v0.3.5

Full Changelog: v0.3.4...v0.3.5

v0.3.3

Full Changelog: v0.3.2...v0.3.3

v0.3.2

Full Changelog: v0.3.1...v0.3.2

v0.3.1

Patch over 0.3.0 — no functional/source changes. It corrects the published Node floor:

• engines.node: >=20 → >=22.22.0. The Kùzu native addon is unstable on Node 20 under Linux (it segfaulted in CI); the shipped CLI runs under plain node, but 22.22 is the verified, supported floor.
• tsup build target: node20 → node22.

0.3.0 declared >=20 only because the floor bump landed just after that publish. Everything else is identical to 0.3.0.

Install: npm i -g @sshanzel/plex, or run ad-hoc with npx @sshanzel/plex <cmd>. The plugin tracks latest.

v0.3.0

Since 0.2.0.

Review-history analysis (the mine feature is now analyze)

• The feature that turns your PR-review history into reusable pitfalls is renamed end to end: CLI plex analyze, MCP analyze_scan / analyze_history, backed by a dedicated @plex/distill pipeline. Clearer intent, no data-extraction connotation.

Knowledge is learned-only

• Removed plex.md, markdown seeding, and the entire knowledge→rule promotion / external-runner surface (ADR-37). Knowledge now comes only from analyzing your PR history and your review verdicts — one provenance story, no hand-authored files, no wasted per-review tokens. (A committed plex.json policy file is the planned successor.)

Engine & ranking

• Key-less installs still get their accumulated pitfalls: retrieval falls back to lexical (IDF) ranking when no embedding provider is set.
• Outcome-weighted consolidation (a reverted change counts as the strongest confirmation) and accept→pitfall inference with learning idempotency (no double-counted evidence).
• Deletion blast radius, cross-window co-change accumulation, generated-artifact exclusion (lockfiles/bundles are never read line-by-line), measured deterministic prevalence, and an auto-accept audit trail.
• Quality-floor benches (ranking nDCG + retrieval recall@k) guard against ranking/retrieval regressions.

Breaking changes

• MCP tools renamed: mine_scan → analyze_scan, mine_history → analyze_history. Removed: seed_knowledge, propose_promotions. Update any saved agent prompt that references the old names.
• CLI: plex mine → plex analyze; plex seed removed; plex promote → plex consolidate.
• Requires Node ≥ 22.22.

Install: npm i -g @sshanzel/plex, or run ad-hoc with npx @sshanzel/plex <cmd>. The plugin tracks latest.

v0.2.0

First release since 0.1.0.

Ranking & learning

• Principled-tuning engine: Beta-Bernoulli pitfall confidence, Salton association-strength co-change, personalized-PageRank blast radius, adaptive (anisotropy-aware) thresholds.
• Blast enrichment + raw-feature persistence on the brain, and plex eval: an offline nDCG check with a READY / NOT YET / DEFAULTS-ALREADY-WIN verdict on whether a re-weight is worth it.

Review quality & UX

• Findings presented as one Severity | Finding | Location table; no confidence or internal-thought display; report, don't decide.
• The reviewer no longer narrates reconcile/outcome bookkeeping.
• A rejected finding stops re-surfacing (reject now suppresses like waive/acknowledge).
• One-line "embeddings are off" nudge so the learning layer is discoverable.

Setup & CLI

• plex index/init are gated to a git repo; init no longer registers the MCP (the plugin provides it), so no duplicate server.
• Install simplified to the plugin + npx @sshanzel/plex init; CLI docs moved to docs/cli.md.

Install: npm i -g @sshanzel/plex, or run ad-hoc with npx @sshanzel/plex <cmd>. The plugin tracks latest.