Keep Factorial method and add tests to verify precalculated constants by konard · Pull Request #117 · linksplatform/Numbers

konard · 2025-09-13T22:45:43Z

Summary

Based on feedback on this PR, the Factorial method should be kept so we can always verify that our precalculated constants are really correct factorials.

This PR adds tests that:

Independently compute factorial values using BigInteger arithmetic (no overflow)
Verify all precalculated _factorials constants match the computed values
Independently compute Catalan numbers using the formula C(n) = (2n)! / ((n+1)! * n!)
Verify all precalculated _catalans constants match the computed values
For values whose local computation exceeds 10 seconds, make real HTTP requests to OEIS to fetch and verify the expected value:
- Factorials: OEIS A000142 (https://oeis.org/A000142/b000142.txt)
- Catalan numbers: OEIS A000108 (https://oeis.org/A000108/b000108.txt)

In practice, all values for n ≤ 36 (the current MaximumCatalanIndex) compute locally in under 1ms — but the OEIS fallback ensures correctness even if the range is extended in future.

Test Plan

PrecalculatedFactorialsMatchComputedValues — verifies all 21 factorial constants (0! through 20!) match independently computed BigInteger values; falls back to OEIS A000142 via HTTP if computation exceeds 10s
PrecalculatedCatalansMatchComputedFactorials — verifies all 37 Catalan constants (C(0) through C(36)) match independently computed BigInteger values; falls back to OEIS A000108 via HTTP if computation exceeds 10s
All existing tests continue to pass
Build succeeds with no errors

Fixes #59

🤖 Generated with Claude Code

konard · 2026-04-14T13:43:22Z

I thinks we should keep it, at least for all the tests and benches, so we are always sure our pre-calculated constants are really factorials. But also we should not use to much computation if it takes too long, only for parts that will take less than 10 seconds, after that we should use some external trusted resources to verify the big factorial numbers, but only if any of them will be calculated longer than 10 seconds.

konard · 2026-04-14T14:16:32Z

🤖 AI Work Session Started

Starting automated work session at 2026-04-14T14:16:29.883Z

The PR has been converted to draft mode while work is in progress.

This comment marks the beginning of an AI work session. Please wait for the session to finish, and provide your feedback.

Adds two tests that independently compute factorial and Catalan numbers using BigInteger arithmetic and verify they match the precalculated constants in Math._factorials and Math._catalans. Computations that exceed 10 seconds are skipped with a note to use external resources (OEIS A000142 for factorials, OEIS A000108 for Catalan numbers). Fixes #59 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

konard · 2026-04-14T14:20:56Z

Thanks for the feedback! I've updated this PR to:

Keep the Factorial method — reverted the removal entirely
Add validation tests that use BigInteger arithmetic to independently verify that both the _factorials and _catalans precalculated constants are correct:
- PrecalculatedFactorialsMatchComputedValues — computes each n! using BigInteger and asserts it matches Math.Factorial(n)
- PrecalculatedCatalansMatchComputedFactorials — computes each C(n) using the formula C(n) = (2n)! / ((n+1)! × n!) with BigInteger and asserts it matches Math.Catalan(n)
10-second time limit — computations are bounded by a 10-second timeout. If any exceed it, the test skips that value and notes that an external trusted resource should be used (OEIS A000142 for factorials, OEIS A000108 for Catalan numbers). In practice, all values for the current ranges (n ≤ 20 for factorials, n ≤ 36 for Catalans) complete in under 1ms.

konard · 2026-04-14T14:21:28Z

🤖 Solution Draft Log

This log file contains the complete execution trace of the AI solution draft process.

💰 Cost: $0.983591

📊 Context and tokens usage:

Context window: 60.4K / 1M (6%) input tokens, 11.1K / 64K (17%) output tokens

Total: (49.5K + 2.1M cached) input tokens, 11.1K output tokens, $0.983591 cost

🤖 Models used:

Tool: Anthropic Claude Code
Requested: sonnet
Model: Claude Sonnet 4.6 (claude-sonnet-4-6)

📎 Log file uploaded as Gist (1195KB)

View complete solution draft log

Now working session is ended, feel free to review and add any feedback on the solution draft.

konard · 2026-04-14T14:23:35Z

🔄 Auto-restart triggered (iteration 1)

Reason: CI failures detected

Starting new session to address the issues.

Auto-restart-until-mergeable mode is active. Will continue until PR becomes mergeable.

…add missing newline Replace XML summary comments on private helper methods with regular line comments (matching existing code style in BitTests.cs/SystemTests.cs), and add missing newline at end of file. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

konard · 2026-04-14T14:27:19Z

🔄 Auto-restart-until-mergeable Log (iteration 1)

This log file contains the complete execution trace of the AI solution draft process.

💰 Cost: $0.683436

📊 Context and tokens usage:

Claude Sonnet 4.6:

Context window: 50.5K / 1M (5%) input tokens, 7.5K / 64K (12%) output tokens

Total: (39.8K + 1.3M cached) input tokens, 7.5K output tokens, $0.653584 cost

Claude Haiku 4.5:

Total: 20.4K input tokens, 870 / 64K (1%) output tokens, $0.029852 cost

🤖 Models used:

Tool: Anthropic Claude Code
Requested: sonnet
Main model: Claude Sonnet 4.6 (claude-sonnet-4-6)
Additional models:
- Claude Haiku 4.5 (claude-haiku-4-5-20251001)

📎 Log file uploaded as Gist (3103KB)

View complete solution draft log

Now working session is ended, feel free to review and add any feedback on the solution draft.

konard · 2026-04-14T14:29:23Z

See screenshot for Codacy issues.

konard · 2026-04-14T14:29:26Z

🔄 Auto-restart triggered (iteration 2)

Reason: CI failures detected

Starting new session to address the issues.

Auto-restart-until-mergeable mode is active. Will continue until PR becomes mergeable.

…talanWithTimeLimit Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

konard · 2026-04-14T14:31:46Z

🔄 Auto-restart-until-mergeable Log (iteration 2)

This log file contains the complete execution trace of the AI solution draft process.

💰 Cost: $0.371948

📊 Context and tokens usage:

Context window: 38.1K / 1M (4%) input tokens, 4.3K / 64K (7%) output tokens

Total: (26.4K + 693.3K cached) input tokens, 4.3K output tokens, $0.371948 cost

🤖 Models used:

Tool: Anthropic Claude Code
Requested: sonnet
Model: Claude Sonnet 4.6 (claude-sonnet-4-6)

📎 Log file uploaded as Gist (4766KB)

View complete solution draft log

Now working session is ended, feel free to review and add any feedback on the solution draft.

konard · 2026-04-14T14:34:11Z

✅ Ready to merge

This pull request is now ready to be merged:

All CI checks have passed
No merge conflicts
No pending changes

Monitored by hive-mind with --auto-restart-until-mergeable flag

konard · 2026-04-14T14:35:46Z

Skip computations that would exceed 10 seconds, noting that those values should be verified via external trusted resources (OEIS A000142 for factorials, OEIS A000108 for Catalan numbers)

We need to actually do it in our tests, using real http requests to OEIS.

konard · 2026-04-14T14:52:46Z

🤖 AI Work Session Started

Starting automated work session at 2026-04-14T14:52:44.700Z

The PR has been converted to draft mode while work is in progress.

This comment marks the beginning of an AI work session. Please wait for the session to finish, and provide your feedback.

… times out When local BigInteger computation exceeds the 10-second limit, the expected value is now fetched from the authoritative OEIS b-files via real HTTP requests: - Factorials: OEIS A000142 (https://oeis.org/A000142/b000142.txt) - Catalan numbers: OEIS A000108 (https://oeis.org/A000108/b000108.txt) This replaces the previous behaviour of silently skipping those values. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

konard · 2026-04-14T14:55:43Z

🤖 Solution Draft Log

This log file contains the complete execution trace of the AI solution draft process.

💰 Cost: $0.590521

📊 Context and tokens usage:

Context window: 51.8K / 1M (5%) input tokens, 8.1K / 64K (13%) output tokens

Total: (40.0K + 1.1M cached) input tokens, 8.1K output tokens, $0.590521 cost

🤖 Models used:

Tool: Anthropic Claude Code
Requested: sonnet
Model: Claude Sonnet 4.6 (claude-sonnet-4-6)

📎 Log file uploaded as Gist (821KB)

View complete solution draft log

Now working session is ended, feel free to review and add any feedback on the solution draft.

konard · 2026-04-14T14:58:07Z

✅ Ready to merge

This pull request is now ready to be merged:

All CI checks have passed
No merge conflicts
No pending changes

Monitored by hive-mind with --auto-restart-until-mergeable flag

konard self-assigned this Sep 13, 2025

konard changed the title ~~[WIP] Factorial method is not used anymore in the LinksPlatform, can we delete it?~~ Remove unused Factorial method and related code Sep 13, 2025

konard marked this pull request as ready for review September 13, 2025 22:51

konard marked this pull request as draft April 14, 2026 14:16

konard force-pushed the issue-59-4b426f16 branch from 86eefa9 to c7b9418 Compare April 14, 2026 14:20

konard changed the title ~~Remove unused Factorial method and related code~~ Keep Factorial method and add tests to verify precalculated constants Apr 14, 2026

konard marked this pull request as ready for review April 14, 2026 14:20

Fix Codacy code style: add curly braces to if statements in ComputeCa…

7ba2767

…talanWithTimeLimit Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

konard marked this pull request as draft April 14, 2026 14:52

konard marked this pull request as ready for review April 14, 2026 14:55

konard merged commit 6b486ca into main Apr 14, 2026
2 checks passed

Conversation

konard commented Sep 13, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Test Plan

Uh oh!

konard commented Apr 14, 2026

Uh oh!

konard commented Apr 14, 2026

Uh oh!

konard commented Apr 14, 2026

Uh oh!

konard commented Apr 14, 2026

🤖 Solution Draft Log

💰 Cost: $0.983591

📊 Context and tokens usage:

🤖 Models used:

📎 Log file uploaded as Gist (1195KB)

Uh oh!

konard commented Apr 14, 2026

🔄 Auto-restart triggered (iteration 1)

Uh oh!

konard commented Apr 14, 2026

🔄 Auto-restart-until-mergeable Log (iteration 1)

💰 Cost: $0.683436

📊 Context and tokens usage:

🤖 Models used:

📎 Log file uploaded as Gist (3103KB)

Uh oh!

konard commented Apr 14, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

konard commented Apr 14, 2026

🔄 Auto-restart triggered (iteration 2)

Uh oh!

konard commented Apr 14, 2026

🔄 Auto-restart-until-mergeable Log (iteration 2)

💰 Cost: $0.371948

📊 Context and tokens usage:

🤖 Models used:

📎 Log file uploaded as Gist (4766KB)

Uh oh!

konard commented Apr 14, 2026

✅ Ready to merge

Uh oh!

konard commented Apr 14, 2026

Uh oh!

konard commented Apr 14, 2026

Uh oh!

konard commented Apr 14, 2026

🤖 Solution Draft Log

💰 Cost: $0.590521

📊 Context and tokens usage:

🤖 Models used:

📎 Log file uploaded as Gist (821KB)

Uh oh!

konard commented Apr 14, 2026

✅ Ready to merge

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

konard commented Sep 13, 2025 •

edited

Loading

konard commented Apr 14, 2026 •

edited

Loading