Repository navigation
log-execution usage and default ledger; SKILL states the init-block shape; e2e counts plugin reads precisely; live run 15 - #19
Merged
Conversation
…pe; e2e counts plugin reads precisely; run 15 Live run 15 (planner shapes + rules, task-worktree merge): 13/13, 13m13s, $1.42, 6 blocks, 0 planning write blocks (from 8–12), every merged commit traces to its task (8 commit.created). The remaining plugin-source reads were the supervisor learning log-execution's arguments and the init block's sections: log-execution now has --help and a default ledger, SKILL.md gives the call and says the section list is the whole shape, and the e2e counter walks tool calls (--schema uses excluded): 9, 8, 6 reads in runs 13–15. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015QxyVf3NgwsgRyYpBgDDTC
adeelahmad
pushed a commit
that referenced
this pull request
Oct 18, 2026
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014j4wLin3oJTtnvjE9Lq2VV
adeelahmad
pushed a commit
that referenced
this pull request
Oct 18, 2026
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014j4wLin3oJTtnvjE9Lq2VV
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Requested by Adeel · project thread
Before:
log-executionhad no usage and took the ledger file as an undocumented fifth argument, so in live runs 13–15 the supervisor read its source (twice per run) andpipeline/execution/00-red/init.template.md(four times per run) to learn shapes SKILL.md should have stated. The e2e "plugin-source reads" counter also countedmd-db validate --schema <plugin>/schemas/…, a legitimate use, so it read 14–17 when the real number was 6–9.After:
log-execution --helpprints the usage, a wrong call exits 64 with it, and the ledger defaults to the latestdocs/agents/sprintN/execution.log. SKILL.md gives the exact call and says the init-block section list is the whole shape, naming the two files not to read. The e2e counter walks tool calls and excludes--schemauses: runs 13, 14, 15 count 9, 8, 6. ROADMAP M0.8 and OVERVIEW record live run 15 (13/13, 13m13s, $1.42, 6 blocks, 0 planning write blocks, every merged commit traced to its task byevents trace).How:
scripts/test/log-execution.test.py(7 checks, wired intomake test) written first;plugin/bin/log-executionrewritten;make cigreen locally, shellcheck clean.Generated by Claude Code