@cerefox/memory 1.0.4 → 1.0.6

package/dist/bin/cerefox.js

@@ -7184,7 +7184,7 @@ var exports_meta = {};
 __export(exports_meta, {
   PKG_VERSION: () => PKG_VERSION
 });
-var PKG_VERSION = "1.0.4";
+var PKG_VERSION = "1.0.6";
 var init_meta = () => {};
 
 // ../../node_modules/.bun/tslib@2.8.1/node_modules/tslib/tslib.js
@@ -25217,21 +25217,35 @@ function getMaxResponseBytes() {
   const n = Number.parseInt(raw, 10);
   return Number.isNaN(n) || n <= 0 ? MAX_RESPONSE_BYTES : n;
 }
-function getMinSearchScore() {
-  const raw = globalThis.process?.env?.CEREFOX_MIN_SEARCH_SCORE;
-  const fallback = globalThis.process?.env?.CEREFOX_EMBEDDER === "local" ? DEFAULT_MIN_SEARCH_SCORE_LOCAL : DEFAULT_MIN_SEARCH_SCORE;
-  if (raw === undefined || raw === "")
-    return fallback;
-  const n = Number.parseFloat(raw);
-  return Number.isNaN(n) || n < 0 || n > 1 ? fallback : n;
+function readEnv(name) {
+  const g = globalThis;
+  const fromProcess = g.process?.env?.[name];
+  if (fromProcess !== undefined && fromProcess !== "")
+    return fromProcess;
+  try {
+    const fromDeno = g.Deno?.env?.get(name);
+    return fromDeno === "" ? undefined : fromDeno;
+  } catch {
+    return;
+  }
 }
-function getMinTermCoverage() {
-  const raw = globalThis.process?.env?.CEREFOX_MIN_TERM_COVERAGE;
-  if (raw === undefined || raw === "")
+function readUnitInterval(name) {
+  const raw = readEnv(name);
+  if (raw === undefined)
     return;
   const n = Number.parseFloat(raw);
   return Number.isNaN(n) || n < 0 || n > 1 ? undefined : n;
 }
+function getSearchAlpha() {
+  return readUnitInterval("CEREFOX_SEARCH_ALPHA") ?? DEFAULT_SEARCH_ALPHA;
+}
+function getMinSearchScore() {
+  const fallback = readEnv("CEREFOX_EMBEDDER") === "local" ? DEFAULT_MIN_SEARCH_SCORE_LOCAL : DEFAULT_MIN_SEARCH_SCORE;
+  return readUnitInterval("CEREFOX_MIN_SEARCH_SCORE") ?? fallback;
+}
+function getMinTermCoverage() {
+  return readUnitInterval("CEREFOX_MIN_TERM_COVERAGE");
+}
 function applyByteBudget(rows, maxBytes) {
   const accepted = [];
   let usedBytes = 0;
@@ -25259,7 +25273,7 @@ function logUsage(supabase, params) {
     p_extra: params.extra ?? {}
   })).catch(() => {});
 }
-var MAX_RESPONSE_BYTES = 200000, DEFAULT_MIN_SEARCH_SCORE = 0.5, DEFAULT_MIN_SEARCH_SCORE_LOCAL = 0.6;
+var MAX_RESPONSE_BYTES = 200000, DEFAULT_MIN_SEARCH_SCORE = 0.5, DEFAULT_MIN_SEARCH_SCORE_LOCAL = 0.6, DEFAULT_SEARCH_ALPHA = 0.7;
 
 // ../../_shared/mcp-tools/_projects.ts
 async function ensureDocumentInProject(supabase, documentId, projectName) {
@@ -55577,7 +55591,7 @@ async function handler9(supabase, args, ctx) {
   const project_name = args.project_name;
   const match_count = args.match_count ?? 5;
   const mode = args.mode ?? "docs";
-  const alpha = args.alpha ?? 0.7;
+  const alpha = args.alpha ?? getSearchAlpha();
   const min_score = args.min_score ?? getMinSearchScore();
   const min_term_coverage = args.min_term_coverage ?? getMinTermCoverage();
   const coverageParam = min_term_coverage !== undefined ? { p_min_term_coverage: min_term_coverage } : {};
@@ -69069,16 +69083,22 @@ import { join as join2, resolve } from "node:path";
 async function fetchAllPages(makeQuery, batchSize = 200) {
   const results = [];
   let offset = 0;
+  let serverTotal = null;
   for (;; ) {
-    const { data, error } = await makeQuery(offset, offset + batchSize - 1);
+    const { data, error, count } = await makeQuery(offset, offset + batchSize - 1);
     if (error)
       throw new Error(error.message ?? JSON.stringify(error));
+    if (typeof count === "number")
+      serverTotal = count;
     const page = data ?? [];
     results.push(...page);
     if (page.length < batchSize)
       break;
     offset += batchSize;
   }
+  if (serverTotal !== null && results.length !== serverTotal) {
+    throw new Error(`Paginated read returned ${results.length} row(s) but the server reports ` + `${serverTotal}. Refusing to return a partial result — retry, and if this ` + `persists please report it (the rows may be changing under the read).`);
+  }
   return results;
 }
 
@@ -75000,8 +75020,8 @@ import { homedir as homedir6 } from "node:os";
 import { join as join9 } from "node:path";
 
 // ../../_shared/ef-meta/index.ts
-var EF_VERSION = "1.0.4";
-var EF_LAST_CHANGED = "1.0.4";
+var EF_VERSION = "1.0.6";
+var EF_LAST_CHANGED = "1.0.6";
 
 // src/cli/util/checks.ts
 init_config();
@@ -75527,9 +75547,9 @@ async function checkEdgeFunctionsCompat() {
       }
       return {
         name: "edge functions",
-        status: "skipped",
-        detail: `Deployed Edge Functions (v${deployed}) are older than the ones bundled with this client (v${EF_VERSION}). Compatible — nothing is broken — but redeploying ` + `picks up the latest server-side fixes.`,
-        hint: "Redeploy with: cerefox server deploy --functions-only"
+        status: "warn",
+        detail: `Deployed Edge Functions (v${deployed}) are older than this client's bundled v${EF_VERSION} and predate server-side fixes shipped in v${EF_LAST_CHANGED}. Still compatible, but you are missing those fixes.`,
+        hint: "Update the Edge Functions (see remediation below)."
       };
     default:
       return {
@@ -75628,11 +75648,11 @@ async function action15(options) {
     const needsEf = stale("edge functions");
     let remediation = null;
     if (needsSchema && needsEf) {
-      remediation = "Update the server (schema + RPCs + Edge Functions): cerefox server deploy";
+      remediation = "This release needs a server update (schema + RPCs + Edge Functions): cerefox server deploy";
     } else if (needsSchema) {
-      remediation = "Update the schema + RPCs: cerefox server deploy --schema-only";
+      remediation = "This release needs a schema + RPC update: cerefox server deploy --schema-only";
     } else if (needsEf) {
-      remediation = "Update the Edge Functions: cerefox server deploy --functions-only";
+      remediation = "This release needs an Edge Function update: cerefox server deploy --functions-only";
     }
     if (remediation) {
       println(cErr.yellow("→ " + remediation));
@@ -75859,7 +75879,7 @@ class IngestionDbBridge {
     return rows.length > 0 ? rows[0] : null;
   }
   async listChunksForDocument(documentId) {
-    const { data } = await this.supabase.from("cerefox_chunks").select("id, document_id, chunk_index, heading_path, heading_level, title, content, char_count").eq("document_id", documentId).is("version_id", null).order("chunk_index");
+    const data = await fetchAllPages((from, to) => this.supabase.from("cerefox_chunks").select("id, document_id, chunk_index, heading_path, heading_level, title, content, char_count").eq("document_id", documentId).is("version_id", null).order("chunk_index").range(from, to));
     return data ?? [];
   }
   async getDocumentProjectIds(documentId) {
@@ -77474,7 +77494,7 @@ async function action29(query, options) {
     throw userError("Empty query.");
   }
   const matchCount = parsePositiveInt(options.matchCount, "--match-count", 5);
-  const alpha = parseFloat01(options.alpha, "--alpha", 0.7);
+  const alpha = parseFloat01(options.alpha, "--alpha", getSearchAlpha());
   const minScore = parseFloat01(options.minScore, "--min-score", getMinSearchScore());
   const envCoverage = getMinTermCoverage();
   const coverageParam = options.minTermCoverage !== undefined ? { p_min_term_coverage: parseFloat01(options.minTermCoverage, "--min-term-coverage", envCoverage ?? 0.5) } : envCoverage !== undefined ? { p_min_term_coverage: envCoverage } : {};
@@ -77633,7 +77653,7 @@ async function action29(query, options) {
   }
 }
 function registerSearch(program2) {
-  program2.command("search").description("Search the knowledge base (hybrid FTS + semantic).").argument("<query>", "Natural-language search query.").option("-c, --match-count <n>", "Maximum number of documents to return.", "5").option("-p, --project-name <name>", "Filter results to a specific project.").option("-f, --metadata-filter <json>", "JSON containment filter; only docs whose metadata contains ALL pairs are returned.").option("--mode <mode>", "Search mode: docs (default), hybrid, fts.", "docs").option("--alpha <float>", "Semantic weight 0..1 (default: 0.7).", "0.7").option("--min-score <float>", "Minimum cosine similarity threshold (default: CEREFOX_MIN_SEARCH_SCORE; else 0.5, or 0.6 with the local embedder).").option("--min-term-coverage <float>", "OR-fallback keyword matches must cover at least this fraction of the query's meaningful terms to count as confident hits (default: CEREFOX_MIN_TERM_COVERAGE; else the server default 0.5; needs schema ≥ 0.9.1).").option("--max-bytes <n>", "Response size budget in bytes (default: CEREFOX_MAX_RESPONSE_BYTES or 200000).").option("-r, --requestor <name>", "Agent / user name (recorded in usage log).").option("--json", "Emit machine-readable JSON instead of the default text.").option("--only-metadata", "List matching docs (id, score, chunks, chars, partial/full) WITHOUT their content — like the web UI's collapsed result list. Grab a [id:…] then `cerefox document get <id>`.").action(action29);
+  program2.command("search").description("Search the knowledge base (hybrid FTS + semantic).").argument("<query>", "Natural-language search query.").option("-c, --match-count <n>", "Maximum number of documents to return.", "5").option("-p, --project-name <name>", "Filter results to a specific project.").option("-f, --metadata-filter <json>", "JSON containment filter; only docs whose metadata contains ALL pairs are returned.").option("--mode <mode>", "Search mode: docs (default), hybrid, fts.", "docs").option("--alpha <float>", "Semantic weight 0..1 (default: CEREFOX_SEARCH_ALPHA; else 0.7).").option("--min-score <float>", "Minimum cosine similarity threshold (default: CEREFOX_MIN_SEARCH_SCORE; else 0.5, or 0.6 with the local embedder).").option("--min-term-coverage <float>", "OR-fallback keyword matches must cover at least this fraction of the query's meaningful terms to count as confident hits (default: CEREFOX_MIN_TERM_COVERAGE; else the server default 0.5; needs schema ≥ 0.9.1).").option("--max-bytes <n>", "Response size budget in bytes (default: CEREFOX_MAX_RESPONSE_BYTES or 200000).").option("-r, --requestor <name>", "Agent / user name (recorded in usage log).").option("--json", "Emit machine-readable JSON instead of the default text.").option("--only-metadata", "List matching docs (id, score, chunks, chars, partial/full) WITHOUT their content — like the web UI's collapsed result list. Grab a [id:…] then `cerefox document get <id>`.").action(action29);
 }
 
 // src/cli/commands/self-update.ts
@@ -81451,23 +81471,18 @@ function parseMetadataFilter(raw2) {
 }
 async function listDocuments(ctx, opts) {
   const { projectId, limit, offset = 0 } = opts;
-  let docIds = null;
-  if (projectId) {
-    const { data: data2, error: error4 } = await ctx.supabase.from("cerefox_document_projects").select("document_id").eq("project_id", projectId);
-    if (error4)
-      throw error4;
-    docIds = (data2 ?? []).map((r) => r.document_id);
-    if (docIds.length === 0)
-      return [];
-  }
-  let q = ctx.supabase.from("cerefox_documents").select(DOC_COLS).is("deleted_at", null).order("updated_at", { ascending: false });
-  if (docIds)
-    q = q.in("id", docIds);
+  const selectCols = projectId ? `${DOC_COLS}, cerefox_document_projects!inner(project_id)` : DOC_COLS;
+  let q = ctx.supabase.from("cerefox_documents").select(selectCols).is("deleted_at", null).order("updated_at", { ascending: false });
+  if (projectId)
+    q = q.eq("cerefox_document_projects.project_id", projectId);
   q = q.range(offset, offset + limit - 1);
   const { data, error: error3 } = await q;
   if (error3)
     throw error3;
-  return data ?? [];
+  return (data ?? []).map((row) => {
+    const { cerefox_document_projects: _j, ...doc2 } = row;
+    return doc2;
+  });
 }
 async function listAllProjects(ctx) {
   const { data, error: error3 } = await ctx.supabase.from("cerefox_projects").select("*").order("name");
@@ -81583,7 +81598,8 @@ function projectDocResult(r) {
     chunk_count: r.chunk_count ?? 0,
     total_chars: r.total_chars ?? 0,
     doc_updated_at: r.doc_updated_at ?? null,
-    is_partial: r.is_partial ?? false
+    is_partial: r.is_partial ?? false,
+    below_confidence: r.below_confidence ?? false
   };
 }
 function projectChunkResult(r) {
@@ -81599,7 +81615,8 @@ function projectChunkResult(r) {
     doc_title: r.doc_title ?? "",
     doc_source: r.doc_source ?? null,
     doc_project_ids: r.doc_project_ids ?? [],
-    doc_metadata: r.doc_metadata ?? {}
+    doc_metadata: r.doc_metadata ?? {},
+    below_confidence: r.below_confidence ?? false
   };
 }
 async function runSearch(ctx, opts) {
@@ -81640,7 +81657,7 @@ async function runSearch(ctx, opts) {
       p_query_text: query,
       p_query_embedding: embedding,
       p_match_count: count,
-      p_alpha: 0.7,
+      p_alpha: getSearchAlpha(),
       p_use_upgrade: false,
       p_project_id: projectId,
       p_min_score: getMinSearchScore()
@@ -81656,7 +81673,7 @@ async function runSearch(ctx, opts) {
     p_query_text: query,
     p_query_embedding: embedding,
     p_match_count: Math.min(count, 5),
-    p_alpha: 0.7,
+    p_alpha: getSearchAlpha(),
     p_project_id: projectId,
     p_min_score: getMinSearchScore()
   };
@@ -82079,7 +82096,7 @@ function registerDocumentReadRoutes(app, ctx) {
   });
   app.get("/api/v1/documents/:document_id/chunks", async (c2) => {
     const documentId = c2.req.param("document_id");
-    const { data, error: error3 } = await ctx.supabase.from("cerefox_chunks").select("id, document_id, chunk_index, heading_path, heading_level, title, content, char_count").eq("document_id", documentId).is("version_id", null).order("chunk_index");
+    const { data, error: error3 } = await ctx.supabase.from("cerefox_chunks").select("id, document_id, chunk_index, heading_path, heading_level, title, content, char_count").eq("document_id", documentId).is("version_id", null).order("chunk_index").range(0, 4999);
     if (error3)
       return c2.json({ detail: error3.message }, 500);
     const rows = data ?? [];