@pellux/goodvibes-agent 0.1.36 → 0.1.38

package/CHANGELOG.md

@@ -2,6 +2,15 @@
 
 All notable changes to GoodVibes Agent will be recorded here.
 
+## 0.1.38 - 2026-05-31
+
+- 072503c Add routine schedule promotion receipts
+- 5bb9801 Update automation capability benchmark
+
+## 0.1.37 - 2026-05-31
+
+- 656b6f4 Add Agent routine daemon schedule promotion
+
 ## 0.1.36 - 2026-05-31
 
 - 9de2f5e Add guided Agent starter authoring

package/README.md

@@ -68,10 +68,14 @@ Local Agent behavior is editable from the TUI:
 /personas use research
 /routines create --name "Evening Review" --description "Review open work before shutdown" --steps "Check work plan, approvals, and Agent Knowledge status before summarizing." --enabled true
 /routines start evening-review
+/schedule promote-routine evening-review --cron "0 17 * * 1-5" --timezone America/Chicago --yes
+/schedule receipts
 /agent-skills create --name "Morning Brief" --description "Daily briefing flow" --procedure "Check tasks, approvals, calendar, and unread state before summarizing." --enabled true
 /skills local list
 ```
 
+Starting a routine records local usage and prints its steps; it does not spawn background agents or daemon automation jobs. Promotion to a daemon schedule is separate and explicit: it calls the public `schedules.create` route on the externally managed daemon only after `--yes`, records a redacted local receipt, and the generated scheduled prompt keeps Agent Knowledge isolated from default Knowledge/Wiki and HomeGraph.
+
 ## Daemon Prerequisite
 
 Start or restart the daemon from GoodVibes TUI or the daemon host before launching Agent. Agent status and companion/knowledge routes connect to that external daemon, normally on `http://127.0.0.1:3421`.

package/docs/getting-started.md

@@ -70,12 +70,13 @@ Personas, routines, and reusable Agent skills are local to GoodVibes Agent. They
 /personas use research
 /routines create --name "Evening Review" --description "Review open work before shutdown" --steps "Check work plan, approvals, and Agent Knowledge status before summarizing." --enabled true
 /routines start evening-review
+/schedule promote-routine evening-review --cron "0 17 * * 1-5" --timezone America/Chicago --yes
 /agent-skills create --name "Morning Brief" --description "Daily briefing flow" --procedure "Check tasks, approvals, calendar, and unread state before summarizing." --enabled true
 /agent-skills enabled
 /skills local list
 ```
 
-The active persona plus enabled Agent routines and skills are injected into the main serial assistant conversation. Starting a routine records local usage and prints its steps; it does not spawn background agents or daemon automation jobs.
+The active persona plus enabled Agent routines and skills are injected into the main serial assistant conversation. Starting a routine records local usage and prints its steps; it does not spawn background agents or daemon automation jobs. Promoting a routine to a schedule is an explicit `schedules.create` call to the external daemon, requires `--yes`, writes a local redacted promotion receipt, and preserves the rule that Agent Knowledge never falls back to default Knowledge/Wiki or HomeGraph.
 
 ## External Daemon
 

package/docs/operator-capability-benchmark.md

@@ -53,7 +53,7 @@ Primary sources used for the benchmark:
 | Channels | WhatsApp, Telegram, Slack, Discord, Signal, iMessage, web chat | GoodVibes daemon channel and companion surfaces with Agent-side policy, a Channels operator workspace, and per-channel readiness/risk labels |
 | Knowledge/memory | Durable memory, semantic search, wiki/claim layers | Isolated Agent Knowledge routes with workspace ask/search/ingest/review flows plus local memory/skills/personas/routines |
 | Skills/procedural memory | Skills directories, registries, skill lifecycle | Local Agent skills with review/stale/source/provenance fields |
-| Scheduling | Natural-language cron, run/pause/resume/edit/remove, delivery | Guarded automation/schedule routes plus local routines; hidden model scheduling blocked |
+| Scheduling | Natural-language cron, run/pause/resume/edit/remove, delivery | Local routines can be explicitly promoted to external daemon `schedules.create` with `--yes`; redacted local promotion receipts are reviewable; hidden model scheduling and local scheduler spawns are blocked |
 | Tools/MCP | Broad toolsets, MCP, browser, media, terminal, files | GoodVibes SDK tools with Agent policy guards and MCP/provider integrations |
 | Voice/media/canvas/nodes | Voice, TTS, mobile nodes, live canvas, browser automation | GoodVibes media/voice/browser/node primitives with an Agent workspace for setup, image input, browser posture, MCP, and remote/node inspection |
 | Build/code work | Direct terminal/file/code tools and subagents | Explicit delegation to GoodVibes TUI; local WRFC/spawn fanout blocked |
@@ -66,6 +66,7 @@ GoodVibes Agent should exceed OpenClaw/Hermes by making these properties true fr
 
 - Capability surfaces are discoverable through `goodvibes-agent capabilities`, `/capabilities`, onboarding, and the operator workspace.
 - Agent Knowledge isolation is a release gate, not a convention.
+- Routine-to-schedule promotion preserves Agent Knowledge isolation and uses only public external daemon schedule routes.
 - Model-visible tools are policy-gated for serial, non-secret, non-destructive use.
 - Personal assistant state is Agent-local unless an explicit Agent Knowledge ingest route is used.
 - Build work is delegated to the product that owns coding execution instead of turning the personal operator into a second coding TUI.
@@ -77,6 +78,7 @@ GoodVibes Agent should exceed OpenClaw/Hermes by making these properties true fr
 - Artifact and multimodal Agent Knowledge ingest affordances once Agent-specific routes are stable.
 - Visual starter-template editing inside the fullscreen Agent workspace after the command-guided authoring path.
 - Artifact and multimodal Agent Knowledge ingestion when the isolated Agent route accepts artifact-backed media.
+- Live schedule recovery/status correlation for promoted routines.
 - Delegation receipts and artifact review inside the operator workspace.
 - Approval center with route risk labels and saved policy presets.
 - Intent-gated tool exposure so the model sees fewer irrelevant tools per turn while retaining broad capability coverage.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@pellux/goodvibes-agent",
-  "version": "0.1.36",
+  "version": "0.1.38",
   "private": false,
   "description": "Near-fork GoodVibes operator assistant with the GoodVibes TUI shell, renderer, input, fullscreen workspace, and daemon-connected Agent product brain.",
   "type": "module",