Release Notes

Complete version history and changelog. Most recent first.

Version 6.2.0 - Connected & Complete

July 13, 2026

The intelligence pipeline and the tool catalog now point at each other: every tool page lists the intel sources that mention it, and every source page links back to the tools it covers — one shared matcher guarantees the two views can never drift. Behind it, the catalog reached full depth: all 86 tools now carry all three summary cards, with a validation guard so the gap cannot silently regrow.

Intelligence ↔ Tools, Linked Both Ways

  • Intel Mentions tab — tool detail pages gain a fourth tab listing the intel sources that mention the tool, newest first (capped at 50), each linking to the source page.
  • One matcher, two surfaces — a shared matchesRadarTool helper now powers both the new tab and the search_intel MCP radarTool filter, so the page and the API can never disagree.
  • Source pages link back — Radar Context badges on intelligence source pages resolve to tool detail pages on exact name match; unresolvable names degrade to plain text instead of broken links.

Summary-Card Depth — 86/86 Complete

  • 54-tool backfill — backfill-summary-cards.py drafted every missing Adoption / Use Cases / Risks card (51 tools lacked Recommended Use Cases; Conductor, Vibe Kanban, and Warp had other gaps), grounded strictly in each tool's existing evaluated content. Scores untouched.
  • Regression guard — validate-tools.py now warns on any tool missing a summary-card field, surfacing gaps in the pre-push gate without blocking not-yet-evaluated submissions.
  • Batch hardening — the first live gateway run surfaced and fixed a real failure mode: --limit now bounds attempts rather than successes, and authentication errors abort the batch instead of burning one call per tool.

Coverage Campaign

  • Coverage wired into the gate — test-coverage measurement joined the pre-push validation path for both projects (#318), with the intel suite holding a 70% floor.
  • Labs Guide: 0 → 125 tests — the guide feature went from untested to fully covered (#319), alongside characterization tests for timeline/history generators (#316) and direct unit tests for the Slack intake, notification, and backlog libs (#317).
  • Intel gaps closed — validate-digest, validate-tools, ingest admission-scoring/dedup, and git push helpers all gained direct coverage (#313–#315).

Version 6.1.0 - Audited & Anchored

July 3, 2026

A full-repo architecture audit and an evidence-first archival triage put the radar's methodology on display: every removal, rejection, and score in this release traces to a documented bar, a primary source, or a band-anchored comparison. Two new desk evaluations enter through the same gate they will be judged by — including two identity corrections the research itself surfaced.

Evaluation Rigor — the Archival Triage

  • The archive bar, applied — 15 externally proposed archival candidates triaged against the codified bar (terminal primary-source evidence + stall/security cap + floored viability): 6 confirmed (Firebase Studio newly archived on its formal 2027-03-22 sunset) and 9 rejected with evidence — seven verified actively growing, two "lower importance" requests declined because signal level measures evidence depth, not importance.
  • Mention-frequency ≠ tool health — 10 of 16 candidates had zero 90-day mentions in our corpus, several of them demonstrably growing; the bar requires primary-source terminal evidence, not corpus recency.
  • Manus un-archive trigger — a concrete two-part re-entry gate recorded: ownership stabilization AND independently corroborated ARR.

New Evaluations (ACES v3 desk)

  • Google AI Studio (Build mode) — 46, Watch — the Firebase Studio successor, scored against the App Builders cohort with four caps; research corrected the record — there is no "AI Studio 2.0".
  • GSD-Core (open-gsd fork) — 43, Watch — the community continuation of the rug-pulled GSD, entered after identity resolution proved the two rumored fork repos are one renamed repo; provenance risk held in compliance + a funding-concerns cap.
  • Every unverifiable claim is flagged and scored conservatively — vendor claims do not inflate scores.

Architecture & Maintenance

  • ~5,900 lines of dead code removed across radar and intel (legacy fallbacks, chat remnants, unadopted hooks, one-shot scripts).
  • Documentation drift corrected across CLAUDE/AGENTS/skills; hygiene: engines.node pin, version floors raised, graphify-out ignored.

Dependency Modernization

  • Next.js 16.2, TypeScript 6, Tailwind CSS 4 landed with builds and all 3,025 unit tests green; AI SDK 7 + @ai-sdk/* 4 coordinated jump with zero code changes; puppeteer 25, js-yaml 5, analytics 2, prettier 3.9.
  • Deferred with evidence: eslint 10 (rule-runtime crash), vite 8 (A/B-confirmed test flake), jsdom 29 (setPointerCapture gap), lucide 1.0 (brand icons removed).

Reliability

  • E2E suite restored to green — 252 passed / 0 failed across five browser projects; obsolete dark-mode spec removed, chat spec rewritten for /labs/chat, stale assertions fixed, three by-design skips documented.
  • Timeline placement perf budgets widened (25/50 → 150/250 ms) after repeated full-suite flakes; assertions retained.

Version 6.0.0 - Grounded & Consolidated

July 6, 2026

The radar's first hands-on-tested tools — Cursor and Devin Desktop — establish Grade-A decision-grade evidence anchors, with Devin Desktop's rating moving 71→68 once reliability was observed first-hand. Combined with a major surface expansion, MCP consolidation, and full GitHub Actions removal in favor of local validation.

Catalog & Lifecycle

  • Archived tools & board filter — discontinued tools exit the active board behind a "Show archived" toggle; history and detail pages stay intact. Seven tools archived: roo-code, void, vibe-kanban (discontinued/abandoned), gemini-cli and conductor-gemini (individual-tier deprecation, June 18), gsd (abandoned), manus (outside addressable scope).
  • Verified June/July refresh — Cursor's SpaceX acquisition recorded (acquisition-uncertainty cap reframed as post-close integration risk); Windsurf rebranded to Devin Desktop; continue acqui-hire shutdown floored; n8n flagged for two new CVEs; replit and warp pricing freshened; Tier-2/3 re-scores across a dozen tools.
  • Five new entries — LangGraph, Dify, LangSmith, AutoGen/AG2, and the GitHub Copilot coding agent join as initial desk evaluations (Detected), closing coverage gaps in agent orchestration and observability.

New Surfaces

  • Labs experiments kept in `/labs` — History, Chat, and Cards remain experiments under /labs/* (a brief promotion to first-class routes was reverted before launch); the top-level nav stays focused on core surfaces.
  • Digests hero — /intelligence/digests now leads with the current week's digest in full, followed by an archive of prior weeks.
  • Aquarium retired — the experimental Aquarium view is removed; its data surface is folded into the Constellation lab.

MCP — Breaking

  • 22 tools → 11 for token efficiency — curated lists fold into search_tools via a view parameter; compare/history dedup into get_tool_detail; positions, partnerships, pursuits, and decision-log merge into get_knowledge; sources become search_intel; brief_radar becomes get_intel_briefings; list_caps becomes get_insights. Breaking for existing MCP integrators — removed tool names are gone; capability is preserved as parameters on the consolidated tools.

Hands-On Grounding

  • First Grade-A anchors — Cursor and Devin Desktop completed the full T1-T10 hands-on battery (fastify@3983cce8), earning Evidence Grade A — the radar's first decision-grade tested evidence.
  • Devin Desktop 71→68 — the autonomy cap (reliability-complaints) triggered from direct observation: edit-apply truncated a trivial rename (T3) and silently broke a public hook with test-masking (T8). Interface moved 15→14 on slow/non-terminating completion.
  • Cursor 73→74 — context and viability lifted by hands-on evidence; autonomy and compliance caps confirmed and held.
  • Antigravity partial battery — T1-T3 completed before quota lockout; caps confirmed by desk research (T9/T10). Score deferred pending full battery; record is preserved.

Pipeline & Ops

  • Weekly digest reformatted — output restructured as "3 Conversations" with a WWT-impact filter; DRAFT banner removed from published digests.
  • Timeline freshness fixed — timeline-events staleness resolved; the daily pipeline now auto-refreshes via promote-timeline --publish.
  • GitHub Actions fully removed — all .github/workflows/ deleted (2026-06-25); validation is now local via .githooks/pre-push, scoped by path (radar/ → pnpm validate; knowledge/tools/ → gate-prepush.py; intel/** → pytest). Emergency bypass: git push --no-verify.
  • Weekly /evaluate-week cadence — keyless unattended evaluation batch prepped with a self-COI guard (ADR-0001 §6.1).

Version 5.1.1 - Pipeline & Test Hygiene

June 2026

An internal hardening patch: the intel test suite can no longer commit to the live repository, and the daily pipeline exited shadow mode to publish directly — plus accumulated daily intelligence since 5.1.0.

Version 5.1.0 - Comparative Recalibration

June 2026

The ACES scoring framework moved from feature-count anchors to comparative, evidence-gated grading (ACES v3 Phases A+B), and the full catalog was re-scored under the new rubric on June 10. Scores and tiers changed materially across the radar; this release documents what moved and why, plus the pipeline-integrity layer shipped alongside it.

Version 5.0.0 - Public Launch

June 2026

Signal's first full public release. The entire v4 platform goes live on the public domain in one consolidated launch, current as of June 1, 2026. The v4.0–v4.4 line shipped to the signal branch over April–May but was never promoted to the public site; v5.0.0 brings it all live at once, on fresh data.

Version 4.4.0 - Knowledge-Base Currency

June 2026

Pre-release audit on 2026-05-27 found the knowledge layer 91 days stale across positions/partnerships/pursuits, plus a 3-week hole in /intelligence/digests and a 5-day daily-brief blackout. This release closes the knowledge gaps so every /intelligence/* surface reflects late-May reality, hardens the pipeline (test vocab refresh + Zod type guard on timeline promotion), and tidies IA (aquarium → /labs). Three further changes landed before the 6/1 release date: all 78 tool evaluations were re-baselined on Claude Opus 4.8, the /timeline view (frozen since 2026-04-30) was restored and set to auto-publish high-signal events, and the aquarium link was removed from the primary nav.

Version 4.3.0 - Coherence & Maintainability

May 2026

Cleanup pass after the v4.2 surface refinement. Retires residual v3 vocabulary, fixes internal contradictions on the methodology page, and converts the 2466-line hand-typed releases page to a data-driven format over releases.json.

Version 4.2.1 - Beta-Gate Cleanup

May 2026

Closes the two pages that blocked the impeccable 28/40 beta-banner gate after the v4.2 page-by-page refinement. Median heuristic score across the 13 audited surfaces is now 30/40; every page clears 28. NEXT_PUBLIC_SIGNAL_BETA can be flipped to 0.

Version 4.1.0 - Parallel Coordinates Refinement

April 2026

Polish pass on the v4.0 primary visualization based on a UX audit. Persona presets now apply default brushes (not just axis reordering); a Top-N rating filter cuts through 78+ tools when scanning leaders; hover-fade isolates the path under the cursor; evidence grade is encoded in the line via stroke-dasharray (A solid, D dotted); and brush state, hidden categories, highlight dimension, active preset, and Top-N are all persisted to URL query params so a copied URL reproduces the full chart.

Version 4.0.0 - Signal Relaunch

April 2026

Product relaunch with the ACES v2 evaluation framework, parallel coordinates as the primary visualization, and Signal as the new brand identity. Governance split into Compliance and Viability; Collaboration renamed Integration; Status replaced with Signal Levels (Validated / Assessed / Tracked / Detected); Weighted Score replaced by Rating + Signal Level + Evidence Grade. All 78 tools re-scored.

Version 3.0.0 - Dashboard Landing Page

April 2026

New dashboard landing page replaces the cold radar redirect. First-time visitors now see a narrative-driven overview before exploring the chart. The dashboard auto-diffs the two most recent snapshots to surface gainers, decliners, and new tools each evaluation cycle.

Version 2.7.3 - April 2026 Evaluation Cycle

April 2026

Full April evaluation cycle — 78 tools scored, 21 new additions, timeline promotion, knowledge validation cleanup, and a ThemeProvider test fix.

Version 2.7.1 - Skills Migration & Tooling

March 2026

Version 2.7.0 - Markdown-to-JSON Migration

March 2026

Version 2.6.2 - Embeddings Perf & Dependency Updates

February 2026

Version 2.6.1 - MCP Transport Reliability Fix

February 2026

Version 2.6.0 - Chat Full Pass & MCP Formatters

February 2026

Version 2.5.0 - Community CTAs & MCP Expansion

February 2026

Version 2.4.1 - UX Bug Fixes & Test Coverage

February 13, 2026

Bug fixes for comparison modal and timeline empty states, plus 130 new tests.

Version 2.4.0 - Industry Timeline & Evaluation Pipeline

February 13, 2026

New Industry Timeline page, unified evaluation pipeline, data quality audit skill, and hybrid confidence architecture.

Version 2.2.1 - February 2026 Evaluations & Dependency Update

February 5, 2026

Monthly tool evaluation data refresh and MCP SDK dependency update.

Version 2.2.0 - Monthly Evaluation Skill

February 3, 2026

New /evaluate-tools skill for systematic monthly tool evaluations with research persistence and Notion integration.

Version 2.1.0 - Category Simplification & Content Quality

February 3, 2026

Simplified category taxonomy for clarity, added new tools, improved content quality across evaluations.

Version 2.0.0 - Category Reorganization & Platform Maturity

February 2, 2026

Tool categories restructured, Chat UX overhauled, and comprehensive Next.js architecture improvements signal platform maturity.

Version 1.13.0 - MCP Server Integration

February 2, 2026

New Model Context Protocol server enables AI assistants like Claude and ChatGPT to query tool evaluations programmatically.

Version 1.12.0 - Visitor Feedback & Site Footer

January 20, 2026

New user-facing feature for visitor feedback with Slack integration, plus consistent site-wide footer branding.

Version 1.11.1 - UX Polish & Error Handling

January 19, 2026

Bug fixes, UX improvements, and enhanced error observability.

Version 1.11.0 - Intelligent Chat & Visual Trends

January 17, 2026

AI-powered chat with tool calling for intelligent discovery, plus sparkline visualizations for trend analysis.

Version 1.10.0 - Performance & Data Robustness

January 15, 2026

Local favicon caching for faster page loads, robust Notion data parsing to prevent build failures, and UI refinements.

Version 1.8.2 - January 2026 Insights Refresh

January 12, 2026

Insights page refreshed with January re-evaluation data, plus Backlog column visibility fix.

Version 1.8.1 - Quality of Life Improvements

January 12, 2026

Bug fixes, documentation updates, and minor UX enhancement with reset preferences button.

Version 1.8.0 - Chat Experience Overhaul

January 8, 2026

Chat elevated to first-class navigation feature with interactive tool cards, comparison view, enhanced streaming UX, and comprehensive E2E testing infrastructure.

Version 1.7.0 - User Documentation & Contextual Help

January 6, 2026

New user documentation system with contextual help tooltips, comprehensive user guide, and streamlined admin documentation.

Version 1.6.0 - Security & Insights Redesign

January 6, 2026

Security hardening with XSS protection and rate limiting, redesigned Insights page with dynamic statistics, and infrastructure upgrade to Notion SDK v5.6.0.

Version 1.4.0 - Dark Mode & Quality

December 28, 2025

Seven new user-facing features including dark mode, mobile optimization, accessibility improvements, admin dashboard, and comprehensive testing infrastructure.

Version 1.3.0 - Export & Notifications

December 19, 2025

Three new user-facing capabilities: CSV/JSON export for data portability, Slack notifications for team communication, and a health check endpoint for system monitoring.

Version 1.2.0 - Comparison View & State Persistence

December 19, 2025

New comparison view enables side-by-side tool analysis, plus comprehensive state persistence saves user preferences across sessions.

Version 1.1.1 - Holiday Easter Egg

December 18, 2025

Time-bound holiday Easter egg with festive animations active December 1 through January 1.

Version 1.1.0 - Interactive Radar Experience

December 17, 2025

Major UX improvements to the radar visualization with clickable tool dots, floating preset pills, dimension wedge highlighting, and a unified pill button design system across all pages.

Version 1.0.2 - Tooltip Fixes & UI Refinements

December 17, 2025

Bug fixes for tooltip clipping issues, UI consistency improvements with icon standardization, and technical infrastructure enhancements.

Version 1.0.1 - Production Hardening

December 12, 2025

Critical bug fixes for production tool submission, improved error handling, and testing infrastructure to prevent regressions.

Version 1.0.0 - Production Ready

December 11, 2025

Version 0.13.0 - Shareable Presets & Architecture Refresh

December 2025

Version 0.12.0 - Submission UX & Radar Controls

December 2025

Version 0.11.0 - Documentation Navigation & Kanban Enhancements

December 2025

Version 0.10.3 - Hotfix: UI Fixes

December 2025

For complete release history including versions 0.10.0 and earlier, see the full changelog:

View Full Release Notes on GitHub