Skip to content

v2.6.0 — M13: audit remediation & the learning loop

Choose a tag to compare

@danielPoloWork danielPoloWork released this 05 Jul 18:49
80a36a7

v2.6.0 — M13: audit remediation & the learning loop

This release completes milestone M13: a full-repo council audit turned into 14 focused fixes,
whose centrepiece is a closed, mechanical, human-gated learning loop. MINOR — every change is
additive; nothing removed or breaking.

The learning loop, closed and mechanical

  • record_run.py (#172) — one command writes a run record; overrides derive mechanically
    from the manifest's interview provenance, with durable failures and rubric channels.
  • lesson_audit.py (#173) — a report-only watchdog: regressions against a recorded lesson,
    dead lessons, and low rubric trends — the trigger to promote an advisory lesson to a gate.
  • Review-time lesson capture (#174) — an optional PR Lesson: field (a merged PR body is
    owner-approved by construction), lesson_sweep.py to harvest it, and the historical
    L-0003 / L-0004 backfill.
  • run-records schema gate (#175) — learning/runs/** moves inside the enforcement
    perimeter; a malformed record now fails CI instead of silently poisoning the auto-tuner.

Render & interview hardening

  • Interview provenance recorded in the manifest — asked vs defaulted vs imported (#169).
  • A spec-substance floor in validate_manifest — no more hollow repositories (#170).
  • No silent it/d4np namespace fallback (#163); domain overlays are actually applied for
    game / web / mobile projects (#165).

Factory internals

  • render.py --check (validate-only) plus a gate-executability lint (#164).
  • yamlmini extracted as a loud loader that rejects the #153 truncation constructs (#166);
    a leading UTF-8 BOM no longer breaks manifest parsing.
  • The lint reporter is threaded through every check (#167); a test discovery runner means new
    tests need zero CI edits (#168).

Docs

  • The Recall/Record steps are wired into the generation playbook (#171).
  • README sweep (#176): a grouped tools table (all 27 tools), a new "How EADOS learns"
    section, and date-stamped model claims (the stale "Fable 5 not yet available" is fixed).

Full changelog: see CHANGELOG.md[2.6.0].