@llblab/pi-actors 0.22.0 → 0.22.1

package/CHANGELOG.md

@@ -2,6 +2,11 @@
 
 ## Unreleased
 
+## 0.22.1: Tool Registration Lens Hotfix
+
+- `[Skills]` Added tool-registration lenses to the packaged actors skill so agents prefer persistent tools for error-prone workflows, safe preflights around dangerous operations, and context-affordance shortcuts that should be visible in future sessions.
+- `[Package]` Bumped package metadata, lockfile metadata, and packaged skill metadata for the hotfix release.
+
 ## 0.22.0: Cross-Platform Runtime Notification Layer
 
 - `[Runtime]` Started the cross-platform notification layer with a file-backed advisory wake notifier (`wake.jsonl`), explicit initial/wake/poll reconciliation callbacks, periodic reconciliation fallback, and run-message/room-message/branch-inbox wake records. Run messages now persist a canonical inbox record before optional endpoint delivery, can accept mailbox-only control endpoints without FIFO/named-pipe transport, mark delivered endpoint messages `sent`, expose recent run inbox entries through `inspect view=mailbox`, and provide locked run-inbox claim/handle/fail helpers for runtime reconciliation loops. Files remain the canonical mailbox/event state for inspection and crash recovery.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llblab/pi-actors",
-  "version": "0.22.0",
+  "version": "0.22.1",
   "private": false,
   "description": "Local Actor Kernel for Pi",
   "keywords": [

package/skills/actors/SKILL.md

@@ -2,7 +2,7 @@
 name: actors
 description: Highest-density practical guide for pi-actors. Read this skill whenever prompt and tools are not enough for spawn, message, inspect, actor runs, tools, recipes, command templates, async lifecycle, mailboxes, artifacts, and local orchestration mechanics.
 metadata:
-  version: 0.22.0
+  version: 0.22.1
 ---
 
 # Actors (pi-actors)
@@ -244,6 +244,14 @@ Cleanup rule: periodically inspect `~/.pi/agent/recipes` as the live muscle-memo
 
 Use it when a command/template/recipe should become durable agent muscle memory. Prefer typed args or placeholder-derived args; use `update=true` for replacement and `template=null` or `template=""` for deletion. `register_tool` should create/update/delete recipe files in the user recipe root; direct file editing is allowed but is the lower-level path.
 
+Tool-registration lenses:
+
+1. **Error-prone operation lens**: register wrappers for workflows agents often mis-sequence or under-check, such as release preflights, tag verification, package version checks, and context validation.
+2. **Dangerous operation safety lens**: prefer safe read-only or preflight tools around irreversible actions (`push`, `merge`, `tag`, `publish`, destructive cleanup). The tool should make the risky state visible and should not perform the irreversible step unless that is explicitly its guarded purpose.
+3. **Context-affordance lens**: register tools that should be injected as visible capabilities because their presence changes agent behavior for the better. A named tool like `release_preflight` makes the safe path more salient than a remembered shell incantation.
+
+Default bias: register diagnostic/preflight tools before action tools. A good persistent tool shrinks the chance of a subtle operational mistake, not just the number of keystrokes.
+
 Tool templates may be:
 
 - A foreground command template.

package/skills/swarm/SKILL.md

@@ -2,7 +2,7 @@
 name: swarm
 description: Subagent orchestration with scoped locks and quorum consensus. Use for multi-model review, parallel scoped work, delegated audit, and coordinated subagent execution.
 metadata:
-  version: 0.22.0
+  version: 0.22.1
 ---
 
 # Swarm