Hand back findings and release 8.1.0 inspect surveys without reset - #28
Merged
Conversation
Codebase-review goals currently invent a change DAG, stall on the first blocker, and only emit a findings list after close. This plan derives a digest from existing runs, shows it at every handback, and defers an inspect kind until evals show the first eight phases still leak. Co-authored-by: vriesd <vriesd@users.noreply.github.com>
Walk every identified finding across attempts so a later passing review cannot erase historical blockers. Compact always carries the list; close delivery prints live rows then historical ones. Co-authored-by: vriesd <vriesd@users.noreply.github.com>
A blocked, reset, or pending-reviewer idle now sends one conversational prompt to print compact findingsDigest. Mechanical continuation stays start and close only; a second idle at the same revision does not loop. Co-authored-by: vriesd <vriesd@users.noreply.github.com>
Manager and run skills print compact findingsDigest at a checkpoint. Reviewers finish a concurrency matrix only when the packet asked for one. Inspect-only plans invent no repair features. A new ungated eval fails when /flow-auto on a planted inspect goal leaves no user-visible list. Co-authored-by: vriesd <vriesd@users.noreply.github.com>
cursor
Bot
changed the title
… reset. Optional PlanFeature.kind hydrates absent to change. A failed inspect review finishes that survey slice, so the next feature can start without reset. Co-authored-by: vriesd <vriesd@users.noreply.github.com>
The host schema is a separate zod tree from the application schema. Without this field the host rejected inspect plans the runtime already accepted. Co-authored-by: vriesd <vriesd@users.noreply.github.com>
cursor
Bot
changed the title
Bump the package and install pins, and write dated notes. An untagged package version on main creates v8.1.0 and publishes. Pushing that tag from this PR would release before merge. Co-authored-by: vriesd <vriesd@users.noreply.github.com>
cursor
Bot
changed the title
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
2 participants
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.
A
/flow-autocodebase review on 8.0.0 was too thorough, stalled on blockers, and never handed back a findings list. That is the change-lifecycle model, not a missed prompt.This PR implements phases 1 to 9 of
.agents/plans/01-review-workflow/and prepares 8.1.0. Merging tomaincreatesv8.1.0, the GitHub release from the changelog notes, and the npm publish. The tag is not pushed from this branch, because that would release before merge.What landed
findingsDigest(session)walks every identified finding across attempts. A later pass that omits a prior id keeps the row withlive: false. Nothing is persisted. Closure is not required./flow-autoactually reads always includesfindingsDigest. Empty is[], never a missing key.DeliveryProjection.formatReportlists live rows, then historical ones, so a completed retry cannot print onlyterminal findings: nonewhen blockers existed.flow-runblocked review, the manager kernel, and recovery print compactfindingsDigestwhen Flow hands control back.flow_feature_reset, ordispatch-flow-revieweridle sends one conversational prompt to print the digest, then parks or stops. Mechanical continuation is still onlyflow_run_startandflow_session_close. ADR 0008 records that extra prompt.riskLensesis non-empty or its summary includes a matrix.adjacent-defect-refusedis unchanged.kind: "inspect".PlanFeature.kindischangeorinspect. Absent hydrates tochange, so existing Session v5 documents keep the repair loop. A failed inspect review completes that slice. The next feature can start withoutflow_feature_reset. Sessioncompletedthen means the survey finished, not that the tree is clean. Repair stays a later change feature. ADR 0005 records the rule.inspect-goal-delivers-findingsfails when final text, close delivery, and compact digest all omit a planted interval defect.Does not restore the v6 audit ledger. Does not add a persisted intent classifier.
Verification
bun run checkbun run replay(9/9, includingadjacent-defect-refused)bun run release:metadatamatches 8.1.0