Fix: double conversion of pollInterval and timeout in --wait mode

[shiva-manu]

Fix: Double conversion of pollInterval and timeout in --wait mode

Summary

Fixes an issue where pollInterval and timeout were incorrectly converted to milliseconds in the CLI before being passed to the SDK, which also performs its own conversion.

This resulted in extremely long polling intervals (e.g., 5s → ~83 minutes), causing firecrawl crawl --wait to appear stuck while still consuming credits server-side.

---

Root Cause

• CLI converted pollInterval and timeout from seconds to milliseconds
• SDK also converts them internally (seconds → milliseconds)

Result:
5 → 5000 → 5,000,000 ms (~83 minutes)

---

Changes

• Pass pollInterval and timeout as seconds to the SDK
• Remove unnecessary * 1000 conversion in CLI
• Convert to milliseconds only inside the --progress polling loop
• Improve timeout handling using explicit undefined checks

---

Impact

• Fixes hanging behavior in firecrawl crawl --wait
• Prevents silent credit consumption without output
• Keeps --wait --progress mode working correctly
• No breaking changes

---

Verification

firecrawl crawl https://firecrawl.dev --limit 2 --wait --poll-interval 3

[Copilot]

Pull request overview

Fixes an issue in the CLI crawl --wait flow where pollInterval and timeout were being converted to milliseconds before calling the SDK, leading to an unintended “double conversion” and extremely long polling intervals.

Changes:

• Pass pollInterval and timeout to the SDK in seconds (no pre-conversion in CLI).
• Keep milliseconds conversion only for the CLI’s internal --progress polling loop.
• Tighten types for the constructed crawlOptions object.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

timeoutMs is computed using an explicit undefined check, but the timeout enforcement later in this function still relies on a truthy check (if (timeoutMs && ...)). As a result, a valid timeout value of 0 would be treated as “no timeout”. Consider keeping the explicit undefined semantics end-to-end by checking timeoutMs !== undefined where the timeout is enforced.

[Copilot]

This change switches pollInterval/timeout passed to the SDK from milliseconds to seconds (default pollInterval is now 5, not 5000). The existing unit tests for executeCrawl currently assert millisecond values (e.g., pollInterval: 5000, timeout: 300000) and will need to be updated to match the new units so CI stays green.