prism-mcp-server 9.0.4 → 9.0.6

package/README.md

@@ -8,11 +8,11 @@
 [![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)
 
-![Prism Mind Palace Dashboard — v9.0.4](docs/mind-palace-dashboard.png)
+![Prism Mind Palace Dashboard](docs/mind-palace-dashboard.png)
 
 **Your AI agent forgets everything between sessions. Prism fixes that — then teaches it to think.**
 
-Prism v9.0 is the **Autonomous Cognitive OS** for AI agents. Built on a true cognitive architecture inspired by human brain mechanics, Prism gives agents affect-tagged memory, token-economic cost awareness, and multi-hop graph reasoning — your agent now follows causal trains of thought across memory, forms principles from experience, economizes what it stores, and knows when it lacks information. **Your agents don't just remember; they think.**
+Prism v7.8 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.**
 
 ```bash
 npx -y prism-mcp-server
@@ -20,7 +20,7 @@ npx -y prism-mcp-server
 
 Works with **Claude Desktop · Claude Code · Cursor · Windsurf · Cline · Gemini · Antigravity** — **any MCP client.**
 
-## Table of Contents
+## 📖 Table of Contents
 
 - [Why Prism?](#why-prism)
 - [Quick Start](#quick-start)
@@ -28,9 +28,7 @@ Works with **Claude Desktop · Claude Code · Cursor · Windsurf · Cline · Gem
 - [Setup Guides](#setup-guides)
 - [Universal Import: Bring Your History](#universal-import-bring-your-history)
 - [What Makes Prism Different](#what-makes-prism-different)
-- [Autonomous Cognitive OS (v9.0)](#-autonomous-cognitive-os-v90)
-- [Synapse Engine (v8.0)](#synapse-engine-v80)
-- [Cognitive Architecture (v7.8)](#cognitive-architecture-v78)
+- [Cognitive Architecture (v7.8)](#-cognitive-architecture-v78)
 - [Data Privacy & Egress](#data-privacy--egress)
 - [Use Cases](#use-cases)
 - [What's New](#whats-new)
@@ -40,7 +38,6 @@ Works with **Claude Desktop · Claude Code · Cursor · Windsurf · Cline · Gem
 - [Architecture](#architecture)
 - [Scientific Foundation](#scientific-foundation)
 - [Milestones & Roadmap](#milestones--roadmap)
-- [Enterprise & Commercial Support](#enterprise--commercial-support)
 - [Troubleshooting FAQ](#troubleshooting-faq)
 
 ---
@@ -55,15 +52,15 @@ Every time you start a new conversation with an AI coding assistant, it starts f
 
 Prism has three pillars:
 
-1. **🧠 Cognitive Memory** — Memories are ranked like a human brain: recently and frequently accessed context surfaces first, while stale context fades naturally via ACT-R activation decay. Raw experience consolidates into semantic principles through Hebbian learning. The result is retrieval quality that no flat vector search can match. *(See [Cognitive Architecture](#cognitive-architecture-v78) and [Scientific Foundation](#scientific-foundation).)*
+1. **🧠 Cognitive Memory** — Memories are ranked like a human brain: recently and frequently accessed context surfaces first, while stale context fades naturally via ACT-R activation decay. Raw experience consolidates into semantic principles through Hebbian learning. The result is retrieval quality that no flat vector search can match. *(See [Cognitive Architecture](#-cognitive-architecture-v78) and [Scientific Foundation](#-scientific-foundation).)*
 
-2. **⚡ Synapse Engine (GraphRAG)** — When your agent searches for "Error X", the Synapse Engine doesn't just find logs mentioning "Error X". Multi-hop energy propagation traverses the causal graph — dampened by fan effect, bounded by lateral inhibition — and surfaces "Workaround Y" connected to "Architecture Decision Z". Nodes discovered exclusively via graph traversal are tagged `[🌐 Synapse]` so you can *see* the engine working. *(See [Synapse Engine](#synapse-engine-v80).)*
+2. **🔗 Multi-Hop Reasoning** — When your agent searches for "Error X", Prism doesn't just find logs mentioning "Error X". Spreading activation traverses the causal graph and brings back "Workaround Y", which is connected to "Architecture Decision Z" — a literal train of thought. *(See [Cognitive Architecture](#-cognitive-architecture-v78).)*
 
-3. **🏭 Autonomous Execution (Dark Factory)** — When you're ready, Prism can run coding tasks end-to-end with a fail-closed pipeline where an adversarial evaluator catches bugs the generator missed — before you ever see the PR. *(See [Dark Factory](#dark-factory--adversarial-autonomous-pipelines).)*
+3. **🏭 Autonomous Execution (Dark Factory)** — When you're ready, Prism can run coding tasks end-to-end with a fail-closed pipeline where an adversarial evaluator catches bugs the generator missed — before you ever see the PR. *(See [Dark Factory](#-dark-factory--adversarial-autonomous-pipelines).)*
 
 ---
 
-## Quick Start
+## 🚀 Quick Start
 
 ### Prerequisites
 
@@ -137,7 +134,7 @@ Then open `http://localhost:3001` instead.
 
 ---
 
-## The Magic Moment
+## ✨ The Magic Moment
 
 > **Session 1** (Monday evening):
 > ```
@@ -158,7 +155,7 @@ Then open `http://localhost:3001` instead.
 
 ---
 
-## Setup Guides
+## 📖 Setup Guides
 
 <details>
 <summary><strong>Claude Desktop</strong></summary>
@@ -381,7 +378,7 @@ Prism can be deployed natively to cloud platforms like [Render](https://render.c
 
 ---
 
-## Universal Import: Bring Your History
+## 📥 Universal Import: Bring Your History
 
 Switching to Prism? Don't leave months of AI session history behind. Prism can **ingest historical sessions from Claude Code, Gemini, and OpenAI** and give your Mind Palace an instant head start — no manual re-entry required.
 
@@ -414,15 +411,9 @@ npx -y prism-mcp-server universal-import --format gemini --path ./gemini_history
 
 ---
 
-## What Makes Prism Different
+## ✨ What Makes Prism Different
 
 
-### 💰 Token-Economic Memory & Surprisal Gates (v9.0)
-Standard agents dump repetitive garbage into vector databases until they bankrupt your API budget and choke their own context windows. Prism introduces a **Persistent Cognitive Budget** with Universal Basic Income (UBI). Before saving, Prism calculates the semantic novelty (Surprisal) of the thought. Redundant boilerplate is penalized with a 2× cost multiplier; novel insights are rewarded. The agent is mathematically forced to learn compression.
-
-### 🎭 Affect-Tagged Emotional Routing (v9.0)
-Standard RAG retrieves documents based on similarity, not success rate. Prism tags experience events with **Valence** (-1.0 to +1.0). Highly emotional memories (catastrophic failures or massive successes) receive an affective salience boost during retrieval. If an agent heads down an architectural path that previously caused outages, Prism injects a preemptive `⚠️ Historical Friction` warning, giving your AI a "gut feeling" about bad code.
-
 ### 🧠 Your Agent Learns From Mistakes
 When you correct your agent, Prism tracks it. Corrections accumulate **importance** over time. High-importance lessons auto-surface as warnings in future sessions — and can even sync to your `.cursorrules` file for permanent enforcement. Your agent literally gets smarter the more you use it.
 
@@ -463,34 +454,33 @@ OpenTelemetry spans for every MCP tool call, LLM hop, and background worker. Rou
 ### 🌐 Autonomous Web Scholar
 Prism researches while you sleep. A background pipeline searches the web, scrapes articles, synthesizes findings via LLM, and injects results directly into your semantic memory — fully searchable on your next session. Brave Search → Firecrawl scrape → LLM synthesis → Prism ledger. Task-aware, Hivemind-integrated, and zero-config when API keys are missing (falls back to Yahoo + Readability).
 
-### Dark Factory — Adversarial Autonomous Pipelines
+### 🏭 Dark Factory — Adversarial Autonomous Pipelines
 When you trigger a Dark Factory pipeline, Prism doesn't just run your task — it fights itself to produce high-quality output. A `PLAN_CONTRACT` step locks a machine-parseable rubric before any code is written. After execution, an **Adversarial Evaluator** (in a fully isolated context) scores the output against the rubric. It cannot pass the Generator without providing exact file and line evidence for every failing criterion. Failed evaluations inject the critique directly into the Generator's retry prompt so it's never flying blind. The result: security issues, regressions, and lazy debug logs caught autonomously — before you ever see the PR. → [See it in action](examples/adversarial-eval-demo/README.md)
 
 ---
 
 ## 🤖 Autonomous Cognitive OS (v9.0)
 
-> *Memory isn't just about storing data; it's about economics and emotion. v9.0 transforms Prism from a passive memory database into a living Cognitive Operating System that forces agents to learn compression and develop intuition.*
+> *Memory isn't just about storing data; it's about economics and emotion. Prism v9.0 transforms passive memory into a living Cognitive Operating System that forces agents to learn compression and develop intuition.*
 
-Most AI agents have an infinite memory budget. They dump massive, repetitive logs into vector databases until the context window chokes. Prism v9.0 fixes this by introducing **Token-Economic Reinforcement Learning** and **Affect-Tagged Memory**.
+Most AI agents have an infinite memory budget. They dump massive, repetitive logs into vector databases until they bankrupt your API budget and choke their own context windows. Prism v9.0 fixes this by introducing **Token-Economic Reinforcement Learning** and **Affect-Tagged Memory**.
 
-### 1. Memory-as-an-Economy (The Surprisal Gate)
-Prism gives your project a strict **Cognitive Budget** (e.g., 2,000 tokens). Every time the agent saves a memory, it costs tokens. 
+### 💰 Memory-as-an-Economy (The Surprisal Gate)
+Prism assigns every project a strict **Cognitive Budget** (e.g., 2,000 tokens) that persists across sessions. Every time the agent saves a memory, it costs tokens. 
 
-But not all memories are priced equally:
-*   Prism intercepts the save and runs a **Vector-Based Surprisal** calculation against recent memories. 
+But not all memories are priced equally. Prism intercepts the save and runs a **Vector-Based Surprisal** calculation against recent memories:
 *   **High Surprisal (Novel thought):** Costs 0.5× tokens. The agent is rewarded for new insights.
 *   **Low Surprisal (Boilerplate):** Costs 2.0× tokens. The agent is penalized for repeating itself.
-*   **Universal Basic Income (UBI):** The budget recovers passively over time (+100 tokens/hour) or when the agent successfully completes autonomous evaluations. 
+*   **Universal Basic Income (UBI):** The budget recovers passively over time (+100 tokens/hour). 
 
-**The Result:** You don't need to prompt the agent to "be concise." The physics of the system force the LLM to learn data compression to avoid bankruptcy.
+If an agent is too verbose, it goes into **Cognitive Debt**. You don't need to prompt the agent to "be concise." The physics of the system force the LLM to learn data compression to avoid bankruptcy.
 
-### 2. Affect-Tagged Memory (Giving AI a "Gut Feeling")
+### 🎭 Affect-Tagged Memory (Giving AI a "Gut Feeling")
 Vector math measures *semantic similarity*, not *sentiment*. If an agent searches for "Authentication Architecture," standard RAG will return two past approaches—it doesn't know that Approach A caused a 3-day production outage, while Approach B worked perfectly.
 
 *   **Affective Salience:** Prism automatically tags experience events with a `valence` score (-1.0 for failure, +1.0 for success).
 *   **Emotional Retrieval:** At retrieval time, the absolute magnitude (`|valence|`) significantly boosts the memory's ranking score. Extreme failures and extreme successes surface to the top.
-*   **UX Warnings:** If the retrieved memories are historically negative, Prism intercepts the prompt injection: `⚠️ Caution: This topic is strongly correlated with historical failures. Review past decisions before proceeding.`
+*   **UX Warnings:** If an agent retrieves memories that are historically negative, Prism intercepts the prompt injection: `⚠️ Caution: This topic is strongly correlated with historical failures. Review past decisions before proceeding.` Your AI now has a "gut feeling" about bad code.
 
 ### The Paradigm Shift
 
@@ -503,54 +493,7 @@ Vector math measures *semantic similarity*, not *sentiment*. If an agent searche
 
 ---
 
-## Synapse Engine (v8.0)
-
-> *Standard RAG retrieves documents. GraphRAG traverses relationships. The Synapse Engine does both — a pure, storage-agnostic multi-hop propagation engine that turns your agent's memory into an associative reasoning network.*
-
-The Synapse Engine (v8.0) replaces the legacy SQL-coupled spreading activation with a **pure functional graph propagation core** inspired by ACT-R cognitive architecture. It is Prism's native, low-latency GraphRAG solution — no external graph database required.
-
-### Before vs After
-
-| | **v7.x (Standard RAG)** | **v8.0 (Synapse Engine)** |
-|---|---|---|
-| **Query** | "Tell me about Project Apollo" | "Tell me about Project Apollo" |
-| **Retrieval** | Returns the design doc (1 hop, cosine match) | Returns the design doc → follows `caused_by` edge to a developer's debugging session → discovers an old Slack thread about a critical auth bug |
-| **Agent output** | Summarizes the design doc | Summarizes the design doc **and warns about the unresolved auth issue** |
-| **Discovery tag** | — | `[🌐 Synapse]` marks the auth bug node, proving the engine found context the user didn't ask for |
-
-### How It Works
-
-```
-  Query: "Project Apollo status"
-              │
-  ┌───────────┼───────────────┐
-  ▼           ▼               ▼
-[Design    [Sprint          [Deployment
-  Doc]      Retro]            Log]
-  │ 1.0       │ 0.8            │ 0.6    ← semantic anchors
-  │           │                │
-  ▼           ▼                ▼
-[Dev       [Auth Bug      [Perf         ← Synapse discovered
-  Profile    Thread  🌐]    Regression 🌐]   (multi-hop)
-  0.42]      0.38]          0.31]
-```
-
-**Key design decisions:**
-
-| Mechanism | Purpose |
-|---|---|
-| **Dampened Fan Effect** (`1/ln(degree+e)`) | Prevents hub nodes from flooding results |
-| **Asymmetric Propagation** (fwd 100%, back 50%) | Preserves causal directionality |
-| **Cyclic Loop Prevention** (`visitedEdges` set) | Prevents infinite energy amplification |
-| **Sigmoid Normalization** | Structural scores can't overwhelm semantic base |
-| **Lateral Inhibition** | Caps output to top-K most energized nodes |
-| **Hybrid Scoring** (70% semantic / 30% structural) | Base relevance always matters |
-
-> 💡 Synapse is **non-fatal** — if the graph traversal fails for any reason, search gracefully returns the original semantic matches. Zero risk of degraded search.
-
----
-
-## Cognitive Architecture (v7.8)
+## 🧠 Cognitive Architecture (v7.8)
 
 > *Prism v7.8 is our biggest leap forward yet. We have moved beyond flat vector search and implemented a true Cognitive Architecture inspired by human brain mechanics. With the new ACT-R Spreading Activation Engine, Episodic-to-Semantic memory consolidation, and Uncertainty-Aware Rejection Gates, Prism doesn't just store logs anymore — it forms principles, follows causal trains of thought, and possesses the self-awareness to know when it lacks information.*
 
@@ -615,7 +558,7 @@ Standard RAG (Retrieval-Augmented Generation) is now a commodity. Everyone has v
 
 ---
 
-## Data Privacy & Egress
+## 🔒 Data Privacy & Egress
 
 **Where is my data stored?**
 
@@ -646,7 +589,7 @@ Prism will recreate the directory with empty databases on next startup.
 
 ---
 
-## Use Cases
+## 🎯 Use Cases
 
 - **Long-running feature work** — Save state at end of day, restore full context next morning. No re-explaining.
 - **Multi-agent collaboration** — Dev, QA, and PM agents share real-time context without stepping on each other's memory.
@@ -675,7 +618,7 @@ Then continue a specific thread with a follow-up message to the selected agent,
 
 ---
 
-## Adversarial Evaluation in Action
+## ⚔️ Adversarial Evaluation in Action
 
 > **Split-Brain Anti-Sycophancy** — the signature feature of v7.4.0.
 
@@ -780,23 +723,21 @@ The Generator strips the `console.log`, resubmits, and the next `EVALUATE` retur
 
 ---
 
-## What's New
+## 🆕 What's New
 
-> **Current release: v9.0.4 — Autonomous Cognitive OS**
+> **Current release: v9.0.5 — JWKS Auth Security Hardening**
 
-- 🧠 **v9.0.0 — Autonomous Cognitive OS:** Affect-Tagged Memory (valence engine — emotional salience boosts retrieval), Token-Economic Cognitive Budget (UBI + cost-per-save incentivizes novel memories), Surprisal Gate (vector-based novelty scoring). Full SQLite + Supabase parity with auto-migration 42. Hybrid scoring: `0.65 × similarity + 0.25 × activation + 0.10 × |valence|`. All features opt-out via env. **Post-review hardening:** 8 architectural fixes including delta-based concurrent budget writes, energy-weighted valence propagation, and anti-exploit budget decoupling. Graceful degradation: budget exhaustion warns but never blocks.
-- ⚡ **v8.0.0 — Synapse Engine:** Pure, storage-agnostic multi-hop graph propagation engine replaces the legacy SQL-coupled spreading activation. O(T × M) bounded ACT-R energy propagation with dampened fan effect, asymmetric bidirectional flow, cyclic loop prevention, and sigmoid normalization. Full integration into both SQLite and Supabase backends. 5 new config knobs. Battle-hardened with NaN guards, config clamping, non-fatal enrichment, and 16 passing tests. **Memory search now follows the causal graph, not just keywords.** → [Synapse Engine](#synapse-engine-v80)
-- 🧠 **v7.8.x — Cognitive Architecture:** Episodic-to-Semantic consolidation (Hebbian learning), ACT-R Spreading Activation with multi-hop causal reasoning, Uncertainty-Aware Rejection Gate, and Dynamic Fast Weight Decay. Validated by **LoCoMo-Plus benchmark**. → [Cognitive Architecture](#cognitive-architecture-v78)
-- 🌐 **v7.7.0 — Cloud-Native SSE Transport:** Full unauthenticated and authenticated Server-Sent Events MCP support for seamless network deployments.
-- 🩺 **v7.5.0 — Intent Health Dashboard + Security Hardening:** Real-time 0–100 project health scoring (staleness × TODO load × decisions). 10 XSS injection vectors patched. Algorithm hardened with NaN guards and score ceiling.
-- ⚔️ **v7.4.0 — Adversarial Evaluation:** Split-brain anti-sycophancy pipeline. Generator and evaluator in isolated roles with evidence-bound findings.
-- 🏭 **v7.3.x — Dark Factory + Stability:** Fail-closed 3-gate execution pipeline. Dashboard stability and verification diagnostics.
+- 🔒 **v9.0.5 — JWKS Auth Security Hardening:** JWT audience/issuer claim validation (`PRISM_JWT_AUDIENCE`, `PRISM_JWT_ISSUER`), structured error logging for JWT failures, typed `PrismAuthenticatedRequest` interface, 11 new JWKS unit tests, Smithery server card fix. Vendor-neutral — tested with Auth0, AgentLair, Keycloak, and custom JWKS endpoints.
+- 🧠 **v9.0.0 — Autonomous Cognitive OS:** Token-Economic Reinforcement Learning (Surprisal Gate + Cognitive Budget), Affect-Tagged Memory (valence-scored retrieval), and Episodic→Semantic Consolidation. Your agents learn compression and develop intuition. → [Cognitive OS](#-autonomous-cognitive-os-v90)
+- 🧠 **v7.8.0 — Cognitive Architecture:** Episodic-to-Semantic memory consolidation (Hebbian learning), ACT-R Spreading Activation with multi-hop causal reasoning, Uncertainty-Aware Rejection Gate, and Dynamic Fast Weight Decay. → [Cognitive Architecture](#-cognitive-architecture-v78)
+- 🌐 **v7.7.0 — Cloud-Native SSE Transport:** Full Server-Sent Events MCP support for seamless network deployments.
+- ⚔️ **v7.4.0 — Adversarial Evaluation:** Split-brain anti-sycophancy pipeline with evidence-bound findings.
 
 👉 **[Full release history → CHANGELOG.md](CHANGELOG.md)** · **[ROADMAP →](ROADMAP.md)**
 
 ---
 
-## How Prism Compares
+## ⚔️ How Prism Compares
 
 Standard memory servers (like Mem0, Zep, or the baseline Anthropic MCP) act as passive filing cabinets — they wait for the LLM to search them. **Prism is an active cognitive architecture.** Designed specifically for the **Model Context Protocol (MCP)**, Prism doesn't just store vectors — it consolidates experience into principles, traverses causal graphs for multi-hop reasoning, and rejects queries it can't confidently answer.
 
@@ -848,7 +789,7 @@ Every other AI coding pipeline has a fatal flaw: it asks the same model that wro
 
 ---
 
-## Tool Reference
+## 🔧 Tool Reference
 
 Prism ships 30+ tools, but **90% of your workflow uses just three:**
 
@@ -1030,11 +971,9 @@ Requires `PRISM_DARK_FACTORY_ENABLED=true`.
 | `PRISM_ACTR_WEIGHT_ACTIVATION` | No | Composite score ACT-R activation weight (default: `0.3`) |
 | `PRISM_ACTR_ACCESS_LOG_RETENTION_DAYS` | No | Days before access logs are pruned by background scheduler (default: `90`) |
 | `PRISM_DARK_FACTORY_ENABLED` | No | `"true"` to enable Dark Factory autonomous pipeline tools (`session_start_pipeline`, `session_check_pipeline_status`, `session_abort_pipeline`) |
-| `PRISM_SYNAPSE_ENABLED` | No | `"true"` (default) to enable Synapse Engine graph propagation in search results |
-| `PRISM_SYNAPSE_ITERATIONS` | No | Propagation iterations (default: `3`). Higher = deeper graph traversal |
-| `PRISM_SYNAPSE_SPREAD_FACTOR` | No | Energy decay multiplier per hop (default: `0.8`). Range: 0.0–1.0 |
-| `PRISM_SYNAPSE_LATERAL_INHIBITION` | No | Max nodes returned by Synapse (default: `7`, min: `1`) |
-| `PRISM_SYNAPSE_SOFT_CAP` | No | Max candidate pool size during propagation (default: `20`, min: `1`) |
+| `PRISM_JWKS_URI` | No | JWKS endpoint URL for vendor-neutral JWT auth (e.g., `https://your-tenant.auth0.com/.well-known/jwks.json`) |
+| `PRISM_JWT_AUDIENCE` | No | Expected JWT `aud` claim — prevents cross-service token confusion |
+| `PRISM_JWT_ISSUER` | No | Expected JWT `iss` claim — validates token origin |
 
 </details>
 
@@ -1062,11 +1001,10 @@ Prism is a **stdio-based MCP server** that manages persistent agent memory. Here
 │  └──────┬───────┘  └──────────────┘  └────────────────┘  │
 │         ↕                                                │
 │  ┌────────────────────────────────────────────────────┐  │
-│  │  Cognitive Engine (v8.0)                           │  │
-│  │  • Synapse Engine (pure multi-hop propagation)    │  │
+│  │  Cognitive Engine (v7.8)                           │  │
+│  │  • ACT-R Spreading Activation (multi-hop)         │  │
 │  │  • Episodic → Semantic Consolidation (Hebbian)    │  │
 │  │  • Uncertainty-Aware Rejection Gate               │  │
-│  │  • LoCoMo-Plus Benchmark Validation               │  │
 │  │  • Dynamic Fast Weight Decay (dual-rate)          │  │
 │  │  • HDC Cognitive Routing (XOR binding)            │  │
 │  └──────┬─────────────────────────────────────────────┘  │
@@ -1110,7 +1048,7 @@ Prism is a **stdio-based MCP server** that manages persistent agent memory. Here
 
 ### Auto-Load Architecture
 
-Each MCP client has its own mechanism for ensuring Prism context loads on session start. See the platform-specific [Setup Guides](#setup-guides) above for detailed instructions:
+Each MCP client has its own mechanism for ensuring Prism context loads on session start. See the platform-specific [Setup Guides](#-setup-guides) above for detailed instructions:
 
 - **Claude Code** — Lifecycle hooks (`SessionStart` / `Stop`)
 - **Gemini / Antigravity** — Three-layer architecture (User Rules + AGENTS.md + Startup Skill)
@@ -1121,7 +1059,7 @@ All platforms benefit from the **server-side fallback** (v5.2.1): if `session_lo
 
 ---
 
-## Scientific Foundation
+## 🧬 Scientific Foundation
 
 Prism has evolved from smart session logging into a **cognitive memory architecture** — grounded in real research, not marketing. Every retrieval decision is backed by peer-reviewed models from cognitive psychology, neuroscience, and distributed computing.
 
@@ -1155,25 +1093,21 @@ Prism has evolved from smart session logging into a **cognitive memory architect
 | **v7.8** | Multi-Hop Causal Reasoning — spreading activation traverses `caused_by`/`led_to` edges with damped fan effect (`1/ln(fan+e)`) and lateral inhibition | ACT-R spreading activation (Anderson), Collins & Loftus (1975) | ✅ Shipped |
 | **v7.8** | Uncertainty-Aware Rejection Gate — dual-signal (similarity floor + gap distance) safety layer prevents hallucination from low-confidence retrievals | Metacognition research, uncertainty quantification | ✅ Shipped |
 | **v7.8** | Dynamic Fast Weight Decay — `is_rollup` semantic nodes decay 50% slower (`ageModifier = 0.5`) than episodic entries, creating Long-Term Context anchors | ACT-R base-level activation with differential decay rates | ✅ Shipped |
-| **v7.8** | LoCoMo Benchmark Harness — deterministic integration suite (`tests/benchmarks/locomo.ts`, 20 assertions) benchmarking multi-hop compaction structures via `MockLLM` | Long-Context Memory evaluation (cognitive benchmarking) | ✅ Shipped |
-| **v7.8** | LoCoMo-Plus Benchmark — 16-assertion suite (`tests/benchmarks/locomo-plus.ts`) adapted from arXiv 2602.10715 validating cue–trigger semantic disconnect bridging via graph traversal and Hebbian consolidation; reports Precision@1/3/5/10 and MRR | LoCoMo-Plus (Li et al., ARR 2026), cue–trigger disconnect research | ✅ Shipped |
-| **v9.0** | Affect-Tagged Memory — valence-weighted retrieval; emotional salience boosts recall | Affect-modulated retrieval (neuroscience), Somatic marker hypothesis (Damasio) | ✅ Shipped |
-| **v9.0** | Token-Economic Cognitive Budget — UBI + cost-per-save token economy | Behavioral economics, bounded rationality (Simon) | ✅ Shipped |
-| **v9.0** | Surprisal Gate — novelty-based cost multiplier (high surprisal = cheap storage) | Bayesian surprise, predictive coding (Friston) | ✅ Shipped |
-| **v10+** | Zero-Search Retrieval — no index, no ANN, just ask the vector | Holographic Reduced Representations | 🔭 Horizon |
+| **v7.x** | Affect-Tagged Memory — sentiment shapes what gets recalled | Affect-modulated retrieval (neuroscience) | 🔭 Horizon |
+| **v8+** | Zero-Search Retrieval — no index, no ANN, just ask the vector | Holographic Reduced Representations | 🔭 Horizon |
 
-> Informed by Anderson's ACT-R (Adaptive Control of Thought—Rational), Collins & Loftus spreading activation networks (1975), Kanerva's SDM (1988), Hebb's learning rule, Li et al. LoCoMo-Plus (ARR 2026), and LeCun's "Why AI Systems Don't Learn" (Dupoux, LeCun, Malik).
+> Informed by Anderson's ACT-R (Adaptive Control of Thought—Rational), Collins & Loftus spreading activation networks (1975), Kanerva's SDM (1988), Hebb's learning rule, and LeCun's "Why AI Systems Don't Learn" (Dupoux, LeCun, Malik).
 
 ---
 
-## Milestones & Roadmap
+## 📦 Milestones & Roadmap
 
-> **Current: v9.0.0** — Autonomous Cognitive OS ([CHANGELOG](CHANGELOG.md))
+> **Current: v9.0.5** — JWKS Auth Security Hardening ([CHANGELOG](CHANGELOG.md))
 
 | Release | Headline |
 |---------|----------|
-| **v9.0** | 🧠 Autonomous Cognitive OS — Affect-Tagged Memory (valence engine), Token-Economic Cognitive Budget, Surprisal Gate |
-| **v8.0** | ⚡ Synapse Engine — Pure multi-hop GraphRAG propagation, storage-agnostic, NaN-hardened, `[🌐 Synapse]` discovery tags |
+| **v9.0.5** | 🔒 JWKS Auth Security Hardening — audience/issuer validation, JWT failure logging, typed agent identity |
+| **v9.0** | 🧠 Autonomous Cognitive OS — Surprisal Gate, Cognitive Budget, Affect-Tagged Memory |
 | **v7.8** | 🧠 Cognitive Architecture — Hebbian consolidation, multi-hop reasoning, rejection gate, dynamic decay |
 | **v7.7** | 🌐 Cloud-Native SSE Transport |
 | **v7.5** | 🩺 Intent Health Dashboard + Security Hardening |
@@ -1186,14 +1120,13 @@ Prism has evolved from smart session logging into a **cognitive memory architect
 | **v6.2** | 🧩 Synthesize & Prune |
 
 ### Future Tracks
-- **v9.1: Predictive Push Memory** — Proactive context injection before the agent even asks — anticipating what it will need next.
-- **v9.4: Counterfactual Memory Branches** — "What if" reasoning over alternative decision paths.
-- **v10+: Zero-Search Retrieval** — Direct vector-addressed recall via Holographic Reduced Representations.
+- **v7.x: Affect-Tagged Memory** — Recall prioritization improves by weighting memories with affective/contextual valence.
+- **v8+: Zero-Search Retrieval** — Direct vector-addressed recall reduces retrieval indirection.
 
 👉 **[Full ROADMAP.md →](ROADMAP.md)**
 
 
-## Troubleshooting FAQ
+## ❓ Troubleshooting FAQ
 
 **Q: Why is the dashboard project selector stuck on "Loading projects..."?**
 A: Fixed in v7.3.3. The root cause was a multi-layer quote-escaping trap in the `abortPipeline` onclick handler that generated a `SyntaxError` in the browser, silently killing the entire dashboard IIFE. Update to v7.3.3+ (`npx -y prism-mcp-server`). If still stuck, check that Supabase env values are properly set (unresolved placeholders like `${SUPABASE_URL}` cause `/api/projects` to return empty). Prism auto-falls back to local SQLite when Supabase is misconfigured.
@@ -1217,7 +1150,7 @@ A: Run `npm run build && npm test`, then open the Mind Palace dashboard (`localh
 - **MCP client race conditions.** Some MCP clients may not finish tool enumeration before the model generates its first response, causing transient `unknown_tool` errors. This is a client-side timing issue — Prism's server completes the MCP handshake in ~60ms. Workaround: the server-side auto-push fallback and the startup skill's retry logic.
 - **No real-time sync without Supabase.** Local SQLite mode is single-machine only. Multi-device or team sync requires a Supabase backend.
 - **Embedding quality varies by provider.** Gemini `text-embedding-004` and OpenAI `text-embedding-3-small` produce high-quality 768-dim vectors. Prism passes `dimensions: 768` via the Matryoshka API for OpenAI models (native output is 1536-dim; this truncation is lossless and outperforms ada-002 at full 1536 dims). Ollama embeddings (e.g., `nomic-embed-text`) are usable but may reduce retrieval accuracy.
-- **Dashboard is HTTP-only.** The Mind Palace dashboard at `localhost:3000` does not support HTTPS. For remote access, use a reverse proxy (nginx/Caddy) or SSH tunnel. Basic auth is available via `PRISM_DASHBOARD_USER` / `PRISM_DASHBOARD_PASS`.
+- **Dashboard is HTTP-only.** The Mind Palace dashboard at `localhost:3000` does not support HTTPS. For remote access, use a reverse proxy (nginx/Caddy) or SSH tunnel. Basic auth is available via `PRISM_DASHBOARD_USER` / `PRISM_DASHBOARD_PASS`. JWKS JWT auth is available via `PRISM_JWKS_URI` for agent-native authentication (works with Auth0, AgentLair ([llms.txt](https://agentlair.com/llms.txt)), Keycloak, Cognito, or any standard JWKS endpoint).
 - **Long-lived clients can accumulate zombie processes.** MCP clients that run for extended periods (e.g., Claude CLI) may leave orphaned Prism server processes. The lifecycle manager detects true orphans (PPID=1) but allows coexistence for active parent processes. Use `PRISM_INSTANCE` to isolate instances across clients.
 - **Migration is one-way.** Universal Import ingests sessions *into* Prism but does not export back to Claude/Gemini/OpenAI formats. Use `session_export_memory` for portable JSON/Markdown export, or the `vault` format for Obsidian/Logseq-compatible `.zip` archives.
 - **Export ceiling at 10,000 ledger entries.** The `session_export_memory` tool and the dashboard export button cap vault/JSON exports at 10,000 entries per project as an OOM guard. Projects exceeding this limit should use per-project exports and time-based filtering to stay within the ceiling. This limit does not affect search or context loading.
@@ -1225,33 +1158,10 @@ A: Run `npm run build && npm test`, then open the Mind Palace dashboard (`localh
 
 ---
 
-## Enterprise & Commercial Support
-
-Prism is the **cognitive infrastructure layer** for production AI agent deployments. If your organization is building agent-powered products, we offer:
-
-### 🏢 Enterprise Integration
-- **Dedicated integration engineering** — Custom deployment into your existing agent stack (LangChain, LlamaIndex, CrewAI, AutoGen, custom MCP pipelines)
-- **On-premises deployment** — Air-gapped installations with full SQLite local mode, zero cloud dependency
-- **SSO & RBAC** — Enterprise authentication and role-based access control for multi-team Hivemind deployments
-- **SLA-backed support** — Priority issue resolution, architecture review, and upgrade planning
-
-### 🔬 Research & Institutional Partnerships
-- **Academic collaborations** — Prism's cognitive architecture is grounded in peer-reviewed research (ACT-R, Hebbian learning, SDM, HDC). We partner with research labs working on agent memory, cognitive modeling, and neurosymbolic AI.
-- **Grant-funded integrations** — We work with institutions applying for NSF, DARPA, or EU Horizon grants that require production-grade agent memory infrastructure.
-
-### 📬 Contact
-- **Enterprise inquiries:** [enterprise@prism-mcp.dev](mailto:enterprise@prism-mcp.dev)
-- **Partnership proposals:** [partnerships@prism-mcp.dev](mailto:partnerships@prism-mcp.dev)
-- **GitHub Issues:** [github.com/dcostenco/prism-mcp/issues](https://github.com/dcostenco/prism-mcp/issues) (community support)
-
-> 💡 **Open Source commitment:** Prism MCP remains MIT-licensed and free for individual developers, startups, and research teams. Enterprise services fund continued open-source development.
-
----
-
 ## License
 
 MIT
 
 ---
 
-<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, enterprise AI agent infrastructure, autonomous cognitive OS, affect-tagged memory, valence engine, cognitive budget, surprisal gate</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</sub>

package/dist/config.js

@@ -78,10 +78,7 @@ export const VOYAGE_API_KEY = process.env.VOYAGE_API_KEY;
 //
 // Set PRISM_STORAGE=local to use SQLite (once implemented).
 // Set PRISM_STORAGE=supabase to use Supabase REST API (default).
-// NOTE: This constant captures the env-var snapshot at import time.
-// The actual storage backend decision is made in storage/index.ts,
-// which consults prism-config.db first, then process.env, then defaults to "local".
-export const PRISM_STORAGE = process.env.PRISM_STORAGE || "local";
+export const PRISM_STORAGE = process.env.PRISM_STORAGE || "supabase";
 // Logged at debug level — see debug() at bottom of file
 // ─── Optional: Supabase (Session Memory Module) ───────────────
 // When both SUPABASE_URL and SUPABASE_KEY are set, session memory tools
@@ -139,22 +136,8 @@ export const PRISM_DEBUG_LOGGING = process.env.PRISM_DEBUG_LOGGING === "true";
 // The role parameter on existing tools (session_save_ledger, etc.)
 // is always available regardless of this flag — adding a parameter
 // doesn't increase tool count.
-//
-// SOURCE OF TRUTH: The Mind Palace dashboard (Settings → Hivemind Mode)
-// persists this flag to prism-config.db via getSettingSync() at call time.
-//
-// ⚠️ IMPORTANT: This _ENV constant captures ONLY the env-var fallback.
-// config.ts is evaluated at ESM import time, BEFORE initConfigStorage()
-// populates the settings cache. Use getSettingSync("hivemind_enabled",
-// String(PRISM_ENABLE_HIVEMIND_ENV)) at each call site for the live value.
-export const PRISM_ENABLE_HIVEMIND_ENV = process.env.PRISM_ENABLE_HIVEMIND === "true";
-// ─── v3.0: Task Router Feature Flag ──────────────────────────
-// Routes tasks to the local Claw agent when enabled.
-// SOURCE OF TRUTH: dashboard (Settings → Task Router) → prism-config.db.
-// Same _ENV pattern: use getSettingSync() at call sites.
-// REMOVED: PRISM_TASK_ROUTER_ENABLED used to call getSettingSync() at import time,
-// which always returned the fallback due to the ESM race condition (settingsCache=null).
-// Use PRISM_TASK_ROUTER_ENABLED_ENV (line ~368) and getSettingSync() at call sites instead.
+// Set PRISM_ENABLE_HIVEMIND=true to unlock the Agent Registry tools.
+export const PRISM_ENABLE_HIVEMIND = process.env.PRISM_ENABLE_HIVEMIND === "true";
 // ─── v4.1: Auto-Load Projects ────────────────────────────────
 // Auto-load is configured exclusively via the Mind Palace dashboard
 // ("Auto-Load Projects" checkboxes in Settings). The setting is stored
@@ -279,43 +262,9 @@ export const PRISM_VERIFICATION_DEFAULT_SEVERITY = (process.env.PRISM_VERIFICATI
 // ─── v7.3: Dark Factory Orchestration ─────────────────────────
 // Autonomous pipeline runner: PLAN → EXECUTE → VERIFY → iterate.
 // Opt-in because it executes LLM calls in the background.
-/** Master switch for the Dark Factory background runner.
- *  ⚠️ ENV-only fallback. Use getSettingSync("dark_factory_enabled",
- *  String(PRISM_DARK_FACTORY_ENABLED_ENV)) at call sites. */
-export const PRISM_DARK_FACTORY_ENABLED_ENV = process.env.PRISM_DARK_FACTORY_ENABLED === "true"; // Opt-in
+/** Master switch for the Dark Factory background runner. */
+export const PRISM_DARK_FACTORY_ENABLED = process.env.PRISM_DARK_FACTORY_ENABLED === "true"; // Opt-in
 /** Poll interval for the runner loop (ms). Default: 30s. */
 export const PRISM_DARK_FACTORY_POLL_MS = parseInt(process.env.PRISM_DARK_FACTORY_POLL_MS || "30000", 10);
 /** Default max wall-clock time per pipeline (ms). Default: 15 minutes. */
 export const PRISM_DARK_FACTORY_MAX_RUNTIME_MS = parseInt(process.env.PRISM_DARK_FACTORY_MAX_RUNTIME_MS || "900000", 10);
-// ─── v8.0: Synapse — Spreading Activation Engine ──────────────
-// Multi-hop energy propagation through memory_links graph.
-// Enabled by default. Set PRISM_SYNAPSE_ENABLED=false to fall back
-// to 1-hop candidateScopedSpreadingActivation (v7.0 behavior).
-/** Master switch for the Synapse engine. Enabled by default (opt-out). */
-export const PRISM_SYNAPSE_ENABLED = (process.env.PRISM_SYNAPSE_ENABLED ?? "true") !== "false";
-/** Number of propagation iterations (depth). Higher = deeper traversal, more latency. (Default: 3) */
-export const PRISM_SYNAPSE_ITERATIONS = parseInt(process.env.PRISM_SYNAPSE_ITERATIONS || "3", 10);
-/** Energy attenuation per hop. Must be < 1.0 for convergence. (Default: 0.8) */
-export const PRISM_SYNAPSE_SPREAD_FACTOR = parseFloat(process.env.PRISM_SYNAPSE_SPREAD_FACTOR || "0.8");
-/** Hard cap on final output nodes (lateral inhibition). (Default: 7) */
-export const PRISM_SYNAPSE_LATERAL_INHIBITION = parseInt(process.env.PRISM_SYNAPSE_LATERAL_INHIBITION || "7", 10);
-/** Soft cap on active nodes per iteration (prevents explosion). (Default: 20) */
-export const PRISM_SYNAPSE_SOFT_CAP = parseInt(process.env.PRISM_SYNAPSE_SOFT_CAP || "20", 10);
-// ─── v9.0: Affect-Tagged Memory (Valence Engine) ─────────────
-// Derives emotional valence from experience events and uses
-// Affective Salience (|valence| boosts retrieval) for ranking.
-/** Master switch for affect-tagged memory. (Default: true) */
-export const PRISM_VALENCE_ENABLED = (process.env.PRISM_VALENCE_ENABLED ?? "true") !== "false";
-/** Weight of |valence| in hybrid scoring formula. (Default: 0.1) */
-export const PRISM_VALENCE_WEIGHT = parseFloat(process.env.PRISM_VALENCE_WEIGHT || "0.1");
-/** Average valence below this threshold triggers a UX warning. (Default: -0.3) */
-export const PRISM_VALENCE_WARNING_THRESHOLD = parseFloat(process.env.PRISM_VALENCE_WARNING_THRESHOLD || "-0.3");
-// ─── v9.0: Token-Economic RL (Cognitive Budget) ──────────────
-// Implements a strict token economy for agent memory operations.
-// Budget is persistent (stored in session_handoffs.cognitive_budget).
-/** Master switch for the cognitive budget system. (Default: true) */
-export const PRISM_COGNITIVE_BUDGET_ENABLED = (process.env.PRISM_COGNITIVE_BUDGET_ENABLED ?? "true") !== "false";
-/** Initial budget size per project in tokens. (Default: 2000) */
-export const PRISM_COGNITIVE_BUDGET_SIZE = parseInt(process.env.PRISM_COGNITIVE_BUDGET_SIZE || "2000", 10);
-/** Master switch for the surprisal gate. (Default: true) */
-export const PRISM_SURPRISAL_GATE_ENABLED = (process.env.PRISM_SURPRISAL_GATE_ENABLED ?? "true") !== "false";

package/dist/darkfactory/runner.js

@@ -599,13 +599,6 @@ async function runnerTick() {
             const harnessPath = path.join(path.resolve(spec.workingDirectory), 'verification_harness.json');
             if (fs.existsSync(harnessPath)) {
                 try {
-                    // MED-5 FIX: Guard against LLM-generated files that are malformed or
-                    // excessively large. Cap at 1MB to prevent heap exhaustion.
-                    const MAX_HARNESS_SIZE = 1_000_000;
-                    const stat = fs.statSync(harnessPath);
-                    if (stat.size > MAX_HARNESS_SIZE) {
-                        throw new Error(`Verification harness too large (${stat.size} bytes, max ${MAX_HARNESS_SIZE}). Possible corrupt LLM output.`);
-                    }
                     const rawHarness = fs.readFileSync(harnessPath, 'utf8');
                     const harnessData = JSON.parse(rawHarness);
                     // GAP-5 fix: Persist the harness so CLI drift detection works for DarkFactory runs

package/dist/darkfactory/safetyController.js

@@ -45,16 +45,8 @@ export class SafetyController {
         if (!spec.workingDirectory)
             return true;
         // Resolve symlinks and protect against ../ escapes.
-        let resolvedTarget = path.resolve(targetPath);
-        let resolvedWorkspace = path.resolve(spec.workingDirectory);
-        // EDGE-2 FIX: macOS (HFS+/APFS) and Windows (NTFS) use case-insensitive
-        // filesystems by default. Without case normalization, "/App/Workspace"
-        // and "/app/workspace" are treated as different paths — allowing a scope
-        // escape via case mismatch.
-        if (process.platform === 'darwin' || process.platform === 'win32') {
-            resolvedTarget = resolvedTarget.toLowerCase();
-            resolvedWorkspace = resolvedWorkspace.toLowerCase();
-        }
+        const resolvedTarget = path.resolve(targetPath);
+        const resolvedWorkspace = path.resolve(spec.workingDirectory);
         // Path Traversal Guard: A naive startsWith() check is vulnerable to
         // prefix collisions — e.g. /app/workspace-hacked passes startsWith('/app/workspace').
         // We require EITHER exact match OR the target starts with workspace + path separator.