feat: implement flake processing using timeseries models

[joseph-sentry]

• remove code related to old upload states
• create implementation of flake processing that consumes data from timescale
• process flakes uses impl_type

idea is that we'll start with impl_type both for a while which will persist flakes to the current db table and the new one, then at some point we will detect flaky tests in the finisher by checking the new flakes table

[seer-by-sentry]

🚨 Sentry detected 1 potential issue in your recent changes 🚨

• Line 117, services/test_analytics/ta_process_flakes.py: Item "str" of "Any | str" has no attribute "decode"

  • Improperly decoded commit IDs from Redis can cause database queries to fail or take too long, leading to timeouts.
  • This may cause issues similar to: #6431559854

_{Did you find this useful? React with a 👍 or 👎}

[Swatinem]

moving this magic constant to the top level would make sense. and an explanation of "after X passes in a row, the test is not marked as flaky anymore"

[Swatinem]

testing with 2x pass would trigger the error I mentioned above, as you clear the test from the current flakes, and on the second iteration try to access that yet again.

[Swatinem]

in case you use both, you are locking twice in a row. maybe if you move the locking logic out of the function, and the invocation into the lock here, that could be avoided.

[joseph-sentry]

i think this is necessary because they're locking different locks and reading from different keys

there's an edge case where a commit is leftover if we lock only once:

call Task 1 with commit A, old_key = [A], new key = [B]
Task 1: takes repo lock 
Task 1: completes new invocation, old key = [A], new key = []
call Task 2 with commit B, old key = [A, B], new key = [B]
Task 2: fails to take lock and just drops 
Task 1: completes old invocation, old key = [], new key = [B]

B is left over and has to wait for another invocation of process flakes to get processed

[codecov]

Codecov Report

Attention: Patch coverage is 96.20853% with 8 lines in your changes missing coverage. Please review.

Project coverage is 97.71%. Comparing base (c9ed88b) to head (76a8a8e).
Report is 4 commits behind head on main.

✅ All tests successful. No failed tests found.

Files with missing lines	Patch %	Lines
services/test_analytics/ta_process_flakes.py	92.85%	5 Missing ⚠️
tasks/process_flakes.py	57.14%	3 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1140      +/-   ##
==========================================
- Coverage   97.72%   97.71%   -0.01%     
==========================================
  Files         449      451       +2     
  Lines       36866    37036     +170     
==========================================
+ Hits        36028    36191     +163     
- Misses        838      845       +7     

Flag	Coverage Δ
integration	42.81% <41.23%> (-0.08%)	⬇️
unit	90.51% <96.20%> (+0.08%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[codecov-notifications]

Codecov Report

Attention: Patch coverage is 96.20853% with 8 lines in your changes missing coverage. Please review.

✅ All tests successful. No failed tests found.

Files with missing lines	Patch %	Lines
services/test_analytics/ta_process_flakes.py	92.85%	5 Missing ⚠️
tasks/process_flakes.py	57.14%	3 Missing ⚠️

📢 Thoughts on this report? Let us know!