v15.2.1 Breaking risk 24d

⚠ Upgrade required

npm publish now requires an OTP; run `npm install -g [email protected]` when ready.

Breaking changes

Pushes now require passing both a type‑check step (`tsc --noEmit`, `next build`, `mypy`, `pyright`) and the full test suite (`npx vitest run`, `python3 -m pytest`, `npm test`, `jest`).

Notable features

Verification guard script `verification_guard.py` enforces that both type checking and testing steps have been executed before allowing a push.
20 comprehensive test cases covering historical failure scenarios (e.g., missing import, translation fix causing test failures).

Full changelog

What's new

Pre-push verification gate (Rule 19 expanded)

Rule 19 is now a full verification gate — not just tsc --noEmit. Both steps must pass before every git push, regardless of repo type:

Type check — tsc --noEmit / next build / mypy / pyright
Test suite — npx vitest run / python3 -m pytest / npm test / jest

Each catches a different failure class. Type check alone missed 2 incidents in May 2026.

Mechanical guard + 20 test cases

verification_guard.py checks whether both steps ran before a push. 20 test cases including verbatim command sequences from both May 2026 incidents:

Incident #1 (e55211c): aacSpeak import dropped, vitest passed (mocked), Vercel failed
Incident #2 (6ca43ff): translation fix pushed, 2 tests failing, only next build ran

Patch

npm publish requires OTP. Run when ready:

npm install -g [email protected]

View release on GitHub

v15.2.0 New feature 24d

Notable features

Two‑namespace skill architecture: `skill:*` (platform, read‑only) and `user_skill:*` (user‑local, enabled via routing table)
Synalux dynamic skill content: API reads from Supabase `platform_skills` with filesystem fallback, live admin updates, auto‑learn hooks, audit logging
Skill routing schema v2: `resolveSkillsForProject` returns `{ names, user_local }`; routing table adds `user_local: { enabled, key_prefix }`

Full changelog

What's new

Two-namespace skill architecture

skill:* — Platform skills. Read-only cache. Written only by sync-skills.sh or fetched from Synalux. Users cannot overwrite.
user_skill:* — User-local skills. Written via dashboard POST /api/skills. Only loaded when user_local.enabled=true in routing table (off by default). Never sent to Supabase.

Synalux dynamic skill content (no redeploy needed)

GET /api/v1/skills/content checks Supabase platform_skills table first, falls back to filesystem.
POST /api/v1/admin/skills — platform admin only — update skill content live.
Auto-learn hooks can write corrections to platform_skills table automatically.
Audit log on every change.

Skill routing schema v2

resolveSkillsForProject returns { names, user_local } — callers now get the user_local policy alongside skill names.
Routing table gains user_local: { enabled, key_prefix }.

New universal skills

execute-method-literally — 26-case test suite with verbatim May 2026 session replay
pre-push-audit Rule 19 — tsc --noEmit before every push

Bug fix

skill-routing.test.ts updated for v2 return type (was string[], now { names, user_local })

Upgrade

npm install -g [email protected]
# or with npx (no install)
npx [email protected]

No migrations needed. user_skill:* namespace is additive — existing skill:* entries in local SQLite are untouched.

View release on GitHub

v15.1.0 New feature 24d

⚠ Upgrade required

Run `npm install -g [email protected]` for upgrade; no migration required.
Paid‑tier users must ensure `SYNALUX_CONFIGURED=true` to enable Synalux content fetching.

Notable features

Skill content fetched from Synalux portal for paid tiers, with local SQLite fallback for free/offline use
Added universal skill `execute-method-literally` to run exact user‑requested commands verbatim
Added hardened universal skill `critical-thinking-debug` with a new counter‑rule section

Full changelog

What's new

Skill content now routes via Synalux (paid tier)

Previously, skill SKILL.md content was only available from local SQLite (populated by sync-skills.sh). Paid-tier installs now fetch skill content from the Synalux portal on every session — always up-to-date, no manual sync required. Local SQLite remains the free-tier and offline fallback.

Data flow:

session_load_context
  → Synalux /api/v1/skills/routing   (which skills, all tiers)
  → Synalux /api/v1/skills/content   (what content, paid tier)
     └─ local SQLite fallback        (free tier / offline)
  → injected as [📜 SKILL: name] blocks

New universal skills

Two new skills added to the universal routing list (load on every session):

execute-method-literally — When user says "revert to tag X / checkout release Y", execute that exact command. Never substitute an equivalent path. Includes a 26-case test suite with verbatim replay of the May 2026 session that codified the rule.
critical-thinking-debug (hardened) — Added "Counter-rule: Never substitute a method instruction" section with incident history.

Architecture docs

docs/ARCHITECTURE.md — new Section 12: Skill Architecture, with ASCII data flow diagram, tier behaviour table, resolution order, and source-of-truth table.

Upgrade

npm install -g [email protected]

No migration needed. Paid-tier users with SYNALUX_CONFIGURED=true get the Synalux content fetch automatically. Free-tier behaviour is unchanged.

View release on GitHub

v15.0.0 Breaking risk 24d

Notable features

Proactive session drift detection with three Prism MCP calls and Synalux portal alerts
Evidence‑first behavioral protocol enforcing observable proof for all agent claims
TTS audio protection (rapid autoSpeak drop, interrupt handling, volume guard) and SSML rate capping

Full changelog

Prism Coder v15.0.0 — Drift Detection + Evidence-First Protocol

Released: 2026-05-10

The headline

AI agents can now detect when they've drifted from your stated goals mid-session, self-correct, and route alerts to the Synalux portal — using three direct Prism MCP calls, no scripts, no cron, no hooks.

What ships

🔄 Proactive session drift detection

session_save_ledger   → snapshot current state
session_cognitive_route → on_track / minor_drift / major_drift
session_compact_ledger + session_load_context → reset if needed

When major_drift is detected, an alert is posted to synalux.ai/api/v1/prism/memory so the drift is visible across sessions and devices.

Real example it caught: A training session promised BFCL ≥90% for three AI models. The agent spent 3+ hours debugging audio bugs instead. Drift check surfaced: "Training goal unmet. Layer3 corpus missing from all training sets. 0 BFCL scores measured." Session immediately re-aligned.

Skill: ~/.agent/skills/session-drift-detection/SKILL.md
Tests: 10 behavioral test cases in skills/session-drift-detection/tests.md

🛡 Evidence-first behavioral protocol

Hard gates that supersede all other agent instructions:

No positive claim (done/fixed/working/90%+) without observable evidence
Diagnose before asserting causes (run oscillator test before guessing audio output device)
Write regression test before pushing any bug fix
Training quality gate: BFCL ≥90% before "training done"
60-min drift check for long sessions

Evidence gate table maps every claim type to required proof artifact.

Skill: ~/.agent/skills/evidence-first-protocol/SKILL.md

🔊 TTS audio protection (prism-aac)

PROTECT_PLAY_MS=600ms: rapid autoSpeak calls are gracefully dropped instead of killing each other
interrupt parameter replaces shared flag (fixes Speak button being silenced by concurrent tile taps)
volume=0 guard with console.warn
10 unit tests covering all failure classes
SSML rate × 2 formula (capped at 1.4) confirmed working

🔍 Search keyboard routing (prism-aac)

Search opens with keyboard visible immediately
On-screen keys route to search input via searchKeyBridge.ts

📬 Inbox wired (prism-aac + synalux-private)

/api/v1/prism-aac/inbox/poll returns real Gmail unread + unclaimed SMS
Per-message TTS on arrival
Reply button on schedule message tasks

🏪 Marketplace catalog fixed (synalux-private)

marketplace_modules table created and applied to production Supabase.

13 stub fixes (synalux-private)

Accounting providers, Zoom, Telegram/WhatsApp, e-sign, feature-flags, SMS, and more.

Migration

No breaking changes to MCP tools or protocol. Update via:

npm install -g [email protected]
npx prism-mcp-server --version  # should print 15.0.0

What's next (v15.x)

BFCL ≥90% verified on 72B, 32B, 2B models (in training)
Layer3 runtime inference server with 3-layer pipeline
OpenAI-compatible /v1/chat/completions with layer routing

View release on GitHub

v12.0.1 Maintenance 27d

Minor fixes and improvements.

Full changelog