mwguerra/plugins-haiku/retrospective

Retrospective — vetted lessons, never a false one

The suite gets better by learning from its own work — but a "lesson" is a claim, and an unrefuted claim that silently changes behavior is how tools degrade. So this loop refutes before it promotes, and it reuses what already exists: it writes nothing new — lessons live in taskmanager's memories (which already has a draft status, confidence, supersession, and conflict tracking), and the membrane is the existing adversarial-verify.

The loop (harvest → draft → refute → promote)

1. HARVEST (read-only). Gather what happened from docs/.scribe/capture.log (decisions/errors),

.maestro/ledger.log (verification passes + waivers — what was run, what survived, and what was deliberately skipped and why), docs/incidents/ (postmortems), and the live session. Degrade gracefully: if any of these paths are absent, harvest from what exists and still run — none is a hard dependency.

1. DRAFT. Write each candidate lesson as a memories row with status='draft',

source_type='agent', and low `confidence` (well under the 0.8 default, so it reads as unproven), kind = an existing enum value (process when unsure; anti-pattern/integration/ convention/architecture when one clearly fits). A draft is invisible to execution — every memory loader filters WHERE status='active' — so an unpromoted lesson cannot affect work. (No numeric promotion ladder, no scoring engine — `draft` vs `active` is the whole gate.)

1. REFUTE (vote + probe). Invoke the `maestro:adversarial-verify` harness once for the batch —

hand it ALL drafts as claims (not one spawn per lesson). Vote count is counted, never felt: 3 voters, raised to 5 when any draft would supersede an active memory or names a plugin file/hook/skill (it would change how the suite works). Every voter defaults each lesson to failed and flips it only with an attached probe row from skills/adversarial-verify/references/probe-tables.md (P3 quote-both-sides for "we decided/did X", P1/P8 for "this behavior holds"); the aggregate applies the evidenced-failed veto. A lesson survives only on an aggregate met.

1. PROMOTE the survivors. Flip draft → active and raise confidence to the active default.

Overturned drafts stay draft (or deprecated) with the refutation recorded in conflict_resolutions — so a refuted lesson is remembered as refuted, not silently dropped.

The binding ownership gate

• A net-new active lesson (supersedes nothing) is a create — agents may auto-promote it.
• A lesson that would supersede an existing active memory must ask the user (AskUserQuestion)

before flipping the old one to superseded — never auto-override a standing decision.

• A memory with source_type='user' / auto_updatable=0 is NEVER auto-updated or auto-superseded,

full stop. The retrospective must honor this or it can silently overwrite a human's call.

"Improve the plugins" is advisory, never an auto-edit

When a lesson implies the tooling itself should change (a skill/hook/gate), the retrospective flags it for a human (an open-questions.md entry or a high-importance memory) — it does not edit any plugin file. Auto-mutating the suite from a lesson is the exact path by which a false lesson degrades the tools; that door stays closed.

What this does NOT build

• No new lessons store/file/table (memories already exist); no lesson-verifier agent (reuse

adversarial-verify); no scheduled/continuous mining (triggered on wrap-up only); no scoring/ML engine; no new hook (the existing session_retro.sh is the trigger); no auto-edits to any SKILL.md/hook; no promotion of an unrefuted lesson to active.