bbsyaya · Nov 4, 2026 · Oct 30, 2026 · Nov 4, 2026 · Nov 4, 2026 · Nov 4, 2026
diff --git a/.github/workflows/check-derived-files.yml b/.github/workflows/check-derived-files.yml
@@ -0,0 +1,36 @@
+name: Check derived files
+
+# Fails when docs/llms-full*.txt or docs/AGENTS.txt were not regenerated
+# after a source change. Fix: run `python3 scripts/gen_llms_full.py` and commit.
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - "docs/**"
+      - "AGENTS.md"
+      - "scripts/gen_llms_full.py"
+      - ".github/workflows/check-derived-files.yml"
+  pull_request:
+    paths:
+      - "docs/**"
+      - "AGENTS.md"
+      - "scripts/gen_llms_full.py"
+      - ".github/workflows/check-derived-files.yml"
+  workflow_dispatch:
+
+jobs:
+  check:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Check llms-full bundles and AGENTS.txt are up to date
+        run: python3 scripts/gen_llms_full.py --check
diff --git a/AGENTS.md b/AGENTS.md
@@ -47,4 +47,4 @@ If you need to change runtime behavior (tool schemas, error codes, transaction l
 python3 scripts/gen_llms_full.py
 ```
 
-This regenerates `docs/llms-full.txt` with a fresh commit SHA, timestamp, and token estimate. Run it after any change under `docs/`.
+This regenerates `docs/llms-full.txt` with a fresh commit SHA, timestamp, and token estimate, and rebuilds the published `docs/AGENTS.txt` from this file with site-absolute links. Run it after any change under `docs/` or to this file; do not edit `docs/AGENTS.txt` by hand. CI (`check-derived-files.yml`) runs `python3 scripts/gen_llms_full.py --check` and fails if these files are stale.
diff --git a/docs/AGENTS.txt b/docs/AGENTS.txt
@@ -6,28 +6,28 @@ If you are an AI coding agent or an autonomous tool reading this for orientation
 
 ## Entry points for AI agents
 
-- **Curated index:** [docs/llms.txt](docs/llms.txt) — short, link-only map of the documentation, following [llmstxt.org](https://llmstxt.org/). Use this first.
-- **Single-fetch full text:** [docs/llms-full.txt](docs/llms-full.txt) — every English page concatenated for one-shot ingestion. The header records the generating commit SHA, UTC timestamp, page count, and a rough token estimate; check those before relying on the content.
+- **Curated index:** [docs.tronlink.org/llms.txt](https://docs.tronlink.org/llms.txt) — short, link-only map of the documentation, following [llmstxt.org](https://llmstxt.org/). Use this first.
+- **Single-fetch full text:** [docs.tronlink.org/llms-full.txt](https://docs.tronlink.org/llms-full.txt) — every English page concatenated for one-shot ingestion. The header records the generating commit SHA, UTC timestamp, page count, and a rough token estimate; check those before relying on the content.
 - **Human-readable site:** [https://docs.tronlink.org/](https://docs.tronlink.org/)
 
 ## Topic map
 
 | Surface | Doc |
 | --- | --- |
-| DApp integration in the browser (TIP-6963 / `eth_requestAccounts` / `tronWeb`) | [docs/dapp/getting-started.en.md](docs/dapp/getting-started.en.md) + [docs/plugin-wallet/*](docs/plugin-wallet/) |
-| Mobile DeepLink (`tronlinkoutside://`) | [docs/mobile/deeplink.en.md](docs/mobile/deeplink.en.md) |
-| AI-agent tooling overview | [docs/ai-support/ai-llms.en.md](docs/ai-support/ai-llms.en.md) |
-| MCP server (production) | [docs/ai-support/mcp-server-tronlink.en.md](docs/ai-support/mcp-server-tronlink.en.md) |
-| MCP framework / SSOT error codes | [docs/ai-support/tronlink-mcp-core.en.md](docs/ai-support/tronlink-mcp-core.en.md) |
-| MCP signer wrapper (HITL signing) | [docs/ai-support/mcp-tronlink-signer.en.md](docs/ai-support/mcp-tronlink-signer.en.md) |
-| Signer SDK (browser-approval signing) | [docs/ai-support/tronlink-signer.en.md](docs/ai-support/tronlink-signer.en.md) |
-| Read-only Skills package | [docs/ai-support/tronlink-skills.en.md](docs/ai-support/tronlink-skills.en.md) |
-| CLI (transactions via browser approval) | [docs/ai-support/tronlink-cli.en.md](docs/ai-support/tronlink-cli.en.md) |
-| Networks, addresses, glossary, FAQ | [docs/reference/](docs/reference/) |
+| DApp integration in the browser (TIP-6963 / `eth_requestAccounts` / `tronWeb`) | [docs.tronlink.org/dapp/getting-started/](https://docs.tronlink.org/dapp/getting-started/) + [docs.tronlink.org/plugin-wallet/*](https://docs.tronlink.org/plugin-wallet/active-requests/) |
+| Mobile DeepLink (`tronlinkoutside://`) | [docs.tronlink.org/mobile/deeplink/](https://docs.tronlink.org/mobile/deeplink/) |
+| AI-agent tooling overview | [docs.tronlink.org/ai-support/ai-llms/](https://docs.tronlink.org/ai-support/ai-llms/) |
+| MCP server (production) | [docs.tronlink.org/ai-support/mcp-server-tronlink/](https://docs.tronlink.org/ai-support/mcp-server-tronlink/) |
+| MCP framework / SSOT error codes | [docs.tronlink.org/ai-support/tronlink-mcp-core/](https://docs.tronlink.org/ai-support/tronlink-mcp-core/) |
+| MCP signer wrapper (HITL signing) | [docs.tronlink.org/ai-support/mcp-tronlink-signer/](https://docs.tronlink.org/ai-support/mcp-tronlink-signer/) |
+| Signer SDK (browser-approval signing) | [docs.tronlink.org/ai-support/tronlink-signer/](https://docs.tronlink.org/ai-support/tronlink-signer/) |
+| Read-only Skills package | [docs.tronlink.org/ai-support/tronlink-skills/](https://docs.tronlink.org/ai-support/tronlink-skills/) |
+| CLI (transactions via browser approval) | [docs.tronlink.org/ai-support/tronlink-cli/](https://docs.tronlink.org/ai-support/tronlink-cli/) |
+| Networks, addresses, glossary, FAQ | [docs.tronlink.org/reference/*](https://docs.tronlink.org/reference/networks/) |
 
 ## Source-of-truth boundaries
 
-- **Error codes & retry semantics:** the SSOT is [docs/ai-support/tronlink-mcp-core.en.md#error-codes](docs/ai-support/tronlink-mcp-core.en.md#error-codes). Downstream docs link into it; do not duplicate the table.
+- **Error codes & retry semantics:** the SSOT is [docs.tronlink.org/ai-support/tronlink-mcp-core/#error-codes](https://docs.tronlink.org/ai-support/tronlink-mcp-core/#error-codes). Downstream docs link into it; do not duplicate the table.
 - **Per-tool input schemas:** the SSOT is the running MCP server's `list_tools` (returns `inputSchema` per tool). Doc tables are a summary, not a contract.
 - **Versions:** each AI-support page ends with `Version & License` keyed to the corresponding upstream `package.json`.
 
@@ -47,4 +47,4 @@ If you need to change runtime behavior (tool schemas, error codes, transaction l
 python3 scripts/gen_llms_full.py
 ```
 
-This regenerates `docs/llms-full.txt` with a fresh commit SHA, timestamp, and token estimate. Run it after any change under `docs/`.
+This regenerates `docs/llms-full.txt` with a fresh commit SHA, timestamp, and token estimate, and rebuilds the published `docs/AGENTS.txt` from this file with site-absolute links. Run it after any change under `docs/` or to this file; do not edit `docs/AGENTS.txt` by hand. CI (`check-derived-files.yml`) runs `python3 scripts/gen_llms_full.py --check` and fails if these files are stale.
diff --git a/docs/ai-support/mcp-server-tronlink.en.md b/docs/ai-support/mcp-server-tronlink.en.md
@@ -448,7 +448,7 @@ Pinned to the `package.json` of `mcp-server-tronlink@0.1.1`. Re-verify when bump
 
 These are **docs-side mirrors** of the most critical tool inputs — useful when an agent is writing a tool-call call site without an MCP session open. Runtime `list_tools` remains the authoritative source: the schemas there carry full Zod metadata (descriptions, `default`, etc.) plus `meta.schemaVersion`. Fields below are derived from `@tronlink/tronlink-mcp-core` `src/mcp-server/schemas.ts` and follow JSON Schema Draft 7. The full set of 52 tool schemas is **not** reproduced here — see core for the SSOT.
 
-> **Parity is enforced.** `scripts/check_doc_schema_parity.py` (run on push, PR, and daily via [`check-doc-schema-parity.yml`](https://github.com/xueyuanying/docs/blob/main/.github/workflows/check-doc-schema-parity.yml)) diffs the top-level field set + required-flag set of every block below against the live `schemas.ts`. Upstream rename or required→optional drift fails CI.
+> Docs CI checks the field names and required flags of every block below against upstream `schemas.ts`; if they ever disagree, `list_tools` wins.
 
 #### `tl_chain_send` — **Remote Write**
 

diff --git a/docs/ai-support/mcp-server-tronlink.zh.md b/docs/ai-support/mcp-server-tronlink.zh.md
@@ -442,7 +442,7 @@ mcp-server-tronlink/
 
 以下是最关键工具输入的**文档侧镜像**——当 agent 需要在没有打开 MCP 会话的情况下写工具调用站点时使用。运行时 `list_tools` 仍是权威源：那里有完整的 Zod 元信息（描述、`default` 等）以及 `meta.schemaVersion`。下方字段抄自 `@tronlink/tronlink-mcp-core` `src/mcp-server/schemas.ts`，遵循 JSON Schema Draft 7。**未**镜像全部 52 个工具——以 core 仓库为 SSOT。
 
-> **平价由 CI 强制。** `scripts/check_doc_schema_parity.py`（在 push、PR 及每日定时通过 [`check-doc-schema-parity.yml`](https://github.com/xueyuanying/docs/blob/main/.github/workflows/check-doc-schema-parity.yml) 触发）会对下方每个块的顶层字段集 + required 标记与上游 `schemas.ts` 做 diff——上游改名或 required ↔ optional 漂移都会让 CI 失败。
+> 下方各块的字段名和 required 标记由文档 CI 与上游 `schemas.ts` 自动比对；如有不一致，以 `list_tools` 为准。
 
 #### `tl_chain_send` —— **Remote Write**
 

diff --git a/docs/ai-support/tronlink-skills.en.md b/docs/ai-support/tronlink-skills.en.md
@@ -4,11 +4,13 @@
 
 **GitHub**: [https://github.com/TronLink/tronlink-skills](https://github.com/TronLink/tronlink-skills)
 
+> **Version scope.** The command reference on this page (6 skills, 33 commands) was written for **v1.0.x**. The default branch — what `git clone` and `install.sh` install — is now **v1.1.0** (commit `7d2d58cb`): it adds 7 read-only commands (40 in total) and requires exactly **Node.js 24.22.1**. See [Version & License](#version-license); treat `tron_api.mjs --help` / MCP `tools/list` from your installed copy as authoritative.
+
 **TronLink Wallet Skills** is an AI Agent skill set that provides complete TRON blockchain wallet and DeFi functionality through natural language. Designed for Claude Code, Cursor, OpenCode, Codex CLI, and other AI agents.
 
 **Key Highlights:**
 - **6 skills, 33 commands** covering wallet, token research, market data, swaps, resources, and staking
-- **Zero npm dependencies** — uses native Node.js 18+ `fetch` and `crypto`, no `npm install` needed
+- **Zero npm dependencies** — uses native Node.js `fetch` and `crypto` (requires exactly Node.js 24.22.1 — see [Dependencies](#dependencies)), no `npm install` needed
 - **TRON-specific domain knowledge** — dedicated handling of Energy + Bandwidth resource model
 - **Multi-platform support** — Claude Code, Cursor, OpenCode, Codex CLI, LangChain/CrewAI
 - **Read-only & safe** — all commands are query-only, no private keys or signing involved
@@ -39,7 +41,7 @@ Natural Language Input
 AI Agent (Claude Code / Cursor / OpenCode / Custom)
          |
          v
-tron_api.mjs (Node.js 18+, native fetch, zero dependencies)
+tron_api.mjs (Node.js 24.22.1, native fetch, zero dependencies)
     ├── Zero npm dependencies
     ├── TronGrid HTTP API (public or with API key)
     └── Tronscan API for token metadata
@@ -481,7 +483,7 @@ tronlink-skills/
 
 | Dependency | Required? | Purpose |
 |------------|-----------|---------|
-| Node.js >= 18 | Yes | Runtime (native fetch, crypto) |
+| Node.js 24.22.1 (exact; default branch v1.1.0) | Yes | Runtime (native fetch, crypto). Pinned by `.nvmrc` and `package.json` `engines` on the default branch; `install.sh` exits with an error on any other version. Run `nvm install 24.22.1 && nvm use 24.22.1` before installing. |
 | npm install | Not needed | All operations work without any npm dependencies |
 
 ---
@@ -543,7 +545,10 @@ node scripts/tron_api.mjs optimize-cost --address TAddress...
 
 ## Version & License
 
-- **Package:** `tronlink-skills` v1.0.1
+- **Package:** `tronlink-skills` v1.0.1 — the version the command tables on this page describe.
+- **Default branch:** v1.1.0 (commit `7d2d58cb`, `package.json` `version: 1.1.0`), installed by `git clone` / `install.sh`. Differences from v1.0.1 that affect agents:
+    - 7 additional read-only commands, also exposed as `tron_<command>` MCP tools: `wallet-approvals`, `wallet-overview`, `token-overview`, `bandwidth-price`, `tx-cost`, `chain-params`, `health-check`. 40 commands in total; all remain Network Read.
+    - Node.js is pinned to exactly 24.22.1 (`.nvmrc`, `engines`); `install.sh` exits on any other version.
 - **License:** MIT — `SPDX-License-Identifier: MIT`
 - **Changelog / releases:** [https://github.com/TronLink/tronlink-skills/releases](https://github.com/TronLink/tronlink-skills/releases) — no GitHub-tagged releases yet for v1.0.x; track changes by commit until the first tag.
 

diff --git a/docs/ai-support/tronlink-skills.zh.md b/docs/ai-support/tronlink-skills.zh.md
@@ -4,11 +4,13 @@
 
 **GitHub**: [https://github.com/TronLink/tronlink-skills](https://github.com/TronLink/tronlink-skills)
 
+> **版本范围。** 本页的命令说明（6 大技能、33 个命令）基于 **v1.0.x** 编写。默认分支（即 `git clone` 和 `install.sh` 安装的版本）现为 **v1.1.0**（commit `7d2d58cb`）：新增 7 个只读命令（共 40 个），并要求精确版本 **Node.js 24.22.1**。详见文末「版本与许可证」；以你本地安装版本的 `tron_api.mjs --help` / MCP `tools/list` 为准。
+
 **TronLink Wallet Skills** 是一套 AI Agent 技能集，通过自然语言提供完整的 TRON 区块链钱包和 DeFi 功能。专为 Claude Code、Cursor、OpenCode、Codex CLI 及其他 AI 代理设计。
 
 **核心亮点：**
 - **6 大技能，33 个命令**，涵盖钱包、代币研究、市场数据、兑换、资源和质押
-- **零 npm 依赖**：使用原生 Node.js 18+ `fetch` 和 `crypto`，无需 `npm install`
+- **零 npm 依赖**：使用原生 Node.js `fetch` 和 `crypto`（要求精确版本 Node.js 24.22.1，见下方「依赖项」），无需 `npm install`
 - **TRON 专属领域知识** — 专门处理能量 + 带宽资源模型
 - **多平台支持** — Claude Code、Cursor、OpenCode、Codex CLI、LangChain/CrewAI
 - **纯只读安全设计**：所有命令均为查询操作，不涉及私钥或签名
@@ -39,7 +41,7 @@ TronLink Skills 以深度 TRON 领域知识填补了这一空白。
 AI 代理 (Claude Code / Cursor / OpenCode / 自定义)
          |
          v
-tron_api.mjs (Node.js 18+, 原生 fetch, 零依赖)
+tron_api.mjs (Node.js 24.22.1, 原生 fetch, 零依赖)
     ├── 零 npm 依赖
     ├── TronGrid HTTP API（公共或带 API Key）
     └── Tronscan API 用于代币元数据
@@ -483,7 +485,7 @@ tronlink-skills/
 
 | 依赖 | 是否必需？ | 用途 |
 |------|-----------|------|
-| Node.js >= 18 | 是 | 运行时（原生 fetch、crypto） |
+| Node.js 24.22.1（精确版本；默认分支 v1.1.0） | 是 | 运行时（原生 fetch、crypto）。默认分支通过 `.nvmrc` 与 `package.json` 的 `engines` 固定该版本；`install.sh` 检测到其他版本会直接报错退出。安装前先执行 `nvm install 24.22.1 && nvm use 24.22.1`。 |
 | npm install | 不需要 | 所有操作均无需安装任何 npm 依赖 |
 
 ---
@@ -545,7 +547,10 @@ node scripts/tron_api.mjs optimize-cost --address T地址...
 
 ## 版本与许可证
 
-- **包：** `tronlink-skills` v1.0.1
+- **包：** `tronlink-skills` v1.0.1——本页命令表所描述的版本。
+- **默认分支：** v1.1.0（commit `7d2d58cb`，`package.json` 中 `version: 1.1.0`），`git clone` / `install.sh` 安装的就是该版本。与 v1.0.1 相比，影响 agent 的差异：
+    - 新增 7 个只读命令（同时以 `tron_<command>` 形式暴露为 MCP 工具）：`wallet-approvals`, `wallet-overview`, `token-overview`, `bandwidth-price`, `tx-cost`, `chain-params`, `health-check`。共 40 个命令，仍全部为 Network Read。
+    - Node.js 固定为精确版本 24.22.1（`.nvmrc`、`engines`）；`install.sh` 检测到其他版本会直接退出。
 - **许可证：** MIT —— `SPDX-License-Identifier: MIT`
 - **变更记录 / 发布：** [https://github.com/TronLink/tronlink-skills/releases](https://github.com/TronLink/tronlink-skills/releases) —— 截至当前 v1.0.x 尚无 GitHub tag 发布；打 tag 之前请直接看 commit 历史。
 

diff --git a/docs/dapp/multi-sign-transfer.en.md b/docs/dapp/multi-sign-transfer.en.md
@@ -28,14 +28,22 @@ Use the resulting `id` as `permissionId` below.
 ```javascript
 const tronweb = window.tron.tronWeb;
 const toAddress = "TRKb2nAnCBfwxnLxgoKJro6VbyA6QmsuXq";
-const activePermissionId = 2; // obtained via tronWeb.trx.getAccount(...).active_permission
+// fromAddress = the account whose active permission controls the funds (the tx owner).
+// It is not necessarily the connected signer: if the connected account is only a
+// co-signer listed in that permission's keys[], set fromAddress to the controlled account.
+const fromAddress = tronweb.defaultAddress.base58;
+const activePermissionId = 2; // obtained via tronWeb.trx.getAccount(fromAddress).active_permission
 const tx = await tronweb.transactionBuilder.sendTrx(
-  toAddress, 10,
+  toAddress, 10, fromAddress,
   { permissionId: activePermissionId }
 ); // Step 1
 try {
   const signedTx = await tronweb.trx.multiSign(tx, undefined, activePermissionId); // Step 2
-  await tronweb.trx.sendRawTransaction(signedTx); // Step 3
+  const res = await tronweb.trx.sendRawTransaction(signedTx); // Step 3
+  if (!res.result) {
+    // Node rejections are returned, not thrown — see Errors below.
+    console.error(res.code, res.message && tronweb.toUtf8(res.message));
+  }
 } catch (e) {}
 ```
 
@@ -50,8 +58,10 @@ Note that the broadcast only collects one signature in this call — a fully sig
 | Code | Meaning | Where it comes from | Retryable? |
 | :---: | --- | --- | :---: |
 | `'Confirmation declined by user'` (string) | User clicked **Reject** in the signing popup | `tronWeb.trx.multiSign(...)` | No — user declined |
-| (thrown) | `permission_id not active` / `permission_id not exist` | `transactionBuilder.sendTrx({permissionId})` — wrong or revoked permission | No — re-query `getAccount(...).active_permission` |
-| (thrown) | Signature weight below `threshold` after broadcast | `sendRawTransaction` | No — collect more signatures (one `multiSign` call per co-signer) |
+| `code: 'SIGERROR'`, `message` decodes to `Validate signature error: permission isn't exit` | `permissionId` does not exist on `fromAddress` (wrong or revoked). `sendTrx` does **not** validate the permission — the node rejects at broadcast | Return value of `sendRawTransaction(...)` (not thrown) | No — re-query `getAccount(fromAddress).active_permission` and rebuild the transaction |
+| `code: 'SIGERROR'`, other `Validate signature error: …` messages | Signatures do not satisfy the permission — e.g. total weight below `threshold`, or a signer that is not in its `keys[]` | Return value of `sendRawTransaction(...)` (not thrown) | No — collect the missing signatures (one `multiSign` call per co-signer) |
 | `REVERT` / `OUT_OF_ENERGY` / `FAILED` | Broadcast succeeded but execution failed on-chain | `getTransactionInfo(txid)` | **No — the tx is final; never auto-retry** |
 
+`message` in a `sendRawTransaction` result is hex-encoded; decode it with `tronweb.toUtf8(res.message)`. To check before broadcasting, call `tronweb.trx.getSignWeight(signedTx)`: `result.code` is `PERMISSION_ERROR` when the permission does not exist and `NOT_ENOUGH_PERMISSION` while the signatures are still below `threshold`.
+
 For cross-surface translation see the [Error Code Map](../reference/error-code-map.md).