Skip to content

Prefer Firecrawl over Hyperbrowser in the tiered fetcher#305

Open
probably-jaden wants to merge 1 commit into
mainfrom
feat/firecrawl-before-hyperbrowser
Open

Prefer Firecrawl over Hyperbrowser in the tiered fetcher#305
probably-jaden wants to merge 1 commit into
mainfrom
feat/firecrawl-before-hyperbrowser

Conversation

@probably-jaden

Copy link
Copy Markdown
Contributor

Swaps the last two tiers of the default fetcher chain so Firecrawl is tried before Hyperbrowser: cloakbrowser-or-playwright → pdf → firecrawl → hyperbrowser.

Firecrawl stealth ($0.0042/page) is cheaper than Hyperbrowser with proxy ($0.01/page plus bandwidth), and it also handles PDFs natively — so it should absorb most of the anti-bot tail first, leaving Hyperbrowser as the last resort. Docstrings, the README module table, and the chain-composition unit test are updated to match.

Tests: code_tests/unit_tests/test_agents_and_tools/test_source_archive/ — 130 passed.

🤖 Generated with Claude Code

Swap the last two tiers of the default fetcher chain so Firecrawl is
tried before Hyperbrowser. Firecrawl stealth (~$0.0042/page) is cheaper
than Hyperbrowser with proxy (~$0.01/page plus bandwidth) and also
handles PDFs natively, so it should absorb the anti-bot tail first and
leave Hyperbrowser as the last resort.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant