ukeeper / ukeeper-readability

77%

master: 75%

LAST BUILD ON BRANCH openai-auto-extraction

branch: SELECT

CHANGE BRANCH

x

Sync Branches

• No branch selected
• ci-dockerhub-soft-fail
• ci/workflow-hardening
• cleaner_frontend_structure
• dependabot/docker/node-22
• dependabot/github_actions/github-actions-updates-14cb627f6c
• dependabot/github_actions/github-actions-updates-1ee787ebfb
• dependabot/github_actions/github-actions-updates-5714300483
• dependabot/github_actions/github-actions-updates-640176b5ab
• dependabot/github_actions/github-actions-updates-7aa8621bec
• dependabot/github_actions/github-actions-updates-afd9e15987
• dependabot/github_actions/github-actions-updates-e986305a06
• dependabot/go_modules/backend/go-modules-updates-08b33d1c25
• dependabot/go_modules/backend/go-modules-updates-0bc617739e
• dependabot/go_modules/backend/go-modules-updates-407dd4786b
• dependabot/go_modules/backend/go-modules-updates-5e29427af7
• dependabot/go_modules/backend/go-modules-updates-5e519fa3dd
• dependabot/go_modules/backend/go-modules-updates-71a6db2b89
• dependabot/go_modules/backend/go-modules-updates-751992312c
• dependabot/go_modules/backend/go-modules-updates-a616c34cc0
• dependabot/go_modules/backend/go-modules-updates-c1eb5b8ad9
• dependabot/go_modules/backend/go-modules-updates-c2169da76e
• dependabot/go_modules/backend/go-modules-updates-d01d85479d
• dependabot/go_modules/backend/go-modules-updates-d6af324dbd
• dependabot/go_modules/backend/go-modules-updates-ec788c1f9d
• dependabot/go_modules/backend/go-modules-updates-f885172778
• dependabot/go_modules/backend/golang.org/x/crypto-0.31.0
• dependabot/go_modules/backend/golang.org/x/net-0.36.0
• dependabot/go_modules/github.com/moby/go-archive-0.3.0
• dependabot/go_modules/go-modules-updates-0b36ab2f83
• dependabot/go_modules/go-modules-updates-27468d2404
• dependabot/go_modules/go-modules-updates-4ba46721af
• dependabot/npm_and_yarn/frontend/npm-development-modules-updates-89027bf77e
• dependabot/npm_and_yarn/frontend/npm-development-modules-updates-e6f6ae78c6
• deps/update-latest-go1.25
• fix-cf-maxretries-doc
• fix-top3-review
• fix/ci-go-version-from-gomod
• fix/docker-gha-cache
• fix/image-fetch-streaming
• fix/ssrf-ip-guard
• fix/textarea-crlf
• generic-updates
• htmx
• master
• modularise-retrieval
• openai-auto-extraction
• openai-summaries
• openai_rules_generator
• openai_rules_improver
• paskal/bump_modules
• paskal/clarify_comment
• paskal/cleanup_readme
• paskal/fix_build
• paskal/improve_docker_compose
• paskal/index_to_htmx
• paskal/migrate_to_htmx
• paskal/offline_tests
• paskal/remove_edit_html
• paskal/return_rule_id_on_update
• paskal/safe_password_check
• refs/tags/v0.1.0
• refs/tags/v0.1.1
• refs/tags/v0.1.2
• refs/tags/v0.2.0
• remove-jquery
• remove_chi
• typos_fixes
• umputun/add-chatgpt-endpoints
• update-deps-2026-04-11
• worktree-ci-hardening

Build # 39126544912

Build Type

Pull #74

github

Committed by paskal

Commit Message

Suggest article selectors with OpenAI on request

When a page is parsed wrong, an administrator can ask OpenAI for a CSS
selector of the article. The model sees an outline of the page body
instead of raw HTML, and a suggestion is accepted only after it is
applied to the page and matches a plausible amount of text that is
neither nearly the whole page nor what is extracted now. The selector is
stored as a disabled rule with an insert-only write, so an existing rule
of the domain is never replaced and nothing changes for readers until
the rule is enabled. OpenAI is never asked for a selector during normal
extraction. The request shares the per-request deadline used for
summaries.

Pull Request Pull Request #74: Auto-improve content extraction with OpenAI evaluation

Coverage Stats

277 of 321 new or added lines in 7 files covered. (86.29%)

1140 of 1483 relevant lines covered (76.87%)

44.36 hits per line