github l-gevity/l-gevity-skills v5.8.0

15 minutes ago

Alchemy answers are now checked against their own output contracts, and three routing gaps are closed. A consumer's FULL audit turned up both. This release was re-issued at the merge of #57, with the fixes from the v5.7.0 multi-agent field report (#56).

Changes

  • scripts/check_alchemy_report.py: checks the shape of a routed Alchemy answer:

    • trail columns, skip rationales and stage order
    • scope-block fields and their allowed words, and whether Blocking stage matches the trail
    • one record for every stage that reached a decision
    • worth records (required fields, a revisit trigger, measured values in retrospective mode), design principles, the test obligation table, and placement records
    • every unchecked item names a closing command, and an audit names functional correctness

    Run it on any saved answer: python scripts/check_alchemy_report.py answer.md.

  • Scenario check alchemy_report, plus a new scenario: audit-full-reports-unchecked-correctness.

  • full audit now walks FULL from the C₀ baseline. Before, ALCHEMY-PIPELINE-DESIGN.md counted plain audit as full traversal, which contradicted SKILL.md.

  • Audit removals: in Audit mode, DEPRECATE, DELETE and OBSOLETE admit the removal as the candidate's remediation increment. Blocking stage is now the first stage that no candidate passed.

  • Audit reports list functional correctness as unchecked, with the command that reviews it. No gate tests behavior.

  • Installers default to v5.8.0.

Multi-agent fixes (#56, #57)

  • alchemy-orchestrate/scripts/extract_handoff.py: copies a hand-off byte for byte from the agent's transcript or reply, so the lead no longer retypes it. It refuses a final reply without exactly one hand-off.
  • Finding IDs: the ledger refuses a repeated finding ID. gate --review matches a hand-off's findings by package as well as ID, so two agents' F1 can no longer merge silently. Hand-off IDs carry the package prefix (P1-E1, P1-F1).
  • Read-only gate: when blocking or major findings stay open, the gate's output notes that a pass is not a clean audit.
  • Analyst command cap: "at most three" now applies only to packages that verify another package's work.
  • Topology record rule R10: Graph analysis names tool, version, and input hash, or says Not measured.
  • Profile: dropped repository.base_branch, which nothing read.

Verification

  • npm run validate passes. npm run validate:mutation: all 173 deliberate violations caught.
  • The report checker's self-test trips all 15 rules; the topology checker's self-test passes, R10 included.
  • 16 scenarios re-recorded for #54; the 7 orchestrate scenarios re-recorded for #57 meet all expectations.
  • The extractor, run on 71 recorded transcripts: 57 hand-offs copied, 14 replies without a valid hand-off refused.
  • bash scripts/test-installers.sh: 115 checks pass. scripts/test-installers.ps1: 224 checks pass under pwsh 7 and Windows PowerShell 5.1.
  • CI green on #54, #55 and #57.

Limits

  • Known failure: in the new audit scenario, 2 of 2 runs closed some unchecked items with a question to an owner rather than a command.
  • Known failure: in dispatch-followup-redispatch, 2 of 3 runs named a planned route in Core route that never ran.
  • The checker runs on recorded scenarios in CI. It does not run inside a consumer's session unless someone runs it by hand.
  • Between a version bump merging and its release tag existing, the installers on main point to a tag that is not there yet.
  • Re-issued: the v5.8.0 tag moved from 6325718 to the #57 merge. An install pinned to v5.8.0 before the move holds the earlier contents.
  • No check confirms that an agent read the Full-mode topology references; R10 checks only the record's graph field.

Includes #54, #55, #57.

Don't miss a new l-gevity-skills release

NewReleases is sending notifications on new releases.