github l-gevity/l-gevity-skills v5.6.0

one hour ago

Gaps from three consumer alchemy sessions

Three real runs exposed these: a full audit followed by a fix PR, an unattended audit with 13 agents, and a runtime-queue optimisation.

  • Findings cannot vanish.
    • A hand-off may carry a findings list, each finding citing evidence.
    • The gate's --review can be repeated and accepts saved hand-offs, so a dropped blocking or major finding fails with SILENT_SKIP.
    • A read-only audit may leave its evidenced findings open and lists them under open_serious. A finding without evidence fails with the new code UNSUPPORTED_FINDING.
  • Hand-off paths:
    • An absolute path or a file@commit path is a SCHEMA error, no longer STALE_CONTEXT.
    • A deleted file is {"path", "deleted": true} and is checked to be gone.
    • The rejection messages say how to fix the hand-off.
  • Workspace checks:
    • Python bytecode caches no longer cause WORKSPACE_MISMATCH, and record_evidence.py no longer writes them.
    • preflight --root accepts an integrated head.
  • Execution: the plan check counts analyze packages as independent parts and prints mode_override when a plan's mode differs from its recommendation.
  • alchemy:
    • An ambiguous subject names both readings and stops.
    • "Fix them all" after an audit is a new dispatch.
    • Optimisation words route to Y.
    • The Y baseline rule is one rule everywhere: after the increment ships, or on a running system, measure the baseline first.
  • alchemy-orchestrate:
    • A spawn without a passing plan check is reported as a skipped check.
    • Blanket approval does not cover protected paths.
    • Agent instructions carry known tool quirks.
    • Each pull request head is gated.
  • contracts.md: the hand-off rules are written out: criterion tagging, relative paths, plan requirement IDs only, deletions.
  • system-optimization:
    • New Runtime Flow layer.
    • If missing access blocks measurement and the user can grant it quickly, stop with the command instead of a Decision.
    • Baselines go to the owning issue.
  • Installers: no .l-gevity side file when the instruction file differs only in line endings.

Re-render agent definitions with init_workspace.py to pick up the analyst instruction to report findings in the hand-off.

Verification

  • validate-skills.py passed. All 168 deliberate validator mutations were caught.
  • The checker has 9 new adversarial cases.
  • The bytecode-cache ignore and the integrated-head preflight were checked by hand in a throwaway git repository.
  • All 40 behaviour scenarios were re-recorded, 3 of them new. 39 meet every expectation.
  • The shell installer suite passed (83 checks), and the PowerShell suite passed under pwsh 7 and Windows PowerShell 5.1 (160 checks).
  • CI passed on both pull requests before publication.

Limits

  • gate-trial-expired lists one known failure. The recorded run refuses to delete the gate, but in words its pattern does not accept. gate-lifecycle is unchanged.
  • No runtime hook yet blocks spawning agents without a checked plan; it is a written rule.
  • Report-block sentence limits are not checked automatically.
  • The checker still only accepts upper-case secret names, so credential stores need an invented name.
  • The library word budget rose from 49,300 to 49,370.

Includes #50, #51.

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

NewReleases is sending notifications on new releases.