loopctl-mcp-server 2.40.0 → 2.41.0

package/README.md

@@ -2,7 +2,7 @@
 
 MCP (Model Context Protocol) server for [loopctl](https://loopctl.com) -- structural trust for AI development loops.
 
-Wraps the loopctl REST API into 73 typed MCP tools so AI coding agents (Claude Code, etc.) can interact with loopctl without writing curl commands.
+Wraps the loopctl REST API into 76 typed MCP tools so AI coding agents (Claude Code, etc.) can interact with loopctl without writing curl commands.
 
 ## Installation
 
@@ -198,6 +198,8 @@ autonomous agent) can self-remediate without a human. Full agent-tenant lifecycl
 | How many articles? (counts only) | `knowledge_stats` |
 | Browse the catalog (lightweight id/title/category) | `knowledge_index` |
 | Find by topic / relevance (ranked, published-only, lags writes) | `knowledge_search` |
+| One trustworthy answer + provenance (curated-first, retrieval fallback) | `knowledge_hybrid_search` |
+| Survey a topic cheaply (capped stubs) then open only what you need | `knowledge_progressive_index` + `knowledge_progressive_drill` |
 | Enumerate / dedup / repair, or "does X exist?" (full fields, lag-free, all-status) | `knowledge_list` |
 
 | Tool | Description |
@@ -207,6 +209,9 @@ autonomous agent) can self-remediate without a human. Full agent-tenant lifecycl
 | `knowledge_count` | Count articles matching filters **without returning rows** within agent's visible set. Agent callers see only their own and `shared` articles. Same filters as `knowledge_list` (`category`, `status`, `tags`, `match`, `source_type`, `source_id`, `idempotency_key`, `project_id`). With `tags`+`match: all` (+`status`) → "how many published articles tagged both X and Y (that I can see)". Returns `{ count }`. |
 | `knowledge_facets` | Count articles grouped by **distinct tag** within agent's visible set, no rows. Agent callers see only their own and `shared` articles. `tag_prefix` (e.g. `book-`) gives the distinct count of a tag family plus per-member totals. Returns `{ data: { tag: count }, meta: { distinct_count } }`. Optional: `category`, `status`, `tags`, `match`, `project_id`, `limit`. |
 | `knowledge_search` | Search the knowledge wiki by topic (keyword, semantic, or combined). Returns snippets. **Ranked, published-only, and LAGS writes by minutes while embeddings index — do NOT use for existence/idempotency/dedup checks (a fresh write false-negatives); use `knowledge_list` for that.** `q` is optional when `tags`/`category` are supplied — that **list mode** returns the complete filtered set paginated via `offset`/`limit` over `meta.total_count`. `meta.total_count` is mode-dependent — read `meta.total_count_scope` (`keyword_matches`/`ranked_corpus`/`merged_candidates`/`filtered_set`) and don't use a relevance-mode count to size the wiki (use `knowledge_list` or `knowledge_stats`). Optional: `project_id`, `story_id` for attribution. |
+| `knowledge_hybrid_search` | Resolve a topic to a **single best answer with provenance** (US-31.4). Runs combined keyword+semantic over the full ranked pool, then decides whether a governed **curated** source actually answers. `meta.provenance` is `curated` (trust it — the canonical article is first in `data`, `meta.curated_article_id` points at it) or `retrieved` (best fuzzy match, `curated_article_id` null); `meta.confidence` is the winner's absolute score. Prefer over `knowledge_search` when you want one trustworthy answer, not a list to triage. Degrades to keyword-only like `knowledge_search` when embeddings are unavailable. Required: `query`. Optional: `project_id`, `category`, `tags`, `match`, `limit`, `offset`. |
+| `knowledge_progressive_index` | Progressive disclosure — a **cheap, capped index** of what's relevant to a topic (compact stubs: `id`/`title`/`category`/`summary`, **no bodies**), curated-preferred and hub-enriched, capped at top-K (`meta.truncated` when the pool exceeded it). Survey a topic without flooding context, then open only what you need via `knowledge_progressive_drill`. Required: `topic`. Optional: `category`, `limit`. |
+| `knowledge_progressive_drill` | Open one stub from `knowledge_progressive_index` — returns the **full article body** for the given id, scope-enforced. Resolves both tenant-owned articles and published system canonicals (the same set the index surfaces). Required: `article_id`. |
 | `knowledge_list` | List articles (`id`, `title`, `category`, `status`, `tags`, `source_type`, `source_id`, `idempotency_key`, timestamps), filtered + paginated. **Body-less summary by default** (safe to page up to `limit=1000`); pass `include_body: true` to also return `body`, in which case the page is bounded by a ~5 MB byte budget — continue via `meta.next_offset` while `meta.has_more`. **Lag-free, all-status** read of the DB of record — unlike `knowledge_search` (ranked, published-only, lags writes) and `knowledge_index` (id/title/category only). The right tool to enumerate/dedup/repair and for idempotency/existence checks: filter by `tags`, `source_type`+`source_id`, or `idempotency_key` and read `meta.total_count` (exact). Single full body → `knowledge_get`; relevant bodies → `knowledge_context`; bulk dump → `knowledge_export`. Optional: `project_id`, `category`, `status`, `tags`, `source_type`, `source_id`, `idempotency_key`, `offset`, `limit`, `include_body`. |
 | `knowledge_get` | Get full article content by ID. Use after search to read an article in detail. Optional: `project_id`, `story_id` for attribution. |
 | `knowledge_context` | Get relevance-and-recency-ranked full articles for a task query. Best knowledge for your current context. **Agent-memory scoping**: `memory_types` (comma-separated, OR — observation/finding/summary/decision/question/task), `agents` (comma-separated agent_ids, OR), `conversation_id` (exact) filter on article `metadata` (JSONB `@>`). Optional: `project_id`, `story_id` for attribution, `limit`, `recency_weight`. |

package/index.js

@@ -962,6 +962,52 @@ async function knowledgeSearch({ q, project_id, story_id, category, tags, match,
   return withRemediationNotice(result);
 }
 
+async function knowledgeHybridSearch({ query, project_id, category, tags, match, limit, offset }) {
+  const bodyPayload = { query };
+  if (project_id) bodyPayload.project_id = project_id;
+  if (category) bodyPayload.category = category;
+  if (tags) bodyPayload.tags = tags;
+  if (match) bodyPayload.match = match;
+  if (limit != null) bodyPayload.limit = limit;
+  if (offset != null) bodyPayload.offset = offset;
+
+  const result = await apiCall(
+    "POST",
+    "/api/v1/knowledge/hybrid_search",
+    bodyPayload,
+    process.env.LOOPCTL_AGENT_KEY,
+  );
+  // meta.provenance ("curated" | "retrieved") is the load-bearing field and rides
+  // through toContent verbatim. Same missing-embedding-key remediation surfacing as
+  // knowledge_search, since hybrid runs the combined pool underneath.
+  return withRemediationNotice(result);
+}
+
+async function knowledgeProgressiveIndex({ topic, category, limit }) {
+  const params = new URLSearchParams();
+  if (topic != null) params.set("topic", topic);
+  if (category) params.set("category", category);
+  if (limit != null) params.set("limit", String(limit));
+
+  const result = await apiCall(
+    "GET",
+    `/api/v1/knowledge/progressive_index?${params}`,
+    null,
+    process.env.LOOPCTL_AGENT_KEY,
+  );
+  return toContent(result);
+}
+
+async function knowledgeProgressiveDrill({ article_id }) {
+  const result = await apiCall(
+    "GET",
+    `/api/v1/knowledge/progressive/${article_id}`,
+    null,
+    process.env.LOOPCTL_AGENT_KEY,
+  );
+  return toContent(result);
+}
+
 async function knowledgeList({
   project_id,
   category,
@@ -3005,6 +3051,109 @@ const TOOLS = [
       required: [],
     },
   },
+  {
+    name: "knowledge_hybrid_search",
+    description:
+      "Resolve a topic to a SINGLE best answer WITH provenance — the hybrid " +
+      "retrieval entrypoint. Runs the combined keyword+semantic search over the full " +
+      "ranked pool, then decides whether a governed CURATED source actually answers. " +
+      "The verdict is meta.provenance: 'curated' means a curated, canonical article " +
+      "answers — TRUST IT (it is guaranteed first in the results and meta.curated_article_id " +
+      "points at it); 'retrieved' means no curated source cleared the bar, so the answer " +
+      "is the best semantic/keyword match (a fuzzy fallback — verify before relying on it, " +
+      "meta.curated_article_id is null). meta.confidence is the winning candidate's absolute " +
+      "score for its provenance class. Prefer this over knowledge_search when you want ONE " +
+      "trustworthy answer plus its provenance rather than a ranked list to triage yourself; " +
+      "use knowledge_search when you want to browse/enumerate matches. Additive — existing " +
+      "knowledge tools are unchanged. If semantic ranking is unavailable it degrades to " +
+      "keyword-only (meta.fallback/fallback_reason), same as knowledge_search.",
+    inputSchema: {
+      type: "object",
+      properties: {
+        query: {
+          type: "string",
+          description: "The topic/question to resolve (max 500 characters). Required.",
+        },
+        project_id: {
+          type: "string",
+          format: "uuid",
+          description: "Optional: scope to a project UUID.",
+        },
+        category: {
+          type: "string",
+          description: "Optional: filter by category.",
+        },
+        tags: {
+          type: "string",
+          description: "Optional: comma-separated tags to filter by.",
+        },
+        match: {
+          type: "string",
+          enum: ["any", "all"],
+          description: "Optional: tag match mode — 'any' (default, OR) or 'all' (AND, every tag).",
+        },
+        limit: {
+          type: "integer",
+          description: "Optional: max results to return (default 10).",
+        },
+        offset: {
+          type: "integer",
+          description: "Optional: results to skip for pagination (default 0).",
+        },
+      },
+      required: ["query"],
+    },
+  },
+  {
+    name: "knowledge_progressive_index",
+    description:
+      "Progressive disclosure — get a CHEAP, capped index of what's relevant to a topic " +
+      "(compact stubs: id/title/category/summary, NO bodies), then open only what you need " +
+      "with knowledge_progressive_drill. Curated sources are preferred and hub-linked " +
+      "neighbors are enriched in; results are capped at a configured top-K (meta.truncated " +
+      "is true when the candidate pool exceeded it). Use this to survey a topic without " +
+      "flooding your context with full article bodies — it's the index half of the hybrid " +
+      "interface. Follow up on a stub's id with knowledge_progressive_drill to read the body.",
+    inputSchema: {
+      type: "object",
+      properties: {
+        topic: {
+          type: "string",
+          description: "The topic to index (max 500 characters). Required.",
+        },
+        category: {
+          type: "string",
+          description: "Optional: filter by category.",
+        },
+        limit: {
+          type: "integer",
+          description: "Optional: top-K override (clamped to the configured cap).",
+        },
+      },
+      required: ["topic"],
+    },
+  },
+  {
+    name: "knowledge_progressive_drill",
+    description:
+      "Drill into one stub from knowledge_progressive_index — returns the FULL article " +
+      "body for the given id, scope-enforced. Resolves both tenant-owned articles and " +
+      "published system canonicals (the same set the index surfaces). This is the drill " +
+      "half of progressive disclosure: index cheaply, then open only the article(s) you " +
+      "need. (knowledge_get works for tenant articles too; use this to also reach the " +
+      "system canonicals the progressive index can surface.)",
+    inputSchema: {
+      type: "object",
+      properties: {
+        article_id: {
+          type: "string",
+          format: "uuid",
+          description: "The UUID of the article to open (from a progressive index stub).",
+        },
+      },
+      required: ["article_id"],
+    },
+  },
   {
     name: "knowledge_get",
     description:
@@ -4654,6 +4803,15 @@ server.setRequestHandler(CallToolRequestSchema, async (request) => {
     case "knowledge_search":
       return await knowledgeSearch(args);
 
+    case "knowledge_hybrid_search":
+      return await knowledgeHybridSearch(args);
+
+    case "knowledge_progressive_index":
+      return await knowledgeProgressiveIndex(args);
+
+    case "knowledge_progressive_drill":
+      return await knowledgeProgressiveDrill(args);
+
     case "knowledge_list":
       return await knowledgeList(args);
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "loopctl-mcp-server",
-  "version": "2.40.0",
+  "version": "2.41.0",
   "description": "MCP server for loopctl — structural trust for AI development loops",
   "type": "module",
   "main": "index.js",