ed/manual_slop
Private
Public Access
0
0
Fork 0
Code Activity
5,102 Commits 36 Branches 1 Tag
master
Commit Graph
3 Commits
Author SHA1 Message Date
ed 5e95a1bfb7 fix(reports): duration_days -> active days for all 30 top tracks 
Script used calendar-day duration (end_date - init_date), which
inflated tracks that sat dormant between work and archive-move.
Example: external_editor_integration_20260308 reported 60 days
(init 2026-03-08, last archive-move 2026-05-07) when actual work
was 2 active days.

Corrected metric: active days = distinct calendar days with at
least one commit touching the track folder. All 30 top tracks
now show 2-7 active days, matching the user's expectation that
no track lasts more than a week.

Also fixed commit_count + files_touched for all 30 tracks (the
script's work-prefix-only count was always 0-1 for these).

Top 3 examples:
- external_editor_integration_20260308: 60d/1c/4f -> 2d/4c/8f
- code_path_audit_20260607: 18d/1c/7f -> 7d/23c/14f
- nagent_review_20260608: 12d/0c/20f -> 3d/53c/20f

Still stale (need recompute, not hand-fix):
- 3.1 per-era aggregates
- 8 use-case predictions
- 218 other tracks not in top-30
 2026-07-05 18:02:15 -04:00
ed f1c4516034 fix(reports): manually correct commit_count + files_touched for 5 spot-checked tracks 
The script's commit_count and files_touched columns only counted
work-prefix commits (feat|fix|refactor|perf|test) with pathspecs
matching the track folder. Track folders contain only metadata
commits (conductor(*), chore(conductor), docs(track)), so the
script reported 0 commits for any track that did real work.

Corrected rows (now using total commits + total unique files
touching the track folder, any prefix):

- code_path_audit_20260607: 1->23 commits, 7->14 files
- qwen_llama_grok_integration_20260606: 0->25 commits, 4->8 files
- nagent_review_20260608: 0->53 commits, 4->20 files
- data_oriented_error_handling_20260606: 0->21 commits, 4->8 files
- superpowers_review_20260619: 0->63 commits, 8->16 files

Added 9.1 caveat explaining the manual corrections and the
methodology error that caused them.
 2026-07-05 17:54:01 -04:00
ed ce0d143877 feat(reports): META_TOOLING_DURATION_ANALYSIS_2026-07-05.md (10 sections, 379 lines) 
Empirical duration analysis of the meta-tooling that built this
codebase from Feb 21 to Jul 5, 2026 (133 days, 248 tracks, 1003
sub-agent tasks, 1608 work-prefix commits, 312 sessions).

Era detection: 5 eras via multi-signal weighted-vote on
config.toml + conductor/workflow.md + conductor/tech-stack.md +
sub-agent log content (7-day cluster window).

Headline numbers:
- Era 0 (early, Feb 21 - Mar 20): 113 tracks
- Era 1 (mid, Mar 21 - May 3): 4 tracks (small era)
- Era 2 (mid, May 4 - Jun 1): 42 tracks
- Era 3 (late, Jun 2 - Jun 24): 69 tracks (peak productivity)
- Era 4 (current, Jun 25 - present): 20 tracks

Tier 3 worker median task duration: 272.5s (~4.5 min).
Tier 4 QA median task duration: 416s (~7 min).
Tier 1 median task duration: 0s (synthetic/orchestration only).

Use-case predictions (per files-touched bucket):
- 1-5 files (227 tracks): 0d median, 1.0 IQR
- 6-15 files (15 tracks): 1d median, 6.0 IQR
- 16-30 files (4 tracks): 2d median, 4.5 IQR
- 31+ files (2 tracks): 0d median (small sample)

Part of conductor/tracks/meta_tooling_duration_analysis_20260705/.
 2026-07-05 17:14:16 -04:00