#13: bounded task usage/cost breakdowns #43
No reviewers
Labels
No labels
accessibility
bug
documentation
duplicate
enhancement
good first issue
help wanted
invalid
question
wontfix
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
nsaspy/llm-log!43
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "rage/13-usage-breakdown-red"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Implements the next bounded #13 slice after durable retry/attempt accounting.
Canonical research:
research/LLM-LOG-RESEARCH-043-task-usage-breakdowns.orgRED evidence:
evidence/LLM-LOG-EVIDENCE-027-task-usage-breakdown-red.orgGREEN evidence:
evidence/LLM-LOG-EVIDENCE-028-task-usage-breakdown-green.orgAdds restart-durable, task-rooted provider/model/client usage and cost breakdowns to
query_task_accounting, reusing existing bounded Tek9 task/usage retrieval and immutable SWI-Prolog-derived cost assertions. No Tek9, Python-rule-engine, or dotfiles mutation.Accepted RED:
9f3e54909fa3d9527bc7fc658c9598e9ac7d193f, run 33435473703.Implementation GREEN:
6e6df3513e8b5d4cd660f3462ce30492a5deca47, run 33435808798.Evidence-only exact-head GREEN:
4eaabb3ddc60fc288819d4f4bffb44b89ec708f4, run 33435931708.Classification/outcome analytics remain separate RED-first work; #15 must define outcome evidence/labels before outcome-dependent aggregates.