github-mirror/n8n
1
0
Fork 0
mirror of https://github.com/n8n-io/n8n.git synced 2026-10-17 13:39:44 +02:00
Code Issues Actions 13 Packages Projects Releases Wiki Activity Graph
Swiftyos/experiment
n8n/packages/quality
History
Claude 6a60b3aa7f
fix(core): Keep a waiting tool call in agent chat history when its tool call id repeats, and add Simple and Power mode e2e tests (no-changelog) 
Chat history now matches a waiting tool call by its id and its tool, so a repeated id keeps the card after the turn and after a reload.
An earlier call that never got a result shows as cancelled. The editor reads the card outcome from its own tool.
Add e2e tests for the Simple and Power modes.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_018gK4jZbBjL8toMAnrfJ4mh
2026-10-09 04:34:30 +00:00
..
efficiency refactor: Group quality engineering workspaces by capability (#40007) 2026-10-01 11:20:00 +00:00
environments chore: Hashicorp vault does not handle batch (non-renewable) tokens (#39635) 2026-10-05 07:58:49 +00:00
policy chore: Repair Oxlint migration verification (no-changelog) (#40087) 2026-10-02 11:08:39 +00:00
testing fix(core): Keep a waiting tool call in agent chat history when its tool call id repeats, and add Simple and Power mode e2e tests (no-changelog) 2026-10-09 04:34:30 +00:00
AGENTS.md refactor: Group quality engineering workspaces by capability (#40007) 2026-10-01 11:20:00 +00:00
README.md refactor: Group quality engineering workspaces by capability (#40007) 2026-10-01 11:20:00 +00:00

README.md

Quality engineering

Each area owns workspaces. A test stays with its runner, even when it measures another quality concern.

Area Owns Start here
Policy Repository rules and static checks Policy
Testing Test selection, architecture checks, and the Playwright runner Testing
Environments Services and deployment stacks for tests Environments
Efficiency Standalone microbenchmark and load-test tools Efficiency

Use the Playwright suite map to find browser, accessibility, memory, and infrastructure tests. Their specs remain in Playwright because they use its fixtures and projects.