A local-first multi-agent app development platform, built on PenguinHarness
docs(2.2c): 文本面与默认根收尾 —— 非桌面壳里仍把旧名当「现在」的地方
lmliheng37f710d9f275
diff --git a/packages/cli/README.md b/packages/cli/README.mdindex a231461b..47d66659 100644--- a/packages/cli/README.md+++ b/packages/cli/README.md@@ -17,7 +17,7 @@ penguin chat # REPL: /compact,penguin chat --resume # resume the latest session```-Tool calls go through an approval gate — `--approve allow-all` (default) `| deny-all | read-only | always-ask`. Data lives under `~/.penguin/data` (`PENGUIN_HOME` or `--root` override); model credentials come from the Project config or provider env vars (e.g. `DEEPSEEK_API_KEY`).+Tool calls go through an approval gate — `--approve allow-all` (default) `| deny-all | read-only | always-ask`. Data lives under `~/.adelie/data` (`ADELIE_HOME`, the pre-rename `PENGUIN_HOME`, or `--root`); model credentials come from the Project config or provider env vars (e.g. `DEEPSEEK_API_KEY`).Prefer a one-line install with a bundled Node runtime? See [Quickstart → CLI and Web App](https://penguin.ooo/docs/quickstart-cli).diff --git a/packages/core/README.md b/packages/core/README.mdindex ba96c52d..68081754 100644--- a/packages/core/README.md+++ b/packages/core/README.md@@ -19,7 +19,7 @@ for await (const output of session.run([userText("Create hello.txt containing hi}```-A single `run` drives a complete Task: streaming output, per-call approvals, concurrent tool execution, interrupt carry-over, automatic reconnect and context compaction. State lives under `~/.penguin/data` (`PENGUIN_HOME`); every Session restores fully from its Trace.+A single `run` drives a complete Task: streaming output, per-call approvals, concurrent tool execution, interrupt carry-over, automatic reconnect and context compaction. State lives under `~/.adelie/data` (`ADELIE_HOME`, or the pre-rename `PENGUIN_HOME`); every Session restores fully from its Trace.## Documentationdiff --git a/packages/core/src/environment/mcp/provider.ts b/packages/core/src/environment/mcp/provider.tsindex 185fc59b..fe0fe26d 100644--- a/packages/core/src/environment/mcp/provider.ts+++ b/packages/core/src/environment/mcp/provider.ts@@ -423,10 +423,10 @@ export class McpToolProvider {// vault is deliberately NOT injected into MCP server processes (unlike command// subprocesses); a variable a server needs must be listed in the entry's env.// The SDK defaults are an allowlist (HOME/PATH/SHELL-class names only), so the- // harness's own configuration — every PENGUIN_* variable, PORT/HOST and the rest —- // never reaches a server: the same outcome the command-session strip enforces,- // by the opposite mechanism. Widening this base (e.g. to process.env) would undo- // that; the "harness variables never reach a stdio server" test pins it. A+ // harness's own configuration — every ADELIE_* / PENGUIN_* variable, PORT/HOST+ // and the rest — never reaches a server: the same outcome the command-session strip+ // enforces, by the opposite mechanism. Widening this base (e.g. to process.env) would+ // undo that; the "harness variables never reach a stdio server" test pins it. A// sandbox runner's own entries lie over the result.env: { ...getDefaultEnvironment(), ...t.env, ...confined.env },...(cwd !== undefined ? { cwd } : {}),diff --git a/packages/server/src/http/routes/plugins.ts b/packages/server/src/http/routes/plugins.tsindex 953b0c15..205d789d 100644--- a/packages/server/src/http/routes/plugins.ts+++ b/packages/server/src/http/routes/plugins.ts@@ -277,7 +277,7 @@ export function parsePluginArchive(* carry local edits).** The directory is `<config.root>/plugins`, the same one the library reads: the server's data- * root and the library's user plugin root are one directory, both defined by PENGUIN_HOME.+ * root and the library's user plugin root are one directory, both defined by ADELIE_HOME.*/async function importPlugin(deps: PluginsRouteDeps,diff --git a/packages/server/src/install-id.ts b/packages/server/src/install-id.tsindex 08b5a119..2082701e 100644--- a/packages/server/src/install-id.ts+++ b/packages/server/src/install-id.ts@@ -4,7 +4,7 @@* The problem it exists for: the browser keeps UI state in `localStorage` — the new-chat* draft with its Workspace, the sidebar's registered Workspaces, pinned Sessions, seen* markers — and `localStorage` has no relationship whatsoever to the data root. In the- * desktop app it lives in Electron's userData directory, so deleting `PENGUIN_HOME` does+ * desktop app it lives in Electron's userData directory, so deleting `ADELIE_HOME` does* not touch a byte of it. Both halves of every key are compile-time constants* (`ADMIN_USER_ID`, `DEFAULT_PROJECT_ID`), so a wipe-and-restart re-provisions the same* user and the same Project, the keys line up again, and the state the user thought theydiff --git a/packages/server/src/machines/ssh-config.ts b/packages/server/src/machines/ssh-config.tsindex 1b031b5f..64097403 100644--- a/packages/server/src/machines/ssh-config.ts+++ b/packages/server/src/machines/ssh-config.ts@@ -57,7 +57,7 @@ export function parseHostAliases(/*** A remote target's stable name: the SSH identity, `<user>@<alias>`. The Linux account is- * part of it because each account has its own `~/.penguin` — hence its own server, its own+ * part of it because each account has its own `~/.adelie` — hence its own server, its own* accounts — so `deploy@build-box` and `root@build-box` are two machines as far as anything* downstream is concerned.* The ALIAS is used rather than the resolved hostname: it is what the user chose, it isdiff --git a/packages/web/src/lib/strings.ts b/packages/web/src/lib/strings.tsindex 2f94fe8a..f8d80d1d 100644--- a/packages/web/src/lib/strings.ts+++ b/packages/web/src/lib/strings.ts@@ -1458,7 +1458,7 @@ export const zh = {* follows the penguin-config skill — one `penguin config model add` per model with* `--provider` mandatory, the config file never touched by hand, `penguin config model list`* at the end — and carries the Project id and the data root, which the CLI would otherwise- * take from its own defaults (the harness strips `PENGUIN_HOME` from a command's+ * take from its own defaults (the harness strips `ADELIE_HOME` from a command's* environment, so the CLI's default root is not the one the server runs on).*/aiAddTitle: "让 AI 添加模型分组",diff --git a/plugins/agent-development/plugin.json b/plugins/agent-development/plugin.jsonindex d56f13f9..bdda819d 100644--- a/plugins/agent-development/plugin.json+++ b/plugins/agent-development/plugin.json@@ -3,6 +3,6 @@"description_zh": "基于 Adelie 的智能体开发:用 SDK 构建应用、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, unified LLM API, config and orchestration.","short_description_zh": "SDK、统一 LLM API、配置与编排。",- "version": "2026.09.30.2",+ "version": "2026.10.07.1","category": "ai-app-development"}diff --git a/plugins/agent-development/skills/penguin-config/SKILL.md b/plugins/agent-development/skills/penguin-config/SKILL.mdindex 9b06e24f..7cb9d9c9 100644--- a/plugins/agent-development/skills/penguin-config/SKILL.md+++ b/plugins/agent-development/skills/penguin-config/SKILL.md@@ -28,9 +28,9 @@ penguin config model add --provider <group> --model-id <upstream_id> [--api-key- Prices are USD per million tokens (cache read / cache write / output).- `--vision` / `--no-vision` mark whether the model accepts images; omitting both keeps the current value (default is vision-capable).- `--max-tokens <n>` pins a per-model output cap (positive integer), overriding the Agent's `model.max_tokens`; omit to inherit. Lower it for small-context models — the per-Agent default (32000) cannot fit into e.g. a 32k context window together with any prompt.-- All `penguin config model ...` and `penguin config vault ...` commands accept `--root <dir>` to target another data root (default `PENGUIN_HOME`, then `~/.penguin/data`). Two configuration targets — treat the difference as a hard rule:- - **Penguin's own model** (self-configuration: the model Penguin itself runs on): pass `--root <data root>` as well — the parent directory of the App Data Dir named in your Environment section. An agent running inside Adelie never sees `PENGUIN_HOME`: the harness strips every `PENGUIN_*` variable from a command's environment, so a command without `--root` falls back to `~/.penguin/data` and configures a root the running server does not read.- - **An AI app you are building**: `--root` **must** point at the app's own data directory inside the project (e.g. `--root ./penguin_data`, the same path the app gives `createAgent({ root })`) unless the user explicitly chose another location — never write an app's models or keys into the global `~/.penguin/data`, which belongs to the person running Penguin, not to the app.+- All `penguin config model ...` and `penguin config vault ...` commands accept `--root <dir>` to target another data root (default `ADELIE_HOME`, then the pre-rename `PENGUIN_HOME`, then `~/.adelie/data`). Two configuration targets — treat the difference as a hard rule:+ - **Penguin's own model** (self-configuration: the model Penguin itself runs on): pass `--root <data root>` as well — the parent directory of the App Data Dir named in your Environment section. An agent running inside Adelie never sees `ADELIE_HOME` or `PENGUIN_HOME`: the harness strips every `ADELIE_*` and `PENGUIN_*` variable from a command's environment, so a command without `--root` falls back to `~/.adelie/data` and configures a root the running server does not read.+ - **An AI app you are building**: `--root` **must** point at the app's own data directory inside the project (e.g. `--root ./penguin_data`, the same path the app gives `createAgent({ root })`) unless the user explicitly chose another location — never write an app's models or keys into the global `~/.adelie/data`, which belongs to the person running Penguin, not to the app.- While developing an app, review regularly: `penguin config model list --root <app root>` should show the app's entries, and the global list (no `--root`) should stay clean.Other model commands:diff --git a/plugins/agent-development/skills/penguin-sdk/SKILL.md b/plugins/agent-development/skills/penguin-sdk/SKILL.mdindex ea8dc09e..00de006e 100644--- a/plugins/agent-development/skills/penguin-sdk/SKILL.md+++ b/plugins/agent-development/skills/penguin-sdk/SKILL.md@@ -29,7 +29,7 @@ With every reference relative to the project, the user can move or copy the fold## Keys and the data root — check before you build-**The app's Penguin data root must live inside the CWD workspace — never `~/.penguin`.** Point `createAgent({ root })` and every `penguin config ... --root <dir>` at a directory under the current working directory (e.g. `./penguin_data`); the global `~/.penguin` belongs to the person running Penguin and must never hold — or lend — the app's config or keys.+**The app's Penguin data root must live inside the CWD workspace — never `~/.adelie`.** Point `createAgent({ root })` and every `penguin config ... --root <dir>` at a directory under the current working directory (e.g. `./penguin_data`); the global `~/.adelie` belongs to the person running Penguin and must never hold — or lend — the app's config or keys.**Credential first, code second** — a finished app that cannot answer is a failed delivery discovered too late. Before writing any code:@@ -37,7 +37,7 @@ With every reference relative to the project, the user can move or copy the foldenv | grep -oE "(DEEPSEEK|OPENAI|ANTHROPIC|GEMINI)_API_KEY" || echo none```-**Only two sources count as a usable credential**: a vault-injected environment variable (the check above; vault keys also appear in your Vault Keys section), or a key already configured in the app's own data root (`penguin config model list --root <data_dir>`). Keys in the global `~/.penguin` or any other `.penguin` directory do **not** count — a bare `penguin config model list` (no `--root`) reads the global store, because the CLI defaults to the global root unless `--root` is given, so a key showing up there proves nothing for the app and must never be used or copied.+**Only two sources count as a usable credential**: a vault-injected environment variable (the check above; vault keys also appear in your Vault Keys section), or a key already configured in the app's own data root (`penguin config model list --root <data_dir>`). Keys in the global `~/.adelie` or any other `.adelie` directory do **not** count — a bare `penguin config model list` (no `--root`) reads the global store, because the CLI defaults to the global root unless `--root` is given, so a key showing up there proves nothing for the app and must never be used or copied.If neither counted source yields a key, **stop immediately and ask the user to configure one — do not start building, and do not burn turns re-checking in a loop**: have them open this agent's settings via the **gear icon** on its card (left side, Agents page) and add a model API key (e.g. `DEEPSEEK_API_KEY`) in the **key vault** tab — vault values reach your shell environment on the next task. One clear check, then hand back to the user. Build only after a credential is confirmed, or after clearly agreeing with the user to build now and verify later. Model ids to offer the user come from the penguin CLI catalog (`penguin config model add --help`) and the agenthub-models skill's id table.@@ -54,7 +54,7 @@ Configure a model for the app's data root, in this order — stop at the first t1. `penguin config model add --root <data_dir> --provider <group> --model-id <id> --api-key <key> [--base-url <url>] [--client-type openai-chat] --set-default` — prefer `--client-type openai-chat --base-url <endpoint>` (works with any OpenAI Chat Completions compatible endpoint; exact ids in the agenthub-models skill). `--provider` is required: a model is always the `(provider, model_id)` pair and the group is never inferred from the id (`custom` for an endpoint outside the built-in groups).2. Environment variables cover the **credential only** (`DEEPSEEK_API_KEY`, `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, …), and only for an entry whose requests go to the **vendor's own endpoint** (no `--base-url`, or the vendor's official one) — an entry with a `--base-url` of its own (a gateway, a self-hosted server) needs `--api-key`, or `createSession` refuses it. Model selection still comes from the project config, whose preset default is `deepseek-flash`. Env-only setup therefore works out of the box only with `DEEPSEEK_API_KEY`; for another vendor either run the CLI command above or pass a configured `{ provider, modelId }` pair to `createSession`.-Keep model API keys **project-local**: configure them with the penguin CLI into the app's own data root under the working directory, so the project stays self-contained and movable. When building an AI app, **always pass `--root <data_dir>` pointing at the app's data directory inside the current working directory** (the same path you give `createAgent({ root })`, e.g. `./penguin_data`) — never run `penguin config ...` without `--root`, or it writes to the global `~/.penguin/data` instead of the project. Never read, copy or fall back to model keys stored in the user's global `~/.penguin` directory — that config belongs to the person running Penguin, not to the app you are building.+Keep model API keys **project-local**: configure them with the penguin CLI into the app's own data root under the working directory, so the project stays self-contained and movable. When building an AI app, **always pass `--root <data_dir>` pointing at the app's data directory inside the current working directory** (the same path you give `createAgent({ root })`, e.g. `./penguin_data`) — never run `penguin config ...` without `--root`, or it writes to the global `~/.adelie/data` instead of the project. Never read, copy or fall back to model keys stored in the user's global `~/.adelie` directory — that config belongs to the person running Penguin, not to the app you are building.Model config lives in one hidden file under the data root's project directory: `.project_config.toml`. It is CLI-only — never read, print or edit it.diff --git a/plugins/agent-development/skills/unified-llm-api/SKILL.md b/plugins/agent-development/skills/unified-llm-api/SKILL.mdindex ddfd308f..e74fd197 100644--- a/plugins/agent-development/skills/unified-llm-api/SKILL.md+++ b/plugins/agent-development/skills/unified-llm-api/SKILL.md@@ -25,7 +25,7 @@ const client = new AutoLLMClient({ model: "<model_id>", apiKey: "<key>", baseUrlIf the user's message only invokes this skill (e.g. "use agenthub-models skill") without a concrete task, ask the user what they want to build. Do not write code until the requirement is clear.-**Important prerequisite — set the key up first, then develop.** When the script is an AI app you are building for the user, have them add the model API key in **this agent's key vault** (gear icon on its card, Agents page → settings → key vault tab) *before* you start, so the credential is in your shell environment. If the app stores its own model config, keep its Penguin data root **inside the CWD workspace** (`--root ./penguin_data`), never `~/.penguin`. Model ids can come from the penguin CLI catalog and the id table below.+**Important prerequisite — set the key up first, then develop.** When the script is an AI app you are building for the user, have them add the model API key in **this agent's key vault** (gear icon on its card, Agents page → settings → key vault tab) *before* you start, so the credential is in your shell environment. If the app stores its own model config, keep its Penguin data root **inside the CWD workspace** (`--root ./penguin_data`), never `~/.adelie`. Model ids can come from the penguin CLI catalog and the id table below.Check for a usable API key before writing code — the client needs one for whichever provider you target:@@ -33,11 +33,11 @@ Check for a usable API key before writing code — the client needs one for whicenv | grep -oE "(DEEPSEEK|OPENAI|ANTHROPIC|GEMINI|ZAI|MOONSHOT|MINIMAX)_API_KEY" || echo none```-Vault keys also appear in your Vault Keys section. **Only two sources count as a usable key**: a vault-injected environment variable (the check above), or — when the app stores its own model config — a key already configured in the app's own data root (`penguin config model list --root <data_dir>`). Keys living in the global `~/.penguin` or any other `.penguin` directory do **not** count — a bare `penguin config model list` (no `--root`) reads the global store, because the CLI defaults to the global root unless `--root` is given, so a key showing up there proves nothing for your script and must never be used or copied.+Vault keys also appear in your Vault Keys section. **Only two sources count as a usable key**: a vault-injected environment variable (the check above), or — when the app stores its own model config — a key already configured in the app's own data root (`penguin config model list --root <data_dir>`). Keys living in the global `~/.adelie` or any other `.adelie` directory do **not** count — a bare `penguin config model list` (no `--root`) reads the global store, because the CLI defaults to the global root unless `--root` is given, so a key showing up there proves nothing for your script and must never be used or copied.If neither counted source yields a usable key, **stop immediately and ask the user to configure one — do not write code, and do not keep calling tools to retry**: ask them to add one in the agent's **key vault** (gear icon on the agent's card, Agents page → settings → key vault tab); vault values reach your shell environment on the next task. Re-checking the environment or the vault in a loop just wastes turns — one clear check, then hand back to the user.-Keep model API keys **project-local**: for an app that stores its own model config, write the key into the project under the working directory with the penguin CLI, **always passing `--root <data_dir>` for a directory inside the current working directory** (`penguin config model add --root ./penguin_data --provider <group> --model-id <id> --api-key <key>`) — without `--root` it writes to the global `~/.penguin/data` instead. `--provider` is required alongside `--model-id`: a model entry is the `(provider, model_id)` pair and the group is never inferred (use `custom` for an endpoint outside the built-in groups). Otherwise rely on vault-injected environment variables. Never read, copy or fall back to model keys stored in the user's global `~/.penguin` directory — that config belongs to the person running Penguin, not to your script.+Keep model API keys **project-local**: for an app that stores its own model config, write the key into the project under the working directory with the penguin CLI, **always passing `--root <data_dir>` for a directory inside the current working directory** (`penguin config model add --root ./penguin_data --provider <group> --model-id <id> --api-key <key>`) — without `--root` it writes to the global `~/.adelie/data` instead. `--provider` is required alongside `--model-id`: a model entry is the `(provider, model_id)` pair and the group is never inferred (use `custom` for an endpoint outside the built-in groups). Otherwise rely on vault-injected environment variables. Never read, copy or fall back to model keys stored in the user's global `~/.adelie` directory — that config belongs to the person running Penguin, not to your script.## Model IDsdiff --git a/plugins/agent-tuning/plugin.json b/plugins/agent-tuning/plugin.jsonindex e35905d4..6bbaed76 100644--- a/plugins/agent-tuning/plugin.json+++ b/plugins/agent-tuning/plugin.json@@ -3,6 +3,6 @@"description_zh": "闭环的 Agent 调优:依据需求初始化 Agent、设计并校准能力 Benchmark、隔离执行与评分、再根据测得结果改进 Agent。","short_description": "Initialize, benchmark, evaluate and improve agents.","short_description_zh": "初始化、评测、评分与改进 Agent。",- "version": "2026.09.30.1",+ "version": "2026.10.07.1","category": "ai-app-development"}diff --git a/plugins/agent-tuning/skills/agent-evaluation/SKILL.md b/plugins/agent-tuning/skills/agent-evaluation/SKILL.mdindex fb7625e3..5c03af99 100644--- a/plugins/agent-tuning/skills/agent-evaluation/SKILL.md+++ b/plugins/agent-tuning/skills/agent-evaluation/SKILL.md@@ -57,15 +57,15 @@ Before launch, snapshot every file under the Case's `statement/` and `rubric/` dUse an existing verified Penguin CLI or repository-local launcher. Do not install or probe a launcher. Snapshot the isolated Workspace and record the existing Trace files.-Resolve `PROJECT_DIR`, then derive and verify `PROJECT_ID`, then derive and verify `PENGUIN_HOME`. Perform these as separate shell statements in this order. Never compress the assignments onto one command line, derive a value before its input exists, or substitute another Penguin home. Before launch, confirm that `PROJECT_ID` equals the basename of `PROJECT_DIR` and `PENGUIN_HOME` equals its dirname.+Resolve `PROJECT_DIR`, then derive and verify `PROJECT_ID`, then derive and verify `ADELIE_HOME`. Perform these as separate shell statements in this order. Never compress the assignments onto one command line, derive a value before its input exists, or substitute another data root. Before launch, confirm that `PROJECT_ID` equals the basename of `PROJECT_DIR` and `ADELIE_HOME` equals its dirname.Start one foreground execution with a fresh top-level Session. With an explicit pair, use:```bashPROJECT_DIR="<app_data_dir>" # the App Data Dir value from your Environment section is the project rootPROJECT_ID="$(basename "$PROJECT_DIR")"-PENGUIN_HOME="$(dirname "$PROJECT_DIR")"-export PENGUIN_HOME+ADELIE_HOME="$(dirname "$PROJECT_DIR")"+export ADELIE_HOMEpenguin run \--message "Read README.md in the current Workspace and complete the task exactly as specified there." \--provider "<provider>" --model-id "<model_id>" --project-id "$PROJECT_ID" \diff --git a/plugins/agent-tuning/skills/agent-optimization/SKILL.md b/plugins/agent-tuning/skills/agent-optimization/SKILL.mdindex e428f1ad..908dd608 100644--- a/plugins/agent-tuning/skills/agent-optimization/SKILL.md+++ b/plugins/agent-tuning/skills/agent-optimization/SKILL.md@@ -26,7 +26,7 @@ Resolve paths from the Environment's App Data Dir without recursively discoverin```textPROJECT_DIR = <app_data_dir>PROJECT_ID = <basename_of_project_dir>-PENGUIN_HOME = <parent_of_project_dir>+ADELIE_HOME = <parent_of_project_dir>TARGET = <app_data_dir>/agents/<test_agent_id>STATE = <target>/agent_stateTRACES = <target>/tracesdiff --git a/plugins/csu-mail/plugin.json b/plugins/csu-mail/plugin.jsonindex 2f1c7e39..4235fc50 100644--- a/plugins/csu-mail/plugin.json+++ b/plugins/csu-mail/plugin.json@@ -3,7 +3,7 @@"description_zh": "绕开统一身份认证管理 Coremail 邮箱(中南大学学生邮箱):生成客户端专用密码,再用 IMAP/SMTP 从命令行查信、检索、读信、发信,并在「已发送」留底。","short_description": "Coremail mailbox over IMAP/SMTP with an app password, no CAS.","short_description_zh": "Coremail 邮箱免 CAS 收发信:专用密码 + IMAP/SMTP,发信自动留底。",- "version": "2026.10.05.1",+ "version": "2026.10.07.1","category": "office-productivity","preinstall": false}diff --git a/plugins/csu-mail/skills/csu-mail/SKILL.md b/plugins/csu-mail/skills/csu-mail/SKILL.mdindex 5d28db02..fb0bb86e 100644--- a/plugins/csu-mail/skills/csu-mail/SKILL.md+++ b/plugins/csu-mail/skills/csu-mail/SKILL.md@@ -102,7 +102,7 @@ CHROME_PATH=/path/to/chrome \# ③ 存进密钥库并删掉明文# 必须显式带 --project-id / --agent-id:CLI 的默认项目是 default_project,# 不带就会写进别的项目的密钥库(密钥库里查得到,环境变量里永远没有)。-# 项目 id = 运行环境 App Data Dir 的最后一段,如 /root/.penguin/data/asass -> asass+# 项目 id = 运行环境 App Data Dir 的最后一段,如 /root/.adelie/data/asass -> asassP="--project-id <项目id> --agent-id default_agent"penguin config vault set $P --key CSU_MAIL_AUTHCODE --value "$(cat secret.txt)" && shred -u secret.txtpenguin config vault set $P --key CSU_MAIL_ADDR --value "学号@csu.edu.cn"@@ -150,7 +150,7 @@ $V scripts/mail.py send --to [email protected] --subject "..." --body-file body.txt现象是「密钥库里查得到,Agent 的 shell 里却始终没有这个变量」。2026-10-02 真实踩到:专用密码落进了 `default_project`,而 Agent 跑在别的项目里,于是 `mail.py check` 只报「缺少邮箱地址」——**别把它当认证失败去重试登录**。查证方法:`penguin config vault list --project-id <项目id> --agent-id default_agent`,- 项目 id = 运行环境 App Data Dir 的最后一段(`/root/.penguin/data/<项目id>`),列表里有、`env` 里没有就是这个问题。+ 项目 id = 运行环境 App Data Dir 的最后一段(`/root/.adelie/data/<项目id>`),列表里有、`env` 里没有就是这个问题。修法:把值重新 set 到正确项目,并清掉写错的那份:`penguin config vault remove --key <KEY> --project-id default_project --agent-id <agent>`。## 六、边界diff --git a/plugins/csu-mail/skills/csu-mail/scripts/bootstrap.sh b/plugins/csu-mail/skills/csu-mail/scripts/bootstrap.shindex 408aab7e..0a7507a5 100755--- a/plugins/csu-mail/skills/csu-mail/scripts/bootstrap.sh+++ b/plugins/csu-mail/skills/csu-mail/scripts/bootstrap.sh@@ -70,7 +70,7 @@ if [ "${NO_VAULT:-0}" = "1" ]; thenexit 0fi-[ -n "${PROJECT_ID:-}" ] || die "请设置 PROJECT_ID(= 运行环境 App Data Dir 的最后一段,如 /root/.penguin/data/sjaaj -> sjaaj);+[ -n "${PROJECT_ID:-}" ] || die "请设置 PROJECT_ID(= 运行环境 App Data Dir 的最后一段,如 /root/.adelie/data/sjaaj -> sjaaj);否则凭据会落进 default_project:密钥库里查得到,Agent 的 shell 里却永远没有这个变量。"command -v penguin >/dev/null || die "找不到 penguin CLI:请手动写密钥库,或用 NO_VAULT=1 看命令。"diff --git a/plugins/requirements-box/plugin.json b/plugins/requirements-box/plugin.jsonindex 1b3b8c3e..764c3a78 100644--- a/plugins/requirements-box/plugin.json+++ b/plugins/requirements-box/plugin.json@@ -3,7 +3,7 @@"description_zh": "立起一个需求箱:一页受口令保护的表单让用户提需求,一个定时任务按节奏叫 Agent 来做,每轮一封邮件汇报。服务是一个零依赖的 Node 文件(JSON 存储、带口令的 GET/POST/PATCH 接口、它自己那一页、按条目排期、批量勾选,以及一个立刻开会话开工的按钮),巡台协议是一份 Markdown,安装脚本把两者摆好并登记定时任务。","short_description": "A keyed request page plus a scheduled patrol that works through it.","short_description_zh": "一页收需求的表单 + 定时巡台去做 + 每轮邮件汇报。",- "version": "2026.10.06.3",+ "version": "2026.10.07.1","category": "office-productivity","preinstall": false}diff --git a/plugins/requirements-box/skills/requirements-box/kit/install.mjs b/plugins/requirements-box/skills/requirements-box/kit/install.mjsindex 593e75c2..0731cbe5 100644--- a/plugins/requirements-box/skills/requirements-box/kit/install.mjs+++ b/plugins/requirements-box/skills/requirements-box/kit/install.mjs@@ -50,13 +50,15 @@ if (!flags.dir || flags.dir === true) die("必须给 --dir(服务装到哪个const DIR = resolve(String(flags.dir));// Data root: Adelie's `ADELIE_HOME` wins, and the pre-rename `PENGUIN_HOME` is still read after it// (an operator's shell, or a launcher from before the rename, may export that one) — the same order-// core's resolveRoot() applies, so this install points at the root the running server actually reads.+// core's resolveRoot() applies, default included, so this install points at the root the running+// server actually reads: `~/.adelie/data` when neither is set, never the pre-rename `~/.penguin`+// (whose layout also lacked the `data/` step this constant has to name).const DATA_ROOT = resolve(String(flags["data-root"] ??process.env.ADELIE_HOME ??process.env.PENGUIN_HOME ??- join(homedir(), ".penguin"),+ join(homedir(), ".adelie", "data"),),);// Project / Agent ids are Adelie's spelling only: the pre-rename `PENGUIN_PROJECT_ID` /