Bug Fix

Hibernated agents incorrectly shown as standalone — Agents with tmux session history (like Raine) were being classified as "standalone" when they had a recent heartbeat but no active tmux session. This caused the UI to show "Standalone Agent — no terminal view" instead of the hibernation screen with the Wake button.

What changed

• Standalone classification now requires no session history in the agent registry
• Heartbeats only mark agents as "online" for truly standalone agents
• Legacy /api/sessions endpoint also fixed

Impact

All registered agents that were hibernated now correctly show the Wake button again.

The Agent Ecosystem

Introduces the Agent Formula — a clear narrative explaining how the 6 components of the 23blocks agent ecosystem work together:

Complete Agent = Personality (WHO) + Capabilities (HOW) + Identity (TRUST) + Communication (TALK)

What's New

• docs/ECOSYSTEM.md — Canonical reference for how AI Maestro, Agent Library (150+ personalities), Plugin Builder, AID, and AMP fit together
• docs/ecosystem.html — New docs site page with visual dimension cards, assembly flow, and "Build Your First Agent Team" walkthrough
• Ecosystem section in README — Four-dimension table after "Meet Lola"
• Plugin Builder — Added personality cross-references, "Combine Personalities + Skills" section, and example manifest with all 15 agency-agents divisions
• Navigation — ECOSYSTEM link added to all 17 docs site pages
• Companion components — Extracted CompanionInput, FloatingVoiceSettings, MobileCallOverlay into standalone components
• GitHub metadata — Updated repo descriptions and topics

The Formula

AI Maestro is the stage. Pick personalities, give them skills, and run them from one dashboard.

Read the full ecosystem guide →

Highlights

Every API error response across the codebase now follows the AMP protocol format — one consistent, structured shape for all 106 route handlers.

Before: inconsistent error shapes across ~280 services ({ error: 'Human text' }) vs structured AMP routes ({ error: 'code', message: '...', field?, details? }).

After: one shape everywhere.

{ "error": "missing_field", "message": "name is required", "field": "name" }

What changed

Added

• services/service-errors.ts — single source of truth for ServiceResult<T>, ServiceError, and ServiceErrorCode (30 codes: AMP's 18 + 12 generic). Ships 20+ factory functions (missingField, notFound, operationFailed, alreadyExists, gone, invalidState, etc.) and validation helpers (requireString, requireArray, requireNameFormat).
• app/api/_helpers.ts — toResponse() turns any ServiceResult into a NextResponse with consistent error formatting.

Changed

• 25 service files migrated to shared ServiceResult and factories (~305 error returns standardized).
• 88 route files converted to thin wrappers: return toResponse(result).
• 25 component files updated to read data.message || data.error for backward-compatible error display.
• 5 test files updated (49 assertions now match structured ServiceError shape).
• lib/types/amp.ts refactored: AMPErrorCode is now Extract<ServiceErrorCode, ...>, AMPError extends ServiceError. AMPNameTakenError interface corrected to match runtime shape (details.suggestions).
• services/headless-router.ts — sendServiceResult() mirrors toResponse() for headless mode.

Fixed

• preconditionFailed() factory now returns 412 (was 400).
• lookupAgentByName and lookupAgentByDirectoryName catch blocks now propagate real errors via operationFailed() instead of silently returning { exists: false } / { found: false } with a 500 status.
• toResponse() defensive fallback preserves caller's 4xx status instead of always overriding to 500.

Stats

• 154 files changed (+1,365 / -1,977 = net −612 lines) despite adding the new foundation
• 545/545 tests passing
• Build + lint pass on Node 20 and 22

Credits

Huge thanks to @mvillmow for the original issue (#285) that identified the duplication across route handlers. The analysis revealed an even deeper opportunity — the underlying error contract itself was inconsistent — and this release addresses the root cause.

PR

• #327 — feat: unify API errors to AMP format

Closes #285

Added

• Auto-install Claude Code status line — install-plugin.sh now configures the AMP status line automatically, showing agent identity and unread message count in Claude Code's footer. Idempotent and reversible via amp-statusline.sh --uninstall.

Fixed

• AMP mesh routing restored — amp-send.sh was incorrectly using filesystem delivery for remote agents after message migration created local directories. Now checks for config.json to distinguish real local agents from migration-created inbox directories.
• AMP fetch URL fix — amp-fetch.sh was missing /v1/ prefix on fetch and acknowledge endpoints, causing 404s against external providers.
• AMP message ID timestamps — generate_message_id() now uses seconds-precision timestamps per AMP spec.

Agent Identity v0.2.0 — Fully Independent

AID no longer requires AMP to be installed. Agents can now authenticate with OAuth 2.0 servers using just AID alone.

What's new

• aid-init — Standalone identity initialization (no amp-init needed)
• aid-helper — Self-contained helper with OpenSSL auto-detection, Ed25519 signing
• All aid-* scripts are now self-sufficient

Interoperability

If both AMP and AID are installed, they share ~/.agent-messaging/agents/ — one Ed25519 identity serves both protocols. Neither requires the other.

Numbers

• Plugin: 7 skills, 50 scripts (was 48)

Full Changelog: v0.26.2...v0.26.3

Changes

• Replaced all remaining hardcoded skill and script lists with dynamic discovery from the plugin directory
• verify-installation.sh now auto-discovers skills and AMP scripts (was missing agent-identity and 2 AMP scripts)
• install-plugin.sh AMP verification now auto-discovers (was missing 4 of 14 scripts)
• Fixed installer banner alignment

Full Changelog: v0.26.1...v0.26.2

Changes

• Renamed install-messaging.sh → install-plugin.sh — the installer handles all skills, scripts, and CLI tools, not just messaging
• Auto-discover skills — new skills added via the plugin manifest are automatically installed without modifying the installer script
• Added plugin builder references to the installer banner so users know they can customize their plugin at ai-maestro.23blocks.com/plugin-builder.html

Full Changelog: v0.26.0...v0.26.1

Agent Identity (AID) Integration

AI agents can now authenticate with OAuth 2.0 servers using their Ed25519 cryptographic identity — no passwords, no API keys, no secrets to rotate.

What's new

• Agent Identity (AID) added to the ai-maestro plugin build via agentmessaging/agent-identity
• New commands: aid-register, aid-status, aid-token
• New skill: agent-identity
• Plugin now ships 7 skills and 48 scripts

How it works

1. Agent registers its public key with an auth server (one-time)
2. Agent presents a signed identity + proof of possession
3. Auth server verifies and issues a scoped RS256 JWT
4. Agent uses JWT to call any API

Previous releases in this session

• v0.25.16 — Sync AMP plugin scripts to v0.1.3
• v0.25.15 — Key rotation with proof-of-possession + duplicate key rejection

Full Changelog: v0.25.16...v0.26.0

What's New

AMP Plugin synced to v0.1.3

Rebuilt ai-maestro-plugins via the manifest build system (build-plugin.sh --clean) to pull latest AMP scripts from agentmessaging/claude-plugin upstream.

Key upstream changes now included:

• Key rotation with proof-of-possession (--force reinit)
• Local fingerprint uniqueness guard before registration
• --id <uuid> parameter for multi-agent identity resolution
• Client-side UUIDv4 for offline-first agent identity
• Case-insensitive index lookup + single-agent auto-select
• Multiple security, routing, and attachment fixes

Full Changelog: v0.25.15...v0.25.16