@pennixrv/trellis 0.7.0-beta.46 → 0.7.0-beta.48

package/dist/templates/markdown/spec/guides/index.md.txt

@@ -1,97 +1,97 @@
-# Thinking Guides
+# 思考指南（Thinking Guides）
 
-> **Purpose**: Expand your thinking to catch things you might not have considered.
+> **目的（Purpose）**：扩展思考，发现可能遗漏的因素。
 
 ---
 
-## Why Thinking Guides?
+## 为什么需要思考指南（Why Thinking Guides?）
 
-**Most bugs and tech debt come from "didn't think of that"**, not from lack of skill:
+**大多数错误和技术债务来自“没有想到”，而不是能力不足：**
 
-- Didn't think about what happens at layer boundaries → cross-layer bugs
-- Didn't think about code patterns repeating → duplicated code everywhere
-- Didn't think about edge cases → runtime errors
-- Didn't think about future maintainers → unreadable code
+- 没有思考层边界会发生什么 → 出现跨层错误
+- 没有注意代码模式重复 → 到处产生重复代码
+- 没有考虑边界情况 → 出现运行时错误
+- 没有考虑未来维护者 → 代码难以阅读
 
-These guides help you **ask the right questions before coding**.
+这些指南帮助你在编码前**提出正确的问题**。
 
 ---
 
-## Available Guides
+## 可用指南（Available Guides）
 
-| Guide | Purpose | When to Use |
+| 指南（Guide） | 目的（Purpose） | 使用时机（When to Use） |
 |-------|---------|-------------|
-| [Code Reuse Thinking Guide](./code-reuse-thinking-guide.md) | Identify patterns and reduce duplication | When you notice repeated patterns |
-| [Cross-Layer Thinking Guide](./cross-layer-thinking-guide.md) | Think through data flow across layers | Features spanning multiple layers |
+| [代码复用思考指南（Code Reuse Thinking Guide）](./code-reuse-thinking-guide.md) | 识别模式并减少重复 | 发现重复模式时 |
+| [跨层思考指南（Cross-Layer Thinking Guide）](./cross-layer-thinking-guide.md) | 梳理跨层数据流 | 功能跨越多个层时 |
 
 ---
 
-## Quick Reference: Thinking Triggers
+## 快速参考：思考触发条件（Quick Reference: Thinking Triggers）
 
-### When to Think About Cross-Layer Issues
+### 何时思考跨层问题（When to Think About Cross-Layer Issues）
 
-- [ ] Feature touches 3+ layers (API, Service, Component, Database)
-- [ ] Data format changes between layers
-- [ ] Multiple consumers need the same data
-- [ ] You're not sure where to put some logic
-- [ ] You are adding an event kind, JSONL record, RPC payload, or config field
-- [ ] UI / command code starts casting raw payload fields directly
+- [ ] 功能涉及三个或更多层（API、Service、Component、Database）
+- [ ] 数据格式在层之间发生变化
+- [ ] 多个消费者需要同一份数据
+- [ ] 不确定某段逻辑应放在哪里
+- [ ] 正在增加事件类型、JSONL 记录、RPC 载荷或配置字段
+- [ ] UI/命令代码开始直接断言原始载荷字段
 
-→ Read [Cross-Layer Thinking Guide](./cross-layer-thinking-guide.md)
+→ 阅读 [跨层思考指南（Cross-Layer Thinking Guide）](./cross-layer-thinking-guide.md)
 
-### When to Think About Code Reuse
+### 何时思考代码复用（When to Think About Code Reuse）
 
-- [ ] You're writing similar code to something that exists
-- [ ] You see the same pattern repeated 3+ times
-- [ ] You're adding a new field to multiple places
-- [ ] **You're modifying any constant or config**
-- [ ] **You're creating a new utility/helper function** ← Search first!
-- [ ] Two files read the same untyped payload field with local casts
-- [ ] Multiple branches update the same derived state from `kind` / `action`
+- [ ] 正在编写与已有代码相似的代码
+- [ ] 看到同一模式重复三次或更多
+- [ ] 正在多个位置增加新字段
+- [ ] **正在修改任意常量或配置**
+- [ ] **正在创建新的工具/辅助函数** ← 先搜索！
+- [ ] 两个文件使用本地断言读取同一个无类型载荷字段
+- [ ] 多个分支根据 `kind` / `action` 更新同一派生状态
 
-→ Read [Code Reuse Thinking Guide](./code-reuse-thinking-guide.md)
+→ 阅读 [代码复用思考指南（Code Reuse Thinking Guide）](./code-reuse-thinking-guide.md)
 
-### When Verifying AI Cross-Review Results
+### 核验 AI 交叉审查结果时（When Verifying AI Cross-Review Results）
 
-- [ ] Reviewer claims "user input can be malicious" → Check the actual data source (internal manifest? user config? external API?)
-- [ ] Reviewer flags "missing validation" → Is the data from a trusted internal source?
-- [ ] Reviewer says "behavior change" → Read the code comments — is it intentional design?
-- [ ] Reviewer identifies a "bug" in test → Mentally delete the feature being tested — does the test still pass? If yes → tautological test
+- [ ] 审查者声称“用户输入可能恶意” → 检查实际数据来源（内部 manifest？用户配置？外部 API？）
+- [ ] 审查者指出“缺少校验” → 数据是否来自可信内部来源？
+- [ ] 审查者说“行为发生变化” → 阅读代码注释，确认是否属于有意设计。
+- [ ] 审查者在测试中指出“错误” → 在脑中删除被测功能，测试是否仍然通过？如果是 → 这是同义反复测试
 
-**Common AI reviewer false-positive patterns**:
-1. **Trust boundary confusion**: Treating internal data (bundled JSON manifests) as untrusted external input
-2. **Ignoring design comments**: Flagging intentional behavior documented in code comments as bugs
-3. **Variable misreading**: Not tracing a variable to its actual definition (e.g., Map keyed by path vs name)
+**AI 审查者常见的误报模式**：
+1. **信任边界混淆**：将内部数据（打包的 JSON manifest）当作不可信外部输入
+2. **忽略设计注释**：将代码注释中记录的有意行为标记为错误
+3. **误读变量**：不追踪变量的实际定义（例如 Map 以路径而不是名称为键）
 
-**Verification rule**: Every CRITICAL/WARNING finding must be verified against the actual code before prioritizing.
+**核验规则**：每个 CRITICAL/WARNING 发现都必须对照实际代码核验后再排序。
 
 ---
 
-## Pre-Modification Rule (CRITICAL)
+## 修改前规则（Pre-Modification Rule，CRITICAL）
 
-> **Before changing ANY value, ALWAYS search first!**
+> **修改任何值之前，始终先搜索！**
 
 ```bash
 # Search for the value you're about to change
 grep -r "value_to_change" .
 ```
 
-This single habit prevents most "forgot to update X" bugs.
+这一习惯可以预防大多数“忘记更新 X”的错误。
 
 ---
 
-## How to Use This Directory
+## 如何使用本目录（How to Use This Directory）
 
-1. **Before coding**: Skim the relevant thinking guide
-2. **During coding**: If something feels repetitive or complex, check the guides
-3. **After bugs**: Add new insights to the relevant guide (learn from mistakes)
+1. **编码前**：浏览相关思考指南
+2. **编码中**：如果某处感觉重复或复杂，查阅这些指南
+3. **出现错误后**：将新经验加入相关指南，从错误中学习
 
 ---
 
-## Contributing
+## 贡献（Contributing）
 
-Found a new "didn't think of that" moment? Add it to the relevant guide.
+发现新的“没有想到”时刻？将它加入相关指南。
 
 ---
 
-**Core Principle**: 30 minutes of thinking saves 3 hours of debugging.
+**核心原则（Core Principle）**：30 分钟的思考可以节省 3 小时的调试时间。

package/dist/templates/markdown/workspace-index.md

@@ -1,14 +1,14 @@
-# Workspace Index
+# 工作区索引（Workspace Index）
 
-> Records of all AI Agent work records across all developers
+> 记录所有开发者的 AI Agent 工作记录。
 
 ---
 
-## Overview
+## 概览（Overview）
 
-This directory tracks records for all developers working with AI Agents on this project.
+本目录跟踪本项目所有使用 AI Agent 的开发者记录。
 
-### File Structure
+### 文件结构（File Structure）
 
 ```
 workspace/
@@ -23,98 +23,98 @@ workspace/
 
 ---
 
-## Active Developers
+## 活跃开发者（Active Developers）
 
-| Developer | Last Active | Sessions | Active File |
+| 开发者（Developer） | 最近活动（Last Active） | 会话（Sessions） | 活动文件（Active File） |
 |-----------|-------------|----------|-------------|
-| (none yet) | - | - | - |
+| （暂无） | - | - | - |
 
 ---
 
-## Getting Started
+## 开始使用（Getting Started）
 
-### For New Developers
+### 新开发者（For New Developers）
 
-Run the initialization script:
+运行初始化脚本：
 
 ```bash
 python3 ./.trellis/scripts/init_developer.py <your-name>
 ```
 
-This will:
-1. Create your identity file (gitignored)
-2. Create your progress directory
-3. Create your personal index
-4. Create initial journal file
+此命令将：
+1. 创建身份文件（由 git 忽略）
+2. 创建进度目录
+3. 创建个人索引
+4. 创建初始日志文件
 
-### For Returning Developers
+### 已有开发者（For Returning Developers）
 
-1. Get your developer name:
+1. 获取开发者名称：
    ```bash
    python3 ./.trellis/scripts/get_developer.py
    ```
 
-2. Read your personal index:
+2. 阅读个人索引：
    ```bash
    cat .trellis/workspace/$(python3 ./.trellis/scripts/get_developer.py)/index.md
    ```
 
 ---
 
-## Guidelines
+## 指南（Guidelines）
 
-### Journal File Rules
+### 日志文件规则（Journal File Rules）
 
-- **Max 2000 lines** per journal file
-- When limit is reached, create `journal-{N+1}.md`
-- Update your personal `index.md` when creating new files
+- 每个日志文件最多 **2000 行**
+- 达到上限后创建 `journal-{N+1}.md`
+- 创建新文件时更新个人 `index.md`
 
-### Session Record Format
+### 会话记录格式（Session Record Format）
 
-Each session should include:
-- Summary: One-line description
-- Branch: Which branch the work was done on
-- Main Changes: What was modified
-- Git Commits: Commit hashes and messages
-- Next Steps: What to do next
+每个会话应包含：
+- 摘要（Summary）：一行描述
+- 分支（Branch）：工作的分支
+- 主要变更（Main Changes）：修改内容
+- Git 提交（Git Commits）：提交哈希和消息
+- 下一步（Next Steps）：后续工作
 
 ---
 
-## Session Template
+## 会话模板（Session Template）
 
-Use this template when recording sessions:
+记录会话时使用以下模板：
 
 ```markdown
-## Session {N}: {Title}
+## 会话（Session） {N}：{Title}
 
-**Date**: YYYY-MM-DD
-**Task**: {task-name}
-**Branch**: `{branch-name}`
+**日期（Date）**: YYYY-MM-DD
+**任务（Task）**: {task-name}
+**分支（Branch）**: `{branch-name}`
 
-### Summary
+### 摘要（Summary）
 
 {One-line summary}
 
-### Main Changes
+### 主要变更（Main Changes）
 
 - {Change 1}
 - {Change 2}
 
-### Git Commits
+### Git 提交（Git Commits）
 
 | Hash | Message |
 |------|---------|
 | `abc1234` | {commit message} |
 
-### Testing
+### 测试（Testing）
 
 - [OK] {Test result}
 
-### Status
+### 状态（Status）
 
 [OK] **Completed** / # **In Progress** / [P] **Blocked**
 
-### Next Steps
+### 下一步（Next Steps）
 
 - {Next step 1}
 - {Next step 2}
@@ -122,4 +122,4 @@ Use this template when recording sessions:
 
 ---
 
-**Language**: All documentation must be written in **English**.
+**语言（Language）**：所有文档默认使用**简体中文**。

package/dist/templates/opencode/lib/session-utils.js

@@ -402,9 +402,9 @@ Trellis compact SessionStart context. Use it to orient the session; load details
     let rangeEnd = allLines.length
     for (let i = 0; i < allLines.length; i++) {
       const stripped = allLines[i].trim()
-      if (rangeStart === -1 && stripped === "## Phase Index") {
+      if (rangeStart === -1 && (stripped === "## 阶段索引（Phase Index）" || stripped === "## Phase Index")) {
         rangeStart = i
-      } else if (rangeStart !== -1 && stripped === "## Phase 1: Plan") {
+      } else if (rangeStart !== -1 && (stripped === "## 阶段一：规划（Phase 1: Plan）" || stripped === "## Phase 1: Plan")) {
         rangeEnd = i
         break
       }

package/dist/templates/shared-hooks/session-start.py

@@ -754,24 +754,24 @@ def _build_compact_current_state(
     return "\n".join(lines)
 
 
-def _extract_range(content: str, start_header: str, end_header: str) -> str:
+def _extract_range(content: str, start_header: tuple[str, ...], end_header: tuple[str, ...]) -> str:
     """Extract lines starting at `## start_header` up to (but excluding) `## end_header`.
 
-    Both parameters are full header lines WITHOUT the `## ` prefix (e.g. "Phase Index").
+    Parameters contain accepted full header lines WITHOUT the `## ` prefix.
     Returns empty string if start header is not found.
     End header missing → extracts to end of file.
     """
     lines = content.splitlines()
     start: int | None = None
     end: int = len(lines)
-    start_match = f"## {start_header}"
-    end_match = f"## {end_header}"
+    start_matches = {f"## {header}" for header in start_header}
+    end_matches = {f"## {header}" for header in end_header}
     for i, line in enumerate(lines):
         stripped = line.strip()
-        if start is None and stripped == start_match:
+        if start is None and stripped in start_matches:
             start = i
             continue
-        if start is not None and stripped == end_match:
+        if start is not None and stripped in end_matches:
             end = i
             break
     if start is None:
@@ -833,7 +833,7 @@ def _build_workflow_overview(workflow_path: Path) -> str:
         "",
     ]
 
-    phases = _extract_range(content, "Phase Index", "Phase 1: Plan")
+    phases = _extract_range(content, ("阶段索引（Phase Index）", "Phase Index"), ("阶段一：规划（Phase 1: Plan）", "Phase 1: Plan"))
     if phases:
         out_lines.append(_strip_breadcrumb_tag_blocks(phases).rstrip())
 

package/dist/templates/trellis/scripts/add_session.py

@@ -97,8 +97,8 @@ MARKER_PREFIX = "<!-- trellis-session:"
 # fingerprint mixed in the calendar date; see compute_record_fingerprint.
 MARKER_VERSION = 2
 LEGACY_MARKER_RE = re.compile(r"^<!-- trellis-session: fp=([0-9a-f]{16}) -->$")
-ENTRY_DATE_RE = re.compile(r"^\*\*Date\*\*: (\d{4}-\d{2}-\d{2})\s*$")
-SESSION_HEADING_RE = re.compile(r"^## Session (\d+):", re.MULTILINE)
+ENTRY_DATE_RE = re.compile(r"^\*\*(?:Date|日期（Date）)\*\*: (\d{4}-\d{2}-\d{2})\s*$")
+SESSION_HEADING_RE = re.compile(r"^## (?:Session|会话（Session）) (\d+)(?::|：)", re.MULTILINE)
 
 # Recording states, in the order the operation walks them.
 STATE_ABSENT = "absent"
@@ -170,7 +170,7 @@ def _max_session_in_index(content: str) -> int:
 
 
 def _max_session_in_journal(content: str) -> int:
-    """Highest `## Session N:` heading in a journal body (0 when none)."""
+    """Highest old or new session heading in a journal body (0 when none)."""
     numbers = [int(m.group(1)) for m in SESSION_HEADING_RE.finditer(content)]
     return max(numbers) if numbers else 0
 
@@ -195,7 +195,7 @@ def count_journal_files(dev_dir: Path, active_num: int) -> str:
     for f in files:
         filename = f.name
         lines = len(f.read_text(encoding="utf-8").splitlines())
-        status = "Active" if filename == active_file else "Archived"
+        status = "活动（Active）" if filename == active_file else "归档（Archived）"
         result_lines.append(f"| `{filename}` | ~{lines} | {status} |")
 
     return "\n".join(result_lines)
@@ -301,10 +301,10 @@ def create_new_journal_file(
     prev_num = num - 1
     new_file = dev_dir / f"{FILE_JOURNAL_PREFIX}{num}.md"
 
-    content = f"""# Journal - {developer} (Part {num})
+    content = f"""# 日志（Journal）- {developer}（第 {num} 部分）
 
-> Continuation from `{FILE_JOURNAL_PREFIX}{prev_num}.md` (archived at ~{max_lines} lines)
-> Started: {today}
+> 续接自 `{FILE_JOURNAL_PREFIX}{prev_num}.md`（约 {max_lines} 行时归档）
+> 开始日期（Started）: {today}
 
 ---
 
@@ -615,7 +615,7 @@ def _max_session_across_refs(repo_root: Path, refs: list[str], dev_rel: str) ->
             "-h",
             "-E",
             "-e",
-            r"^## Session [0-9]+:",
+            r"^## (Session [0-9]+:|会话（Session） [0-9]+：)",
             "-e",
             r"Total Sessions",
         ]
@@ -629,7 +629,7 @@ def _max_session_across_refs(repo_root: Path, refs: list[str], dev_rel: str) ->
 
     # `git grep` prefixes each hit with `<rev>:<path>:`, so the numbers are
     # matched anywhere in the line rather than anchored.
-    numbers = [int(m.group(1)) for m in re.finditer(r"## Session (\d+):", out)]
+    numbers = [int(m.group(1)) for m in re.finditer(r"## (?:Session|会话（Session）) (\d+)(?::|：)", out)]
     numbers += [
         int(m.group(1)) for m in re.finditer(r"Total Sessions[^\d]{0,8}(\d+)", out)
     ]
@@ -843,7 +843,7 @@ def classify_record(
     if session_num is None:
         return "", None, None, (
             f"{journal_file.name} carries this record's marker without a "
-            "'## Session N:' heading above it. The pending record is malformed; "
+            "session heading above it. The pending record is malformed; "
             "repair it by hand before retrying."
         )
 
@@ -884,9 +884,9 @@ def _render_bullet_section(header: str, items: list[str], bullet_prefix: str = "
 def _render_main_changes(changes: list[str], extra_content: str | None) -> str:
     """Render the Main Changes section from --change bullets or freeform content."""
     if changes:
-        return _render_bullet_section("Main Changes", changes)
+        return _render_bullet_section("主要变更（Main Changes）", changes)
     if extra_content:
-        return f"\n\n### Main Changes\n\n{extra_content}"
+        return f"\n\n### 主要变更（Main Changes）\n\n{extra_content}"
     return ""
 
 
@@ -906,39 +906,39 @@ def generate_session_content(
 ) -> str:
     """Generate session content."""
     if evidence:
-        commit_table = """| Hash | Message |
+        commit_table = """| 哈希（Hash） | 消息（Message） |
 |------|---------|"""
         for oid, subject in evidence:
             commit_table += f"\n| `{oid}` | {escape_markdown_cell(subject)} |"
     else:
-        commit_table = "(No commits - planning session)"
+        commit_table = "（无提交——规划会话）"
 
-    package_line = f"\n**Package**: {package}" if package else ""
-    branch_line = f"\n**Branch**: `{branch}`" if branch else ""
+    package_line = f"\n**包（Package）**: {package}" if package else ""
+    branch_line = f"\n**分支（Branch）**: `{branch}`" if branch else ""
 
     main_changes_section = _render_main_changes(changes or [], extra_content)
-    testing_section = _render_bullet_section("Testing", tests or [], bullet_prefix="- [OK] ")
-    next_steps_section = _render_bullet_section("Next Steps", next_steps or [])
+    testing_section = _render_bullet_section("测试（Testing）", tests or [], bullet_prefix="- [OK] ")
+    next_steps_section = _render_bullet_section("下一步（Next Steps）", next_steps or [])
 
     return f"""
 
-## Session {session_num}: {title}
+## 会话（Session） {session_num}：{title}
 {marker}
 
-**Date**: {today}
-**Task**: {title}{package_line}{branch_line}
+**日期（Date）**: {today}
+**任务（Task）**: {title}{package_line}{branch_line}
 
-### Summary
+### 摘要（Summary）
 
 {summary}{main_changes_section}
 
-### Git Commits
+### Git 提交（Git Commits）
 
 {commit_table}{testing_section}
 
-### Status
+### 状态（Status）
 
-[OK] **Completed**{next_steps_section}
+[OK] **已完成（Completed）**{next_steps_section}
 """
 
 
@@ -992,9 +992,9 @@ def update_index(
         if "@@@auto:current-status" in line:
             new_lines.append(line)
             in_current_status = True
-            new_lines.append(f"- **Active File**: `{active_file}`")
-            new_lines.append(f"- **Total Sessions**: {new_session}")
-            new_lines.append(f"- **Last Active**: {today}")
+            new_lines.append(f"- **活动文件（Active File）**: `{active_file}`")
+            new_lines.append(f"- **会话总数（Total Sessions）**: {new_session}")
+            new_lines.append(f"- **最近活动（Last Active）**: {today}")
             continue
 
         if "@@@/auto:current-status" in line:
@@ -1005,7 +1005,7 @@ def update_index(
         if "@@@auto:active-documents" in line:
             new_lines.append(line)
             in_active_documents = True
-            new_lines.append("| File | Lines | Status |")
+            new_lines.append("| 文件（File） | 行数（Lines） | 状态（Status） |")
             new_lines.append("|------|-------|--------|")
             new_lines.append(files_table)
             continue
@@ -1038,13 +1038,16 @@ def update_index(
                 r"^\|\s*#\s*\|\s*Date\s*\|\s*Title\s*\|\s*Commits\s*\|\s*Branch\s*\|\s*Base Branch\s*\|\s*$",
                 line,
             ):
-                new_lines.append("| # | Date | Title | Commits | Branch |")
+                new_lines.append("| # | 日期（Date） | 标题（Title） | 提交（Commits） | 分支（Branch） |")
                 continue
             if re.match(r"^\|\s*#\s*\|\s*Date\s*\|\s*Title\s*\|\s*Commits\s*\|\s*Branch\s*\|\s*$", line):
-                new_lines.append("| # | Date | Title | Commits | Branch |")
+                new_lines.append("| # | 日期（Date） | 标题（Title） | 提交（Commits） | 分支（Branch） |")
+                continue
+            if re.match(r"^\|\s*#\s*\|\s*日期（Date）\s*\|\s*标题（Title）\s*\|\s*提交（Commits）\s*\|\s*分支（Branch）\s*\|\s*$", line):
+                new_lines.append("| # | 日期（Date） | 标题（Title） | 提交（Commits） | 分支（Branch） |")
                 continue
             if re.match(r"^\|\s*#\s*\|\s*Date\s*\|\s*Title\s*\|\s*Commits\s*\|\s*$", line):
-                new_lines.append("| # | Date | Title | Commits | Branch |")
+                new_lines.append("| # | 日期（Date） | 标题（Title） | 提交（Commits） | 分支（Branch） |")
                 continue
             if re.match(r"^\|[-| ]+\|\s*$", line) and not header_written:
                 new_lines.append("|---|------|-------|---------|--------|")

package/dist/templates/trellis/scripts/common/developer.py

@@ -78,10 +78,10 @@ def init_developer(name: str, repo_root: Path | None = None) -> bool:
     journal_file = workspace_dir / f"{FILE_JOURNAL_PREFIX}1.md"
     if not journal_file.exists():
         today = datetime.now().strftime("%Y-%m-%d")
-        journal_content = f"""# Journal - {name} (Part 1)
+        journal_content = f"""# 日志（Journal）- {name}（第 1 部分）
 
-> AI development session journal
-> Started: {today}
+> AI 开发会话日志
+> 开始日期（Started）: {today}
 
 ---
 
@@ -95,46 +95,46 @@ def init_developer(name: str, repo_root: Path | None = None) -> bool:
     # Create index.md with markers for auto-update
     index_file = workspace_dir / "index.md"
     if not index_file.exists():
-        index_content = f"""# Workspace Index - {name}
+        index_content = f"""# 工作区索引（Workspace Index）- {name}
 
-> Journal tracking for AI development sessions.
+> AI 开发会话跟踪日志。
 
 ---
 
-## Current Status
+## 当前状态（Current Status）
 
 <!-- @@@auto:current-status -->
-- **Active File**: `journal-1.md`
-- **Total Sessions**: 0
-- **Last Active**: -
+- **活动文件（Active File）**: `journal-1.md`
+- **会话总数（Total Sessions）**: 0
+- **最近活动（Last Active）**: -
 <!-- @@@/auto:current-status -->
 
 ---
 
-## Active Documents
+## 活动文档（Active Documents）
 
 <!-- @@@auto:active-documents -->
-| File | Lines | Status |
+| 文件（File） | 行数（Lines） | 状态（Status） |
 |------|-------|--------|
-| `journal-1.md` | ~0 | Active |
+| `journal-1.md` | ~0 | 活动（Active） |
 <!-- @@@/auto:active-documents -->
 
 ---
 
-## Session History
+## 会话历史（Session History）
 
 <!-- @@@auto:session-history -->
-| # | Date | Title | Commits | Branch |
+| # | 日期（Date） | 标题（Title） | 提交（Commits） | 分支（Branch） |
 |---|------|-------|---------|--------|
 <!-- @@@/auto:session-history -->
 
 ---
 
-## Notes
+## 备注（Notes）
 
-- Sessions are appended to journal files
-- New journal file created when current exceeds 2000 lines
-- Use `add_session.py` to record sessions
+- 会话会追加到日志文件
+- 当前日志超过 2000 行时创建新的日志文件
+- 使用 `add_session.py` 记录会话
 """
         try:
             index_file.write_text(index_content, encoding="utf-8")

package/dist/templates/trellis/scripts/common/task_store.py

@@ -306,27 +306,27 @@ def _parse_meta_pairs(pairs: list[str] | None) -> dict[str, str] | None:
 
 def _default_prd_content(title: str, description: str | None = None) -> str:
     """Return the default PRD skeleton created with every task."""
-    goal = (description or "").strip() or "TBD."
-    heading = title.strip() or "Untitled task"
+    goal = (description or "").strip() or "待填写。"
+    heading = title.strip() or "未命名任务"
     return f"""# {heading}
 
-## Goal
+## 目标（Goal）
 
 {goal}
 
-## Requirements
+## 需求（Requirements）
 
-- TBD
+- 待填写
 
-## Acceptance Criteria
+## 验收标准（Acceptance Criteria）
 
-- [ ] TBD
+- [ ] 待填写
 
-## Notes
+## 备注（Notes）
 
-- Keep `prd.md` focused on requirements, constraints, and acceptance criteria.
-- Lightweight tasks can remain PRD-only.
-- For complex tasks, add `design.md` for technical design and `implement.md` for execution planning before `task.py start`.
+- 让 `prd.md` 聚焦需求、约束和验收标准。
+- 轻量任务可以只保留 PRD。
+- 复杂任务在 `task.py start` 前增加 `design.md` 记录技术设计，增加 `implement.md` 记录执行计划。
 """