@vortex-os/base 0.9.0 → 0.11.0

package/dist/statusline-NQKJ3NWD.js

@@ -0,0 +1,30 @@
+import {
+  collectStatuslineProbes,
+  effortMeter,
+  ensureStatusline,
+  formatTokens,
+  formatWindow,
+  makeBar,
+  parseStatuslineInput,
+  renderStatusline,
+  runStatuslineCli,
+  safeSegment,
+  sniffEffortFromTranscript,
+  statuslineCommand
+} from "./chunk-DWANI3LV.js";
+import "./chunk-PZ5AY32C.js";
+export {
+  collectStatuslineProbes,
+  effortMeter,
+  ensureStatusline,
+  formatTokens,
+  formatWindow,
+  makeBar,
+  parseStatuslineInput,
+  renderStatusline,
+  runStatuslineCli,
+  safeSegment,
+  sniffEffortFromTranscript,
+  statuslineCommand
+};
+//# sourceMappingURL=statusline-NQKJ3NWD.js.map

package/dist/statusline-NQKJ3NWD.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":[],"sourcesContent":[],"mappings":"","names":[]}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@vortex-os/base",
-  "version": "0.9.0",
+  "version": "0.11.0",
   "description": "Base entry point for VortEX — a Multi-Agent Personal AI Work OS framework",
   "license": "MIT",
   "author": "vortex-os-project",

package/templates/manifest.json

@@ -1,6 +1,6 @@
 {
   "schema": "vortex-template-index/1",
-  "baseVersion": "0.9.0",
+  "baseVersion": "0.11.0",
   "files": [
     {
       "templateId": "commands/agenda.md",
@@ -45,7 +45,7 @@
     {
       "templateId": "routers/AI-RULES.md",
       "path": "routers/AI-RULES.md",
-      "sha256": "dc184f977c4a9970e5934b3a87a0bc533f7811c9bc5ecbfe68c6adffb0f4cc82"
+      "sha256": "8d611216cedece461557033e99d19a4e561b9997bdedce94dd47f8523197c979"
     },
     {
       "templateId": "routers/CLAUDE.md",

package/templates/routers/AI-RULES.md

@@ -29,8 +29,8 @@ npx vortex init --name "<your name>" --role "<your role>"
 Operating principle: **auto-maintain the operational memory; propose changes to the knowledge base.** You should never have to learn commands to get value — the records that make recall smarter accumulate on their own, while you keep full control over your own topic documentation.
 
 **Auto (no prompt — append-only operational records; *show, don't ask*):**
-- **Session start.** Run the start ritual: if a sync remote is configured, `git pull` (report conflicts, never auto-resolve); detect the environment if one is configured (and if a label resolves with a matching `.agent/env/<label>.md`, read that file as session-specific operating guidance); backfill any worklog missing from prior sessions; **load your `data/_memory/` always-on rules and scan its `_INDEX.md`** (see "The `data/` layout" → memory loading); report status. If the `SessionStart` hook is configured, the **data-side** ritual already ran and its report was **injected into your context — the user has NOT seen it. Start your first reply by relaying the key points: recent work, what's in progress, the time, any update notices, and any warnings.** If no hook ran, perform the ritual yourself first, then report the same status. (Automatic means the records updated on their own — informing the user is still your job.)
-- **Worklog.** As a work unit completes — and at session wind-down ("that's it for today", "wrap up") — ensure today's worklog exists and append the work. The agent is the primary path; the `SessionEnd` hook is the net.
+- **Session start.** Run the start ritual: if a sync remote is configured, `git pull` (report conflicts, never auto-resolve); detect the environment if one is configured (and if a label resolves with a matching `.agent/env/<label>.md`, read that file as session-specific operating guidance); auto-reindex the memory index if stale; backfill any worklog the report flags as missing (see **Worklog** below); **load your `data/_memory/` always-on rules and scan its `_INDEX.md`** (see "The `data/` layout" → memory loading); report status. If the `SessionStart` hook is configured, the **data-side** ritual already ran and its report was **injected into your context — the user has NOT seen it. Start your first reply by relaying the key points: recent work, what's in progress, the time, any update notices, and any warnings.** When you relay carried-over / stale-index / interrupted-git signals, explain them plainly and **offer to handle them** ("there are leftover changes from before — want me to check what they are?") rather than telling the user to run a command they may not know. If no hook ran, perform the ritual yourself first, then report the same status. (Automatic means the records updated on their own — informing the user is still your job.)
+- **Worklog.** As a work unit completes — and at session wind-down ("that's it for today", "wrap up") — ensure today's worklog exists and append the work. The agent is the primary path; the net is the **next session's start report**, which flags any day with commits but no worklog. Backfill each (newest first, **at most 3 per session** — list the rest): reconstruct what happened from that day's archived session(s), or from its commits/diffs when there is no archive, write it via `ensureWorklogEntry`, and **open the file with a one-line note that it was reconstructed after the fact** (which day was missed, when and from what it was rebuilt — in the worklog's language) so it is not taken for a live-authored record; then tell the user plainly what you filled in. Skip a day with nothing substantive, and skip entirely if the pull diverged.
 - **Session hand-off.** At wind-down — or whenever the user asks to hand off / continue later ("hand off", "wrap up so I can resume", "leave it for next time", "인수인계") — write a hand-off with `/handoff` (or `npx vortex handoff "<title>"`): **one file per session** under `data/_handoff/`, carrying the concrete next steps as unchecked `- [ ]` items, plus the current state and the pointers to resume from (files, commit hashes, decisions). A hand-off is a **forward-looking baton kept SEPARATE from the worklog** (the permanent "what happened" record): put next steps + how-to-resume here, leave the narrative in the worklog. One session that spans several topics writes **ONE** hand-off covering all of them — never a per-topic split, never a "hand-off" worklog file, and never carry another session's items forward (concurrent sessions each leave their own). The next session's start report surfaces the active hand-off(s) automatically (multiple are normal), and hand-offs older than the retention window (default 7 days) are swept to `_handoff/_archive/` on their own — so you never tidy them by hand.
 - **Decisions.** When the user makes a *substantive* decision ("let's go with X"), record it in the Decision Log. Real decisions, not casual asides.
 - **Ambient recall** (read-only). When the user references earlier work, run `/recall <the reference>` and weave a confident hit into one sentence. One nudge, not a list; drop it if waved off. Conversations are vectorized automatically at session start. With the `@vortex-os/memory-extended` add-on installed, the first session also sets recall up on its own — downloading the local search model (~470 MB, once) in the **background** — so recall and these ambient lookups just work with no prompt and no manual step (the session-start report notes the one-time download while it runs; relay that). To keep that download manual instead (metered line, CI), set `autoRecord.vectorizeAutoDownload: false` (or env `VORTEX_VECTORIZE_AUTO_DOWNLOAD=0`) and set it up once with `/recall` or `vortex vectorize`.