Determinism Sprint 0 + 1: audit + rule codification#68
Open
maryadawson-code wants to merge 6 commits into
Open
Determinism Sprint 0 + 1: audit + rule codification#68maryadawson-code wants to merge 6 commits into
maryadawson-code wants to merge 6 commits into
Conversation
Classify all 91 Netlify function handlers against the 7-level automation determinism framework. 70 are Level 1, 18 are Level 2, 2 are Level 3, 2 are Level 5. Seven functions flagged for downgrade with Level 1/2 rebuild notes. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Classify all 3 exported n8n workflows against the 7-level framework. Fact-Check + Rewrite, Newsletter Draft Writer, and SAM.gov Scanner are all Level 3 (n8n hosting) with Level 2 targets. All three are downgrade candidates. SAM.gov Scanner is already retired per spec. n8n instance not running at audit time; classification based on exported workflow definitions at ~/Projects/mmt-site/n8n-workflows/. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Classify 6 OpenClaw agents, 5 launchd plists, and 2 crontab entries. All 6 agents run on Level 7 infrastructure when most tasks only need Level 1, 2, or 6. com.mmt.sentinel is the strongest launchd downgrade candidate (6 to 2). penny-pincher, cost-tracker-weekly, and the gateway itself are already right-sized. Two side findings flagged out of scope: plaintext API keys in the gateway plist and scheduled jobs targeting the diverged mmt-site clone at \$HOME/mmt-site instead of ~/Projects/mmt-site. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Ecosystem summary across 108 classified items (91 Netlify functions, 3 n8n workflows, 6 OpenClaw agents, 5 launchd jobs, 2 deferred crontab entries). Level distribution: 68% Level 1, 17% Level 2, the rest spread across Levels 3/5/6/7. Top 5 downgrade opportunities ranked by estimated cost-saving: generate-tactical-brief-background, contract-intel-refresh-background, score-deck-background, MMT Newsletter Draft Writer, com.mmt.sentinel. Seventeen total items flagged for downgrade. Recommended Sprint 2 ordering is starts-safe, ends-revenue-critical. Token cost numbers are qualitative until DET-401 pulls Anthropic console data. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
…e sidebar Every other premium page's Tools section lists all three tools. Pursuit Score was the only one missing them, so members who landed there couldn't see the other two tools in the nav. Co-Authored-By: Claude Opus 4 (1M context) <noreply@anthropic.com>
Add pointer to ~/.openclaw/automation-selection-rule.md at the top of the repo's CLAUDE.md so future Claude sessions default to the lowest- level automation that handles the task. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
✅ Deploy Preview for curious-pony-0dec76 ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
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
1 participant
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.
Summary
Sprint 0 + 1 of the Determinism Sprint. Two sprints bundled into one PR because they are all doc changes (audit + rule pointer) with no code/behavior changes.
Sprint 0 (audit, read-only):
Output:
docs/determinism-audit.md(334 lines).Sprint 1 (rule codification):
CLAUDE.mdnow points to~/.openclaw/automation-selection-rule.mdKey findings
Side findings flagged out of scope
~/Library/LaunchAgents/ai.openclaw.gateway.plistEnvironmentVariables— separate security ticket recommendedcom.mmt.sentinelandcom.mmt.seo-agentscheduled jobs target\$HOME/mmt-site(diverged clone), not~/Projects/mmt-site(Netlify-linked primary) — separate clone-remediation ticketNote on branch history
A commit from a parallel session (
1d98026 fix(premium): restore Compliance Check + Signal Chain in Pursuit Score sidebar) appears interleaved in this branch between DET-004 and DET-103. That same commit is already merged tomainvia cherry-pick (b622fda), so when merging this PR, the net diff vs main will only show the 5 DET commits.Test plan
CLAUDE.mdrenders correctly in GitHub previewCo-Authored-By: Claude Opus 4.7 (1M context) noreply@anthropic.com