prism-mcp-server 12.5.0 → 12.5.4

package/README.md

@@ -4,12 +4,12 @@
 [![MCP Registry](https://img.shields.io/badge/MCP_Registry-listed-00ADD8?logo=data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCAyNCAyNCI+PHBhdGggZmlsbD0id2hpdGUiIGQ9Ik0xMiAyTDIgN2wxMCA1IDEwLTUtMTAtNXpNMiAxN2wxMCA1IDEwLTV2LTJMMTI0djJMMiA5djh6Ii8+PC9zdmc+)](https://github.com/modelcontextprotocol/servers)
 [![Glama](https://img.shields.io/badge/Glama-listed-FF5601)](https://glama.ai/mcp/servers?query=prism-mcp)
 [![Smithery](https://img.shields.io/badge/Smithery-listed-6B4FBB)](https://smithery.ai/server/@dcostenco/prism-mcp)
-[![License: BSL-1.1](https://img.shields.io/badge/License-BSL--1.1-blue.svg)](LICENSE)
+[![License: BSL-1.1](https://img.shields.io/badge/License-BUSL--1.1-blue.svg)](LICENSE)
 [![TypeScript](https://img.shields.io/badge/TypeScript-5.0+-3178C6?logo=typescript&logoColor=white)](https://www.typescriptlang.org/)
 [![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](CONTRIBUTING.md)
 
 <!-- 🌐 Translations auto-generated by scripts/generate_i18n.py — triggered by GitHub Actions on README.md changes -->
-🌐 **Translate:** [English](#prism-coder-ide-ship-not-just-code) · [Español](docs/i18n/README_es.md) · [Français](docs/i18n/README_fr.md) · [Português](docs/i18n/README_pt.md) · [Română](docs/i18n/README_ro.md) · [Українська](docs/i18n/README_uk.md) · [Русский](docs/i18n/README_ru.md) · [Deutsch](docs/i18n/README_de.md) · [日本語](docs/i18n/README_ja.md) · [한국어](docs/i18n/README_ko.md) · [中文](docs/i18n/README_zh.md) · [العربية](docs/i18n/README_ar.md)
+🌐 **Translate:** [English](README.md) · [Español](docs/i18n/README_es.md) · [Français](docs/i18n/README_fr.md) · [Português](docs/i18n/README_pt.md) · [Română](docs/i18n/README_ro.md) · [Українська](docs/i18n/README_uk.md) · [Русский](docs/i18n/README_ru.md) · [Deutsch](docs/i18n/README_de.md) · [日本語](docs/i18n/README_ja.md) · [한국어](docs/i18n/README_ko.md) · [中文](docs/i18n/README_zh.md) · [العربية](docs/i18n/README_ar.md)
 
 ---
 
@@ -17,6 +17,15 @@
 
 > **NEW:** The full-stack AI-native desktop IDE that combines coding, building, and deploying in one tool. No competitor offers all of this.
 
+### Downloads
+
+| Platform | Package | Size |
+|----------|---------|------|
+| **Windows** | [Prism Coder-1.0.0-Setup.exe](https://github.com/dcostenco/prism-coder/releases/download/v1.0.0/Prism.Coder-1.0.0-Setup.exe) | 99 MB |
+| **macOS (Apple Silicon)** | [Prism Coder-1.0.0-arm64.dmg](https://github.com/dcostenco/prism-coder/releases/download/v1.0.0/Prism.Coder-1.0.0-arm64.dmg) | 113 MB |
+| **Linux** | [Prism Coder-1.0.0.AppImage](https://github.com/dcostenco/prism-coder/releases/download/v1.0.0/Prism.Coder-1.0.0.AppImage) | 119 MB |
+| **npm (MCP Server)** | `npx -y prism-mcp-server` | — |
+
 | What You Get | Time Saved vs. Traditional |
 |---|:---:|
 | 🤖 **Agent Mode** — autonomous multi-step task execution with diff previews | ~95% |
@@ -36,7 +45,7 @@
 
 **27/27 features** — more than any competitor (Cursor: 9, Windsurf: 9, Replit: 12, Bolt: 9).
 
-👉 **[Full IDE README with screenshots, architecture, and technical details →](https://github.com/nicecode-dev/prism-coder-ide/blob/main/README.md)**
+👉 **[Full IDE README with screenshots, architecture, and technical details →](https://github.com/dcostenco/prism-coder/releases/tag/v1.0.0)**
 
 ---
 
@@ -45,9 +54,9 @@
 **Your AI agent forgets everything between sessions. Prism fixes that — then teaches it to think.**
 
 <details>
-<summary>Cognitive Architecture Deep Dive (v12.0.0)</summary>
+<summary>Cognitive Architecture Deep Dive (v12.5)</summary>
 
-Prism v12.0.0 is a true **Cognitive Architecture** inspired by human brain mechanics. Beyond flat vector search, your agent now forms principles from experience, follows causal trains of thought, and possesses the self-awareness to know when it lacks information. **Your agents don't just remember; they learn.** With v12.0.0, the entire cognitive pipeline — including ledger compaction, task routing, semantic search, and **Agent Infrastructure Resilience** — runs **100% on-device** or via secure clinical discovery (PubMed/ERIC), backed by `prism-coder:7b`, a HIPAA-hardened local LLM. No API keys for core features. No data leaves your machine.
+Prism v12.5 is a true **Cognitive Architecture** inspired by human brain mechanics. Beyond flat vector search, your agent now forms principles from experience, follows causal trains of thought, and possesses the self-awareness to know when it lacks information. **Your agents don't just remember; they learn.** With v12.5, the entire cognitive pipeline — including ledger compaction, task routing, semantic search, and **Agent Infrastructure Resilience** — runs **100% on-device** or via secure clinical discovery (PubMed/ERIC), backed by `prism-coder:7b`, a HIPAA-hardened local LLM. No API keys for core features. No data leaves your machine.
 
 </details>
 
@@ -57,11 +66,11 @@ npx -y prism-mcp-server
 
 Works with **Claude Desktop · Claude Code · Cursor · Windsurf · Cline · Gemini · Antigravity** — **any MCP client.**
 
-https://github.com/dcostenco/prism-mcp/raw/main/docs/prism_mcp_demo.mp4
+https://github.com/dcostenco/prism-coder/raw/main/docs/prism_mcp_demo.mp4
 
 ## 📖 Table of Contents
 
-- [💳 v12.0.0 Unified Billing & Agent Skill Ecosystem](#unified-billing)
+- [💳 v12.5 Unified Billing & Agent Skill Ecosystem](#unified-billing)
 - [🏗️ v11.6.0 Agent Infrastructure Resilience](#agent-infrastructure)
 - [🔬 v11.5.1 Deep Research Intelligence (Auto-Scholar)](#deep-research-intelligence)
 - [⚡ Zero-Search Retrieval (HRR Architecture)](#zero-search)
@@ -86,9 +95,9 @@ https://github.com/dcostenco/prism-mcp/raw/main/docs/prism_mcp_demo.mp4
 
 ---
 
-## 💳 <a name="unified-billing"></a>v12.0.0 Unified Billing & Agent Skill Ecosystem
+## 💳 <a name="unified-billing"></a>v12.5 Unified Billing & Agent Skill Ecosystem
 
-Prism v12.0.0 unifies Prism and Synalux into a **single billing architecture** with identical tier pricing and a 14-day free trial on all paid tiers.
+Prism v12.5 unifies Prism and Synalux into a **single billing architecture** with identical tier pricing and a 14-day free trial on all paid tiers.
 
 ### Prism Cloud Pricing
 
@@ -111,7 +120,7 @@ Prism v12.0.0 unifies Prism and Synalux into a **single billing architecture** w
 - **10 Vendor Skills** — Vercel, Supabase, Stripe, Sentry, OpenAI, Addy Osmani, Garry Tan/gstack
 - **30+ Community Skills** — Installed and optimized from the Gemini ecosystem
 
-> 📦 **Packages:** [`prism-mcp-server`](https://www.npmjs.com/package/prism-mcp-server) (npm) · [Prism Coder IDE](https://github.com/nicecode-dev/prism-coder-ide) (VS Code) · `prism` CLI
+> 📦 **Packages:** [`prism-mcp-server`](https://www.npmjs.com/package/prism-mcp-server) (npm) · [Prism Coder IDE](https://github.com/dcostenco/prism-coder/releases/tag/v1.0.0) (VS Code) · `prism` CLI
 
 ---
 
@@ -131,7 +140,7 @@ Prism v11.6.0 introduces **production-grade agent infrastructure** for running m
 | **Queue Watchdog** | Deadlocks from zombie queue entries |
 | **Status Dashboard** | Blind spots in infrastructure health |
 
-> 🧪 **Verified:** 115/115 tests passing across unit, concurrent, shell integration, mock Ollama, and live stress test suites. v12.0.0 billing tests included.
+> 🧪 **Verified:** 115/115 tests passing across unit, concurrent, shell integration, mock Ollama, and live stress test suites. v12.5 billing tests included.
 
 ---
 
@@ -141,7 +150,7 @@ Prism v11.5.1 transforms your AI agent from a "Coder" into a "Clinical Scientist
 
 ### 🥊 The Global Benchmarks: Prism v11 vs. Standard RAG
 
-| Feature | **Standard AI Memory (Mem0/Zep)** | **Prism v12.0.0 (Elite Architecture)** |
+| Feature | **Standard AI Memory (Mem0/Zep)** | **Prism v12.5 (Elite Architecture)** |
 | :--- | :--- | :--- |
 | **Search Complexity** | $O(N)$ or $O(\log N)$ (Scales with data) | **$O(1)$ Zero-Search (Constant time via HRR) ** |
 | **Discovery Logic** | General Web Search (Snippets) | **Parallel Academic Discovery (PubMed, ERIC, S2)** |
@@ -1019,9 +1028,9 @@ The Generator strips the `console.log`, resubmits, and the next `EVALUATE` retur
 
 ## <a name="whats-new"></a>🆕 What's New
 
-> **Current release: v12.0.0 — Unified Billing & Agent Skill Ecosystem**
+> **Current release: v12.5 — Unified Billing & Agent Skill Ecosystem**
 
-- 💳 **v12.0.0 — Unified Billing & Agent Skill Ecosystem:** Aligned Prism and Synalux tiers (Standard $19, Advanced $49, Enterprise $99), 14-day free trial, 54 agent skills, BSL-1.1 license. → [Changelog](CHANGELOG.md#1200)
+- 💳 **v12.5 — Unified Billing & Agent Skill Ecosystem:** Aligned Prism and Synalux tiers (Standard $19, Advanced $49, Enterprise $99), 14-day free trial, 54 agent skills, BSL-1.1 license. → [Changelog](CHANGELOG.md#1200)
 - 🏗️ **v11.6.0 — Agent Infrastructure Resilience:** Production-grade concurrent agent execution with serialized queue (Python `fcntl`), memory guardian daemon, queue watchdog, and unified status dashboard. 115/115 tests verified across 5 suites. → [Changelog](CHANGELOG.md#1160)
 - 🧠 **v11.5.1 — Structural GRPO Alignment:** GRPO-aligned local engine with held-out benchmark suite (N=15). **100% tool-call accuracy**, 100% JSON validity, 100% retrieval accuracy, 100% reasoning abstention. → [Changelog](CHANGELOG.md#1150)
 - 🛡️ **v11.0.0 — HIPAA-Hardened Local LLM:** `prism-coder:7b` for local compaction, task routing, and semantic search. `PRISM_STRICT_LOCAL_MODE`, SSRF protection, full XML escaping. 22-finding adversarial audit. → [Changelog](CHANGELOG.md#1100)
@@ -1108,8 +1117,8 @@ Prism's local engine (`prism-coder:7b`) is optimized for low-latency, high-valid
 
 | Metric | Score | Details |
 |:-------|:---:|:---|
-| **Overall Accuracy** | **99.3%** (avg) | 3 runs: 49/50, 50/50, 50/50 |
-| **Median** | **100%** (50/50) | 2 perfect runs out of 3 |
+| **Overall Accuracy** | **100%** (avg) | 3 runs: 50/50, 50/50, 50/50 |
+| **Median** | **100%** (50/50) | 3 perfect runs out of 3 |
 | **Tool-Call Accuracy** | **100%** (31/31) | Correct tool on all tool-requiring prompts |
 | **Abstention Accuracy** | **100%** (19/19) | Correctly avoids tool calls on all adversarial traps |
 | **Adversarial Traps** | **100%** (15/15 × 3) | Express.js sessions, LSTM forget gates, context managers |
@@ -1193,7 +1202,7 @@ Compared against the **[Berkeley Function Calling Leaderboard (BFCL V4)](https:/
 
 | Model | Provider | Tool-Call Accuracy | SWE-bench | Cost |
 |:---|:---|:---:|:---:|:---:|
-| **Prism-Coder 7B** | **Prism (local)** | **99.3%** ⭐ | — | **$0 (on-device)** |
+| **Prism-Coder 7B** | **Prism (local)** | **100%** ⭐ | — | **$0 (on-device)** |
 | Claude Opus 4.7 | Anthropic | 77.3% | 87.6% | $5 / $25 per 1M tok |
 | Gemini 3.1 Pro | Google | 77.1% | 80.6% | $1.25 / $10 per 1M tok |
 | Claude Opus 4.5 | Anthropic | 77.47% | 70.3% | $15 / $75 per 1M tok |
@@ -1295,13 +1304,13 @@ prism scm dora --repo synalux/portal --period 2024-Q4
 <summary>📸 Screenshots — SCM CLI in action (click to expand)</summary>
 
 #### Code Search (Semantic Mode)
-![prism scm search — semantic code search across repos](docs/scm_search_cli.png)
+![prism scm search — semantic code search across repos](docs/scm_search_cli.jpg)
 
 #### AI Review with HIPAA Check
-![prism scm review — AI code review with HIPAA compliance](docs/scm_review_cli.png)
+![prism scm review — AI code review with HIPAA compliance](docs/scm_review_cli.jpg)
 
 #### Security Scan
-![prism scm scan — secret detection and Dockerfile analysis](docs/scm_scan_cli.png)
+![prism scm scan — secret detection and Dockerfile analysis](docs/scm_scan_cli.jpg)
 
 </details>
 
@@ -1720,11 +1729,11 @@ Prism MCP is open-source and free for individual developers. For teams and enter
 
 ## <a name="milestones-roadmap"></a>📦 Milestones & Roadmap
 
-> **Current: v12.0.0** — Unified Billing & Agent Skill Ecosystem ([CHANGELOG](CHANGELOG.md))
+> **Current: v12.5** — Unified Billing & Agent Skill Ecosystem ([CHANGELOG](CHANGELOG.md))
 
 | Release | Headline |
 |---------|----------|
-| **v12.0.0** | 💳 **Unified Billing & Agent Skill Ecosystem** — Synalux-priced tiers ($19/$49/$99), 14-day trial, 54 skills, BSL-1.1 license. |
+| **v12.5** | 💳 **Unified Billing & Agent Skill Ecosystem** — Synalux-priced tiers ($19/$49/$99), 14-day trial, 54 skills, BSL-1.1 license. |
 | **v11.6.0** | 🏗️ **Agent Infrastructure Resilience** — Production-grade serialized queue, memory guardian, queue watchdog, status dashboard. 115/115 tests. |
 | **v11.5.1** | 🧠 **Structural GRPO Alignment** — Perfect 100% accuracy cross-validated on Synalux Elite platform. |
 | **v11.0.1** | 🧪 **Production Stability** — Field-tested Zero-Search logic merge, local logic finalization, HIPAA-hardened security refinement. |
@@ -1779,8 +1788,8 @@ A: Run `npm run build && npm test`, then open the Mind Palace dashboard (`localh
 
 ## License
 
-MIT
+BUSL-1.1
 
 ---
 
-<sub>**Keywords:** MCP server, Model Context Protocol, Claude Desktop memory, persistent session memory, AI agent memory, cognitive architecture, ACT-R spreading activation, Hebbian learning, episodic semantic consolidation, multi-hop reasoning, uncertainty rejection gate, local-first, SQLite MCP, Mind Palace, time travel, visual memory, VLM image captioning, OpenTelemetry, GDPR, agent telepathy, multi-agent sync, behavioral memory, cursorrules, Ollama MCP, Brave Search MCP, TurboQuant, progressive context loading, knowledge management, LangChain retriever, LangGraph agent</sub>
+<sub>**Keywords:** MCP server, Model Context Protocol, Claude Desktop memory, persistent session memory, AI agent memory, cognitive architecture, ACT-R spreading activation, Hebbian learning, episodic semantic consolidation, multi-hop reasoning, uncertainty rejection gate, local-first, SQLite MCP, Mind Palace, time travel, visual memory, VLM image captioning, OpenTelemetry, GDPR, agent telepathy, multi-agent sync, behavioral memory, cursorrules, Ollama MCP, Brave Search MCP, TurboQuant, progressive context loading, knowledge management, LangChain retriever, LangGraph agent, business, enterprise, hipaa</sub>

package/dist/backgroundScheduler.js

@@ -644,6 +644,25 @@ export async function runSchedulerSweep(cfg = DEFAULT_SCHEDULER_CONFIG) {
             debugLog(`[Scheduler] Distributed lock released (pid: ${processId})`);
         }
     }
+    // ── Evict stale project entries from tracking Maps ──────────
+    try {
+        const activeProjects = new Set(await storage.listProjects());
+        for (const key of lastSynthesisAt.keys()) {
+            if (!activeProjects.has(key))
+                lastSynthesisAt.delete(key);
+        }
+        for (const key of synthesisBackoffUntil.keys()) {
+            if (!activeProjects.has(key))
+                synthesisBackoffUntil.delete(key);
+        }
+        for (const key of lastPruneAt.keys()) {
+            if (!activeProjects.has(key))
+                lastPruneAt.delete(key);
+        }
+    }
+    catch {
+        // Non-critical — stale entries are harmless, just wasteful
+    }
     // ── Finalize ───────────────────────────────────────────────
     result.completedAt = new Date().toISOString();
     result.durationMs = Date.now() - sweepStart;

package/dist/dashboard/authUtils.js

@@ -180,10 +180,11 @@ export function createRateLimiter(opts) {
                 entry = { timestamps: [] };
                 store.set(key, entry);
             }
-            // Filter to only timestamps within the window
-            entry.timestamps = entry.timestamps.filter(t => now - t < opts.windowMs);
             if (entry.timestamps.length >= opts.maxAttempts) {
-                return false; // Rate limited
+                entry.timestamps = entry.timestamps.filter(t => now - t < opts.windowMs);
+                if (entry.timestamps.length >= opts.maxAttempts) {
+                    return false;
+                }
             }
             entry.timestamps.push(now);
             return true;

package/dist/dashboard/server.js

@@ -36,7 +36,7 @@ import { safeCompare, generateToken, isAuthenticated, createRateLimiter, initJWK
 const PORT = parseInt(process.env.PRISM_DASHBOARD_PORT || "3000", 10);
 /** Read HTTP request body as string (Buffer-based to avoid GC thrash on large imports) */
 /** SECURITY: 10MB limit prevents memory exhaustion from oversized POST payloads. */
-const MAX_BODY_BYTES = 10 * 1024 * 1024; // 10MB
+const MAX_BODY_BYTES = parseInt(process.env.PRISM_MAX_REQUEST_BYTES ?? String(10 * 1024 * 1024), 10);
 function readBody(req) {
     return new Promise((resolve, reject) => {
         const chunks = [];
@@ -92,8 +92,8 @@ export async function startDashboardServer() {
     if (AUTH_JWKS_URI) {
         initJWKS(AUTH_JWKS_URI);
     }
-    const SESSION_TTL_MS = 24 * 60 * 60 * 1000; // 24 hours
-    const activeSessions = new Map(); // token → expiry timestamp
+    const SESSION_TTL_MS = parseInt(process.env.PRISM_SESSION_TTL_MS ?? String(24 * 60 * 60 * 1000), 10);
+    const activeSessions = new Map();
     // Auth config object — injectable for testing via authUtils.ts
     const authConfig = {
         authEnabled: AUTH_ENABLED,
@@ -1435,4 +1435,12 @@ self.addEventListener('message', (e) => {
     // Run immediately on startup, then every 12 hours
     runTtlSweep().catch(() => { });
     setInterval(() => { runTtlSweep().catch(() => { }); }, 12 * 60 * 60 * 1000);
+    // Prune expired dashboard sessions every hour
+    setInterval(() => {
+        const now = Date.now();
+        for (const [token, expiry] of activeSessions) {
+            if (now > expiry)
+                activeSessions.delete(token);
+        }
+    }, 60 * 60 * 1000);
 }