources
- 1
- 1 primary, linked below
What changed
| # | What the source says | Status |
|---|---|---|
| 01 | The Features list opens with "Make gpt-6-luna crewAI's default model everywhere." Crews that do not set their own model would use gpt-6-luna after upgrading to 1.15.38, according to the notes. | Reported |
| 02 | The notes also list "Read spreadsheet URLs in an agent's input with tools over every row." They do not say which hosts, file types or size limits apply. | Reported |
| 03 | A Features item adds "--no-open to crewai eval for headless use," so an evaluation can skip opening a browser. | Reported |
| 04 | Under Bug Fixes, the notes say the CLI will "Exit non-zero when crewai run's project script fails," which matters for CI jobs that treated a printed error as success. | Reported |
| 05 | Another bug fix says the project .env is created "owner-only when crewai eval turns tracing on." The notes do not state the file mode. | Reported |
reported by the sourcemeasured or run by usnot verified
Primary source: CrewAI 1.15.38 release notes (GitHub). We are the fast, independent index; the vendor’s own page is the source of record for this release.
In the source’s words
“Make gpt-6-luna crewAI's default model everywhere”
“Read spreadsheet URLs in an agent's input with tools over every row”
“Add --no-open to crewai eval for headless use”
Early verdict
Anyone running CrewAI without pinning a model should read the 1.15.38 notes before upgrading, because they say gpt-6-luna is now the default everywhere. People who pass spreadsheet URLs into agent inputs, or who run crewai eval and crewai run in CI or over SSH, are the others most likely to notice; the notes do not describe this as an emergency upgrade.
Basis: Based only on the CrewAI 1.15.38 GitHub release notes as read on November 8, 2026; we have not run the release.
What we have not verified
- We did not install or run CrewAI 1.15.38, or try the gpt-6-luna default, spreadsheet URL reading, or the --no-open flag.
- We did not check gpt-6-luna's availability, pricing or behavior with OpenAI, or what CrewAI used as the default model before 1.15.38.
- We did not verify the .env permission change or the crewai run exit-code change on a real project.
This brief is Reported: written from the sources below, not from running the release ourselves.
Sources
- CrewAI 1.15.38 release notes (GitHub)primary source · fetched 2026-11-08
Related
Spotted an error? See our corrections policy or email the address on the contact page. Markdown version for agents: /news/crewai-1-15-38.md
Want these briefs in your Google Top Stories? Add Agentic Weekly as a preferred source on Google.
Newsletter
The Weekly Verdict. Free, every Monday.
A free email every Monday: the week's few big AI releases, then 5 short use cases for the new models, each with a prompt you can paste.
Free. Double opt-in. One click to unsubscribe.