@adelie/agent-development 0.5.0 → 0.5.2

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@adelie/agent-development",
-  "version": "0.5.0",
+  "version": "0.5.2",
   "description": "Agent development on Adelie: build agent apps on the SDK or connect them to an agent over the Agent API, call any model through one unified LLM API, manage models and secrets, and orchestrate agents, sessions, costs and schedules.",
   "license": "Apache-2.0",
   "repository": {

package/plugin.json

@@ -3,6 +3,6 @@
   "description_zh": "基于 Adelie 的智能体开发：用 SDK 构建应用或经 Agent API 接入智能体、经统一的 LLM API 调用任意模型、管理模型与密钥、编排智能体/会话/成本/定时任务。",
   "short_description": "SDK, Agent API, unified LLM API, config and orchestration.",
   "short_description_zh": "SDK、Agent API、统一 LLM API、配置与编排。",
-  "version": "2026.10.17.2",
+  "version": "2026.10.18.1",
   "category": "ai-app-development"
 }

package/skills/penguin-orchestration/SKILL.md

@@ -127,7 +127,7 @@ penguin schedule update daily-report --period 12h    # adjust; --enable/--disabl
 penguin schedule rm daily-report                     # remove — no confirmation prompt
 ```
 
-- `--agent-id` defaults to yourself from the caller env, so this schedules the current agent. `--start-at` takes ISO 8601 or `now`; `--period` is at least 5m (`30m`/`12h`/`1d`/`7d`), omit it for a one-shot; `--end-at` bounds recurrence. Target the session you are in — `--session-id "$ADELIE_SESSION_ID"` — unless the user asked for somewhere else: the prompt then arrives in this conversation, with its context. Leave the target off when the user wants a separate session, or when the task is better off starting clean (a nightly report that should not inherit this conversation); each firing then opens a new session, which `--workspace <path>` and the `--model-id` + `--provider` pair configure.
+- `--agent-id` defaults to yourself from the caller env, so this schedules the current agent. `--start-at` takes ISO 8601 or `now`; `--period` is at least 5m (`30m`/`12h`/`1d`/`7d`), omit it for a one-shot, which needs a future `--start-at` (`now` is refused there); `--end-at` bounds recurrence. Target the session you are in — `--session-id "$ADELIE_SESSION_ID"` — unless the user asked for somewhere else: the prompt then arrives in this conversation, with its context. Leave the target off when the user wants a separate session, or when the task is better off starting clean (a nightly report that should not inherit this conversation); each firing then opens a new session, which `--workspace <path>` and the `--model-id` + `--provider` pair configure.
 - `add` creates the schedule **enabled** (`--disabled` stages it off) — deliberately diverging from the raw file, where `enabled` defaults to false. `update` is read-modify-write: unspecified fields keep their stored values, and switching the target form clears the other one.
 - In `schedule ls`, read: the AGENT column (without `--agent-id` the listing spans agents), `enabled` (a disabled entry never fires), `startAt` (first firing), `period` (absent means one-shot), the target — an existing session versus a new session per firing — and `lastFiredAt`.
 - The CLI writes through the schedules API, so mistakes are rejected synchronously. The TOML file stays the single source of truth — `<app_data_dir>/agents/<agent_id>/agent_state/schedule/<name>.toml`, fields mirroring the flags (`prompt`, `enabled` — false by default in the file, `start_at`, `period`, `end_at`, `session_id` / `workspace`+`provider`+`model_id`) — and remains editable with file tools; your system prompt's schedule roster lists yours. A hand edit is only validated by the periodic reconcile (roughly every 30s), with errors landing in error records rather than your terminal — prefer the CLI.