loopctl-mcp-server 2.68.0 → 2.69.0

package/README.md

@@ -304,6 +304,7 @@ it is enforced server-side and a no-op for a non-superadmin key — see below.)
 | `knowledge_bulk_delete` | **Requires `LOOPCTL_USER_KEY`.** Bulk archive (default, reversible) or IRREVERSIBLE hard-delete by selector. Provide exactly one selector: `article_ids` (list), `source_type`+`source_id` (every active article from a source), or `tag`+`confirm:true` (every active article with the tag — high blast radius). Default = set-based soft archive (idempotent; `meta.count`=archived, `meta.counts`/`meta.results` give the breakdown; ≤5000). **Dry-run** (`dry_run:true`) mutates nothing, returns `meta.would_affect` (with `hard:true` also a single-use `meta.token`, or `meta.confirm_hash` for oversized selectors). **Hard delete** (irreversible): dry-run with `hard:true` for a token, then call again with `hard:true`+`token` to FK-correctly delete the frozen id-set (links first, access events cascade). |
 | `knowledge_drafts` | List draft (unpublished) knowledge articles with pagination. Optional: `limit` (default 20, max 1000 — over-max → 400, no silent clamp), `offset` (default 0), `project_id`. Returns `meta.total_count`. |
 | `knowledge_lint` | Run a lint check on the knowledge wiki to identify stale or low-coverage articles. Optional: `project_id`, `stale_days`, `min_coverage`, `max_per_category` (default 50, max 500). True totals returned in `summary.total_per_category`. |
+| `knowledge_consolidation` | Read the nightly consolidation ("dream") report: NUMBERED proposals for reconciling the corpus, each naming the articles involved and quoting an excerpt from each as evidence. **REPORT ONLY** — the pass writes no articles, links or conflict resolutions; every proposal is `pending` and this tool applies nothing. Classes: `duplicate_capture` (titles that collide once case/punctuation normalize away, or idempotency keys that collide under the same normalization while differing verbatim — capture tag-format drift, which the novelty gate does not catch because novelty scoring and idempotency are separate paths), `contradiction_candidate` (a SYSTEM-flagged `potential_conflict` pair of PUBLISHED articles with no recorded verdict — record one with `knowledge_resolve_conflict`, which accepts exactly these pairs), `generic_title` (a placeholder title that collides on active-title uniqueness and blocks hub creation), `stale_entry`. **Denominators:** `corpus_size` = PUBLISHED articles owned by the tenant at scan time, not its total article count; `proposal_count` = the TRUE pre-cap count of PROPOSALS, not of articles (one duplicate group of three articles is ONE proposal, and one article can appear in proposals of several classes); `persisted_count` = proposal ROWS the report carries, lower than `proposal_count` exactly when a class hit `max_per_class` (`truncated` flags which); `meta.total_count` counts persisted proposals matching the `class` filter, so it is bounded by `persisted_count`, never `proposal_count`. `review_status`/`reviewed_by`/`reviewed_at` reset to pending/null whenever the nightly pass re-derives a proposal — refreshed machine output never inherits an approval. Requires orchestrator role. Optional: `day` (ISO8601, default most recent report), `class`, `limit` (default 50, max 500), `offset`. |
 | `knowledge_export` | Export all knowledge articles as an OKF v0.1 bundle (gzipped tar archive, unbounded, bounded-memory streaming, fail-closed). Returns a curl command for direct download — **the download requires `LOOPCTL_USER_KEY`** (an orchestrator key would 403). Pass `format=json` for buffered in-memory JSON (convenience tool for file writers; capped at `export_max_buffered_export_articles` — returns 413 if over-cap). Optional: `project_id`, `format` (`tar.gz` default or `json`). |
 | `knowledge_ingest` | Submit a URL or raw content for knowledge extraction. Enqueues an Oban job. Extracted articles are **drafts by default** (lower-trust LLM output); pass `publish: true` to publish on extraction. **BYO:** runs on the tenant's own Anthropic key — a keyless tenant gets a 422 whose result leads with an `ACTION REQUIRED` notice pointing at `set_llm_config` (see [First-time setup](#first-time-setup--provision-your-byo-llm-keys)). Required: `source_type`. One of: `url` or `content`. Optional: `project_id`, `publish`. |
 | `knowledge_ingest_batch` | Submit up to 50 ingestion items in a single request. Each item has the same shape as `knowledge_ingest` (incl. `publish`). Returns per-item results. Required: `items`. Optional: batch-level `project_id` / `publish` defaults. |

package/index.js

@@ -1927,6 +1927,20 @@ async function knowledgeLint({ project_id, stale_days, min_coverage, max_per_cat
   return toContent(result);
 }
 
+async function knowledgeConsolidation({ day, class: klass, limit, offset } = {}) {
+  const params = new URLSearchParams();
+  if (day) params.set("day", String(day));
+  if (klass) params.set("class", String(klass));
+  if (limit != null) params.set("limit", String(limit));
+  if (offset != null) params.set("offset", String(offset));
+  const qs = params.toString();
+  const path = qs
+    ? `/api/v1/knowledge/consolidation?${qs}`
+    : "/api/v1/knowledge/consolidation";
+  const result = await apiCall("GET", path, null, process.env.LOOPCTL_ORCH_KEY);
+  return toContent(result);
+}
+
 async function knowledgeIngest({ url, content, source_type, project_id, publish }) {
   const body = { source_type };
   if (url) body.url = url;
@@ -5447,6 +5461,63 @@ const TOOLS = [
       required: [],
     },
   },
+  {
+    name: "knowledge_consolidation",
+    description:
+      "Read the nightly consolidation (\"dream\") report: NUMBERED proposals for reconciling " +
+      "the corpus, each naming the articles involved and quoting an excerpt from each as " +
+      "evidence. REPORT ONLY — the pass writes no articles, links or conflict resolutions, " +
+      "every proposal is `pending`, and this tool applies nothing. Requires orchestrator role.\n\n" +
+      "Classes: `duplicate_capture` (titles that collide once case/punctuation normalize away, " +
+      "or idempotency keys that collide under the same normalization while differing verbatim — " +
+      "capture tag-format drift, which the novelty gate does not catch because novelty scoring " +
+      "and idempotency are separate paths); `contradiction_candidate` (a SYSTEM-flagged " +
+      "potential_conflict pair of PUBLISHED articles with no recorded verdict — record one via " +
+      "knowledge_resolve_conflict, which accepts exactly these pairs; this report writes " +
+      "none); `generic_title` (a placeholder title that collides on active-title uniqueness and " +
+      "blocks hub creation); `stale_entry` (past the lint staleness threshold, never reconciled).\n\n" +
+      "Denominators: `corpus_size` counts PUBLISHED articles owned by the tenant at scan time, " +
+      "not its total article count. `proposal_count` is the TRUE pre-cap count of PROPOSALS, not " +
+      "of articles — one duplicate group of three articles is ONE proposal, and one article can " +
+      "appear in proposals of several classes. `persisted_count` is how many proposal ROWS the " +
+      "report carries, lower than `proposal_count` exactly when a class hit `max_per_class` " +
+      "(`truncated` flags which). `meta.total_count` counts persisted proposals matching the " +
+      "`class` filter, so it is bounded by `persisted_count`, never by `proposal_count`.\n\n" +
+      "Review state (`review_status`/`reviewed_by`/`reviewed_at`) RESETS to pending/null whenever " +
+      "the nightly pass re-derives a proposal: refreshed machine output never inherits an approval.",
+    inputSchema: {
+      type: "object",
+      properties: {
+        day: {
+          type: "string",
+          description:
+            "Optional ISO8601 date (YYYY-MM-DD, UTC) of the report to read. Defaults to the most recent report.",
+        },
+        class: {
+          type: "string",
+          enum: [
+            "duplicate_capture",
+            "contradiction_candidate",
+            "generic_title",
+            "stale_entry",
+          ],
+          description: "Optional: return only proposals of this class.",
+        },
+        limit: {
+          type: "integer",
+          description: "Proposals per page. Default 50, max 500 (clamped, never rejected).",
+          default: 50,
+          minimum: 1,
+        },
+        offset: {
+          type: "integer",
+          description: "Proposals to skip. Default 0.",
+          minimum: 0,
+        },
+      },
+      required: [],
+    },
+  },
   {
     name: "knowledge_export",
     description:
@@ -6899,6 +6970,9 @@ server.setRequestHandler(CallToolRequestSchema, async (request) => {
     case "knowledge_lint":
       return await knowledgeLint(args);
 
+    case "knowledge_consolidation":
+      return await knowledgeConsolidation(args);
+
     case "knowledge_export":
       return await knowledgeExport(args);
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "loopctl-mcp-server",
-  "version": "2.68.0",
+  "version": "2.69.0",
   "description": "MCP server for loopctl \u2014 structural trust for AI development loops",
   "type": "module",
   "main": "index.js",