prism-mcp-server 17.1.0 → 18.0.0

package/README.md

@@ -28,12 +28,12 @@ Ask "what did I decide about the auth flow last month?" and get the answer with
 ### 🧬 Cognitive routing
 Different memory types live in different stores: episodic (what happened), semantic (what's true), procedural (how to do X). The router picks where to store and where to retrieve.
 
-### 🔄 Proactive session drift detection *(new in v15)*
+### 🔄 Proactive session drift detection *(new in v15, HRR-powered in v17)*
 Your AI agent can now detect when it has drifted from your original goals — mid-session, automatically — and self-correct before you notice the problem.
 
 Three direct Prism calls:
 1. **`session_save_ledger`** — snapshot current state
-2. **`session_cognitive_route`** — compare current work against original goals, returns `on_track / minor_drift / major_drift`
+2. **`session_detect_drift`** — HRR-powered semantic comparison of current work vs original goals, returns `on_track / minor_drift / major_drift` with domain-specific signals (BCBA/Coding/AAC)
 3. **`session_compact_ledger`** — if drifted, compress and reload only what matters
 
 When major drift is detected, the alert routes to the **Synalux portal** so it's visible across sessions and devices — not just in the current conversation.
@@ -42,6 +42,19 @@ When major drift is detected, the alert routes to the **Synalux portal** so it's
 
 No scripts. No cron. No hooks. Three tool calls, Prism handles the rest.
 
+### 🛡 PHI Guard *(new in v17)*
+Automatic Protected Health Information detection and redaction in the memory pipeline. Every `session_save_ledger` and `session_save_handoff` call passes through the PHI guard before storage.
+
+**What it catches:** Names, DOBs, SSNs, MRNs, phone numbers, email addresses, and 18 HIPAA identifier categories. Redaction is deterministic (regex + pattern matching, no LLM) — zero false negatives on structured identifiers.
+
+**Fail-closed:** PHI detection errors log to stderr (never suppressed) and block the save. Metric: `phi_guard.detected` count per category is always emitted for audit compliance.
+
+### ⚡ Prompt-based skill routing *(new in v17)*
+114 agent skills auto-load based on prompt keywords. No manual skill selection needed — the MCP server scans the user's prompt and injects the relevant skill instructions into the session context before the AI responds.
+
+### 💰 Tier enforcement *(new in v17.1)*
+`prism_infer` now enforces subscription-tier gates: model ceiling, max tokens, daily limits, and cloud fallback are all gated by your plan. Free users get local-only inference up to 4b; paid tiers unlock higher models, more tokens, and cloud fallback. Flat-rate seat caps via `max_seats` per plan.
+
 ### 🛡 Local-first — security + speed
 Free tier runs entirely on your machine — SQLite, local embedding model, no API keys, no cloud. Paid tier adds cloud sync via Synalux portal.
 
@@ -92,7 +105,7 @@ prism-coder:4b ── verifies claims ──────────▶  grounde
 prism-coder:32b ── deep reasoning ──────────▶  serve  (~8s, 19GB, FREE)
   │
   ▼  (cloud fallback when local insufficient)
-Claude Sonnet 4 → Claude Opus 4.7 ─────────▶  serve  (cloud, ~$0.01/req)
+Claude Sonnet 4 ────────────────────────────▶  serve  (cloud, ~$0.01/req)
 ```
 
 | Tier | Model | Role | RAM | Latency | Cost |
@@ -100,7 +113,7 @@ Claude Sonnet 4 → Claude Opus 4.7 ─────────▶  serve  (clou
 | **Default** | prism-coder:14b | Router + general inference | 9 GB | ~3s | $0 |
 | **Verifier** | prism-coder:4b | Grounding claims check | 2.5 GB | <1s | $0 |
 | **Complex** | prism-coder:32b | Deep reasoning (on-demand) | 19 GB | ~8s | $0 |
-| **Cloud** | Sonnet → Opus | Fallback for max quality | — | ~5-10s | ~$0.01 |
+| **Cloud** | Claude Sonnet 4 | Fallback for max quality | — | ~5-10s | ~$0.01 |
 
 **Mobile / offline cascade** (Prism AAC iOS):
 ```
@@ -155,7 +168,58 @@ Categories: abstention, adversarial traps, cascade, disambiguation, edge cases,
 **What it does NOT mean**: these scores measure routing precision on a 17-tool taxonomy, not general intelligence. Claude outperforms on everything outside this task. The value is **offline reliability at zero cost**, not replacing Claude. Code and clinical knowledge come from RAG via `knowledge_search`.
 
 ### 🔍 L3 Grounding Verifier
-When `prism_infer` receives an `evidence` payload, the grounding verifier automatically checks the model's response against the provided evidence before returning to the caller. Unverified or hallucinated claims are flagged. This is the third layer (L3) of the cascade — after tool routing (L1) and confidence gating (L2).
+
+Fail-closed fact-checking layer. When `prism_infer` receives an `evidence` payload, a separate verifier model (default: `prism-coder:4b`) checks every factual claim in the draft against the evidence before serving it. This is the third layer (L3) of the cascade — after tool routing (L1) and confidence gating (L2).
+
+**Three-tier pre-check:**
+
+| Tier | Condition | Action |
+|---|---|---|
+| **0 — Conversational** | Draft has no numbers, dates, names, codes, or $ amounts | Serve without verification |
+| **0a — No evidence** | Assertive draft + zero evidence snippets | Refuse (fail-closed) |
+| **2 — NLI** | Assertive draft + evidence provided | Verify each claim against evidence |
+
+**Per-claim verdicts:**
+- `ENTAILED` — claim matches evidence (including arithmetic identity: "3" ≈ "three")
+- `CONTRADICTED` — evidence states a different value for the same fact → **refuse**
+- `NEUTRAL` — claim not covered by evidence → **refuse** (fail-closed default)
+
+**Fail-closed guarantees:** HTTP errors, malformed JSON, timeouts → all treated as refusal. The caller gets the specific claim that failed and can retry with more evidence or fall back to cloud.
+
+**Usage with `prism_infer`:**
+```json
+{
+  "prompt": "What was the patient's last A1C?",
+  "evidence": [
+    { "source": "lab_2026-05-01", "content": "HbA1c: 6.8% (ref <7.0)" }
+  ]
+}
+```
+
+**Structured output:**
+```json
+{
+  "output": "The patient's last A1C was 6.8%.",
+  "verification": {
+    "action": "served",
+    "claims": [{ "text": "A1C was 6.8%", "verdict": "ENTAILED" }],
+    "verifierChain": [{ "model": "prism-coder:4b", "verdict": "ENTAILED", "latencyMs": 340 }]
+  }
+}
+```
+
+When a claim is contradicted or unsupported:
+```json
+{
+  "output": "⚠ Verification failed: claim 'A1C was 7.2%' is CONTRADICTED by evidence.",
+  "verification": {
+    "action": "refused_fabricated",
+    "refusalClaim": "A1C was 7.2%"
+  }
+}
+```
+
+The verifier model (`prism-coder:4b`) is intentionally different from the inference model — satisfying the independent-reviewer principle. Requires a paid plan (see [Plans](#plans)). Set `verify: false` to explicitly skip verification even when evidence is provided.
 
 ### 🧠 HRR Semantic Drift Detection (v17.0)
 Detects when long AI agent sessions drift from their original goal — using Holographic Reduced Representations for temporal trajectory encoding and anomaly detection.
@@ -214,6 +278,74 @@ Multiple AI agents share the same Mind Palace. Each agent has a role (dev / qa /
 
 ---
 
+## Why Prism Coder
+
+### vs AI coding assistants
+
+| Feature | Prism Coder | GitHub Copilot | Cursor | Windsurf | Amazon Q | Tabnine | Devin |
+|---|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
+| Local inference (1.7B–32B) | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
+| Works offline (local-only mode) | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
+| Open-weight models (HuggingFace) | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
+| Data stays on machine (local tier) | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
+| Persistent cross-session memory | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ |
+| Cognitive routing (episodic/semantic) | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
+| Session drift detection (HRR) | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
+| L3 grounding verifier | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
+| Multi-agent hivemind | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
+| MCP server (tools + memory for agents) | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
+| Cloud fallback (14b → 32b → Sonnet) | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
+| Web IDE | ✅ | ✅ | ❌ | ❌ | ✅ | ❌ | ✅ |
+| VS Code extension | ✅ | ✅ | ❌ | ❌ | ✅ | ✅ | ❌ |
+| HIPAA / air-gapped ready | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
+| Flat-rate pricing (not per-seat) | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
+
+### vs local AI tools
+
+| Feature | Prism Coder | Ollama | LM Studio | Jan.ai | Mem0 | Zep |
+|---|:---:|:---:|:---:|:---:|:---:|:---:|
+| Local inference (1.7B–32B cascade) | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
+| Automatic cloud fallback | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ |
+| Persistent cross-session memory | ✅ | ❌ | ❌ | ❌ | ✅ | ✅ |
+| Knowledge ingestion (MCP + webhook + REST) | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ |
+| Cognitive routing (3-store) | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ |
+| L3 grounding verifier | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ |
+| Session drift detection | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ |
+| Native MCP server | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ |
+| Web IDE + VS Code extension | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ |
+| Analytics dashboard | ✅ | ❌ | ❌ | ❌ | ✅ | ✅ |
+
+### Pricing — flat-rate, not per-seat
+
+| | **Prism Coder** | GitHub Copilot | Cursor | Windsurf | Amazon Q | Tabnine |
+|---|:---:|:---:|:---:|:---:|:---:|:---:|
+| **Individual** | **$19/mo** | $10/mo | $20/mo | $15–20/mo | $19/mo | $39/mo |
+| **Team (5 devs)** | **$49/mo flat** | $95/mo | $200/mo | $200/mo | $95/mo | $295/mo |
+| **Enterprise (25 devs)** | **$99/mo flat** | $195/mo | $1,000/mo | Custom | Custom | Custom |
+| **Cost per dev (team)** | **$9.80** | $19 | $40 | $40 | $19 | $59 |
+| **Annual savings (5 devs)** | — | **$552** | **$1,812** | **$1,812** | **$552** | **$2,952** |
+
+---
+
+## Plans
+
+| | **Free** | **Standard $19/mo** | **Advanced $49/mo** | **Enterprise $99/mo** |
+|---|---|---|---|---|
+| **Seats included** | 1 | 1 | up to 5 | up to 25 |
+| **Local model ceiling** | up to 4b | up to 14b | up to 32b | up to 32b |
+| **Daily inference limit** | 50 | 200 | 2,000 | 100,000 |
+| **Max output tokens** | 512 | 1,024 | 2,048 | 4,096 |
+| **Cloud fallback** | — | Claude Sonnet 4 | Claude Sonnet 4 | Priority + Sonnet 4 |
+| **L3 grounding verifier** | — | ✅ | ✅ | ✅ |
+| **Knowledge search** | limited | unlimited | unlimited | unlimited |
+| **Session memory** | limited | unlimited | unlimited | unlimited |
+| **Analytics dashboard** | — | ✅ | ✅ | ✅ |
+| **HIPAA BAA** | — | — | — | ✅ |
+
+All on-device models are open-weight and free to run locally via Ollama. The subscription gates cloud features, higher model tiers, and increased limits. Need 25+ seats? [Contact sales](https://synalux.ai/contact). 14-day free trial on all paid plans. [Subscribe →](https://synalux.ai/pricing)
+
+---
+
 ## Get started
 
 ```bash
@@ -298,6 +430,7 @@ Paid Synalux subscribers get a built-in analytics dashboard at `/app/memory-anal
 | `knowledge_search` | Semantic + keyword search over all memories |
 | `query_memory_natural` | Natural-language Q&A over your Mind Palace |
 | `extract_entities` | Pull people / projects / decisions from text |
+| `session_detect_drift` | HRR-powered semantic drift detection (BCBA/Coding/AAC) |
 | `session_synthesize_edges` | Auto-link related memories into a graph |
 
 (35+ tools total — full TypeScript signatures in `src/tools/`. Architecture overview in [`docs/ARCHITECTURE.md`](docs/ARCHITECTURE.md).)
@@ -502,7 +635,7 @@ ollama pull dcostenco/prism-coder:32b
 
 Set `LOCAL_LLM_URL=http://localhost:11434` in your portal config. Routing is automatic:
 
-**Desktop/server**: 14B → 32B → Claude Opus fallback · **Mobile/offline**: 14B → 8B → 1.7B
+**Desktop/server**: 14B → 32B → Claude Sonnet 4 fallback · **Mobile/offline**: 14B → 8B → 1.7B
 
 iOS/mobile on same WiFi: `OLLAMA_HOST=0.0.0.0 ollama serve` on the Mac, then point `LOCAL_LLM_URL` at the Mac's IP.  
 Routing accuracy (May 2026, v36/v7 system prompt, 3-seed mean): 32B v7 = **100.0%** · 8B v36 = **100.0%** · 14B v36 = **100.0%** · 1.7B v42 = **100.0%**  
@@ -510,104 +643,6 @@ Cascade (14B→32B): **100.0%** · Opus solo: 98.3% · Opus engaged: **0% of req
 
 ---
 
-## Plans
-
-| | **Free** | **Standard $19/mo** | **Advanced $49/mo** | **Enterprise $99/mo** |
-|---|---|---|---|---|
-| **Local model ceiling** | up to 4b | up to 14b | up to 32b | up to 32b |
-| **Daily inference limit** | 50 | 200 | 2,000 | 100,000 |
-| **Max output tokens** | 512 | 1,024 | 2,048 | 4,096 |
-| **Cloud fallback** | — | Portal cascade (14b → 32b) | Portal cascade (14b → 32b → Claude Opus) | Priority cascade + Claude Opus |
-| **L3 grounding verifier** | — | ✓ | ✓ | ✓ |
-| **Knowledge search** | limited | unlimited | unlimited | unlimited |
-| **Session memory** | limited | unlimited | unlimited | unlimited |
-| **Analytics dashboard** | — | ✓ | ✓ | ✓ |
-| **HIPAA BAA** | — | — | — | ✓ |
-
-### What free users get
-
-- Local Ollama inference with models up to 4b (prism-coder:1b7 and prism-coder:4b)
-- 50 calls/day, 512 max output tokens per call
-- Local SQLite storage for session memory and knowledge
-- All open-weight models available to pull via `ollama pull`
-
-### What paid users get
-
-- **Higher model ceilings** — Standard unlocks 14b, Advanced/Enterprise unlock 32b
-- **Cloud fallback** — when local Ollama is down or underpowered, inference routes through the Synalux portal cascade (14b → 32b → Claude Opus)
-- **L3 grounding verifier** — evidence-based claim verification that rejects hallucinated outputs
-- **Unlimited knowledge search and session memory** — no caps on stored context
-- **Analytics dashboard** — usage metrics, latency tracking, model performance
-- **Higher daily limits and token caps** — see table above
-
-All on-device models are open-weight and free to run locally via Ollama. The subscription gates cloud features, higher model tiers, and increased limits.
-
-14-day free trial on all paid plans. [Subscribe →](https://synalux.ai/pricing)
-
-### Why Prism MCP
-
-**Pricing — flat-rate, not per-seat:**
-
-| | **Prism MCP** | GitHub Copilot | Cursor | Windsurf | Amazon Q | Tabnine |
-|---|---|---|---|---|---|---|
-| **Individual** | **$19/mo** | $10/mo | $20/mo | $15-20/mo | $19/mo | $39/mo |
-| **Team (5 devs)** | **$49/mo flat** | $95/mo | $200/mo | $200/mo | $95/mo | $295/mo |
-| **Enterprise** | **$99/mo flat** | $195/mo | $1,000/mo | Custom | Custom | Custom |
-
-**Features — full stack vs single-purpose:**
-
-| | **Prism MCP** | GitHub Copilot | Cursor | Windsurf | Amazon Q | Tabnine | Devin |
-|---|---|---|---|---|---|---|---|
-| **Web IDE** | **Synalux Coder** | github.dev | — | — | Console | — | Browser |
-| **VS Code extension** | **Yes** | Yes | N/A (is a fork) | N/A (is a fork) | Yes | Yes | No |
-| **MCP server** | **Native** | No | Partial | No | No | No | No |
-| **Works with Claude Code** | **Yes** | No | N/A | No | No | No | No |
-| **Local inference (Ollama)** | **1.7B–32B fleet** | No | No | No | No | No | No |
-| **Cloud fallback** | **14b→32b→Opus** | Cloud only | Cloud only | Cloud only | Cloud only | Cloud only | Cloud only |
-| **Works offline** | **Yes** | No | No | No | No | No | No |
-| **Open-weight models** | **HuggingFace** | Proprietary | Proprietary | Proprietary | Proprietary | Proprietary | Proprietary |
-| **Persistent memory** | **Cross-session** | No | No | No | No | No | Partial |
-| **Cognitive routing** | **Episodic/semantic/procedural** | No | No | No | No | No | No |
-| **Session drift detection** | **HRR-based** | No | No | No | No | No | No |
-| **Codebase indexing** | **Knowledge ingest (MCP + webhook + REST)** | Partial | Yes | Yes | Yes | Yes | Yes |
-| **L3 grounding verifier** | **Evidence-based** | No | No | No | No | No | No |
-| **Multi-agent hivemind** | **Shared Mind Palace** | No | No | No | No | No | No |
-| **Analytics dashboard** | **Yes** | No | Yes | Yes | Yes | No | Yes |
-| **HIPAA / air-gapped** | **On-prem, no BAA needed** | Requires BAA | No | No | Partial | No | No |
-| **Data stays local** | **Yes** | No | No | No | No | No | No |
-
-**vs local AI tools:**
-
-| | **Prism MCP** | Ollama | LM Studio | Jan.ai | Mem0 | Zep |
-|---|---|---|---|---|---|---|
-| **Local inference** | 1.7B–32B cascade | Any GGUF | Any GGUF | Any GGUF | No | No |
-| **Cloud fallback** | Automatic | No | No | Partial | Cloud only | Cloud only |
-| **Persistent memory** | Cross-session | No | No | No | Yes | Yes |
-| **Knowledge ingestion** | MCP + GitHub webhook + REST | No | No | No | Partial | No |
-| **Cognitive routing** | 3-store (episodic/semantic/procedural) | No | No | No | No | Temporal graph |
-| **Grounding verifier** | L3 evidence-based | No | No | No | No | No |
-| **Drift detection** | HRR-based | No | No | No | No | No |
-| **MCP server** | Native | No | No | No | No | No |
-| **Web IDE** | Synalux Coder | No | No | No | No | No |
-| **VS Code extension** | Yes | No | No | No | No | No |
-| **Analytics** | Dashboard + Datadog | No | No | No | Yes | Yes |
-| **Price** | $0–99/mo flat | Free | Free/$10/user | Free | $249/mo | $99/mo |
-
-**Why developers choose Prism:**
-- **Full IDE experience** — Synalux Coder (web) + VS Code extension + MCP for Claude Code, Cursor, JetBrains
-- **Local-first** — your code and context never leave your machine unless you opt in to cloud
-- **Flat-rate pricing** — $49/mo for your whole team, not $40/seat/mo
-- **Works offline** — airplane, hospital, air-gapped classified environments
-- **Open models** — prism-coder weights are on HuggingFace, not locked behind an API
-- **Memory that persists** — cognitive routing stores episodic, semantic, and procedural memory across sessions
-- **Drift detection** — HRR-based session monitoring catches when your AI agent goes off-track
-- **Grounding verification** — L3 verifier rejects hallucinated outputs before they reach you
-- **Codebase indexing** — knowledge ingestion via MCP tool, GitHub webhooks, or REST API
-- **Multi-agent ready** — Hivemind lets multiple agents share the same Mind Palace with role-scoped context
-- **HIPAA without paperwork** — local inference means no BAA required, PHI never leaves the device
-
----
-
 ## What you can build with it
 
 - **Persistent coding assistant** that remembers your codebase, your decisions, your team's conventions
@@ -624,17 +659,17 @@ All on-device models are open-weight and free to run locally via Ollama. The sub
 
 **[synalux.ai/prism-mcp](https://synalux.ai/prism-mcp)** — full documentation, dashboard, subscription plans, and model downloads.
 
-### 💻 Web IDE — Synalux Coder
+### 💻 Web IDE — Prism Coder
 
-Use Prism Coder directly in your browser — no install required. Local-first IDE with the prism-coder agent built in. Connects to GitHub repos, Synalux Mail, Drive, and Source for cross-product workflows.
+Use Prism Coder directly in your browser — no install, no desktop app required. Standalone coding IDE with the prism-coder agent built in. Works with any Prism plan (no Synalux health subscription needed).
 
-**[synalux.ai/coder](https://synalux.ai/coder)** · also reachable at **[synalux.ai/prism-ide](https://synalux.ai/prism-ide)**
+**[synalux.ai/coder](https://synalux.ai/coder)**
 
 | Feature | Detail |
 |---|---|
-| Agent | prism-coder:7b offline · Claude Sonnet 4 (Standard+) · Claude Opus 4 (Enterprise) |
-| Integrations | GitHub repos, Synalux Mail, Drive, Source — same OAuth, no separate accounts |
-| Compliance | Audit log on every turn · PHI redaction · air-gapped offline mode (HIPAA) |
+| Agent | prism-coder:8b offline · Claude Sonnet 4 (Standard+) |
+| Integrations | GitHub repos · same Prism account, no separate sign-up |
+| Plans | Free (4b) · Standard $19/mo (14b) · Advanced $49/mo (32b) · Enterprise $99/mo |
 
 ### 🧩 VS Code Extension — Synalux
 
@@ -705,7 +740,7 @@ prism register-models         # Alias dcostenco/prism-coder:* → prism-coder:*
 ## Testing
 
 ```bash
-npm test                           # 2,418 test cases across 81 files (vitest)
+npm test                           # 2,676 test cases across 89 files (vitest)
 npm test -- --coverage             # coverage report
 python3 tests/benchmarks/prism-routing-100/benchmark.py --models 1b7 14b 32b
 ```

package/dist/tools/ledgerHandlers.js

@@ -801,11 +801,15 @@ export async function sessionLoadContextHandler(args) {
                 const eff = computeEffectiveImportance(s.importance, s.last_accessed_at, s.created_at, Boolean(s.is_rollup));
                 impStr = ` [Imp: ${eff}]`;
             }
-            return `  [${s.session_date?.split("T")[0]}]${impStr} ${s.summary}`;
+            const dateStr = (s.session_date || s.created_at || s.date || "unknown").split("T")[0];
+            return `  [${dateStr}]${impStr} ${s.summary}`;
         }).join("\n") + `\n`;
     }
     if (d.session_history?.length) {
-        formattedContext += `\n📂 Session History (${d.session_history.length} entries):\n` + d.session_history.map((s) => `  [${s.session_date?.split("T")[0]}] ${s.summary}`).join("\n") + `\n`;
+        formattedContext += `\n📂 Session History (${d.session_history.length} entries):\n` + d.session_history.map((s) => {
+            const dateStr = (s.session_date || s.created_at || s.date || "unknown").split("T")[0];
+            return `  [${dateStr}] ${s.summary}`;
+        }).join("\n") + `\n`;
     }
     if (d.recent_validations?.length) {
         formattedContext += `\n🔬 Recent Validations:\n` + d.recent_validations.map((v) => {

package/dist/tools/prismInferHandler.js

@@ -91,12 +91,12 @@ export const PRISM_INFER_TOOL = {
                 type: "boolean",
                 description: "Enable the L3 grounding verifier. Default: true when `evidence` is provided, " +
                     "false otherwise. When enabled, the model's draft is checked by a different model " +
-                    "(prism-coder:1b7 by default) against the supplied `evidence`. Drafts with " +
+                    "(prism-coder:4b by default) against the supplied `evidence`. Drafts with " +
                     "NEUTRAL or CONTRADICTED claims are refused.",
             },
             verifier_model: {
                 type: "string",
-                description: "Override the verifier model. Default: prism-coder:1b7.",
+                description: "Override the verifier model. Default: prism-coder:4b.",
             },
             verifier_timeout_ms: {
                 type: "number",

package/dist/utils/entitlements.js

@@ -17,6 +17,7 @@ export const FREE_ENTITLEMENTS = {
     model_ceiling: "4b",
     daily_infer_limit: 50,
     max_tokens: 512,
+    max_seats: 1,
     features: {
         cloud_fallback: false,
         grounding_verifier: false,
@@ -27,7 +28,7 @@ export const FREE_ENTITLEMENTS = {
     upgrade_url: "https://synalux.ai/pricing",
 };
 // ── Cache ─────────────────────────────────────────────────────────
-const CACHE_TTL_MS = 60 * 60 * 1000; // 1 hour
+const CACHE_TTL_MS = 5 * 60 * 1000; // 5 minutes
 let cache = null;
 let inFlight = null;
 // ── Model tier ordering for ceiling enforcement ───────────────────

package/package.json

@@ -1,8 +1,8 @@
 {
   "name": "prism-mcp-server",
-  "version": "17.1.0",
+  "version": "18.0.0",
   "mcpName": "io.github.dcostenco/prism-coder",
-  "description": "Prism Coder — Cognitive memory + tool-calling intelligence for AI agents. Mind Palace persistent memory (BFCL Gold Certified, 100% Tool-Call Accuracy, 114 Agent Skills, Zero-Search HDC/HRR retrieval, HRR Semantic Drift Detection across BCBA/Coding/AAC domains, HIPAA-hardened local-first storage, SLERP-optimized GRPO alignment) plus the prism-coder:7b / 14b open-weights LLM fleet.",
+  "description": "Prism Coder — Cognitive memory + tool-calling intelligence for AI agents. Mind Palace persistent memory (BFCL Gold Certified, 100% Tool-Call Accuracy, 114 Agent Skills, PHI Guard, Tier Enforcement, Prompt-Based Skill Routing, Zero-Search HDC/HRR retrieval, HRR Semantic Drift Detection across BCBA/Coding/AAC domains, HIPAA-hardened local-first storage, SLERP-optimized GRPO alignment) plus the prism-coder 1.7B–32B open-weights LLM fleet.",
   "module": "index.ts",
   "type": "module",
   "main": "dist/server.js",