@mindstudio-ai/remy 0.1.301 → 0.1.303

package/dist/headless.js

@@ -7712,16 +7712,7 @@ function clearSession(state) {
     log11.warn("Session archive on clear failed", { error: err.message });
   }
   state.messages = [];
-  state.models = void 0;
-  try {
-    if (fs21.existsSync(SESSION_FILE)) {
-      fs21.unlinkSync(SESSION_FILE);
-    }
-  } catch (err) {
-    log11.warn("Session clear: could not remove live file", {
-      error: err.message
-    });
-  }
+  saveSession(state);
 }
 
 // src/compaction/trigger.ts
@@ -10480,6 +10471,7 @@ var HeadlessSession = class {
   handleClear() {
     clearSession(this.state);
     return {
+      ...this.state.models && { models: this.state.models },
       modelSurfaces: getEffectiveModelSurfaces(),
       allowedModelsByType: ALLOWED_MODELS_BY_TYPE
     };

package/dist/index.js

@@ -2843,16 +2843,7 @@ function clearSession(state) {
     log3.warn("Session archive on clear failed", { error: err.message });
   }
   state.messages = [];
-  state.models = void 0;
-  try {
-    if (fs10.existsSync(SESSION_FILE)) {
-      fs10.unlinkSync(SESSION_FILE);
-    }
-  } catch (err) {
-    log3.warn("Session clear: could not remove live file", {
-      error: err.message
-    });
-  }
+  saveSession(state);
 }
 var log3, SESSION_FILE, ARCHIVE_DIR, ARCHIVE_NAME_RE, archiveSortKey, ARCHIVE_COUNT_RE, archiveCountCache, archiveMsgCache, ARCHIVE_MSG_CACHE_MAX;
 var init_session = __esm({
@@ -11470,6 +11461,7 @@ var init_headless = __esm({
       handleClear() {
         clearSession(this.state);
         return {
+          ...this.state.models && { models: this.state.models },
           modelSurfaces: getEffectiveModelSurfaces(),
           allowedModelsByType: ALLOWED_MODELS_BY_TYPE
         };

package/dist/prompt/skills/dataSources.md

@@ -31,13 +31,13 @@ const { results } = await Policies.search('what are the payment terms?', { topK:
 const context = results.map((r) => r.text).join('\n\n');
 ```
 
-Hits are `{ score, text, citation }` with `citation: { documentId, filename, pageNumber, chunkIndex, headingPath, boundingBox?, url }`, plus `retrievalRank`/`retrievalScore` — the position before reranking, so you can show what reranking did.
+Hits are `{ score, text, citation }` with `citation: { documentId, filename, pageNumber, chunkIndex, headingPath, boundingBox?, url }`, plus `retrievalRank`/`retrievalScore` — the position before reranking, so you can show what reranking did. With reranking on (the default) `score` is the reranker's 0–1 relevance and the right place for quality cutoffs; without it the scale varies by mode (cosine / rank-fusion / keyword overlap). `scoreThreshold` floors the retrieval branch before fusion and reranking — leave it unset unless measured on the corpus.
 
 **Always render the citation.** `citation.url` is a stable on-domain link — put it in an `<a href>` beside the answer. Retrieval is approximate; a user who can click through can judge for themselves. An answer with no citation is an assertion.
 
 Created on first use, so searching a source the build hasn't populated returns no results rather than throwing. `search` options: `topK` (default 5, max 50), `scoreThreshold`, `filter`, `mode`, `maxPerDocument`, `highlight`, `rerank`, `hybrid`.
 
-**Filtering** narrows a search before ranking, and every condition only narrows: `filter: { metadata: { department: 'legal', year: [2025, 2026] }, filename, documentIds, pages: { min?, max? }, contains: 'all these words', phrase: 'exact adjacent sequence' }`. Metadata is tagged at add time (scalars only, ≤16 keys); re-adding the same bytes with different metadata updates the tags in place, free. Filters are the right tool for scoping retrieval (per-user, per-category); they are NOT a substitute for a `db` query over structured data.
+**Filtering** narrows a search before ranking, and every condition only narrows: `filter: { metadata: { department: 'legal', year: [2025, 2026], signedAt: { gte: 20250101 } }, filename, documentIds, pages: { min?, max? }, contains: 'all these words', phrase: 'exact adjacent sequence' }`. Metadata matches per key: scalar = equals, array = any-of, `{ gte?, lte? }` = numeric range — ranges are numeric only, so store dates as sortable integers at add time (YYYYMMDD or epoch seconds) to range on them. Metadata is tagged at add time (scalars only, ≤16 keys); re-adding the same bytes with different metadata updates the tags in place, free. Filters are the right tool for scoping retrieval (per-user, per-category, a date window); they are NOT a substitute for a `db` query over structured data.
 
 **Modes**: `mode: 'hybrid'` (default) fuses semantic and keyword retrieval; `'semantic'` is the embedding alone; `'lexical'` is keyword-only with **no query embedding** — cheapest and fastest, right when the query is an identifier (an error code, a SKU, a name) rather than a meaning. `maxPerDocument: 2` stops one document monopolizing the results when the answer should draw on several. `highlight: true` adds `matches` (`{start, end}` offsets into `text`) for rendering highlighted excerpts.
 
@@ -84,7 +84,7 @@ Retrieve → join passages as context → have a model answer *from that context
 | Kind | Settings | Cost |
 |---|---|---|
 | **Free** (ranking) | `--rerank`, `--rerank-model`, `--hybrid`, `--top-k` | none, next search |
-| **Rebuild** (how docs become vectors) | `--max-chars`, `--min-chars`, `--drop-blocks`, `--contextual`, `--describe-images`, `--embedding-model`, `--extraction-model` | every document reprocessed |
+| **Rebuild** (how docs become vectors) | `--max-chars`, `--min-chars`, `--drop-blocks`, `--contextual`, `--contextual-model`, `--describe-images`, `--embedding-model`, `--extraction-model` | every document reprocessed |
 
 Images inside documents are described by a vision model and the description substituted into the searchable text (`--describe-images`, on by default) — without it a chart contributes nothing to search at all. Documents with no images cost nothing.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mindstudio-ai/remy",
-  "version": "0.1.301",
+  "version": "0.1.303",
   "description": "Remy coding agent",
   "repository": {
     "type": "git",