prism-mcp-server 7.8.6 → 7.8.8

package/README.md

@@ -691,9 +691,9 @@ The Generator strips the `console.log`, resubmits, and the next `EVALUATE` retur
 
 ## 🆕 What's New
 
-> **Current release: v7.8.2 — Cognitive Architecture**
+> **Current release: v7.8.7 — Cognitive Architecture**
 
-- 🧠 **v7.8.0 — Cognitive Architecture:** The biggest leap forward yet. Moved beyond flat vector search into a true cognitive architecture inspired by human brain mechanics. Episodic-to-Semantic memory consolidation (Hebbian learning), ACT-R Spreading Activation with multi-hop causal reasoning, Uncertainty-Aware Rejection Gate (your agent can say "I don't know"), and Dynamic Fast Weight Decay (semantic memories outlive episodic chatter by 2×). **Your agents don't just remember; they learn.** → [Cognitive Architecture](#-cognitive-architecture-v78)
+- 🧠 **v7.8.x — Cognitive Architecture:** The biggest leap forward yet. Moved beyond flat vector search into a true cognitive architecture inspired by human brain mechanics. Episodic-to-Semantic memory consolidation (Hebbian learning), ACT-R Spreading Activation with multi-hop causal reasoning, Uncertainty-Aware Rejection Gate (your agent can say "I don't know"), and Dynamic Fast Weight Decay (semantic memories outlive episodic chatter by 2×). Validated by **LoCoMo-Plus benchmark** (arXiv 2602.10715) with Precision@K and MRR metrics. **Your agents don't just remember; they learn.** → [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.
@@ -968,6 +968,7 @@ Prism is a **stdio-based MCP server** that manages persistent agent memory. Here
 │  │  • 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)            │  │
 │  └──────┬─────────────────────────────────────────────┘  │
@@ -1056,16 +1057,18 @@ 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 |
 | **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, 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, Li et al. LoCoMo-Plus (ARR 2026), and LeCun's "Why AI Systems Don't Learn" (Dupoux, LeCun, Malik).
 
 ---
 
 ## 📦 Milestones & Roadmap
 
-> **Current: v7.8.2** — Cognitive Architecture ([CHANGELOG](CHANGELOG.md))
+> **Current: v7.8.7** — Cognitive Architecture ([CHANGELOG](CHANGELOG.md))
 
 | Release | Headline |
 |---------|----------|

package/dist/dashboard/ui.js

@@ -1253,7 +1253,9 @@ Example:\n## Dev Rules\n- Always write tests first\n- Use TypeScript strict mode
               onchange="onEmbeddingProviderChange(this.value)">
               <option value="auto">🔄 Auto (same as Text Provider)</option>
               <option value="gemini">🔵 Gemini</option>
-              <option value="openai">🟢 OpenAI / Ollama</option>
+              <option value="openai">🟢 OpenAI</option>
+              <option value="voyage">🔮 Voyage AI</option>
+              <option value="ollama">🟠 Ollama (Local)</option>
             </select>
           </div>
 
@@ -1261,7 +1263,7 @@ Example:\n## Dev Rules\n- Always write tests first\n- Use TypeScript strict mode
           <div id="anthropic-embed-warning" style="display:none;margin-top:0.5rem;padding:0.5rem 0.75rem;background:rgba(251,146,60,0.1);border:1px solid rgba(251,146,60,0.3);border-radius:6px;font-size:0.78rem;color:#fb923c;line-height:1.5">
             ⚠️ <strong>Anthropic has no native embedding API.</strong>
             Auto mode will route embeddings to <strong>Gemini</strong>.
-            Set Embedding Provider to <strong>OpenAI / Ollama</strong> to use a local model (e.g. <code>nomic-embed-text</code>).
+            Set Embedding Provider to <strong>Ollama (Local)</strong> for free local embeddings, or <strong>Voyage AI</strong> for the Anthropic-recommended cloud pairing.
           </div>
 
           <!-- OpenAI embedding model field (shown when embedding_provider = openai) -->
@@ -1269,7 +1271,7 @@ Example:\n## Dev Rules\n- Always write tests first\n- Use TypeScript strict mode
             <div class="setting-row">
               <div>
                 <div class="setting-label">Embedding Model</div>
-                <div class="setting-desc">Must output 768 dims. Ollama: nomic-embed-text · OpenAI: text-embedding-3-small</div>
+                <div class="setting-desc">Must output 768 dims. Default: text-embedding-3-small</div>
               </div>
               <input type="text" id="input-openai-embedding-model"
                 placeholder="text-embedding-3-small"
@@ -1279,9 +1281,61 @@ Example:\n## Dev Rules\n- Always write tests first\n- Use TypeScript strict mode
             </div>
           </div>
 
+          <!-- Voyage AI embedding fields (shown when embedding_provider = voyage) -->
+          <div id="embed-fields-voyage" style="display:none">
+            <div class="setting-row">
+              <div>
+                <div class="setting-label">Voyage API Key</div>
+                <div class="setting-desc">Get one free at <a href="https://dash.voyageai.com" target="_blank" style="color:var(--accent)">dash.voyageai.com</a></div>
+              </div>
+              <input type="password" id="input-voyage-api-key"
+                placeholder="pa-…"
+                style="padding: 0.2rem 0.5rem; background: var(--bg-hover); color: var(--text-primary); border: 1px solid var(--border-color); border-radius: 4px; font-size: 0.85rem; font-family: var(--font-mono); width: 180px;"
+                onchange="saveBootSetting('VOYAGE_API_KEY', this.value)"
+                oninput="clearTimeout(this._pv); var self=this; this._pv=setTimeout(function(){saveBootSetting('VOYAGE_API_KEY',self.value)},800)" />
+            </div>
+            <div class="setting-row">
+              <div>
+                <div class="setting-label">Voyage Model</div>
+                <div class="setting-desc">voyage-code-3 (code) · voyage-3 (general). Both MRL → 768 dims.</div>
+              </div>
+              <input type="text" id="input-voyage-model"
+                placeholder="voyage-code-3"
+                style="padding: 0.2rem 0.5rem; background: var(--bg-hover); color: var(--text-primary); border: 1px solid var(--border-color); border-radius: 4px; font-size: 0.85rem; font-family: var(--font-mono); width: 160px;"
+                onchange="saveBootSetting('voyage_model', this.value)"
+                oninput="clearTimeout(this._pvm); var self=this; this._pvm=setTimeout(function(){saveBootSetting('voyage_model',self.value)},800)" />
+            </div>
+          </div>
+
+          <!-- Ollama embedding fields (shown when embedding_provider = ollama) -->
+          <div id="embed-fields-ollama" style="display:none">
+            <div class="setting-row">
+              <div>
+                <div class="setting-label">Ollama Base URL</div>
+                <div class="setting-desc">Where Ollama is running locally</div>
+              </div>
+              <input type="text" id="input-ollama-base-url"
+                placeholder="http://localhost:11434"
+                style="padding: 0.2rem 0.5rem; background: var(--bg-hover); color: var(--text-primary); border: 1px solid var(--border-color); border-radius: 4px; font-size: 0.85rem; font-family: var(--font-mono); width: 220px;"
+                onchange="saveBootSetting('ollama_base_url', this.value)"
+                oninput="clearTimeout(this._pou); var self=this; this._pou=setTimeout(function(){saveBootSetting('ollama_base_url',self.value)},800)" />
+            </div>
+            <div class="setting-row">
+              <div>
+                <div class="setting-label">Embedding Model</div>
+                <div class="setting-desc">Must output 768 dims. <code>nomic-embed-text</code> recommended.</div>
+              </div>
+              <input type="text" id="input-ollama-model"
+                placeholder="nomic-embed-text"
+                style="padding: 0.2rem 0.5rem; background: var(--bg-hover); color: var(--text-primary); border: 1px solid var(--border-color); border-radius: 4px; font-size: 0.85rem; font-family: var(--font-mono); width: 180px;"
+                onchange="saveBootSetting('ollama_model', this.value)"
+                oninput="clearTimeout(this._pom); var self=this; this._pom=setTimeout(function(){saveBootSetting('ollama_model',self.value)},800)" />
+            </div>
+          </div>
+
           <div style="margin-top:1rem;padding:0.6rem 0.8rem;background:rgba(139,92,246,0.08);border:1px solid rgba(139,92,246,0.2);border-radius:6px;font-size:0.78rem;color:var(--text-secondary);line-height:1.5">
-            💡 <strong>Cost-optimized setup:</strong> Text Provider → <code>Anthropic</code>, Embedding Provider → <code>OpenAI / Ollama</code>.<br>
-            Use Claude 3.5 Sonnet for reasoning &amp; <code>nomic-embed-text</code> (free, local) for embeddings.
+            💡 <strong>Zero-cost setup:</strong> Text Provider → <code>Anthropic</code>, Embedding Provider → <code>Ollama (Local)</code>.<br>
+            Use Claude for reasoning &amp; <code>nomic-embed-text</code> (free, local, 768-dim native) for embeddings.
           </div>
 
           <span class="setting-saved" id="savedToastProviders">Saved ✓</span>
@@ -3135,8 +3189,10 @@ function onTextProviderChange(value) {
 // Called when the EMBEDDING provider dropdown changes.
 function onEmbeddingProviderChange(value) {
     var textVal = document.getElementById('select-text-provider').value;
-    // Show the OpenAI embedding model field only when embedding=openai
+    // Show provider-specific fields based on the selected embedding provider
     document.getElementById('embed-fields-openai').style.display = value === 'openai' ? '' : 'none';
+    document.getElementById('embed-fields-voyage').style.display = value === 'voyage' ? '' : 'none';
+    document.getElementById('embed-fields-ollama').style.display = value === 'ollama' ? '' : 'none';
     refreshAnthropicWarning(textVal, value);
     saveBootSetting('embedding_provider', value);
 }
@@ -3174,7 +3230,17 @@ function loadAiProviderSettings() {
                     if (embedSel)
                         embedSel.value = embedProvider;
                     document.getElementById('embed-fields-openai').style.display = embedProvider === 'openai' ? '' : 'none';
+                    document.getElementById('embed-fields-voyage').style.display = embedProvider === 'voyage' ? '' : 'none';
+                    document.getElementById('embed-fields-ollama').style.display = embedProvider === 'ollama' ? '' : 'none';
                     refreshAnthropicWarning(textProvider, embedProvider);
+                    var vKey = document.getElementById('input-voyage-api-key');
+                    if (vKey) vKey.placeholder = s.VOYAGE_API_KEY ? '(key saved — paste to update)' : 'pa-…';
+                    var vMod = document.getElementById('input-voyage-model');
+                    if (vMod && s.voyage_model) vMod.value = s.voyage_model;
+                    var olUrl = document.getElementById('input-ollama-base-url');
+                    if (olUrl && s.ollama_base_url) olUrl.value = s.ollama_base_url;
+                    var olMod = document.getElementById('input-ollama-model');
+                    if (olMod && s.ollama_model) olMod.value = s.ollama_model;
                     gKey = document.getElementById('input-google-api-key');
                     if (gKey)
                         gKey.placeholder = s.GOOGLE_API_KEY ? '(key saved — paste to update)' : 'AIza…';

package/dist/utils/llm/adapters/ollama.js

@@ -0,0 +1,153 @@
+/**
+ * Ollama Adapter (v1.0 — nomic-embed-text)
+ * ─────────────────────────────────────────────────────────────────────────────
+ * PURPOSE:
+ *   Implements LLMProvider using Ollama's native /api/embed REST endpoint for
+ *   fully local, zero-cost text embeddings. No API key required — Ollama runs
+ *   on localhost.
+ *
+ * TEXT GENERATION:
+ *   This adapter is embeddings-only. generateText() throws an explicit error.
+ *   Set text_provider separately (anthropic, openai, or gemini).
+ *
+ * EMBEDDING DIMENSION PARITY (768 dims):
+ *   Prism's SQLite (sqlite-vec) and Supabase (pgvector) schemas define
+ *   embedding columns as EXACTLY 768 dimensions.
+ *
+ *   nomic-embed-text natively outputs 768 dims — zero truncation needed.
+ *   It is the recommended default local model for Prism.
+ *
+ * SUPPORTED MODELS (all confirmed 768-dim via Ollama):
+ *   nomic-embed-text     — 768 dims, 274MB, best quality/size trade-off ✅ DEFAULT
+ *   nomic-embed-text:v1.5 — 768 dims, 274MB, same (stable alias)
+ *
+ *   Models to AVOID with this adapter (wrong dim count):
+ *   mxbai-embed-large    — 1024 dims ❌  (use OpenAIAdapter instead)
+ *   all-minilm           — 384 dims  ❌
+ *   snowflake-arctic-embed — varies  ❌
+ *
+ * BATCH EMBEDDINGS:
+ *   Uses /api/embed (plural) which is the official Ollama batch endpoint
+ *   introduced in Ollama ≥ 0.3.0. Falls back gracefully for older versions.
+ *
+ * CONFIG KEYS (Prism dashboard "AI Providers" tab OR environment variables):
+ *   ollama_base_url   — Base URL of Ollama server (default: http://localhost:11434)
+ *   ollama_model      — Embedding model (default: nomic-embed-text)
+ *
+ * USAGE:
+ *   In the Prism dashboard, set:
+ *     embedding_provider = ollama
+ *   Optionally set ollama_base_url and ollama_model to override defaults.
+ *
+ * API REFERENCE:
+ *   https://github.com/ollama/ollama/blob/main/docs/api.md#generate-embeddings
+ */
+import { getSettingSync } from "../../../storage/configStorage.js";
+import { debugLog } from "../../logger.js";
+// ─── Constants ────────────────────────────────────────────────────────────────
+// Must match Prism's DB schema (sqlite-vec and pgvector column sizes).
+const EMBEDDING_DIMS = 768;
+// Generous character cap — nomic-embed-text has an 8192-token context window.
+const MAX_EMBEDDING_CHARS = 8000;
+const DEFAULT_BASE_URL = "http://localhost:11434";
+const DEFAULT_MODEL = "nomic-embed-text";
+// Connection retry settings — handles the common "forgot to start Ollama" race.
+const MAX_RETRIES = 2;
+const RETRY_DELAY_MS = 500;
+// ─── Adapter ─────────────────────────────────────────────────────────────────
+export class OllamaAdapter {
+    baseUrl;
+    model;
+    constructor() {
+        this.baseUrl = getSettingSync("ollama_base_url", DEFAULT_BASE_URL).replace(/\/$/, "");
+        this.model = getSettingSync("ollama_model", DEFAULT_MODEL);
+        debugLog(`[OllamaAdapter] Initialized — baseUrl=${this.baseUrl}, model=${this.model}`);
+    }
+    // ─── Text Generation (Not Supported) ────────────────────────────────────
+    async generateText(_prompt, _systemInstruction) {
+        throw new Error("OllamaAdapter does not support text generation. " +
+            "Set text_provider to 'anthropic', 'openai', or 'gemini' in the dashboard.");
+    }
+    // ─── Batch Embedding Generation ─────────────────────────────────────────
+    async generateEmbeddings(texts) {
+        if (!texts || texts.length === 0)
+            return [];
+        const model = this.model;
+        // Word-safe truncation — consistent with Voyage and OpenAI adapters.
+        const truncatedTexts = texts.map(text => {
+            if (text.length > MAX_EMBEDDING_CHARS) {
+                const cut = text.slice(0, MAX_EMBEDDING_CHARS);
+                const lastSpace = cut.lastIndexOf(" ");
+                return lastSpace > 0 ? cut.slice(0, lastSpace) : cut;
+            }
+            return text;
+        });
+        debugLog(`[OllamaAdapter] generateEmbeddings — model=${model}, count=${truncatedTexts.length}`);
+        // Retry loop — catches ECONNREFUSED when Ollama service hasn't started yet.
+        let response;
+        let lastError = null;
+        for (let attempt = 0; attempt <= MAX_RETRIES; attempt++) {
+            try {
+                response = await fetch(`${this.baseUrl}/api/embed`, {
+                    method: "POST",
+                    headers: { "Content-Type": "application/json" },
+                    body: JSON.stringify({ model, input: truncatedTexts }),
+                });
+                if (!response.ok) {
+                    const errorText = await response.text().catch(() => "unknown error");
+                    throw new Error(`[OllamaAdapter] /api/embed request failed — status=${response.status}: ${errorText}. ` +
+                        `Make sure Ollama is running (ollama serve) and '${model}' has been pulled (ollama pull ${model}).`);
+                }
+                // Success — break out of retry loop.
+                lastError = null;
+                break;
+            }
+            catch (err) {
+                lastError = err instanceof Error ? err : new Error(String(err));
+                const isNetworkError = lastError.message.includes("ECONNREFUSED") ||
+                    lastError.message.includes("fetch failed") ||
+                    lastError.message.includes("ECONNRESET");
+                if (isNetworkError && attempt < MAX_RETRIES) {
+                    debugLog(`[OllamaAdapter] Connection failed (attempt ${attempt + 1}/${MAX_RETRIES + 1}): ` +
+                        `${lastError.message.substring(0, 80)}. Retrying in ${RETRY_DELAY_MS}ms...`);
+                    await new Promise(resolve => setTimeout(resolve, RETRY_DELAY_MS));
+                    continue;
+                }
+                throw lastError;
+            }
+        }
+        if (lastError)
+            throw lastError;
+        const data = (await response.json());
+        const embeddings = data?.embeddings;
+        if (!Array.isArray(embeddings) || embeddings.length === 0) {
+            throw new Error(`[OllamaAdapter] Empty embeddings response from model '${model}'.`);
+        }
+        if (embeddings.length !== texts.length) {
+            throw new Error(`[OllamaAdapter] Response length mismatch — expected ${texts.length}, got ${embeddings.length}.`);
+        }
+        // Validate dimensions and slice if model returned > 768 (shouldn't happen
+        // with nomic-embed-text but guards against model swaps).
+        return embeddings.map((emb, i) => {
+            if (emb.length > EMBEDDING_DIMS) {
+                debugLog(`[OllamaAdapter] Embedding[${i}] has ${emb.length} dims — truncating to ${EMBEDDING_DIMS}. ` +
+                    `Consider using a model that natively outputs ${EMBEDDING_DIMS} dims (e.g. nomic-embed-text).`);
+                return emb.slice(0, EMBEDDING_DIMS);
+            }
+            if (emb.length !== EMBEDDING_DIMS) {
+                throw new Error(`[OllamaAdapter] Dimension mismatch at index ${i}: expected ${EMBEDDING_DIMS}, ` +
+                    `got ${emb.length}. Model '${model}' is not compatible with Prism's 768-dim schema. ` +
+                    `Use nomic-embed-text which natively outputs 768 dims.`);
+            }
+            return emb;
+        });
+    }
+    // ─── Single Embedding (delegates to batch) ───────────────────────────────
+    async generateEmbedding(text) {
+        if (!text || !text.trim()) {
+            throw new Error("[OllamaAdapter] generateEmbedding called with empty text.");
+        }
+        const results = await this.generateEmbeddings([text]);
+        return results[0];
+    }
+}

package/dist/utils/llm/factory.js

@@ -1,5 +1,5 @@
 /**
- * LLM Provider Factory (v4.5 — Voyage AI Embedding Support)
+ * LLM Provider Factory (v4.6 — Ollama Local Embedding Support)
  * ─────────────────────────────────────────────────────────────────────────────
  * PURPOSE:
  *   Single point of resolution for the active LLMProvider.
@@ -11,7 +11,7 @@
  *   Two independent settings control text and embedding routing:
  *
  *   text_provider      — "gemini" (default) | "openai" | "anthropic"
- *   embedding_provider — "auto" (default)   | "gemini" | "openai" | "voyage"
+ *   embedding_provider — "auto" (default)   | "gemini" | "openai" | "voyage" | "ollama"
  *
  *   When embedding_provider = "auto":
  *     * If text_provider is gemini or openai → use same provider for embeddings
@@ -24,8 +24,10 @@
  *   text_provider=openai,    embedding_provider=auto   → OpenAI+OpenAI
  *   text_provider=anthropic, embedding_provider=auto   → Claude+Gemini (auto-bridge)
  *   text_provider=anthropic, embedding_provider=voyage → Claude+Voyage (Anthropic-recommended)
- *   text_provider=anthropic, embedding_provider=openai → Claude+Ollama (cost-optimized)
+ *   text_provider=anthropic, embedding_provider=openai → Claude+OpenAI cloud embeddings
+ *   text_provider=anthropic, embedding_provider=ollama → Claude+Ollama (fully local, zero-cost)
  *   text_provider=gemini,    embedding_provider=voyage → Gemini+Voyage (mixed)
+ *   text_provider=gemini,    embedding_provider=ollama → Gemini+Ollama (hybrid cloud/local)
  *
  * SINGLETON + GRACEFUL DEGRADATION:
  *   Same as before — instance cached per process, errors fall back to Gemini.
@@ -44,6 +46,7 @@ import { GeminiAdapter } from "./adapters/gemini.js";
 import { OpenAIAdapter } from "./adapters/openai.js";
 import { AnthropicAdapter } from "./adapters/anthropic.js";
 import { VoyageAdapter } from "./adapters/voyage.js";
+import { OllamaAdapter } from "./adapters/ollama.js";
 import { TracingLLMProvider } from "./adapters/traced.js";
 // Module-level singleton — one composed provider per MCP server process.
 let providerInstance = null;
@@ -62,10 +65,12 @@ function buildEmbeddingAdapter(type) {
     // Note: "anthropic" is intentionally absent from this switch.
     // Anthropic has no embedding API, so it can never be an embedding provider.
     // The factory resolves "auto" away from "anthropic" before calling this.
-    // For Anthropic text users, "voyage" is the Anthropic-recommended pairing.
+    // For Anthropic text users, "voyage" is the recommended pairing;
+    // "ollama" is the fully local zero-cost alternative.
     switch (type) {
         case "openai": return new OpenAIAdapter();
         case "voyage": return new VoyageAdapter();
+        case "ollama": return new OllamaAdapter();
         case "gemini":
         default: return new GeminiAdapter();
     }
@@ -90,10 +95,15 @@ export function getLLMProvider() {
     let embedType = getSettingSync("embedding_provider", "auto");
     if (embedType === "auto") {
         if (process.env.VOYAGE_API_KEY) {
-            // If Voyage is available, use it as the default embedding provider
-            // since voyage-code-3 strongly outperforms general embeddings on code contexts.
+            // Voyage takes first priority when available — voyage-code-3 strongly
+            // outperforms general embeddings on code contexts.
             embedType = "voyage";
         }
+        else if (process.env.OLLAMA_HOST || process.env.OLLAMA_BASE_URL) {
+            // Ollama is second priority: fully local, zero-cost, zero-latency.
+            // Activated when OLLAMA_HOST or OLLAMA_BASE_URL env var is set.
+            embedType = "ollama";
+        }
         else {
             // Anthropic has no embedding API — auto-bridge to Gemini.
             // For all other text providers, use the same provider for embeddings.
@@ -101,9 +111,9 @@ export function getLLMProvider() {
             if (textType === "anthropic") {
                 console.error("[LLMFactory] text_provider=anthropic with embedding_provider=auto: " +
                     "routing embeddings to GeminiAdapter (Anthropic has no native embedding API). " +
-                    "For the Anthropic-recommended pairing, set embedding_provider=voyage in the dashboard " +
-                    "(voyage-code-3 supports 768-dim output via MRL). " +
-                    "Alternatively, set embedding_provider=openai to use Ollama/OpenAI.");
+                    "For the Anthropic-recommended pairing, set embedding_provider=voyage in the dashboard. " +
+                    "For a fully local, zero-cost option, set embedding_provider=ollama " +
+                    "(requires 'ollama pull nomic-embed-text').");
             }
         }
     }

package/dist/utils/llm/provider.js

@@ -16,6 +16,8 @@
  *   - gemini.ts    → Google Gemini (default; all methods including VLM)
  *   - openai.ts    → OpenAI Cloud + Ollama + LM Studio + vLLM
  *   - anthropic.ts → Anthropic Claude (VLM supported; embeddings unsupported)
+ *   - voyage.ts    → Voyage AI (embeddings only; Anthropic-recommended pairing)
+ *   - ollama.ts    → Ollama native /api/embed (embeddings only; fully local, zero-cost)
  *
  * FACTORY RESOLUTION:
  *   Never instantiate adapters directly. Always call:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "prism-mcp-server",
-  "version": "7.8.6",
+  "version": "7.8.8",
   "mcpName": "io.github.dcostenco/prism-mcp",
   "description": "The Mind Palace for AI Agents — a true Cognitive Architecture with Hebbian learning (episodic→semantic consolidation), ACT-R spreading activation (multi-hop causal reasoning), uncertainty-aware rejection gates (agents that know when they don't know), adversarial evaluation (anti-sycophancy), fail-closed Dark Factory pipelines, persistent memory (SQLite/Supabase), multi-agent Hivemind, time travel & visual dashboard. Zero-config local mode.",
   "module": "index.ts",