[crepuscular-drizzle]

Summary

• Allow deepseek-v4-pro as the task agent and as an explicit model override for the built-in deepseek endpoint improver. The improver still defaults to deepseek-flash.
• Include Pro measurements in the default task difficulty report. --model still filters by exact agent model name.

Validation

• Passed 65 offline tests in test_task_difficulty.py, test_improver.py, test_improver_registry_override.py, and test_driver_readiness_closures.py.
• Ran the difficulty report CLI on synthetic Flash and Pro records. Verified that both models contribute to the default report and that --model deepseek-v4-pro selects only Pro records.

[Copilot]

Copilot was unable to review this pull request because the user who requested the review has insufficient remaining quota. Try requesting a review at a lower effort level.

An organization owner can choose the repository organization as the billing source for reviews requested by members with a paid Copilot license. Learn about Copilot code review billing. Review the Copilot code review billing settings.