bitmosh.dev/Blog/Dev Log/2026-06-11
v0.2.8cerebra

Lattice Step 2 — retrieval-side sibling deduplication

Adds lattice-aware sibling dedup between scorer and floor filter in both `search` and `context` commands, with D2 routing rules, DB column updates, and event emission.

v0.1.10gwells

GWells runtime lifecycle hygiene

Hardened GWells controller pause, resume, stop, pinning, and live override behavior to avoid duplicate loops and stale runtime caches.

v0.3.6policy-scout

Data Cleanup Deletion Path

Replaced dry-run-only planning with an explicit --apply flag for actual deletion. Default behaviour (no --apply) is unchanged — plan preview only.

v0.1.9gwells

GWells hub-ring crowding relief

Added deterministic top-level ring spacing so large explicit-spine layouts avoid origin crowding while preserving small-graph behavior.

v0.3.5policy-scout

pnpm/yarn/bun Sandbox Execution

PM-aware lockfile snapshots and diff capture for all four package managers, plus pnpm transitive dependency analysis. yarn and bun skip transitive (incompatible list output formats, documented).

v0.1.8gwells

GWells fallback seeding safety

Added deterministic fallback seeding for no-spine, orphan, and unreached graph nodes so non-filesystem layouts avoid origin clumping.

v0.2.7cerebra

Tower visibility in memory status + Phase 5 e2e suite

Extends `cerebra memory status` to show truth tower contents, and ships the Phase 5 end-to-end integration test suite covering all 6 behavioral classes.

v0.3.4policy-scout

Documentation Staleness Update

Refreshed IMPLEMENTATION_STATUS.md, INSTALL.md, and INTEGRATION_BOUNDARIES.md to reflect the completed state of all 13 Tier 2/3 plans — no code changes.

v0.3.3policy-scout

Supply Chain Detection Depth

Multi-layer lifecycle script analysis wired non-fatally into the sandbox flow — JS static analysis, Python AST visitor, dependency confusion detection, transitive npm tree scan, and publish anomaly signals.

v0.1.7gwells

GWells resolver-backed assignment

Routed GWells well assignment through structural analysis fallback while preserving existing radial-backbone and parallel-spines behavior.

v0.2.5cerebra

cerebra context T1 auto-population

Wires T1 auto-promotion into `cerebra context` so every retrieval run feeds selected memory into the Truth Tower, with --no-promote and abstention guard rails.

v0.1.6gwells

GWells structural resolver foundation

Added a behavior-neutral structural resolver so GWells can analyze non-filesystem graph shapes before routing layout behavior through topology-aware roles.

v0.2.4cerebra

Phase 5 Step 5 — Truth Tower T1+T2 core (two-tier evidence stack)

TruthTower class with T1 auto-promotion from retrieval results, T2 manual promotion citing a T1 anchor, staleness cascade on T1 eviction, chronological render, and full inspector event suite.

v0.2.3cerebra

Phase 5 Step 4 — Interpretive Lattice Phase 1 (confidence-gated multi-commit)

When ≥2 categories score ≥0.65, classify_record_lattice() writes sibling memory_records for each additional category, all linked by a shared lattice_lineage_id; existing classify_record() untouched.

v0.2.2cerebra

Phase 5 Steps 3+4 — WorkingMemory core + memory CLI

WorkingMemory class with capacity eviction, tower-cited penalty, and pin guards; `cerebra memory` CLI (status / promote / evict).

v0.2.1cerebra

Phase 5 Steps 1+2 — cognitive runtime schema + session management

Migration009 (sessions/wm/tower tables), slot constants, PHASE_5_EVENT_TYPES, new_session(), vault lockfile, and `cerebra session` CLI commands.

v112.6.1lumaweave

v112 arc close — semver 0.18.0 → 0.19.0

Semver bump to 0.19.0; v112 arc reconciled in NOW.md + ROADMAP with full commit table; 10 new KNOWN_SHARP_EDGES lessons appended.

v0.3.2policy-scout

Agent integration — MCP server, injection detection, sandbox, intel, watch

MCP server (5 tools, PreToolUse hook), prompt injection scanner (8 categories + base64 rescan), Linux namespace sandbox (overlayfs + strace), package intel adapter (typosquatting, known-bad registry), and real-time fs watch daemon with event routing.

v112.6.0lumaweave

Clear opacity debt + fix stale status-cluster i18n assertion

Diagnoses and closes the v112.4 opacity regression report (binding intact, no code fix needed) and resolves the pre-existing i18n.spec.ts:187 stale assertion.

v0.3.1policy-scout

Policy management UI — ADR-008 three-phase implementation

Policy management UI delivered in three ADR-008 phases: JSON schema contracts and TypeScript domain types; strict type coverage with browser preview mocks and pagination; then the full management card suite with rule display and simulation controls.

v0.3.0policy-scout

Tier 2 safety suite — HMAC chain, integrity, response, git, scan, policy

Six Tier 2 safety subsystems shipped: HMAC audit chain, integrity checks, incident response with lockdown and playbooks, git pre-commit hooks, secret scanning, and policy management with simulation. CLI wired; ADRs 001–008 and plans 01–13 added.

v0.2.3policy-scout

Docs audit — data paths, report surfaces, release checklist

Audited and documented the full data visibility story for the native dashboard: CLI-first setup path, data path catalog, report evidence surfaces, audit events display, and a consolidated v0.2 smoke checklist. Added a local alpha release checklist.

v0.2.2policy-scout

Dark mode consolidation and decision check UI

Consolidated the dark-mode CSS architecture to eliminate per-card overrides and fixed contrast failures. Added the full decision check flow: Rust adapter, TypeScript card shell, invoke wiring, and result display.

v0.2.1policy-scout

Tauri adapter hardening — validated selectors, Rust unit tests, CI

Replaced cleanup dry-run wrappers with validated target selectors, extracted audit event ID validation into a dedicated Rust helper, added full unit test coverage for adapter validators, and wired a Tauri desktop CI job.

v112.5.1lumaweave

AgentChatTile + Agents settings category + chat UI

Wires the agent chat frontend — AgentChatTile with ephemeral conversation state, ChatInput with Enter-to-send, Agents settings category (endpoint/model/API key/test connection), and schema v95 migration.

v112.5.0lumaweave

InferenceBackend trait + RemoteClient + Tauri commands

Adds the Rust inference module — InferenceBackend trait, RemoteClient (OpenAI-compat HTTP), and chat/test_inference_connection Tauri commands. No frontend wiring yet; that's Commit 2.