prism-mcp-server 4.2.0 → 4.3.0

package/README.md

@@ -42,7 +42,13 @@
 
 ---
 
-## What's New in v4.2.0 — Project Repo Registry 🗂️
+## What's New in v4.3.0 — The Bridge 🌉
+
+> **🧠 Active Behavioral Memory & IDE Sync**
+> Prism doesn't just log what happened—it learns. When an agent is corrected, the memory gains "Importance". Once an insight graduates (Importance >= 7), Prism can automatically sync it directly to your `.cursorrules` or `.clauderules` file, turning dynamic behavioral learnings into permanent, zero-token IDE enforcement.
+
+<details>
+<summary><strong>What's in v4.2.0 — Project Repo Registry 🗂️</strong></summary>
 
 | Feature | Description |
 |---|---|
@@ -50,6 +56,8 @@
 | 🔄 **Universal Auto-Load** | Auto-load projects via dynamic tool descriptions — works across all MCP clients (Claude, Cursor, Gemini, Antigravity) without lifecycle hooks. Dashboard is the sole source of truth. |
 | 🏠 **Dashboard-First Config** | Removed `PRISM_AUTOLOAD_PROJECTS` env var override. The Mind Palace dashboard is now the single source of truth for auto-load project configuration. |
 
+</details>
+
 <details>
 <summary><strong>What's in v4.1.0 — Auto-Migration & Multi-Instance 🔀</strong></summary>
 
@@ -690,6 +698,41 @@ The tool and dashboard button both call the same repair logic — the dashboard
 4. On `session_load_context`, high-importance corrections auto-surface as `[⚠️ BEHAVIORAL WARNINGS]`
 5. Agent sees warnings and avoids repeating past mistakes
 
+### v4.2 Knowledge Sync Rules — "The Bridge"
+
+Bridges **v4.0 Behavioral Memory** (graduated insights) with **v4.2 Project Registry** (repo paths) to physically write agent learnings into your project's IDE rules file.
+
+| Feature | Without Sync Rules | With `knowledge_sync_rules` |
+|---------|-------------------|----------------------------|
+| **Insight Visibility** | Only in Prism context injection | Persisted as static IDE context (`.cursorrules` / `.clauderules`) |
+| **Cross-Session** | Loaded per-session via tool call | Always-on — IDE reads rules file on every prompt |
+| **Agent Learning Loop** | Behavioral warnings during context load | Rules enforced even without Prism connected |
+| **Idempotency** | N/A | Sentinel markers ensure safe re-runs |
+| **User Control** | View in dashboard | User-maintained rules preserved; only sentinel block updated |
+
+**Syncing graduated insights:**
+
+```json
+{ "name": "knowledge_sync_rules", "arguments": {
+    "project": "my-app",
+    "target_file": ".cursorrules",
+    "dry_run": true
+}}
+```
+
+**How it works:**
+1. Fetches graduated insights (`importance >= 7`) from the ledger
+2. Formats them as markdown rules inside `<!-- PRISM:AUTO-RULES:START/END -->` sentinel markers
+3. Idempotently writes them into the target file at the project's configured `repo_path`
+
+| Tool | Purpose | Key Args |
+|------|---------|----------|
+| `knowledge_sync_rules` | Sync graduated insights to IDE rules file | `project`, `target_file`, `dry_run` |
+| `knowledge_upvote` | Increase entry importance (+1) | `id` |
+| `knowledge_downvote` | Decrease entry importance (-1) | `id` |
+
+> 💡 **Prerequisite:** Set a `repo_path` for your project in the Mind Palace dashboard (⚙️ Settings → Project Repo Paths) before syncing.
+
 ### Code Mode Templates (v2.1)
 
 Instead of writing custom JavaScript, pass a `template` name for instant extraction:
@@ -1348,13 +1391,14 @@ See [`vertex-ai/`](vertex-ai/) for setup and benchmarks.
 
 > **[View the full project board →](https://github.com/users/dcostenco/projects/1/views/1)**
 
-### ✅ v4.2 — Project Repo Registry (Shipped!)
+### ✅ v4.2 — Project Repo Registry + Knowledge Sync Rules (Shipped!)
 
 | Feature | Description |
 |---|---|
 | 🗂️ **Project Repo Paths** | Dashboard UI to map projects to repo directories + `session_save_ledger` path validation. |
 | 🔄 **Universal Auto-Load** | Dynamic tool descriptions replace env var — dashboard is sole source of truth. |
 | 🏠 **Dashboard-First Config** | Removed `PRISM_AUTOLOAD_PROJECTS` env var override. |
+| 🌉 **Knowledge Sync Rules** | `knowledge_sync_rules` — auto-sync graduated insights to `.cursorrules` / `.clauderules` with idempotent sentinel markers. |
 
 ### ✅ v4.1 — Auto-Migration & Multi-Instance (Shipped!)
 
@@ -1376,7 +1420,6 @@ See [What's in v3.0.0](#whats-in-v300--agent-hivemind-) above.
 
 | Feature | Issue | Description |
 |---------|-------|-------------|
-| Insight Graduation | — | `knowledge_upvote` / `knowledge_downvote` — importance ≥ 7 promotes to rule |
 | OpenTelemetry | [#6](https://github.com/dcostenco/prism-mcp/issues/6) | W3C tracing with Jaeger/Zipkin export |
 | GDPR Portability | [#7](https://github.com/dcostenco/prism-mcp/issues/7) | `session_export_memory` for Art. 20 |
 | CRDT Conflict Resolution | [#9](https://github.com/dcostenco/prism-mcp/issues/9) | Conflict-free types for concurrent edits |

package/dist/server.js

@@ -102,6 +102,8 @@ sessionForgetMemoryHandler,
 knowledgeSetRetentionHandler, 
 // v4.0: Active Behavioral Memory handlers
 sessionSaveExperienceHandler, knowledgeUpvoteHandler, knowledgeDownvoteHandler, 
+// v4.2: Knowledge Sync Rules
+KNOWLEDGE_SYNC_RULES_TOOL, knowledgeSyncRulesHandler, 
 // ─── v3.0: Agent Hivemind tools ───
 AGENT_REGISTRY_TOOLS, agentRegisterHandler, agentHeartbeatHandler, agentListTeamHandler, } from "./tools/index.js";
 // ─── Dynamic Tool Registration ───────────────────────────────────
@@ -159,6 +161,8 @@ function buildSessionMemoryTools(autoloadList) {
         SESSION_SAVE_EXPERIENCE_TOOL, // session_save_experience — record typed experience events
         KNOWLEDGE_UPVOTE_TOOL, // knowledge_upvote — increase entry importance
         KNOWLEDGE_DOWNVOTE_TOOL, // knowledge_downvote — decrease entry importance
+        // ─── v4.2: Knowledge Sync Rules tool ───
+        KNOWLEDGE_SYNC_RULES_TOOL, // knowledge_sync_rules — sync graduated insights to IDE rules files
     ];
 }
 // ─── v0.4.0: Resource Subscription Tracking ──────────────────────
@@ -638,6 +642,11 @@ export function createServer() {
                     if (!SESSION_MEMORY_ENABLED)
                         throw new Error("Session memory not configured. Set SUPABASE_URL and SUPABASE_KEY.");
                     return await knowledgeDownvoteHandler(args);
+                // ─── v4.2: Knowledge Sync Rules Tool ───
+                case "knowledge_sync_rules":
+                    if (!SESSION_MEMORY_ENABLED)
+                        throw new Error("Session memory not configured. Set SUPABASE_URL and SUPABASE_KEY.");
+                    return await knowledgeSyncRulesHandler(args);
                 // ─── v3.0: Agent Hivemind Tools ───
                 case "agent_register":
                     if (!SESSION_MEMORY_ENABLED)

package/dist/storage/sqlite.js

@@ -1391,4 +1391,35 @@ export class SqliteStorage {
         });
         debugLog(`[SqliteStorage] Adjusted importance for ${id} by ${delta > 0 ? "+" : ""}${delta}`);
     }
+    // ─── v4.2: Graduated Insights Query ──────────────────────────
+    //
+    // Returns ledger entries that have "graduated" — i.e., their
+    // importance score has reached the threshold (default 7).
+    // Used by knowledge_sync_rules to physically write insights
+    // into .cursorrules / .clauderules files at the project repo path.
+    async getGraduatedInsights(project, userId, minImportance = 7) {
+        const result = await this.db.execute({
+            sql: `SELECT id, project, user_id, role, summary, importance,
+                   event_type, decisions, created_at
+            FROM session_ledger
+            WHERE project = ? AND user_id = ?
+              AND importance >= ?
+              AND deleted_at IS NULL
+              AND archived_at IS NULL
+            ORDER BY importance DESC, created_at DESC`,
+            args: [project, userId, minImportance],
+        });
+        return result.rows.map(row => ({
+            id: row.id,
+            project: row.project,
+            user_id: row.user_id,
+            role: row.role || "global",
+            summary: row.summary,
+            importance: Number(row.importance),
+            event_type: row.event_type || "session",
+            decisions: this.parseJsonColumn(row.decisions),
+            created_at: row.created_at,
+            conversation_id: "",
+        }));
+    }
 }

package/dist/storage/supabase.js

@@ -383,4 +383,29 @@ export class SupabaseStorage {
             debugLog("[SupabaseStorage] adjustImportance failed: " + (e instanceof Error ? e.message : String(e)));
         }
     }
+    // ─── v4.2: Graduated Insights Query ──────────────────────────
+    async getGraduatedInsights(project, userId, minImportance = 7) {
+        const data = await supabaseGet("session_ledger", {
+            project: `eq.${project}`,
+            user_id: `eq.${userId}`,
+            importance: `gte.${minImportance}`,
+            deleted_at: "is.null",
+            archived_at: "is.null",
+            select: "id,project,user_id,role,summary,importance,event_type,decisions,created_at",
+            order: "importance.desc,created_at.desc",
+        });
+        const rows = Array.isArray(data) ? data : [];
+        return rows.map((r) => ({
+            id: r.id,
+            project: r.project,
+            user_id: r.user_id,
+            role: r.role || "global",
+            summary: r.summary,
+            importance: r.importance || 0,
+            event_type: r.event_type || "session",
+            decisions: Array.isArray(r.decisions) ? r.decisions : [],
+            created_at: r.created_at,
+            conversation_id: "",
+        }));
+    }
 }

package/dist/tools/index.js

@@ -26,8 +26,8 @@ export { webSearchHandler, braveWebSearchCodeModeHandler, localSearchHandler, br
 // This file always exports them — server.ts decides whether to include them in the tool list.
 //
 // v0.4.0: Added SESSION_COMPACT_LEDGER_TOOL and SESSION_SEARCH_MEMORY_TOOL
-export { SESSION_SAVE_LEDGER_TOOL, SESSION_SAVE_HANDOFF_TOOL, SESSION_LOAD_CONTEXT_TOOL, KNOWLEDGE_SEARCH_TOOL, KNOWLEDGE_FORGET_TOOL, SESSION_COMPACT_LEDGER_TOOL, SESSION_SEARCH_MEMORY_TOOL, MEMORY_HISTORY_TOOL, MEMORY_CHECKOUT_TOOL, SESSION_SAVE_IMAGE_TOOL, SESSION_VIEW_IMAGE_TOOL, SESSION_HEALTH_CHECK_TOOL, SESSION_FORGET_MEMORY_TOOL, KNOWLEDGE_SET_RETENTION_TOOL, SESSION_SAVE_EXPERIENCE_TOOL, KNOWLEDGE_UPVOTE_TOOL, KNOWLEDGE_DOWNVOTE_TOOL } from "./sessionMemoryDefinitions.js";
-export { sessionSaveLedgerHandler, sessionSaveHandoffHandler, sessionLoadContextHandler, knowledgeSearchHandler, knowledgeForgetHandler, sessionSearchMemoryHandler, backfillEmbeddingsHandler, memoryHistoryHandler, memoryCheckoutHandler, sessionSaveImageHandler, sessionViewImageHandler, sessionHealthCheckHandler, sessionForgetMemoryHandler, knowledgeSetRetentionHandler, sessionSaveExperienceHandler, knowledgeUpvoteHandler, knowledgeDownvoteHandler } from "./sessionMemoryHandlers.js";
+export { SESSION_SAVE_LEDGER_TOOL, SESSION_SAVE_HANDOFF_TOOL, SESSION_LOAD_CONTEXT_TOOL, KNOWLEDGE_SEARCH_TOOL, KNOWLEDGE_FORGET_TOOL, SESSION_COMPACT_LEDGER_TOOL, SESSION_SEARCH_MEMORY_TOOL, MEMORY_HISTORY_TOOL, MEMORY_CHECKOUT_TOOL, SESSION_SAVE_IMAGE_TOOL, SESSION_VIEW_IMAGE_TOOL, SESSION_HEALTH_CHECK_TOOL, SESSION_FORGET_MEMORY_TOOL, KNOWLEDGE_SET_RETENTION_TOOL, SESSION_SAVE_EXPERIENCE_TOOL, KNOWLEDGE_UPVOTE_TOOL, KNOWLEDGE_DOWNVOTE_TOOL, KNOWLEDGE_SYNC_RULES_TOOL } from "./sessionMemoryDefinitions.js";
+export { sessionSaveLedgerHandler, sessionSaveHandoffHandler, sessionLoadContextHandler, knowledgeSearchHandler, knowledgeForgetHandler, sessionSearchMemoryHandler, backfillEmbeddingsHandler, memoryHistoryHandler, memoryCheckoutHandler, sessionSaveImageHandler, sessionViewImageHandler, sessionHealthCheckHandler, sessionForgetMemoryHandler, knowledgeSetRetentionHandler, sessionSaveExperienceHandler, knowledgeUpvoteHandler, knowledgeDownvoteHandler, knowledgeSyncRulesHandler } from "./sessionMemoryHandlers.js";
 // ── Compaction Handler (v0.4.0 — Enhancement #2) ──
 // The compaction handler is in a separate file because it's significantly
 // more complex than the other session memory handlers (chunked Gemini

package/dist/tools/sessionMemoryDefinitions.js

@@ -743,3 +743,43 @@ export function isKnowledgeVoteArgs(args) {
         "id" in args &&
         typeof args.id === "string");
 }
+// ─── v4.2: Knowledge Sync Rules Tool ─────────────────────────
+export const KNOWLEDGE_SYNC_RULES_TOOL = {
+    name: "knowledge_sync_rules",
+    description: "Auto-sync graduated insights (importance >= 7) into your project's IDE rules file " +
+        "(.cursorrules or .clauderules). This bridges behavioral memory with static IDE context — " +
+        "turning dynamic agent learnings into always-on rules.\n\n" +
+        "**How it works:**\n" +
+        "1. Fetches graduated insights from the ledger\n" +
+        "2. Formats them as markdown rules inside sentinel markers\n" +
+        "3. Idempotently writes them into the target file at the project's configured repo_path\n\n" +
+        "**Requirements:** The project must have a repo_path configured in the dashboard.\n\n" +
+        "**Idempotency:** Uses `<!-- PRISM:AUTO-RULES:START -->` / `<!-- PRISM:AUTO-RULES:END -->` " +
+        "sentinel markers. Running this tool multiple times produces the same file. " +
+        "User-maintained content outside the sentinels is never touched.",
+    inputSchema: {
+        type: "object",
+        properties: {
+            project: {
+                type: "string",
+                description: "Project identifier. Must have a repo_path configured in the dashboard.",
+            },
+            target_file: {
+                type: "string",
+                description: "Target rules filename (default: '.cursorrules'). " +
+                    "Common values: '.cursorrules', '.clauderules'.",
+            },
+            dry_run: {
+                type: "boolean",
+                description: "If true, returns a preview of the rules block without writing to disk. Default: false.",
+            },
+        },
+        required: ["project"],
+    },
+};
+export function isKnowledgeSyncRulesArgs(args) {
+    return (typeof args === "object" &&
+        args !== null &&
+        "project" in args &&
+        typeof args.project === "string");
+}

package/dist/tools/sessionMemoryHandlers.js

@@ -34,7 +34,13 @@ import { isSessionSaveLedgerArgs, isSessionSaveHandoffArgs, isSessionLoadContext
 isSessionForgetMemoryArgs, // Phase 2: GDPR-compliant memory deletion type guard
 isKnowledgeSetRetentionArgs, // v3.1: TTL retention policy type guard
 // v4.0: Active Behavioral Memory type guards
-isSessionSaveExperienceArgs, isKnowledgeVoteArgs, } from "./sessionMemoryDefinitions.js";
+isSessionSaveExperienceArgs, isKnowledgeVoteArgs, 
+// v4.2: Sync Rules type guard
+isKnowledgeSyncRulesArgs, } from "./sessionMemoryDefinitions.js";
+// v4.2: File system access for knowledge_sync_rules
+import { readFile, writeFile, mkdir } from "node:fs/promises";
+import { existsSync } from "node:fs";
+import { join, dirname } from "node:path";
 // v3.1: In-memory debounce lock for auto-compaction.
 // Prevents multiple concurrent Gemini compaction tasks for the same project
 // when many agents call session_save_ledger at the same time.
@@ -1703,3 +1709,127 @@ export async function knowledgeDownvoteHandler(args) {
         isError: false,
     };
 }
+// ─── v4.2: Knowledge Sync Rules Handler ─────────────────────
+//
+// "The Bridge" — bridges v4.0 Behavioral Memory with v4.2 Repo
+// Registry. Extracts graduated insights (importance >= 7) from
+// the ledger and idempotently syncs them into the project's
+// .cursorrules or .clauderules file, turning dynamic learnings
+// into static, always-on IDE context.
+//
+// Sentinel markers ensure the auto-generated block is isolated
+// from user-maintained rules. Re-running always produces the
+// same output, preventing drift.
+const SENTINEL_START = "<!-- PRISM:AUTO-RULES:START -->";
+const SENTINEL_END = "<!-- PRISM:AUTO-RULES:END -->";
+/**
+ * Formats graduated insights into a markdown rules block.
+ * Each insight is rendered as a bullet with its importance score,
+ * event type, and the summary/correction text.
+ */
+function formatRulesBlock(insights, project) {
+    const header = `## Prism Graduated Insights (auto-synced)\n\n` +
+        `> These rules were automatically generated by [Prism MCP](https://github.com/fdarcy/prism) ` +
+        `from behavioral memory for project \"${project}\".\n` +
+        `> Last synced: ${new Date().toISOString().split("T")[0]}\n\n`;
+    const rules = insights.map(i => {
+        const tag = i.event_type && i.event_type !== "session" ? ` (${i.event_type})` : "";
+        return `- **[importance: ${i.importance}]**${tag} ${i.summary}`;
+    }).join("\n");
+    return `${SENTINEL_START}\n${header}${rules}\n${SENTINEL_END}`;
+}
+/**
+ * Idempotently replaces or appends the sentinel block in a rules file.
+ * Content outside the sentinels is never modified.
+ */
+function applySentinelBlock(existingContent, rulesBlock) {
+    const startIdx = existingContent.indexOf(SENTINEL_START);
+    const endIdx = existingContent.indexOf(SENTINEL_END);
+    if (startIdx !== -1 && endIdx !== -1) {
+        // Replace existing block
+        const before = existingContent.substring(0, startIdx);
+        const after = existingContent.substring(endIdx + SENTINEL_END.length);
+        return `${before}${rulesBlock}${after}`;
+    }
+    // Append with separator
+    const separator = existingContent.length > 0 && !existingContent.endsWith("\n\n")
+        ? (existingContent.endsWith("\n") ? "\n" : "\n\n")
+        : "";
+    return `${existingContent}${separator}${rulesBlock}\n`;
+}
+export async function knowledgeSyncRulesHandler(args) {
+    if (!isKnowledgeSyncRulesArgs(args)) {
+        throw new Error("Invalid arguments for knowledge_sync_rules");
+    }
+    const { project, target_file = ".cursorrules", dry_run = false } = args;
+    const storage = await getStorage();
+    // 1. Resolve repo path
+    const repoPath = await getSetting(`repo_path:${project}`, "");
+    if (!repoPath || !repoPath.trim()) {
+        return {
+            content: [{
+                    type: "text",
+                    text: `❌ No repo_path configured for project "${project}".\n` +
+                        `Set it in the Mind Palace dashboard (Settings → Project Repo Paths) before syncing rules.`,
+                }],
+            isError: true,
+        };
+    }
+    const normalizedRepoPath = repoPath.trim().replace(/\/+$/, "");
+    // 2. Fetch graduated insights
+    const insights = await storage.getGraduatedInsights(project, PRISM_USER_ID, 7);
+    if (insights.length === 0) {
+        return {
+            content: [{
+                    type: "text",
+                    text: `ℹ️ No graduated insights found for project "${project}".\n` +
+                        `Insights graduate when their importance score reaches 7 or higher.\n` +
+                        `Use \`knowledge_upvote\` to increase importance of valuable entries.`,
+                }],
+            isError: false,
+        };
+    }
+    // 3. Format rules block
+    const rulesBlock = formatRulesBlock(insights.map(i => ({ ...i, importance: i.importance ?? 0 })), project);
+    // 4. Dry-run: return preview without writing
+    if (dry_run) {
+        return {
+            content: [{
+                    type: "text",
+                    text: `🔍 **Dry Run Preview** — ${insights.length} graduated insight(s) for "${project}":\n\n` +
+                        `Target: ${normalizedRepoPath}/${target_file}\n\n` +
+                        `\`\`\`markdown\n${rulesBlock}\n\`\`\`\n\n` +
+                        `Run again without \`dry_run\` to write this to disk.`,
+                }],
+            isError: false,
+        };
+    }
+    // 5. Idempotent file write
+    const targetPath = join(normalizedRepoPath, target_file);
+    // Ensure directory exists (handles nested target_file like ".config/rules.md")
+    const targetDir = dirname(targetPath);
+    if (!existsSync(targetDir)) {
+        await mkdir(targetDir, { recursive: true });
+    }
+    let existingContent = "";
+    try {
+        existingContent = await readFile(targetPath, "utf-8");
+    }
+    catch {
+        // File doesn't exist yet — will be created
+        debugLog(`[knowledge_sync_rules] File ${targetPath} doesn't exist, creating new`);
+    }
+    const newContent = applySentinelBlock(existingContent, rulesBlock);
+    await writeFile(targetPath, newContent, "utf-8");
+    debugLog(`[knowledge_sync_rules] Synced ${insights.length} insights to ${targetPath}`);
+    return {
+        content: [{
+                type: "text",
+                text: `✅ Synced ${insights.length} graduated insight(s) to \`${targetPath}\`\n\n` +
+                    `Top insights synced:\n` +
+                    insights.slice(0, 5).map(i => `  • [${i.importance}] ${i.summary.substring(0, 80)}${i.summary.length > 80 ? "..." : ""}`).join("\n") +
+                    (insights.length > 5 ? `\n  ... and ${insights.length - 5} more` : ""),
+            }],
+        isError: false,
+    };
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "prism-mcp-server",
-  "version": "4.2.0",
+  "version": "4.3.0",
   "mcpName": "io.github.dcostenco/prism-mcp",
   "description": "The Mind Palace for AI Agents — local-first MCP server with persistent memory (SQLite/Supabase), visual dashboard, time travel, multi-agent sync, Morning Briefings, reality drift detection, code mode templates, semantic vector search, and Brave Search + Gemini analysis. Zero-config local mode.",
   "module": "index.ts",