STUPID-2026-0011
Devin PR broke ledger list API and created buckets on deleted resources
Why 2/10
The PR was closed without merging, so the only cost was maintainer review time.
- Scope
- 0/4
- Time, tokens or the agent's own working state only
- Recoverability
- 0/3
- Nothing was lost
- Did it happen
- 2/2
- Happened in real use
- Beyond the user
- 0/1
- Only the user's own non-production work
The score is the sum of these four factors. How each factor is scored · scored 2026-10-29
Instruction given
Implement bucket deletion functionality for the Formance Ledger system
Expected behavior
Implement soft-delete and hard-delete for buckets while maintaining existing API contracts and following project conventions
Actual behavior
Broke the ledger list endpoint, allowed creating ledgers on deleted buckets, used inconsistent test/handler naming conventions. 65% code coverage with 142 lines missing coverage.
Damage
PR closed without merge. Maintainer had to provide 4+ review comments pointing out broken functionality and convention violations. Wasted reviewer time.
Full write-up
Devin submitted a PR to implement bucket deletion in Formance Ledger. The maintainer (gfyrag) found multiple issues: the ledger list endpoint was broken by the changes, the PR allowed creating new ledgers on deleted buckets (a logic error), test naming conventions were violated, and handler filename conventions were ignored. Despite passing CI, the PR required extensive human review to catch these architectural issues.
Classification
- Agent
- Devin
- Failure mode
- Logic Error
- Root cause
- Scope Misunderstanding
- Domain
- Backend
- Language
- Go
- MIT AI Risk Repository (our mapping)
- 7.3 Lack of capability or robustness taxonomy
- Source
- Github Pr
Related incidents
Cite this record
StupidLLM. "STUPID-2026-0011: Devin PR broke ledger list API and created buckets on deleted resources." AI Agent Incident Database, 2026. https://www.stupidllm.com/incident/STUPID-2026-0011/ (accessed 2026-10-29). CC BY 4.0.
By IDSTUPID-2026-0012 →
Get told when an agent breaks something
We document AI agent failures daily, severity-scored against a published scale. Each Monday, if any scored 7 or above that week — deleted data, leaked secrets, broken production — you get one email with the sources. When nothing did, you get nothing.
This database is callable over MCP — query it from inside your agent.