This dream found work to do.

Run run-live-20260615T012808096Z-83eee46c
Work item work-item:memory-fabric
Source report.mdsvx
Template joel/tufte-mdsvx@0.1.0
Review data review-surface.json

This dream found work to do.

This is a human review surface, not an autopatcher. The report puts findings first, then proof, so the human can decide what to accept, hold, reject, or turn into work.

Run context

Run run-live-20260615T012808096Z-83eee46c searched 58 memory hits, hydrated 8 redacted receipts, and produced 58 findings for human review.

Findings: 58. Unique receipts: 55. Expiry: 24h, noindex.

The actual findings

Finding 1: PDF brain needs human review

Matched docs/pdf-brain chunk in Building Microservices 2nd Edition Sam Newman: In this example, @doctocat owns any file in the /docs # directory in the root of your repository. /docs/ @doctocat > CHAPTER 12 > Durability of data > How Much Is Too Much? | 393 > Degrading Functionality > It’s Not All or Nothing.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 2: PDF brain needs human review

Matched docs/pdf-brain chunk in Guide to Documenting Learning, A Hale, Janet A., Tolisano, Silvia Rosenthal & Janet A. Hale: A Guide to Documenting Learning > Text and Visual Platforms and Tools > Text and Backchannel Documentation.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 3: PDF brain needs human review

Matched docs/pdf-brain chunk in Adopting Elixir : From Concept to Production: catch all gets get _ do > Next, we should handle non-get requests, like this: > Let’s take a look at the client now:7 > Moving Incremental Releases into Production.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 4: PDF brain needs human review

Matched docs/pdf-brain chunk in Adopting Elixir : From Concept to Production: Ensuring Code Consistency > mix credo lib/belief_structure.ex:1:11 > To get started, let’s take a look at a Phoenix controller test: > end.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 5: PDF brain needs human review

Matched docs/pdf-brain chunk in Adopting Elixir : From Concept to Production: Ensuring Code Consistency > mix credo lib/belief_structure.ex:1:11 > To get started, let’s take a look at a Phoenix controller test:.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 6: PDF brain needs human review

Matched docs/pdf-brain chunk in Concept Catalog Template: How t us thi templat : > To use the template below, follow this three-step process: > Nam an T.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 7: PDF brain needs human review

Matched docs/pdf-brain chunk in Concept Catalog Template: How t us thi templat : > To use the template below, follow this three-step process: > Nam an T.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 8: PDF brain needs human review

Matched docs/pdf-brain chunk in ng book2 r7: Data Architecture with Observables Part 1: Services > Observables and RxJS > Note: Some RxJS Knowledge Required.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 9: PDF brain needs human review

Matched docs/pdf-brain chunk in ng book2 r7: Data Architecture with Observables Part 1: Services > Observables and RxJS > Note: Some RxJS Knowledge Required.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 10: PDF brain needs human review

Matched docs/pdf-brain chunk in Universal Design for Learning in the Classroom Practiions Tracey E. Hall & Anne Meyer & and David H. Rose: THE GUILFORD PRESS > C H A P T E R 4 > Ge vue and Tracey e. Hall.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 11: agent transcripts needs human review

Matched indexed JoelClaw session memory in JoelClaw session index (cross-machine agent transcripts).

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 12: agent transcripts needs human review

Matched indexed JoelClaw session memory in JoelClaw session index (cross-machine agent transcripts).

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 13: agent transcripts needs human review

Matched indexed JoelClaw session memory in JoelClaw session index (cross-machine agent transcripts).

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 14: agent transcripts needs human review

Matched indexed JoelClaw session memory in JoelClaw session index (cross-machine agent transcripts).

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 15: agent transcripts needs human review

Matched indexed JoelClaw session memory in JoelClaw session index (cross-machine agent transcripts).

Reasoning. The search hit has matching redacted hydration, so the report can point at receipts without returning full transcripts.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 16: agent transcripts needs human review

Matched indexed JoelClaw session memory in JoelClaw session index (cross-machine agent transcripts).

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 17: agent transcripts needs human review

Matched indexed JoelClaw session memory in JoelClaw session index (cross-machine agent transcripts).

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 18: agent transcripts needs human review

Matched indexed JoelClaw session memory in JoelClaw session index (cross-machine agent transcripts).

Reasoning. The search hit has matching redacted hydration, so the report can point at receipts without returning full transcripts.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 19: agent transcripts needs human review

Matched indexed JoelClaw session memory in JoelClaw session index (cross-machine agent transcripts).

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 20: agent transcripts needs human review

Matched indexed JoelClaw session memory in JoelClaw session index (cross-machine agent transcripts).

Reasoning. The search hit has matching redacted hydration, so the report can point at receipts without returning full transcripts.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 21: agent transcripts needs human review

Matched indexed JoelClaw session memory in JoelClaw session index (cross-machine agent transcripts).

Reasoning. The search hit has matching redacted hydration, so the report can point at receipts without returning full transcripts.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 22: agent transcripts needs human review

Matched indexed JoelClaw session memory in JoelClaw session index (cross-machine agent transcripts).

Reasoning. The search hit has matching redacted hydration, so the report can point at receipts without returning full transcripts.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 23: agent transcripts needs human review

Matched indexed JoelClaw session memory in JoelClaw session index (cross-machine agent transcripts).

Reasoning. The search hit has matching redacted hydration, so the report can point at receipts without returning full transcripts.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 24: agent transcripts needs human review

Matched indexed JoelClaw session memory in JoelClaw session index (cross-machine agent transcripts).

Reasoning. The search hit has matching redacted hydration, so the report can point at receipts without returning full transcripts.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 25: agent transcripts needs human review

Matched indexed JoelClaw session memory in JoelClaw session index (cross-machine agent transcripts).

Reasoning. The search hit has matching redacted hydration, so the report can point at receipts without returning full transcripts.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 26: agent transcripts needs human review

Matched indexed JoelClaw session memory in JoelClaw session index (cross-machine agent transcripts).

Reasoning. The search hit has matching redacted hydration, so the report can point at receipts without returning full transcripts.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 27: agent transcripts needs human review

Matched indexed JoelClaw session memory in JoelClaw session index (cross-machine agent transcripts).

Reasoning. The search hit has matching redacted hydration, so the report can point at receipts without returning full transcripts.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 28: agent transcripts needs human review

Matched indexed JoelClaw session memory in JoelClaw session index (cross-machine agent transcripts).

Reasoning. The search hit has matching redacted hydration, so the report can point at receipts without returning full transcripts.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 29: Brain notes needs human review

Matched 8 term(s) in Pi Cloudflare Sandbox Workflows Brain.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 30: Brain notes needs human review

Matched 7 term(s) in Pi Cloudflare Sandbox Workflows Brain.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 31: Brain notes needs human review

Matched 7 term(s) in Pi Cloudflare Sandbox Workflows Brain.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 32: Brain notes needs human review

Matched 7 term(s) in Pi Cloudflare Sandbox Workflows Brain.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 33: Brain notes needs human review

Matched 6 term(s) in Pi Cloudflare Sandbox Workflows Brain.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 34: Brain notes needs human review

Matched 6 term(s) in Pi Cloudflare Sandbox Workflows Brain.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 35: Brain notes needs human review

Matched 6 term(s) in Pi Cloudflare Sandbox Workflows Brain.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 36: Brain notes needs human review

Matched 6 term(s) in Pi Cloudflare Sandbox Workflows Brain.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 37: Brain notes needs human review

Matched 5 term(s) in Pi Cloudflare Sandbox Workflows Brain.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 38: Brain notes needs human review

Matched 5 term(s) in Pi Cloudflare Sandbox Workflows Brain.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 39: Cloudflare runs needs human review

Matched 10 term(s) in Workflow app Cloudflare receipts.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 40: Cloudflare runs needs human review

Matched 10 term(s) in Workflow app Cloudflare receipts.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 41: Cloudflare runs needs human review

Matched 10 term(s) in Workflow app Cloudflare receipts.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 42: Cloudflare runs needs human review

Matched 10 term(s) in Workflow app Cloudflare receipts.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 43: Cloudflare runs needs human review

Matched 10 term(s) in Workflow app Cloudflare receipts.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 44: Cloudflare runs needs human review

Matched 10 term(s) in Workflow app Cloudflare receipts.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 45: Cloudflare runs needs human review

Matched 10 term(s) in Workflow app Cloudflare receipts.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 46: Cloudflare runs needs human review

Matched 10 term(s) in Workflow app Cloudflare receipts.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 47: Cloudflare runs needs human review

Matched 10 term(s) in Workflow app Cloudflare receipts.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 48: Cloudflare runs needs human review

Matched 10 term(s) in Workflow app Cloudflare receipts.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 49: repo outputs needs human review

Matched 9 term(s) in Pi Cloudflare Sandbox Workflows repo outputs.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 50: repo outputs needs human review

Matched 9 term(s) in Pi Cloudflare Sandbox Workflows repo outputs.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 51: repo outputs needs human review

Matched 8 term(s) in Pi Cloudflare Sandbox Workflows repo outputs.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 52: repo outputs needs human review

Matched 8 term(s) in Pi Cloudflare Sandbox Workflows repo outputs.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 53: repo outputs needs human review

Matched 7 term(s) in Pi Cloudflare Sandbox Workflows repo outputs.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 54: repo outputs needs human review

Matched 7 term(s) in Pi Cloudflare Sandbox Workflows repo outputs.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 55: repo outputs needs human review

Matched 6 term(s) in Pi Cloudflare Sandbox Workflows repo outputs.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 56: repo outputs needs human review

Matched 5 term(s) in Pi Cloudflare Sandbox Workflows repo outputs.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 57: repo outputs needs human review

Matched 4 term(s) in Pi Cloudflare Sandbox Workflows repo outputs.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

Finding 58: repo outputs needs human review

Matched 4 term(s) in Pi Cloudflare Sandbox Workflows repo outputs.

Reasoning. The search hit has receipt metadata but no matching hydration yet, so treat this as a lead instead of a claim.

Rating. 10/10

Recommendation. Review the receipts, decide whether this updates .brain, and turn any capture gap into a recovery task instead of normal workflow behavior.

Receipts.

What to do with these findings

Use this as HITL input, not autopilot. Accept a finding only when the receipt trail is good enough to update .brain, create a capture fix, or refine a workflow/package decision.

Refinement proposals were REASONED by an agent lane over the analysis-method kernel skill and the hydrated evidence; ratings discriminate and each proposal is tied to receipts the agent could actually cite.

Refinement proposals emitted: 4. Accepted proposals should become Brain/package changes or constraints for the next generated workflow.

HITL decision receipt

Write human decisions as memory.hitl-decision.v1 at report/hitl-decision.json, backed by this report and its source refs.

Schema export: memory-hitl-decision-schema from contract://workflow/memory-fabric/hitl-decision.v1.

Decisions that must feed the next generated workflow seed: accept, turn-into-work.

Actionable line items

Report node

joelclaw.memory.hitl-report rendered this artifact as an installed workflow cartridge node. The JSON document is the machine contract; this sibling text/mdsvx artifact is the publishable HITL source.

Workflow state machine

The D2 figure below is rendered from the pinned generated workflow.xstate-machine.v1 config for this run, not from a static node list. It belongs below the findings so proof does not bury the human decision.

direction: down
s0: "ready"
s1: "captureRun\ncapture-run"
s2: "captureGeneratedMachine\ncapture-generated-machine"
s3: "captureGeneratedPlan\ncapture-generated-plan"
s4: "minePrimarySignals\nmine-primary-signals"
s5: "searchTranscripts24h\nsearch-transcripts-24h"
s6: "searchTranscripts7d\nsearch-transcripts-7d"
s7: "searchTranscripts30d\nsearch-transcripts-30d"
s8: "searchTranscriptsQuarter\nsearch-transcripts-quarter"
s9: "searchTranscriptsAllTime\nsearch-transcripts-all-time"
s10: "searchBrainDecisions\nsearch-brain-decisions"
s11: "searchCloudflareRuns\nsearch-cloudflare-runs"
s12: "searchRepoOutputs\nsearch-repo-outputs"
s13: "searchDocsBrain\nsearch-docs-brain"
s14: "hydratePrimaryReceipts\nhydrate-primary-receipts"
s15: "correlateEvidence\ncorrelate-evidence"
s16: "proposeRefinements\npropose-refinements"
s17: "renderHitlReport\nrender-hitl-report"
s18: "seedHitlDecisionWorkflow\nseed-hitl-decision-workflow"
s19: "draftFollowUpRunRequest\ndraft-follow-up-run-request"
s20: "reviewSummary\nreview-summary"
s21: "done\nfinal"
s22: "blocked\nfinal"
s0 -> s1: "NEXT"
s1 -> s2: "STEP_DONE"
s1 -> s22: "STEP_BLOCKED"
s2 -> s3: "STEP_DONE"
s2 -> s22: "STEP_BLOCKED"
s3 -> s4: "STEP_DONE"
s3 -> s22: "STEP_BLOCKED"
s4 -> s5: "STEP_DONE"
s4 -> s22: "STEP_BLOCKED"
s5 -> s6: "STEP_DONE"
s5 -> s22: "STEP_BLOCKED"
s6 -> s7: "STEP_DONE"
s6 -> s22: "STEP_BLOCKED"
s7 -> s8: "STEP_DONE"
s7 -> s22: "STEP_BLOCKED"
s8 -> s9: "STEP_DONE"
s8 -> s22: "STEP_BLOCKED"
s9 -> s10: "STEP_DONE"
s9 -> s22: "STEP_BLOCKED"
s10 -> s11: "STEP_DONE"
s10 -> s22: "STEP_BLOCKED"
s11 -> s12: "STEP_DONE"
s11 -> s22: "STEP_BLOCKED"
s12 -> s13: "STEP_DONE"
s12 -> s22: "STEP_BLOCKED"
s13 -> s14: "STEP_DONE"
s13 -> s22: "STEP_BLOCKED"
s14 -> s15: "STEP_DONE"
s14 -> s22: "STEP_BLOCKED"
s15 -> s16: "STEP_DONE"
s15 -> s22: "STEP_BLOCKED"
s16 -> s17: "STEP_DONE"
s16 -> s22: "STEP_BLOCKED"
s17 -> s18: "STEP_DONE"
s17 -> s22: "STEP_BLOCKED"
s18 -> s19: "STEP_DONE"
s18 -> s22: "STEP_BLOCKED"
s19 -> s20: "STEP_DONE"
s19 -> s22: "STEP_BLOCKED"
s20 -> s21: "STEP_DONE"
s20 -> s22: "STEP_BLOCKED"
initial: "ready"
machine: "machine:run-live-20260615T012808096Z-83eee46c"
Generated workflow state machine - D2 source from the pinned report artifact. The canonical .mdsvx source is published beside this preview.

Dynamic generation proof

Dynamic generation proof level: generated-machine.

Generated machine: artifact://piwf-run-live-20260615t012808096z-83eee46c/runs/run-live-20260615T012808096Z-83eee46c/workflows/machine.config.json hash 12ad1c539dfe098f3264c03f7e1e9f043084ea50d6f552f95d13ba3ce0fe1f29.

Generated machine source: artifact://piwf-run-live-20260615t012808096z-83eee46c/runs/run-live-20260615T012808096Z-83eee46c/workflows/machine.ts hash 8a04d4a39ca2eb528b502d78f27689747c28f44f0958fdd99539ace3c145d8f3.

Generated harness: artifact://piwf-run-live-20260615t012808096z-83eee46c/runs/run-live-20260615T012808096Z-83eee46c/workflows/harness.ts hash 29292202121110492cfa67db4b428c25d9f19b1031418ef3dc5501dfd80d2277.

Verification contract: artifact://piwf-run-live-20260615t012808096z-83eee46c/runs/run-live-20260615T012808096Z-83eee46c/run/verification-contract.json hash e2f77f8bc9fb70dbf056c068564c5da1409f5f8cd9de8b8073f244db98d99a55.

D2 figure source hash: 5bed3d0fe7b01290fe027c4566256cbbe657a0c6fb8e5683bf7e5c94da718763. Binding: bound-to-generated-machine to artifact://piwf-run-live-20260615t012808096z-83eee46c/runs/run-live-20260615T012808096Z-83eee46c/workflows/machine.config.json hash 12ad1c539dfe098f3264c03f7e1e9f043084ea50d6f552f95d13ba3ce0fe1f29.

Planner lane: pi-planner-lane, nonce nonce-20260615T012820Z-a7f3c9d2. Plan plan:run-live-20260615T012808096Z-83eee46c has 20 step(s).

The report records report-level generated artifact refs and hashes. Final acceptance still depends on the surrounding workflow.execution-proof.v1, cartridge invocation proofs, post-execution memory.generated-workflow-proof.v1, and verifier result.

Definition of done audit

Audit status: not-proven. Captured 5/9; blocked 0; missing 0; not proven 4.

Run coverage

Skipped sources reported as caveats: source:docs-pdf-brain:local-artifacts:unavailable.

Correlation graph: 15 nodes, 36 source-backed edges.

Access adapter shape

Memory access goes through the trusted Memory relay contract. Cloudflare receives redacted receipt metadata, source freshness, hashes, coverage counts, and follow-up refs; raw local paths, raw transcripts, and credentials stay behind the relay.

Report standard

Template: joel/tufte-mdsvx@0.1.0. Public Wzrrd publication must remain noindex and expiring by default. The canonical source file is this MDSvX artifact, not a rendered preview.

What did not happen

Technical appendix

Correlation graph: 15 nodes, 36 source-backed edges.

Receipt count: 55. Raw transcripts returned: no.

Correlation graph schema: memory.correlation-graph.v1. Refinement proposal count: 4. Template seed: joel/tufte-mdsvx@0.1.0. Publish policy: noindex and 24h expiry by default.