feat: add star repo shortcut to installer dialog

- Changed default HTML embed type from 'artifacts' to 'richui' for direct OpenWebUI chat display
- Updated system prompt guidance to recommend RichUI mode by default, with artifacts only on explicit user request
- Maintains backward compatibility with existing configurations

.agent/learnings/README.md

@@ -0,0 +1,46 @@
+# `.agent/learnings/` — Engineering Learnings & Reusable Patterns
+
+This directory stores **hard-won engineering insights** discovered during development.
+Each file is a standalone Markdown note covering a specific topic, pattern, or gotcha.
+
+The goal is to avoid re-investigating the same issue twice.
+
+---
+
+## Conventions
+
+- **File naming**: `{topic}.md`, e.g., `openwebui-tool-injection.md`
+- **Scope**: One clear topic per file. Keep files focused and concise.
+- **Format**: Use the template below.
+
+---
+
+## Template
+
+```markdown
+# [Topic Title]
+
+> Discovered: YYYY-MM-DD
+
+## Context
+Where / when does this apply?
+
+## Finding
+What exactly did we learn?
+
+## Solution / Pattern
+The code or approach that works.
+
+## Gotchas
+Edge cases or caveats to watch out for.
+```
+
+---
+
+## Index
+
+| File | Topic |
+|------|-------|
+| [openwebui-tool-injection.md](./openwebui-tool-injection.md) | How OpenWebUI injects parameters into Tool functions, and what the Pipe must provide |
+| [openwebui-mock-request.md](./openwebui-mock-request.md) | How to build a valid Mock Request for calling OpenWebUI-internal APIs from a Pipe |
+| [copilot-plan-mode-prompt-parity.md](./copilot-plan-mode-prompt-parity.md) | Why Plan Mode prompt logic must be shared between fresh-session and resume-session injection |

.agent/learnings/async-context-compression-progress-mapping.md

@@ -0,0 +1,27 @@
+# Async Context Compression Progress Mapping
+
+> Discovered: 2026-03-10
+
+## Context
+Applies to `plugins/filters/async-context-compression/async_context_compression.py` once the inlet has already replaced early history with a synthetic summary message.
+
+## Finding
+`compressed_message_count` cannot be recalculated from the visible message list length after compression. Once a summary marker is present, the visible list mixes:
+- preserved head messages that are still before the saved boundary
+- one synthetic summary message
+- tail messages that map to original history starting at the saved boundary
+
+## Solution / Pattern
+Store the original-history boundary on the injected summary message metadata, then recover future progress using:
+- `original_count = covered_until + len(messages_after_summary_marker)`
+- `target_progress = max(covered_until, original_count - keep_last)`
+
+When the summary-model window is too small, trim newest atomic groups from the summary input so the saved boundary still matches what the summary actually covers.
+
+## Gotchas
+- If you trim from the head of the summary input, the saved progress can overstate coverage and hide messages that were never summarized.
+- Status previews for the next context must convert the saved original-history boundary back into the current visible view before rebuilding head/summary/tail.
+- `inlet(body["messages"])` and `outlet(body["messages"])` can both represent the full conversation while using different serializations:
+	- inlet may receive expanded native tool-call chains (`assistant(tool_calls) -> tool -> assistant`)
+	- outlet may receive a compact top-level transcript where tool calls are folded into assistant `<details type="tool_calls">` blocks
+- These two views do not share a safe `compressed_message_count` coordinate system. If outlet is in the compact assistant/details view, do not persist summary progress derived from its top-level message count.

.agent/learnings/copilot-plan-mode-prompt-parity.md

@@ -0,0 +1,40 @@
+# Copilot Plan Mode Prompt Parity
+
+> Discovered: 2026-03-06
+
+## Context
+
+The GitHub Copilot SDK pipe builds system prompts in two paths:
+
+- fresh session creation via `_build_session_config(...)`
+- resumed session injection via the `system_parts` rebuild branch
+
+Plan Mode guidance was duplicated across those branches.
+
+## Finding
+
+If Plan Mode instructions are edited in only one branch, resumed sessions silently lose planning behavior or capability hints that fresh sessions still have.
+
+This is especially easy to miss because both branches still work, but resumed chats receive a weaker or stale prompt.
+
+Session mode switching alone is also not enough. Even when `session.rpc.mode.set(Mode.PLAN)` succeeds, the SDK may still skip creating the expected `plan.md` if the runtime system prompt does not explicitly include the original Plan Mode persistence contract.
+
+## Solution / Pattern
+
+Extract the Plan Mode prompt into one shared helper and call it from both branches:
+
+```python
+def _build_plan_mode_context(plan_path: str) -> str:
+    ...
+```
+
+Then inject it in both places with the chat-specific `plan.md` path.
+
+For extra safety, when the pipe later reads `session.rpc.plan.read()`, mirror the returned content into the chat-specific `COPILOTSDK_CONFIG_DIR/session-state/<chat_id>/plan.md` path. This keeps the UI-visible file in sync even if the SDK persists plan state internally but does not materialize the file where the chat integration expects it.
+
+## Gotchas
+
+- Keep the helper dynamic: the `plan.md` path must still be resolved per chat/session.
+- Do not only update debug prompt artifacts; the effective runtime prompt lives in `plugins/pipes/github-copilot-sdk/github_copilot_sdk.py`.
+- Resume-session parity matters for capability guidance just as much as for session context.
+- If users report that Plan Mode is active but `plan.md` is missing, check both halves: prompt parity and the final `rpc.plan.read()` -> `plan.md` sync path.

.agent/learnings/filter-async-context-compression-design.md

@@ -0,0 +1,171 @@
+# Filter: async-context-compression 设计模式与工程实践
+
+**日期**: 2026-03-12  
+**模块**: `plugins/filters/async-context-compression/async_context_compression.py`  
+**关键特性**: 上下文压缩、异步摘要生成、状态管理、LLM 工程优化
+
+---
+
+## 核心工程洞察
+
+### 1. Request 对象的 Filter-to-LLM 传导链
+
+**问题**：Filter 的 `outlet` 阶段启动背景异步任务（`asyncio.create_task`）调用 `generate_chat_completion`（内部 API），但无法直接访问原始 HTTP `request`。早期代码用最小化合成 Request（仅 `{"type": "http", "app": webui_app}`），暴露兼容性风险。
+
+**解决方案**：
+
+- OpenWebUI 对 `outlet` 同样支持 `__request__` 参数注入（即 `inlet` + `outlet` 都支持）
+- 透传 `__request__` 通过整个异步调用链：`outlet → _locked_summary_task → _check_and_generate_summary_async → _generate_summary_async → _call_summary_llm`
+- 在最终调用处：`request = __request__ or Request(...)`（兜底降级）
+
+**收获**：LLM 调用路径应始终倾向于使用真实请求上下文，而非人工合成。即使后台任务中，`request.app` 的应用级状态仍持续有效。
+
+---
+
+### 2. 异步摘要生成中的上下文完整性
+
+**关键场景分化**：
+
+| 情况 | `summary_index` 值 | 旧摘要位置 | 需要 `previous_summary` |
+|------|--------|----------|---------|
+| Inlet 已注入旧摘要 | Not None | `messages[0]`（middle_messages 首项） | ❌ 否，已在 conversation_text 中 |
+| Outlet 收原始消息（未注入） | None | DB 存档 | ✅ **是**，必须显式读取并透传 |
+
+**问题根源**：`outlet` 收到的消息来自原始数据库查询，未经过 `inlet` 的摘要注入。当 LLM 看不到历史摘要时，已压缩的知识（旧对话、已解决的问题、先前的发现）会被重新处理或遗忘。
+
+**实现要点**：
+
+```python
+# 仅当 summary_index is None 时异步加载旧摘要
+if summary_index is None:
+    previous_summary = await asyncio.to_thread(
+        self._load_summary, chat_id, body
+    )
+else:
+    previous_summary = None
+```
+
+---
+
+### 3. 上下文压缩的 LLM Prompt 设计
+
+**工程原则**：
+
+1. **Clear Input Boundaries**：用 XML 风格标签（`<previous_working_memory>`, `<new_conversation>`）明确分界，避免 LLM 混淆"指令示例"与"待处理数据"
+2. **State-Aware Merging**：不是"保留所有旧事实"，而是**更新状态**——`"bug X exists" → "bug X fixed"` 或彻底移除已解决项
+3. **Goal Evolution**：Current Goal 反映**最新**意图；旧目标迁移到 Working Memory 作为上下文
+4. **Error Verbatim**：Stack trace、异常类型、错误码必须逐字引用（是调试的一等公民）
+5. **Format Strictness**：结构变为 **REQUIRED**（而非 Suggested），允许零内容项省略，但布局一致
+
+**新 Prompt 结构**：
+
+```
+[Rules] → [Output Constraints] → [Required Structure Header] → [Boundaries] → <previous_working_memory> → <new_conversation>
+```
+
+关键改进：
+
+- 规则 3（Ruthless Denoising） → 新增规则 4（Error Verbatim） + 规则 5（Causal Chain）
+- "Suggested" Structure → "Required" Structure with Optional Sections
+- 新增 `## Causal Log` 专项，强制单行因果链格式：`[MSG_ID?] action → result`
+- Token 预算策略明确：按近期性和紧迫性优先裁剪（RRF）
+
+---
+
+### 4. 异步任务中的错误边界与恢复
+
+**现象**：背景摘要生成任务（`asyncio.create_task`）的异常不会阻塞用户响应，但需要：
+
+- 完整的日志链路（`_log` 调用 + `event_emitter` 通知）
+- 数据库事务的原子性（摘要和压缩状态同时保存）
+- 前端 UI 反馈（status event: "generating..." → "complete" 或 "error"）
+
+**最佳实践**：
+
+- 用 `asyncio.Lock` 按 chat_id 防止并发摘要任务
+- 后台执行繁重操作（tokenize、LLM call）用 `asyncio.to_thread`
+- 所有 I/O（DB reads/writes）需包裹异步线程池
+- 异常捕获限制在 try-except，日志不要吞掉堆栈信息
+
+---
+
+### 5. Filter 单例与状态设计陷阱
+
+**约束**：Filter 实例是全局单例，所有会话共享同一个 `self`。
+
+**禁忌**：
+
+```python
+# ❌ 错误：self.temp_buffer = ... （会被其他并发会话污染）
+self.temp_state = body  # 危险！
+
+# ✅ 正确：无状态或使用锁/chat_id 隔离
+self._chat_locks[chat_id] = asyncio.Lock()  # 每个 chat 一个锁
+```
+
+**设计**：
+
+- Valves（Pydantic BaseModel）保存全局配置 ✅
+- 使用 dict 按 `chat_id` 键维护临时状态（lock、计数器）✅
+- 传参而非全局变量保存请求级数据 ✅
+
+---
+
+## 集成场景：Filter + Pipe 的配合
+
+**当 Pipe 模型调用 Filter 时**：
+
+1. `inlet` 注入摘要，削减上下文会话消息数
+2. Pipe 模型（通常为 Copilot SDK 或自定义内核）处理精简消息
+3. `outlet` 触发背景摘要，无阻塞用户响应
+4. 下一轮对话时，`inlet` 再次注入最新摘要
+
+**关键约束**：
+
+- `_should_skip_compression` 检测 `__model__.get("pipe")` 或 `copilot_sdk`，必要时跳过注入
+- Pipe 模型若有自己的上下文管理（如 Copilot 的 native tool calling），过度压缩会失去工具调用链
+- 摘要模型选择（`summary_model` Valve）应兼容当前 Pipe 环境的 API（推荐用通用模型如 gemini-flash）
+
+---
+
+## 内部 API 契约速记
+
+### `generate_chat_completion(request, payload, user)`
+
+- **request**: FastAPI Request；可来自真实 HTTP 或 `__request__` 注入
+- **payload**: `{"model": id, "messages": [...], "stream": false, "max_tokens": N, "temperature": T}`
+- **user**: UserModel；从 DB 查询或 `__user__` 转换（需 `Users.get_user_by_id()`）
+- **返回**: dict 或 JSONResponse；若是后者需 `response.body.decode()` + JSON parse
+
+### Filter 生命周期
+
+```
+New Message → inlet (User input) → [Plugins wait] → LLM → outlet (Response) → Summary Task (Background)
+```
+
+---
+
+## 调试清单
+
+- [ ] `__request__` 在 `outlet` 签名中声明且被 OpenWebUI 注入（非 None）
+- [ ] 异步调用链中每层都透传 `__request__`，最底层兜底合成
+- [ ] `summary_index is None` 时从 DB 异步读取 `previous_summary`
+- [ ] LLM Prompt 中 `<previous_working_memory>` 和 `<new_conversation>` 有明确边界
+- [ ] 错误处理不吞堆栈：`logger.exception()` 或 `exc_info=True`
+- [ ] `asyncio.Lock` 按 chat_id 避免并发工作冲突
+- [ ] Copilot SDK / Pipe 模型需 `_should_skip_compression()` 检查
+- [ ] Token budget 在 max_summary_tokens 下规划，优先保留近期事件
+
+---
+
+## 相关文件
+
+- 核心实现：`plugins/filters/async-context-compression/async_context_compression.py`
+- README：`plugins/filters/async-context-compression/README.md` + `README_CN.md`
+- OpenWebUI 内部：`open_webui/utils/chat.py` → `generate_chat_completion()`
+
+---
+
+**版本**: 1.0  
+**维护者**: Fu-Jie  
+**最后更新**: 2026-03-12

.agent/learnings/openwebui-community-api.md

@@ -0,0 +1,45 @@
+# OpenWebUI Community API Patterns
+
+## Post Data Structure Variations
+
+When fetching posts from the OpenWebUI Community API (`https://api.openwebui.com/api/v1/posts/...`), the structure of the `data` field varies significantly depending on the `type` of the post.
+
+### Observed Mappings
+
+| Post Type | Data Key (under `data`) | Usual Content |
+|-----------|-------------------------|---------------|
+| `action`  | `function`              | Plugin code and metadata |
+| `filter`  | `function`              | Filter logic and metadata |
+| `pipe`    | `function`              | Pipe logic and metadata |
+| `tool`    | `tool`                  | Tool definition and logic |
+| `prompt`  | `prompt`                | Prompt template strings |
+| `model`   | `model`                 | Model configuration |
+
+### Implementation Workaround
+
+To robustly extract metadata (like `version` or `description`) regardless of the post type, the following heuristic logic is recommended:
+
+```python
+def _get_plugin_obj(post: dict) -> dict:
+    data = post.get("data", {}) or {}
+    post_type = post.get("type")
+    
+    # Priority 1: Use specific type key
+    if post_type in data:
+        return data[post_type]
+    
+    # Priority 2: Fallback to common keys
+    for k in ["function", "tool", "pipe"]:
+        if k in data:
+            return data[k]
+            
+    # Priority 3: First available key
+    if data:
+        return list(data.values())[0]
+        
+    return {}
+```
+
+### Gotchas
+- Some older posts or different categories might not have a `version` field in `manifest`, leading to empty strings or `N/A` in reports.
+- `slug` should be used as the unique identifier rather than `title` when tracking stats across history.

.agent/learnings/openwebui-mock-request.md

@@ -0,0 +1,131 @@
+# Building a Valid Mock Request for OpenWebUI Pipes
+
+> Discovered: 2026-03-05
+
+## Context
+
+OpenWebUI Pipes run as a Pipe plugin, not as a real HTTP request handler. When the Pipe
+needs to call OpenWebUI-internal APIs (like `generate_chat_completion`, `get_tools`, etc.)
+or load Tools that do the same, it must provide a **fake-but-complete Request object**.
+
+## Finding
+
+OpenWebUI's internal functions expect `request` to satisfy several contracts:
+
+```
+request.app.state.MODELS     → dict { model_id: ModelModel }  — MUST be populated!
+request.app.state.config     → config object with all env variables
+request.app.state.TOOLS      → dict (can start empty)
+request.app.state.FUNCTIONS  → dict (can start empty)
+request.app.state.redis      → None is fine
+request.app.state.TOOL_SERVERS → []  is fine
+request.app.url_path_for(name, **path_params) → str
+request.headers              → dict with Authorization, host, user-agent
+request.state.user           → user dict
+request.state.token.credentials → str (the Bearer token, without "Bearer " prefix)
+await request.json()         → dict (the raw request body)
+await request.body()         → bytes (the raw request body as JSON bytes)
+```
+
+## Solution / Pattern
+
+```python
+from types import SimpleNamespace
+import json as _json_mod
+
+def _build_openwebui_request(user: dict, token: str, body: dict = None):
+    from open_webui.config import PERSISTENT_CONFIG_REGISTRY
+    from open_webui.models.models import Models as _Models
+
+    # 1. Build config from registry
+    config = SimpleNamespace()
+    for item in PERSISTENT_CONFIG_REGISTRY:
+        val = item.value
+        if hasattr(val, "value"):
+            val = val.value
+        setattr(config, item.env_name, val)
+
+    # 2. Populate MODELS from DB — critical for model validation
+    system_models = {}
+    try:
+        for m in _Models.get_all_models():
+            system_models[m.id] = m
+    except Exception:
+        pass
+
+    # 3. Build app_state
+    app_state = SimpleNamespace(
+        config=config,
+        TOOLS={},
+        TOOL_CONTENTS={},
+        FUNCTIONS={},
+        FUNCTION_CONTENTS={},
+        MODELS=system_models,   # <-- KEY: must not be empty!
+        redis=None,
+        TOOL_SERVERS=[],
+    )
+
+    # 4. url_path_for helper
+    def url_path_for(name: str, **params):
+        if name == "get_file_content_by_id":
+            return f"/api/v1/files/{params.get('id')}/content"
+        return f"/mock/{name}"
+
+    app = SimpleNamespace(state=app_state, url_path_for=url_path_for)
+
+    # 5. Async body helpers
+    async def _json():
+        return body or {}
+
+    async def _body_fn():
+        return _json_mod.dumps(body or {}).encode("utf-8")
+
+    # 6. Headers
+    headers = {
+        "user-agent": "Mozilla/5.0",
+        "host": "localhost:8080",
+        "accept": "*/*",
+    }
+    if token:
+        headers["Authorization"] = token if token.startswith("Bearer ") else f"Bearer {token}"
+
+    return SimpleNamespace(
+        app=app,
+        headers=headers,
+        method="POST",
+        cookies={},
+        base_url="http://localhost:8080",
+        url=SimpleNamespace(path="/api/chat/completions", base_url="http://localhost:8080"),
+        state=SimpleNamespace(
+            token=SimpleNamespace(credentials=token or ""),
+            user=user or {},
+        ),
+        json=_json,
+        body=_body_fn,
+    )
+```
+
+## Token Extraction
+
+Tokens can be found in multiple places. Check in order:
+
+```python
+# 1. Direct in body (some SDK requests embed it)
+token = body.get("token")
+
+# 2. In metadata
+token = token or (metadata or {}).get("token")
+
+# 3. In the original __request__ Authorization header
+if not token and __request__ is not None:
+    auth = getattr(__request__, "headers", {}).get("Authorization", "")
+    if auth.startswith("Bearer "):
+        token = auth.split(" ", 1)[1]
+```
+
+## Gotchas
+
+- **`app.state.MODELS` empty = "Model not found"** for *any* model ID, even correct ones.
+- `TOOL_SERVER_CONNECTIONS` must be synced from DB, not from in-memory cache (stale in multi-worker).
+- `request.state.token.credentials` should be the **raw token** (no "Bearer " prefix).
+- Tools may call `await request.json()` — must be an async method, not a regular attribute.

.agent/learnings/openwebui-tool-call-context-inflation.md

@@ -0,0 +1,26 @@
+# OpenWebUI Tool Call Context Inflation
+
+> Discovered: 2026-03-11
+
+## Context
+When analyzing why the `async_context_compression` plugin sees different array lengths of `messages` between the `inlet` (e.g. 27 items) and `outlet` (e.g. 8 items) phases, especially when native tool calling (Function Calling) is involved in OpenWebUI.
+
+## Finding
+There is a fundamental disparity in how OpenWebUI serializes conversational history at different stages of the request lifecycle:
+
+1. **Outlet (UI Rendering View)**:
+   After the LLM completes generation and tools have been executed, OpenWebUI's `middleware.py` (and streaming builders) bundles intermediate tool calls and their raw results. It hides them inside an HTML `<details type="tool_calls">...</details>` block within a single `role: assistant` message's `content`. 
+   Concurrently, the actual native API tool-calling data is saved in a hidden `output` dict field attached to that message. At this stage, the `messages` array looks short (e.g., 8 items) because tool interactions are visually folded.
+
+2. **Inlet (LLM Native View)**:
+   When the user sends the *next* message, the request enters `main.py` -> `process_chat_payload` -> `middleware.py:process_messages_with_output()`.
+   Here, OpenWebUI scans historical `assistant` messages for that hidden `output` field. If found, it completely **inflates (unfolds)** the raw data back into an exact sequence of OpenAI-compliant `tool_call` and `tool_result` messages (using `utils/misc.py:convert_output_to_messages`).
+   The HTML `<details>` string is entirely discarded before being sent to the LLM.
+
+**Conclusion on Token Consumption**:
+In the next turn, tool context is **NOT** compressed at all. It is fully re-expanded to its original verbose state (e.g., back to 27 items) and consumes the maximum amount of tokens required by the raw JSON arguments and results.
+
+## Gotchas
+- Any logic operating in the `outlet` phase (like background tasks) that relies on the `messages` array index will be completely misaligned with the array seen in the `inlet` phase.
+- Attempting to slice or trim history based on `outlet` array lengths will cause index out-of-bounds errors or destructive cropping of recent messages.
+- The only safe way to bridge these two views is either to translate the folded view back into the expanded view using `convert_output_to_messages`, or to rely on unique `id` fields (if available) rather than array indices.

.agent/learnings/openwebui-tool-injection.md

@@ -0,0 +1,83 @@
+# OpenWebUI Tool Parameter Injection
+
+> Discovered: 2026-03-05
+
+## Context
+
+When OpenWebUI loads a Python Tool and calls one of its functions (e.g. `generate_mind_map`),
+it automatically matches parameters from an `extra_params` dict against the function's
+signature **by name**. This is done in:
+
+```
+open_webui/utils/tools.py → get_async_tool_function_and_apply_extra_params()
+```
+
+The lookup is: `extra_params = {k: v for k, v in extra_params.items() if k in sig.parameters}`
+
+## Finding
+
+A Tool function declares its dependencies via its parameter names. Common injected names:
+
+| Parameter Name        | What it contains                                  |
+|-----------------------|---------------------------------------------------|
+| `__user__`            | User context dict (id, email, role, name)         |
+| `__event_emitter__`   | Async callable to emit status/notification events |
+| `__event_call__`      | Async callable for JS `__event_call__` roundtrips |
+| `__request__`         | Request-like object (must have `.app.state.MODELS`) |
+| `__metadata__`        | Dict: `{model, base_model_id, chat_id, ...}`      |
+| `__messages__`        | Full conversation history list                    |
+| `__chat_id__`         | Current chat UUID                                 |
+| `__message_id__`      | Current message UUID                              |
+| `__session_id__`      | Current session UUID                              |
+| `__files__`           | Files attached to the current message             |
+| `__task__`            | Task type string (e.g. `title_generation`)        |
+| `body`                | Raw request body dict (non-dunder variant)        |
+| `request`             | Request object (non-dunder variant)               |
+
+## Key Rule
+
+**`extra_params` must contain ALL keys a Tool's function signature declares.**
+If a key is missing from `extra_params`, the parameter silently receives its default
+value (e.g. `{}` for `__metadata__`). This means the Tool appears to work but
+gets empty/wrong context.
+
+## Solution / Pattern
+
+When a Pipe calls an OpenWebUI Tool, it must populate `extra_params` with **all** the above:
+
+```python
+extra_params = {
+    "__request__": request,      # Must have app.state.MODELS populated!
+    "request": request,          # Non-dunder alias
+    "__user__": user_data,
+    "__event_emitter__": __event_emitter__,
+    "__event_call__": __event_call__,
+    "__messages__": messages,
+    "__metadata__": __metadata__ or {},
+    "__chat_id__": chat_id,
+    "__message_id__": message_id,
+    "__session_id__": session_id,
+    "__files__": files,
+    "__task__": task,
+    "__task_body__": task_body,
+    "body": body,                # Non-dunder alias
+    ...
+}
+```
+
+## Model Resolution
+
+Tools that call `generate_chat_completion` internally need a **valid model ID**.
+When the conversation is running under a Pipe/Manifold model (e.g. `github_copilot.gpt-4o`),
+the Tool's `valves.MODEL_ID` must be a *real* model known to the system.
+
+`generate_chat_completion` validates model IDs against `request.app.state.MODELS`.
+➡️  That dict **must be populated** from the database (see `openwebui-mock-request.md`).
+
+## Gotchas
+
+- Tools call `generate_chat_completion` with a `request` arg that must be the full Mock Request.
+- If `app.state.MODELS` is empty, even a correctly-spelled model ID will cause "Model not found".
+- `__metadata__['model']` can be a **dict** (from DB) **or a string** (manifold ID). Tools must
+  handle both types.
+- For manifold models not in the DB, strip the prefix: `github_copilot.gpt-4o` → `gpt-4o`.

.agent/rules/antigravity.md

@@ -0,0 +1,160 @@
+---
+description: >
+  Antigravity development mode rules. Apply when the user requests high-speed iteration,
+  a quick prototype, or says "反重力开发" / "antigravity mode".
+globs: "plugins/**/*.py"
+always_on: false
+---
+# Antigravity Development Mode
+
+> High-speed delivery + strict reversibility. Every decision must keep both roll-forward and rollback feasible.
+
+---
+
+## Core Principles
+
+1. **Small, isolated edits** — one logical change per operation; no mixing refactor + feature.
+2. **Deterministic interfaces** — function signatures and return shapes must not change without an explicit contract update.
+3. **Multi-level fallback** — every I/O path has a degraded alternative (e.g., S3 → local → DB).
+4. **Reversible by default** — every file write, API call, or schema change must have an undo path recorded or be idempotent.
+
+---
+
+## Mandatory Safety Patterns
+
+### 1. Timeout Guards on All Frontend Calls
+
+Any `__event_call__` or `__event_emitter__` JS execution MUST be wrapped:
+
+```python
+import asyncio
+
+try:
+    result = await asyncio.wait_for(
+        __event_call__({"type": "execute", "data": {"code": js_code}}),
+        timeout=2.0
+    )
+except asyncio.TimeoutError:
+    logger.warning("Frontend JS execution timed out; falling back.")
+    result = fallback_value
+except Exception as e:
+    logger.error(f"Frontend call failed: {e}", exc_info=True)
+    result = fallback_value
+```
+
+JS side must also guard internally:
+
+```javascript
+try {
+    return (localStorage.getItem('locale') || navigator.language || 'en-US');
+} catch (e) {
+    return 'en-US';
+}
+```
+
+### 2. Path Sandbox Validation
+
+Resolve every workspace path and verify it stays inside the repo root:
+
+```python
+import os
+
+def _validate_workspace_path(path: str, workspace_root: str) -> str:
+    resolved = os.path.realpath(os.path.abspath(path))
+    root = os.path.realpath(workspace_root)
+    if not resolved.startswith(root + os.sep) and resolved != root:
+        raise PermissionError(f"Path escape detected: {resolved} is outside {root}")
+    return resolved
+```
+
+### 3. Dual-Channel Upload Fallback
+
+Always try API first; fall back to DB/local on failure:
+
+```python
+async def _upload_file(self, filename: str, content: bytes) -> str:
+    # Channel 1: API upload (S3-compatible)
+    try:
+        url = await self._api_upload(filename, content)
+        if url:
+            return url
+    except Exception as e:
+        logger.warning(f"API upload failed: {e}; falling back to local.")
+
+    # Channel 2: Local file + DB registration
+    return await self._local_db_upload(filename, content)
+```
+
+### 4. Progressive Status Reporting
+
+For tasks > 3 seconds, emit staged updates:
+
+```python
+await self._emit_status(emitter, "正在分析内容...", done=False)
+# ... phase 1 ...
+await self._emit_status(emitter, "正在生成输出...", done=False)
+# ... phase 2 ...
+await self._emit_status(emitter, "完成", done=True)
+```
+
+Always emit `done=True` on completion and `notification(error)` on failure.
+
+### 5. Emitter Guard
+
+Check before every emit to prevent crashes on missing emitter:
+
+```python
+if emitter and self.valves.SHOW_STATUS:
+    await emitter({"type": "status", "data": {"description": msg, "done": done}})
+```
+
+### 6. Exception Surface Rule
+
+Never swallow exceptions silently. Every `except` block must:
+
+- Log to backend: `logger.error(f"...: {e}", exc_info=True)`
+- Notify user: `await self._emit_notification(emitter, f"处理失败: {str(e)}", "error")`
+
+---
+
+## Edit Discipline
+
+| ✅ DO | ❌ DO NOT |
+|-------|-----------|
+| One function / one Valve / one method per edit | Mix multiple unrelated changes in one operation |
+| Validate input at the function boundary | Assume upstream data is well-formed |
+| Return early on invalid state | Nest complex logic beyond 3 levels |
+| Check fallback availability before primary path | Assume primary path always succeeds |
+| Log before and after expensive I/O | Skip logging for "obvious" operations |
+
+---
+
+## Rollback Checklist
+
+Before completing an antigravity operation, confirm:
+
+- [ ] No global state mutated on `self` (filter singleton rule)
+- [ ] File writes are atomic or can be recreated
+- [ ] Database changes are idempotent (safe to re-run)
+- [ ] Timeout guards are in place for all async calls to external systems
+- [ ] The user can observe progress through status/notification events
+- [ ] Non-obvious findings / gotchas are saved to `.agent/learnings/{topic}.md`
+
+---
+
+## Mandatory: Knowledge Capture
+
+Any non-obvious pattern, internal API contract, or workaround discovered during an
+antigravity session **MUST** be saved to `.agent/learnings/{topic}.md` before the
+session ends. This ensures hard-won insights are not lost between sessions.
+
+**Format**: See `.agent/learnings/README.md`
+**Existing entries**: Browse `.agent/learnings/` for prior knowledge to reuse.
+
+---
+
+## References
+
+- Full engineering spec: `.github/copilot-instructions.md` → Section: **Antigravity Development Mode**
+- Design document: `docs/development/copilot-engineering-plan.md` → Section 5
+- Knowledge base: `.agent/learnings/` — reusable engineering patterns and gotchas

.agent/rules/plugin_standards.md

@@ -12,19 +12,22 @@ All plugins MUST follow the standard README template.
 **Reference Template**: @docs/PLUGIN_README_TEMPLATE.md
 
 ### Language Requirements
+
 - **English Version (`README.md`)**: The primary documentation source. Must follow the template strictly.
 - **Chinese Version (`README_CN.md`)**: MUST be translated based on the English version (`README.md`) to ensure consistency in structure and content.
 
 ### Metadata Requirements
+
 The metadata line must follow this format:
-`**Author:** [Name](Link) | **Version:** [X.Y.Z] | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **License:** MIT`
+`**Author:** [Name](Link) | **Version:** [X.Y.Z] | **Project:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **License:** MIT`
 
 ### Structure Checklist
-1.  **Title & Description**
-2.  **Metadata Line** (Author, Version, Project, License)
-3.  **Preview** (Screenshots/GIFs)
-4.  **What's New** (Keep last 3 versions)
-5.  **Key Features**
-6.  **How to Use**
-7.  **Configuration (Valves)**
-8.  **Troubleshooting** (Must include link to GitHub Issues)
+
+1. **Title & Description**
+2. **Metadata Line** (Author, Version, Project, License)
+3. **Preview** (Screenshots/GIFs)
+4. **What's New** (Keep last 3 versions)
+5. **Key Features**
+6. **How to Use**
+7. **Configuration (Valves)**
+8. **Troubleshooting** (Must include link to GitHub Issues)

.agent/skills/README.md

@@ -0,0 +1,71 @@
+# Agent Skills Index
+
+This folder contains reusable Agent Skills for GitHub Copilot / VS Code custom agent workflows.
+
+## Available Skills
+
+- **community-announcer**
+  - Purpose: Generate community announcement content and related assets.
+  - Entry: `community-announcer/SKILL.md`
+
+- **doc-mirror-sync**
+  - Purpose: Sync mirrored documentation content and helper scripts.
+  - Entry: `doc-mirror-sync/SKILL.md`
+
+- **gh-issue-replier**
+  - Purpose: Draft standardized issue replies with templates.
+  - Entry: `gh-issue-replier/SKILL.md`
+
+- **gh-issue-scheduler**
+  - Purpose: Schedule and discover unanswered issues for follow-up.
+  - Entry: `gh-issue-scheduler/SKILL.md`
+
+- **i18n-validator**
+  - Purpose: Validate translation key consistency across i18n dictionaries.
+  - Entry: `i18n-validator/SKILL.md`
+
+- **plugin-scaffolder**
+  - Purpose: Scaffold OpenWebUI plugin boilerplate with repository standards.
+  - Entry: `plugin-scaffolder/SKILL.md`
+
+- **version-bumper**
+  - Purpose: Assist with semantic version bumping workflows.
+  - Entry: `version-bumper/SKILL.md`
+
+- **xlsx-single-file**
+  - Purpose: Single-file spreadsheet operations workflow without LibreOffice.
+  - Entry: `xlsx-single-file/SKILL.md`
+
+---
+
+## Release Pipeline Skills
+
+These four skills form a complete release pipeline and are designed to be used in sequence:
+
+```
+release-prep  →  pr-submitter  →  pr-reviewer  →  release-finalizer
+ (prepare)       (push & PR)      (respond to review)  (merge & close issue)
+```
+
+- **release-prep**
+  - Purpose: Full release preparation — version sync across 7+ files, bilingual release notes creation, consistency check, and commit.
+  - Entry: `release-prep/SKILL.md`
+
+- **pr-submitter**
+  - Purpose: Shell-escape-safe PR submission — writes body to temp file, validates sections, pushes branch, creates PR via `gh pr create --body-file`.
+  - Entry: `pr-submitter/SKILL.md`
+
+- **pr-reviewer**
+  - Purpose: Fetch PR review comments, categorize feedback, implement fixes, commit and push, reply to reviewers.
+  - Entry: `pr-reviewer/SKILL.md`
+
+- **release-finalizer**
+  - Purpose: Merge release PR to main with proper commit message, auto-link and close related issues, post closing messages.
+  - Entry: `release-finalizer/SKILL.md`
+
+## Notes
+
+- Skill definitions follow the expected location pattern:
+  - `.github/skills/<skill-name>/SKILL.md`
+- Each skill may include optional `assets/`, `references/`, and `scripts/` folders.
+- This directory mirrors `.gemini/skills` for compatibility.

.agent/skills/community-announcer/SKILL.md

@@ -0,0 +1,23 @@
+---
+name: community-announcer
+description: Drafts engaging English and Chinese update announcements for the OpenWebUI Community and other social platforms. Use when a new version is released.
+---
+
+# Community Announcer
+
+## Overview
+Automates the drafting of high-impact update announcements.
+
+## Workflow
+1. **Source Intel**: Read the latest version's `What's New` section from `README.md`.
+2. **Drafting**: Create two versions:
+   - **Community Post**: Professional, structured, technical.
+   - **Catchy Short**: For Discord/Twitter, use emojis and bullet points.
+3. **Multi-language**: Generate BOTH English and Chinese versions automatically.
+
+## Announcement Structure (Recommended)
+- **Headline**: "Update vX.X.X - [Main Feature]"
+- **Introduction**: Brief context.
+- **Key Highlights**: Bulleted list of fixes/features.
+- **Action**: "Download from [Market Link]"
+- **Closing**: Thanks and Star request.

.agent/skills/doc-mirror-sync/SKILL.md

@@ -0,0 +1,50 @@
+---
+name: doc-mirror-sync
+description: Automatically synchronizes plugin READMEs to the official documentation directory (docs/). Use after editing a plugin's local documentation to keep the MkDocs site up to date.
+---
+
+# Doc Mirror Sync
+
+## Overview
+Automates the mirroring of `plugins/{type}/{name}/README.md` to `docs/plugins/{type}/{name}.md`.
+
+## Docs-Only Mode (No Release Changes)
+Use this mode when the request is "only sync docs".
+
+- Only update documentation mirror files under `docs/plugins/**`.
+- Do **not** bump plugin version.
+- Do **not** modify plugin code (`plugins/**.py`) unless explicitly requested.
+- Do **not** update root badges/dates for release.
+- Do **not** run release preparation steps.
+
+## Workflow
+1. Identify changed READMEs.
+2. Copy content to corresponding mirror paths.
+3. Update version badges in `docs/plugins/{type}/index.md`.
+
+## Commands
+
+### Sync all mirrors (EN + ZH)
+
+```bash
+python .github/skills/doc-mirror-sync/scripts/sync.py
+```
+
+### Sync only one plugin (EN only)
+
+```bash
+cp plugins/<type>/<name>/README.md docs/plugins/<type>/<name>.md
+```
+
+### Sync only one plugin (EN + ZH)
+
+```bash
+cp plugins/<type>/<name>/README.md docs/plugins/<type>/<name>.md
+cp plugins/<type>/<name>/README_CN.md docs/plugins/<type>/<name>.zh.md
+```
+
+## Notes
+
+- If asked for English-only update, sync only `README.md` -> `.md` mirror.
+- If both languages are requested, sync both `README.md` and `README_CN.md`.
+- After syncing, verify git diff only contains docs file changes.

.agent/skills/doc-mirror-sync/scripts/sync.py

@@ -0,0 +1,38 @@
+#!/usr/bin/env python3
+import os
+import shutil
+import re
+
+def sync_mirrors():
+    plugins_root = "plugins"
+    docs_root = "docs/plugins"
+    
+    types = ["actions", "filters", "pipes", "pipelines", "tools"]
+    
+    for t in types:
+        src_type_dir = os.path.join(plugins_root, t)
+        dest_type_dir = os.path.join(docs_root, t)
+        
+        if not os.path.exists(src_type_dir): continue
+        os.makedirs(dest_type_dir, exist_ok=True)
+        
+        for name in os.listdir(src_type_dir):
+            plugin_dir = os.path.join(src_type_dir, name)
+            if not os.path.isdir(plugin_dir): continue
+            
+            # Sync README.md -> docs/plugins/{type}/{name}.md
+            src_readme = os.path.join(plugin_dir, "README.md")
+            if os.path.exists(src_readme):
+                dest_readme = os.path.join(dest_type_dir, f"{name}.md")
+                shutil.copy(src_readme, dest_readme)
+                print(f"✅ Mirrored: {t}/{name} (EN)")
+            
+            # Sync README_CN.md -> docs/plugins/{type}/{name}.zh.md
+            src_readme_cn = os.path.join(plugin_dir, "README_CN.md")
+            if os.path.exists(src_readme_cn):
+                dest_readme_zh = os.path.join(dest_type_dir, f"{name}.zh.md")
+                shutil.copy(src_readme_cn, dest_readme_zh)
+                print(f"✅ Mirrored: {t}/{name} (ZH)")
+
+if __name__ == "__main__":
+    sync_mirrors()

.agent/skills/gh-issue-replier/SKILL.md

@@ -0,0 +1,51 @@
+---
+name: gh-issue-replier
+description: Professional English replier for GitHub issues. Use when a task is completed, a bug is fixed, or more info is needed from the user. Automates replying using the 'gh' CLI tool.
+---
+
+# Gh Issue Replier
+
+## Overview
+
+The `gh-issue-replier` skill enables Gemini CLI to interact with GitHub issues professionally. It enforces English for all communications and leverages the `gh` CLI to post comments.
+
+## Workflow
+
+1.  **Identify the Issue**: Find the issue number (e.g., #49).
+2.  **Check Star Status**: Run the bundled script to check if the author has starred the repo.
+    *   Command: `bash scripts/check_star.sh <issue-number>`
+    *   Interpretation: 
+        *   Exit code **0**: User has starred. Use "Already Starred" templates.
+        *   Exit code **1**: User has NOT starred. Include "Star Request" in the reply.
+3.  **Select a Template**: Load [templates.md](references/templates.md) to choose a suitable English response pattern.
+4.  **Draft the Reply**: Compose a concise message based on the star status.
+5.  **Post the Comment**: Use the `gh` tool to submit the reply.
+
+## Tool Integration
+
+### Check Star Status
+```bash
+bash scripts/check_star.sh <issue-number>
+```
+
+### Post Comment
+```bash
+gh issue comment <issue-number> --body "<message-body>"
+```
+
+Example (if user has NOT starred):
+```bash
+gh issue comment 49 --body "This has been fixed in v1.2.7. If you find this helpful, a star on the repo would be much appreciated! ⭐"
+```
+
+Example (if user HAS starred):
+```bash
+gh issue comment 49 --body "This has been fixed in v1.2.7. Thanks for your support!"
+```
+
+## Guidelines
+
+-   **Language**: ALWAYS use English for the comment body, even if the system prompt or user conversation is in another language.
+-   **Tone**: Professional, helpful, and appreciative.
+-   **Precision**: When announcing a fix, mention the specific version or the logic change (e.g., "Updated regex pattern").
+-   **Closing**: If the issue is resolved and you have permission, you can also use `gh issue close <number>`.

.agent/skills/gh-issue-replier/references/example_reference.md

@@ -0,0 +1,17 @@
+# Reference Documentation for Gh Issue Replier
+
+This is a placeholder for detailed reference documentation.
+Replace with actual reference content or delete if not needed.
+
+## Structure Suggestions
+
+### API Reference Example
+- Overview
+- Authentication
+- Endpoints with examples
+- Error codes
+
+### Workflow Guide Example
+- Prerequisites
+- Step-by-step instructions
+- Best practices

.agent/skills/gh-issue-replier/references/templates.md

@@ -0,0 +1,45 @@
+# Issue Reply Templates
+
+Use these templates to craft professional English replies. Adjust placeholders like `@username`, `v1.2.x`, and `[commit hash]` as needed.
+
+## 1. Acknowledging a New Issue
+Use when you first see an issue and want to let the user know you are working on it.
+
+- "Thank you for reporting this! I'm looking into it right now."
+- "Thanks for bringing this to my attention. I'll try to reproduce this behavior and get back to you shortly."
+
+## 2. Requesting More Information
+Use when you need logs or specific details to fix the bug.
+
+- "Could you please provide the **'Original'** vs **'Normalized'** content from your browser console logs (F12)? It would help a lot in debugging."
+- "It would be very helpful if you could share the specific Markdown text that triggered this issue."
+
+## 3. Announcing a Fix
+Use when you have pushed the fix to the repository.
+
+- "This has been fixed in version **v1.2.x**. You can update the plugin to resolve it."
+- "I've just pushed a fix for this in [commit hash]. Please let me know if it works for you after updating."
+- "The issue was caused by a greedy regex pattern. I've updated it to use a tempered greedy token to prevent incorrect merging."
+
+## 4. Guiding to Official Market
+Always provide the official market link to ensure the user gets the latest verified version.
+
+- "The fix is now live! You can download the latest version from the official OpenWebUI Community page here: [Plugin Market Link]. Simply update the function in your OpenWebUI instance to apply the changes."
+- "I recommend getting the updated version from the official store: [Link]. It includes the fix for the spacing issue we discussed."
+
+## 5. Closing the Issue
+Use when the issue is confirmed resolved.
+
+- "Glad to hear it's working now! Closing this for now. Feel free to reopen it if the problem persists."
+- "Since this is resolved, I'm closing this issue. Thanks again for your feedback!"
+
+## 5. Pro-tip: Star Request
+Gently handle star requests based on the user's current status.
+
+### If User has NOT starred:
+- "If you find this plugin helpful, a star on the repo would be much appreciated! ⭐"
+- "We'd love your support! If this fixed your issue, please consider starring the repository. ⭐"
+
+### If User HAS already starred:
+- "Thanks again for starring the project and for your continuous support!"
+- "I appreciate your support and for being a stargazer of this project!"

.agent/skills/gh-issue-replier/scripts/check_star.sh

@@ -0,0 +1,31 @@
+#!/usr/bin/env bash
+
+# Robust Star Checker v2
+# Usage: ./check_star.sh <issue_number>
+
+ISSUE_NUM=$1
+if [ -z "$ISSUE_NUM" ]; then exit 2; fi
+
+# 1. Get Repo and Author info
+REPO_FULL=$(gh repo view --json owner,name -q ".owner.login + \"/\" + .name")
+USER_LOGIN=$(gh issue view "$ISSUE_NUM" --json author -q ".author.login")
+
+# 2. Use GraphQL for high precision (Detects stars even when REST 404s)
+IS_STARRED=$(gh api graphql -f query='
+query($owner:String!, $repo:String!, $user:String!) {
+  repository(owner:$owner, name:$repo) {
+    stargazers(query:$user, first:1) {
+      nodes {
+        login
+      }
+    }
+  }
+}' -f owner="${REPO_FULL%/*}" -f repo="${REPO_FULL#*/}" -f user="$USER_LOGIN" -q ".data.repository.stargazers.nodes[0].login")
+
+if [ "$IS_STARRED" == "$USER_LOGIN" ]; then
+    echo "Confirmed: @$USER_LOGIN HAS starred $REPO_FULL. ⭐"
+    exit 0
+else
+    echo "Confirmed: @$USER_LOGIN has NOT starred $REPO_FULL."
+    exit 1
+fi

.agent/skills/gh-issue-scheduler/SKILL.md

@@ -0,0 +1,42 @@
+---
+name: gh-issue-scheduler
+description: Finds all open GitHub issues that haven't been replied to by the owner, summarizes them, and generates a solution plan. Use when the user wants to audit pending tasks or plan maintenance work.
+---
+
+# Gh Issue Scheduler
+
+## Overview
+
+The `gh-issue-scheduler` skill helps maintainers track community feedback by identifying unaddressed issues and drafting actionable technical plans to resolve them.
+
+## Workflow
+
+1.  **Identify Unanswered Issues**: Run the bundled script to fetch issues without owner replies.
+    *   Command: `bash scripts/find_unanswered.sh`
+2.  **Analyze and Summarize**: For each identified issue, summarize the core problem and the user's intent.
+3.  **Generate Solution Plans**: Draft a technical "Action Plan" for each issue, including:
+    *   **Root Cause Analysis** (if possible)
+    *   **Proposed Fix/Implementation**
+    *   **Verification Strategy**
+4.  **Present to User**: Display a structured report of all pending issues and their respective plans.
+
+## Tool Integration
+
+### Find Unanswered Issues
+```bash
+bash scripts/find_unanswered.sh
+```
+
+## Report Format
+
+When presenting the summary, use the following Markdown structure:
+
+### 📋 Unanswered Issues Audit
+
+#### Issue #[Number]: [Title]
+- **Author**: @username
+- **Summary**: Concise description of the problem.
+- **Action Plan**:
+    1. Step 1 (e.g., Investigate file X)
+    2. Step 2 (e.g., Apply fix Y)
+    3. Verification (e.g., Run test Z)

.agent/skills/gh-issue-scheduler/scripts/find_unanswered.sh

@@ -0,0 +1,42 @@
+#!/usr/bin/env bash
+
+# Fetch all open issues and filter for those without responses from the owner/collaborators.
+# Uses 'gh' CLI.
+
+REPO_FULL=$(gh repo view --json owner,name -q ".owner.login + "/" + .name")
+OWNER=${REPO_FULL%/*}
+
+# 1. Get all open issues
+OPEN_ISSUES=$(gh issue list --state open --json number,title,author,createdAt --limit 100)
+
+echo "Analysis for repository: $REPO_FULL"
+echo "------------------------------------"
+
+# Process each issue
+echo "$OPEN_ISSUES" | jq -c '.[]' | while read -r issue; do
+    NUMBER=$(echo "$issue" | jq -r '.number')
+    TITLE=$(echo "$issue" | jq -r '.title')
+    AUTHOR=$(echo "$issue" | jq -r '.author.login')
+    
+    # Check comments for owner responses
+    # We look for comments where the author is the repo owner
+    COMMENTS=$(gh issue view "$NUMBER" --json comments -q ".comments[].author.login" 2>/dev/null)
+    
+    HAS_OWNER_REPLY=false
+    for COMMENT_AUTHOR in $COMMENTS; do
+        if [ "$COMMENT_AUTHOR" == "$OWNER" ]; then
+            HAS_OWNER_REPLY=true
+            break
+        fi
+    done
+    
+    if [ "$HAS_OWNER_REPLY" == "false" ]; then
+        echo "ISSUE_START"
+        echo "ID: $NUMBER"
+        echo "Title: $TITLE"
+        echo "Author: $AUTHOR"
+        echo "Description:"
+        gh issue view "$NUMBER" --json body -q ".body"
+        echo "ISSUE_END"
+    fi
+done

.agent/skills/i18n-validator/SKILL.md

@@ -0,0 +1,14 @@
+---
+name: i18n-validator
+description: Validates multi-language consistency in the TRANSLATIONS dictionary of a plugin. Use to check if any language keys are missing or if translations need updating.
+---
+
+# I18n Validator
+
+## Overview
+Ensures all 12 supported languages (en-US, zh-CN, etc.) have aligned translation keys.
+
+## Features
+- Detects missing keys in non-English dictionaries.
+- Suggests translations using the core AI engine.
+- Validates the `fallback_map` for variant redirects.

.agent/skills/i18n-validator/scripts/validate_i18n.py

@@ -0,0 +1,54 @@
+#!/usr/bin/env python3
+import sys
+import ast
+import os
+
+def check_i18n(file_path):
+    if not os.path.exists(file_path):
+        print(f"Error: File not found {file_path}")
+        return
+    
+    with open(file_path, 'r', encoding='utf-8') as f:
+        tree = ast.parse(f.read())
+    
+    translations = {}
+    for node in tree.body:
+        if isinstance(node, ast.Assign):
+            for target in node.targets:
+                if isinstance(target, ast.Name) and target.id == "TRANSLATIONS":
+                    translations = ast.literal_eval(node.value)
+                    break
+    
+    if not translations:
+        print("⚠️ No TRANSLATIONS dictionary found.")
+        return
+
+    # Base keys from English
+    base_lang = "en-US"
+    if base_lang not in translations:
+        print(f"❌ Error: {base_lang} missing in TRANSLATIONS.")
+        return
+    
+    base_keys = set(translations[base_lang].keys())
+    print(f"🔍 Analyzing {file_path}...")
+    print(f"Standard keys ({len(base_keys)}): {', '.join(sorted(base_keys))}
+")
+
+    for lang, keys in translations.items():
+        if lang == base_lang: continue
+        lang_keys = set(keys.keys())
+        missing = base_keys - lang_keys
+        extra = lang_keys - base_keys
+        
+        if missing:
+            print(f"❌ {lang}: Missing {len(missing)} keys: {', '.join(missing)}")
+        if extra:
+            print(f"⚠️ {lang}: Has {len(extra)} extra keys: {', '.join(extra)}")
+        if not missing and not extra:
+            print(f"✅ {lang}: Aligned.")
+
+if __name__ == "__main__":
+    if len(sys.argv) < 2:
+        print("Usage: validate_i18n.py <path_to_plugin.py>")
+        sys.exit(1)
+    check_i18n(sys.argv[1])

.agent/skills/plugin-scaffolder/SKILL.md

@@ -0,0 +1,19 @@
+---
+name: plugin-scaffolder
+description: Generates a standardized single-file i18n Python plugin template based on project standards. Use when starting a new plugin development to skip boilerplate writing.
+---
+
+# Plugin Scaffolder
+
+## Overview
+Generates compliant OpenWebUI plugin templates with built-in i18n, common utility methods, and required docstring fields.
+
+## Usage
+1. Provide the **Plugin Name** and **Type** (action/filter/pipe).
+2. The skill will generate the `.py` file and the bilingual `README` files.
+
+## Template Standard
+- `Valves(BaseModel)` with `UPPER_SNAKE_CASE`
+- `_get_user_context` with JS fallback and timeout
+- `_emit_status` and `_emit_debug_log` methods
+- Standardized docstring metadata

.agent/skills/plugin-scaffolder/assets/README_template.md

@@ -0,0 +1,34 @@
+# {{TITLE}}
+
+**Author:** [Fu-Jie](https://github.com/Fu-Jie/openwebui-extensions) | **Version:** 0.1.0 | **Project:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **License:** MIT
+
+{{DESCRIPTION}}
+
+## 🔥 What's New in v0.1.0
+
+* Initial release of {{TITLE}}.
+
+## 🌐 Multilingual Support
+
+Supports automatic interface and status switching for the following languages:
+`English`, `简体中文`, `繁體中文 (香港)`, `繁體中文 (台灣)`, `한국어`, `日本語`, `Français`, `Deutsch`, `Español`, `Italiano`, `Tiếng Việt`, `Bahasa Indonesia`.
+
+## ✨ Core Features
+
+* Feature 1
+* Feature 2
+
+## How to Use 🛠️
+
+1. Install the plugin in Open WebUI.
+2. Configure settings in Valves.
+
+## Configuration (Valves) ⚙️
+
+| Parameter | Default | Description |
+| :--- | :--- | :--- |
+| `priority` | `50` | Execution priority. |
+
+## ⭐ Support
+
+If this plugin has been useful, a star on [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) is a big motivation for me. Thank you for the support.

.agent/skills/plugin-scaffolder/assets/template.py

@@ -0,0 +1,80 @@
+"""
+title: {{TITLE}}
+author: Fu-Jie
+author_url: https://github.com/Fu-Jie/openwebui-extensions
+funding_url: https://github.com/open-webui
+version: 0.1.0
+description: {{DESCRIPTION}}
+"""
+
+import asyncio
+import logging
+import json
+from typing import Optional, Dict, Any, List, Callable, Awaitable
+from pydantic import BaseModel, Field
+from fastapi import Request
+
+# Configure logging
+logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s")
+logger = logging.getLogger(__name__)
+
+TRANSLATIONS = {
+    "en-US": {"status_starting": "Starting {{TITLE}}..."},
+    "zh-CN": {"status_starting": "正在启动 {{TITLE}}..."},
+    "zh-HK": {"status_starting": "正在啟動 {{TITLE}}..."},
+    "zh-TW": {"status_starting": "正在啟動 {{TITLE}}..."},
+    "ko-KR": {"status_starting": "{{TITLE}} 시작 중..."},
+    "ja-JP": {"status_starting": "{{TITLE}} を起動中..."},
+    "fr-FR": {"status_starting": "Démarrage de {{TITLE}}..."},
+    "de-DE": {"status_starting": "{{TITLE}} wird gestartet..."},
+    "es-ES": {"status_starting": "Iniciando {{TITLE}}..."},
+    "it-IT": {"status_starting": "Avvio di {{TITLE}}..."},
+    "vi-VN": {"status_starting": "Đang khởi động {{TITLE}}..."},
+    "id-ID": {"status_starting": "Memulai {{TITLE}}..."},
+}
+
+class {{CLASS_NAME}}:
+    class Valves(BaseModel):
+        priority: int = Field(default=50, description="Priority level (lower = earlier).")
+        show_status: bool = Field(default=True, description="Show status updates in UI.")
+
+    def __init__(self):
+        self.valves = self.Valves()
+        self.fallback_map = {
+            "zh": "zh-CN", "en": "en-US", "ko": "ko-KR", "ja": "ja-JP",
+            "fr": "fr-FR", "de": "de-DE", "es": "es-ES", "it": "it-IT",
+            "vi": "vi-VN", "id": "id-ID"
+        }
+
+    def _get_translation(self, lang: str, key: str, **kwargs) -> str:
+        target_lang = lang
+        if target_lang not in TRANSLATIONS:
+            base = target_lang.split("-")[0]
+            target_lang = self.fallback_map.get(base, "en-US")
+        
+        lang_dict = TRANSLATIONS.get(target_lang, TRANSLATIONS["en-US"])
+        text = lang_dict.get(key, TRANSLATIONS["en-US"].get(key, key))
+        return text.format(**kwargs) if kwargs else text
+
+    async def _get_user_context(self, __user__: Optional[dict], __event_call__: Optional[Callable] = None, __request__: Optional[Request] = None) -> dict:
+        user_data = __user__ if isinstance(__user__, dict) else {}
+        user_language = user_data.get("language", "en-US")
+        if __event_call__:
+            try:
+                js = "try { return (document.documentElement.lang || localStorage.getItem('locale') || navigator.language || 'en-US'); } catch (e) { return 'en-US'; }"
+                frontend_lang = await asyncio.wait_for(__event_call__({"type": "execute", "data": {"code": js}}), timeout=2.0)
+                if frontend_lang: user_language = frontend_lang
+            except: pass
+        return {"user_language": user_language}
+
+    async def {{METHOD_NAME}}(self, body: dict, __user__: Optional[dict] = None, __event_emitter__=None, __event_call__=None, __request__: Optional[Request] = None) -> dict:
+        if self.valves.show_status and __event_emitter__:
+            user_ctx = await self._get_user_context(__user__, __event_call__, __request__)
+            msg = self._get_translation(user_ctx["user_language"], "status_starting")
+            await __event_emitter__({"type": "status", "data": {"description": msg, "done": False}})
+        
+        # Implement core logic here
+        
+        if self.valves.show_status and __event_emitter__:
+            await __event_emitter__({"type": "status", "data": {"description": "Done", "done": True}})
+        return body

.agent/skills/plugin-scaffolder/assets/template.py.j2

@@ -0,0 +1,80 @@
+"""
+title: {{TITLE}}
+author: Fu-Jie
+author_url: https://github.com/Fu-Jie/openwebui-extensions
+funding_url: https://github.com/open-webui
+version: 0.1.0
+description: {{DESCRIPTION}}
+"""
+
+import asyncio
+import logging
+import json
+from typing import Optional, Dict, Any, List, Callable, Awaitable
+from pydantic import BaseModel, Field
+from fastapi import Request
+
+# Configure logging
+logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s")
+logger = logging.getLogger(__name__)
+
+TRANSLATIONS = {
+    "en-US": {"status_starting": "Starting {{TITLE}}..."},
+    "zh-CN": {"status_starting": "正在启动 {{TITLE}}..."},
+    "zh-HK": {"status_starting": "正在啟動 {{TITLE}}..."},
+    "zh-TW": {"status_starting": "正在啟動 {{TITLE}}..."},
+    "ko-KR": {"status_starting": "{{TITLE}} 시작 중..."},
+    "ja-JP": {"status_starting": "{{TITLE}} を起動中..."},
+    "fr-FR": {"status_starting": "Démarrage de {{TITLE}}..."},
+    "de-DE": {"status_starting": "{{TITLE}} wird gestartet..."},
+    "es-ES": {"status_starting": "Iniciando {{TITLE}}..."},
+    "it-IT": {"status_starting": "Avvio di {{TITLE}}..."},
+    "vi-VN": {"status_starting": "Đang khởi động {{TITLE}}..."},
+    "id-ID": {"status_starting": "Memulai {{TITLE}}..."},
+}
+
+class {{CLASS_NAME}}:
+    class Valves(BaseModel):
+        priority: int = Field(default=50, description="Priority level (lower = earlier).")
+        show_status: bool = Field(default=True, description="Show status updates in UI.")
+
+    def __init__(self):
+        self.valves = self.Valves()
+        self.fallback_map = {
+            "zh": "zh-CN", "en": "en-US", "ko": "ko-KR", "ja": "ja-JP",
+            "fr": "fr-FR", "de": "de-DE", "es": "es-ES", "it": "it-IT",
+            "vi": "vi-VN", "id": "id-ID"
+        }
+
+    def _get_translation(self, lang: str, key: str, **kwargs) -> str:
+        target_lang = lang
+        if target_lang not in TRANSLATIONS:
+            base = target_lang.split("-")[0]
+            target_lang = self.fallback_map.get(base, "en-US")
+        
+        lang_dict = TRANSLATIONS.get(target_lang, TRANSLATIONS["en-US"])
+        text = lang_dict.get(key, TRANSLATIONS["en-US"].get(key, key))
+        return text.format(**kwargs) if kwargs else text
+
+    async def _get_user_context(self, __user__: Optional[dict], __event_call__: Optional[Callable] = None, __request__: Optional[Request] = None) -> dict:
+        user_data = __user__ if isinstance(__user__, dict) else {}
+        user_language = user_data.get("language", "en-US")
+        if __event_call__:
+            try:
+                js = "try { return (document.documentElement.lang || localStorage.getItem('locale') || navigator.language || 'en-US'); } catch (e) { return 'en-US'; }"
+                frontend_lang = await asyncio.wait_for(__event_call__({"type": "execute", "data": {"code": js}}), timeout=2.0)
+                if frontend_lang: user_language = frontend_lang
+            except: pass
+        return {"user_language": user_language}
+
+    async def {{METHOD_NAME}}(self, body: dict, __user__: Optional[dict] = None, __event_emitter__=None, __event_call__=None, __request__: Optional[Request] = None) -> dict:
+        if self.valves.show_status and __event_emitter__:
+            user_ctx = await self._get_user_context(__user__, __event_call__, __request__)
+            msg = self._get_translation(user_ctx["user_language"], "status_starting")
+            await __event_emitter__({"type": "status", "data": {"description": msg, "done": False}})
+        
+        # Implement core logic here
+        
+        if self.valves.show_status and __event_emitter__:
+            await __event_emitter__({"type": "status", "data": {"description": "Done", "done": True}})
+        return body

.agent/skills/plugin-scaffolder/scripts/scaffold.py

@@ -0,0 +1,66 @@
+#!/usr/bin/env python3
+import sys
+import os
+
+
+def scaffold(p_type, p_name, title, desc):
+    target_dir = f"plugins/{p_type}/{p_name}"
+    os.makedirs(target_dir, exist_ok=True)
+
+    class_name = (
+        "Action"
+        if p_type == "actions"
+        else (
+            "Filter"
+            if p_type == "filters"
+            else "Tools" if p_type == "tools" else "Pipe"
+        )
+    )
+    method_name = (
+        "action"
+        if p_type == "actions"
+        else (
+            "outlet"
+            if p_type == "filters"
+            else "execute" if p_type == "tools" else "pipe"
+        )
+    )
+
+    replacements = {
+        "{{TITLE}}": title,
+        "{{DESCRIPTION}}": desc,
+        "{{CLASS_NAME}}": class_name,
+        "{{METHOD_NAME}}": method_name,
+    }
+
+    # Files to generate
+    templates = [
+        ("assets/template.py.j2", f"{p_name}.py"),
+        ("assets/README_template.md", "README.md"),
+        ("assets/README_template.md", "README_CN.md"),
+    ]
+
+    # Path relative to skill root
+    skill_root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+
+    for t_path, t_name in templates:
+        template_file = os.path.join(skill_root, t_path)
+        if not os.path.exists(template_file):
+            print(f"⚠️ Warning: Template not found {template_file}")
+            continue
+
+        with open(template_file, "r") as f:
+            content = f.read()
+        for k, v in replacements.items():
+            content = content.replace(k, v)
+
+        with open(os.path.join(target_dir, t_name), "w") as f:
+            f.write(content)
+        print(f"✅ Generated: {target_dir}/{t_name}")
+
+
+if __name__ == "__main__":
+    if len(sys.argv) < 5:
+        print("Usage: scaffold.py <type> <name> <title> <desc>")
+        sys.exit(1)
+    scaffold(sys.argv[1], sys.argv[2], sys.argv[3], sys.argv[4])

.agent/skills/pr-reviewer/SKILL.md

@@ -0,0 +1,180 @@
+---
+name: pr-reviewer
+description: Fetches PR review comments, analyzes requested changes, implements fixes, commits and pushes the resolution. Use after a reviewer has left comments on an open PR to close the feedback loop efficiently.
+---
+
+# PR Reviewer
+
+## Overview
+
+This skill automates the response cycle for code review. When a reviewer leaves comments on a Pull Request, this skill fetches all pending feedback, categorizes issues by severity, implements fixes, and submits a follow-up commit with appropriate review response comments.
+
+## Prerequisites
+
+- An open PR exists with pending review comments
+- The local branch matches the PR's head branch
+- `gh` CLI is authenticated
+
+---
+
+## Workflow
+
+### Step 1 — Fetch Review State
+
+Retrieve all review comments and overall review status:
+
+```bash
+# Get overall review decisions
+PAGER=cat GH_PAGER=cat gh pr view <PR-NUMBER> --json reviews,reviewDecision,headRefName \
+  --jq '{decision: .reviewDecision, reviews: [.reviews[] | {author: .author.login, state: .state, body: .body}]}'
+
+# Get inline code comments (specific line comments)
+PAGER=cat GH_PAGER=cat gh api repos/Fu-Jie/openwebui-extensions/pulls/<PR-NUMBER>/comments \
+  --jq '[.[] | {path: .path, line: .line, body: .body, author: .user.login, id: .id}]'
+
+# Get general issue comments
+PAGER=cat GH_PAGER=cat gh issue view <PR-NUMBER> --comments --json comments \
+  --jq '[.comments[] | {author: .author.login, body: .body}]'
+```
+
+Confirm the current local branch matches the PR head:
+```bash
+git branch --show-current
+```
+If mismatched, checkout the correct branch first.
+
+### Step 2 — Categorize Review Feedback
+
+Group feedback into categories:
+
+| Category | Examples | Action |
+|----------|---------|--------|
+| **Code Bug** | Logic error, incorrect variable, broken condition | Fix code immediately |
+| **Style / Formatting** | Indentation, naming convention, missing blank line | Fix code |
+| **Documentation** | Missing i18n key, wrong version in README, typo | Fix docs |
+| **Design Question** | Suggestion to restructure, alternative approach | Discuss with user before implementing |
+| **Nitpick / Optional** | Minor style preferences reviewer marked as optional | Fix if quick; document if skipped |
+| **Blocking** | Reviewer explicitly blocks merge | Must fix before proceeding |
+
+Present the full categorized list to the user and confirm the resolution plan.
+
+### Step 3 — Implement Fixes
+
+For each accepted fix:
+
+1. Read the affected file at the commented line for context:
+   ```bash
+   sed -n '<line-5>,<line+10>p' <file-path>
+   ```
+2. Apply the fix using appropriate file edit tools
+3. After editing, verify the specific area looks correct
+
+**For code changes that might affect behavior:**
+- Check if tests exist: `ls tests/test_*.py`
+- If tests exist, run them: `python -m pytest tests/ -v`
+
+**For documentation fixes:**
+- If modifying README.md, check if `docs/` mirror needs the same fix
+- Apply the same fix to both locations
+
+### Step 4 — Run Consistency Checks
+
+After all fixes are applied:
+
+```bash
+# Version consistency (if any version files were touched)
+python3 scripts/check_version_consistency.py
+
+# Quick syntax check for Python files
+python3 -m py_compile plugins/{type}/{name}/{name}.py && echo "✅ Syntax OK"
+```
+
+### Step 5 — Stage and Commit
+
+Create a new commit (do NOT amend if the branch has already been pushed, to avoid force-push):
+
+```bash
+git add -A
+git status
+```
+
+Draft a Conventional Commits message for the fixup:
+
+Format: `fix(scope): address review feedback`
+
+Body should list what was fixed, referencing reviewer concerns:
+```
+fix(github-copilot-sdk): address review feedback from @reviewer
+
+- Fix X per review comment on line Y of file Z
+- Update README to clarify auth requirement
+- Correct edge case in _parse_mcp_servers logic
+```
+
+```bash
+git commit -m "<fixup commit message>"
+```
+
+### Step 6 — Push the Fix Commit
+
+```bash
+git push origin $(git branch --show-current)
+```
+
+**Force-push policy:**
+- Use `git push` (non-force) by default
+- Only use `git push --force-with-lease` if:
+  1. The user explicitly requests it, AND
+  2. The only change is an amended commit squash (cosmetic, no logic change)
+  3. Never use `--force` (without `--lease`)
+
+### Step 7 — Respond to Reviewers
+
+For each addressed review comment, post a reply:
+
+```bash
+# Reply to inline comment
+gh api repos/Fu-Jie/openwebui-extensions/pulls/<PR-NUMBER>/comments/<COMMENT-ID>/replies \
+  -X POST -f body="Fixed in commit <SHORT-SHA>. <Brief explanation of what was changed.>"
+
+# General comment to summarize all fixes
+gh issue comment <PR-NUMBER> --body "All review feedback addressed in commit <SHORT-SHA>:
+- Fixed: <item 1>
+- Fixed: <item 2>
+Ready for re-review. 🙏"
+```
+
+### Step 8 — Re-Request Review (Optional)
+
+If the reviewer had submitted a `CHANGES_REQUESTED` review, request a new review after fixes:
+
+```bash
+PAGER=cat GH_PAGER=cat gh api repos/Fu-Jie/openwebui-extensions/pulls/<PR-NUMBER>/requested_reviewers \
+  -X POST -f reviewers[]='<reviewer-login>'
+```
+
+---
+
+## Decision Guide
+
+### When NOT to implement a suggestion immediately
+
+- **Design questions**: "Should this be a separate class?" — Present to user for decision
+- **Optional nitpicks**: Reviewer marked as `nit:` — Ask user if they want to include it
+- **Large refactors**: If fix would require changing >50 lines, propose a separate follow-up issue instead
+
+### When to ask the user before proceeding
+
+- Any fix involving behavioral changes to plugin logic
+- Renaming Valve keys (breaking change — requires migration notes)
+- Changes that affect the bilingual release notes already committed
+
+---
+
+## Anti-Patterns to Avoid
+
+- ❌ Do NOT `git commit --amend` on a pushed commit without user approval for force-push
+- ❌ Do NOT silently skip a reviewer's comment; always acknowledge it (implement or explain why not)
+- ❌ Do NOT use `--force` (only `--force-with-lease` when absolutely necessary)
+- ❌ Do NOT make unrelated changes in the fixup commit; keep scope focused on review feedback
+- ❌ Do NOT respond to reviewer comments in Chinese if the PR language context is English

.agent/skills/pr-submitter/SKILL.md

@@ -0,0 +1,194 @@
+---
+name: pr-submitter
+description: Submits a feature branch as a Pull Request with a validated, properly formatted bilingual PR body. Handles shell-escape-safe body writing via temp files. Use after release-prep has committed all changes.
+---
+
+# PR Submitter
+
+## Overview
+
+This skill handles the final step of pushing a feature branch and creating a validated Pull Request on GitHub. Its primary purpose is to avoid the shell-escaping pitfalls (backticks, special characters in `gh pr create --body`) by always writing the PR body to a **temp file** first.
+
+## Prerequisites
+
+- All changes are committed (use `release-prep` skill first)
+- The `gh` CLI is authenticated (`gh auth status`)
+- Current branch is NOT `main` or `master`
+
+---
+
+## Workflow
+
+### Step 0 — Initialize Temp Directory (Project-Based)
+
+For all temporary files, use the project's `.temp/` directory instead of system `/tmp`:
+
+```bash
+# Create temp directory if it doesn't exist
+mkdir -p .temp
+```
+
+**Why**: All temporary files stay within the project workspace, avoiding system `/tmp` pollution and better aligning with OpenWebUI workspace isolation principles.
+
+### Step 1 — Pre-Flight Checks
+
+Run these checks before any push:
+
+```bash
+# 1. Confirm not on protected branch
+git branch --show-current
+
+# 2. Verify there are commits to push
+git log origin/$(git branch --show-current)..HEAD --oneline 2>/dev/null || echo "No remote tracking branch yet"
+
+# 3. Check gh CLI auth
+gh auth status
+```
+
+If any check fails, stop and report clearly.
+
+### Step 2 — Collect PR Metadata
+
+Gather:
+- **PR Title**: Must follow Conventional Commits format, English only (e.g., `feat(github-copilot-sdk): release v0.8.0 with conditional tool filtering`)
+- **Target base branch**: Default is `main`
+- **Plugin name + version** (to build body sections)
+- **Key changes** (reuse from release-prep or the latest What's New section)
+
+### Step 3 — Build PR Body File (Shell-Escape-Safe)
+
+**Always write the body to a temp file in `.temp/` directory.** Never embed multi-line markdown with special characters directly in a shell command.
+
+```bash
+cat > .temp/pr_body.md << 'HEREDOC'
+## Summary
+
+Brief one-sentence description of what this PR accomplishes.
+
+## Changes
+
+### New Features
+- Feature 1 description
+- Feature 2 description
+
+### Bug Fixes
+- Fix 1 description
+
+## Plugin Version
+- `PluginName` bumped to `vX.X.X`
+
+## Documentation
+- README.md / README_CN.md updated
+- docs/ mirrors synced
+
+## Testing
+- [ ] Tested locally in OpenWebUI
+- [ ] i18n validated (all language keys present)
+- [ ] Version consistency check passed (`python3 scripts/check_version_consistency.py`)
+
+---
+
+## 变更摘要（中文）
+
+简要描述本次 PR 的改动内容。
+
+### 新功能
+- 功能1描述
+- 功能2描述
+
+### 问题修复
+- 修复1描述
+HEREDOC
+```
+
+**Critical rules for the body file:**
+- Use `<< 'HEREDOC'` (quoted heredoc) to prevent variable expansion
+- Keep all backticks literal — they are safe inside a heredoc
+- Paths like `/api/v1/files/` are safe too since heredoc doesn't interpret them as commands
+
+### Step 4 — Validate PR Body
+
+Before submitting, verify the body file contains expected sections:
+
+```bash
+# Check key sections exist
+grep -q "## Summary" .temp/pr_body.md && echo "✅ Summary" || echo "❌ Summary missing"
+grep -q "## Changes" .temp/pr_body.md && echo "✅ Changes" || echo "❌ Changes missing"
+grep -q "## 变更摘要" .temp/pr_body.md && echo "✅ CN Section" || echo "❌ CN Section missing"
+
+# Preview the body
+cat .temp/pr_body.md
+```
+
+Ask the user to confirm the body content before proceeding.
+
+### Step 5 — Push Branch
+
+```bash
+git push -u origin $(git branch --show-current)
+```
+
+If push is rejected (non-fast-forward), report to user and ask whether to force-push. **Do NOT force-push without explicit confirmation.**
+
+### Step 6 — Create Pull Request
+
+```bash
+gh pr create \
+  --base main \
+  --head $(git branch --show-current) \
+  --title "<PR title from Step 2>" \
+  --body-file .temp/pr_body.md
+```
+
+Always use `--body-file`, never `--body` with inline markdown.
+
+### Step 7 — Verify PR Creation
+
+```bash
+PAGER=cat GH_PAGER=cat gh pr view --json number,url,title,body --jq '{number: .number, url: .url, title: .title, body_preview: .body[:200]}'
+```
+
+Confirm:
+- PR number and URL
+- Title matches intended Conventional Commits format
+- Body preview includes key sections (not truncated/corrupted)
+
+If the body appears corrupted (empty sections, missing backtick content), use edit:
+
+```bash
+gh pr edit <PR-NUMBER> --body-file /tmp/pr_body.md
+```
+
+### Step 8 — Cleanup
+
+```bash
+rm -f .temp/pr_body.md
+```
+
+**Note**: The `.temp/` directory itself is preserved for reuse; only the individual PR body file is deleted. To fully clean up: `rm -rf .temp/`
+
+Report final PR URL to the user.
+
+---
+
+## Shell-Escape Safety Rules
+
+| Risk | Safe Approach |
+|------|--------------|
+| Backticks in `--body` | Write to file, use `--body-file` |
+| Paths like `/api/...` | Safe in heredoc; risky in inline `--body` |
+| Newlines in `--body` | File-based only |
+| `$variable` expansion | Use `<< 'HEREDOC'` (quoted) |
+| Double quotes in body | Safe in heredoc file |
+| Temp file storage | Use `.temp/` dir, not `/tmp` |
+| Cleanup after use | Always delete temp file (keep dir) |
+
+---
+
+## Anti-Patterns to Avoid
+
+- ❌ Never use `--body "..."` with multi-line content directly in shell command
+- ❌ Never interpolate variables directly into heredoc without quoting the delimiter
+- ❌ Never force-push (`--force`) without explicit user confirmation
+- ❌ Never target `main` as the source branch (only as base)
+- ❌ Never skip the body validation step — a PR with empty body is worse than a delayed PR

.agent/skills/release-finalizer/SKILL.md

@@ -0,0 +1,208 @@
+---
+name: release-finalizer
+description: Merges a release PR, associates it with resolved issues, replies to issue reporters, and closes issues. Use after PR review is complete and ready for merge. Closes the release cycle.
+---
+
+# Release Finalizer
+
+## Overview
+
+This skill completes the final step of the release cycle: merging the release PR to `main`, replying to all related issues with solutions, and automatically closing them using GitHub's issue linking mechanism.
+
+## Prerequisites
+
+- The PR is in `OPEN` state and ready to merge
+- All status checks have passed (CI green)
+- All review feedback has been addressed
+- The PR relates to one or more GitHub issues (either in PR description or through commits)
+
+---
+
+## Workflow
+
+### Step 1 — Pre-Merge Verification
+
+Verify that the PR is ready:
+
+```bash
+PAGER=cat GH_PAGER=cat gh pr view <PR-NUMBER> --json state,statusCheckRollup,reviewDecision
+```
+
+Checklist:
+- ✅ `state` is `OPEN`
+- ✅ `statusCheckRollup` all have `conclusion: SUCCESS`
+- ✅ `reviewDecision` is `APPROVED` or empty (no blocking reviews)
+
+If any check fails, **do NOT merge**. Report the issue to the user.
+
+### Step 2 — Identify Related Issues
+
+Issues can be linked to a PR in multiple ways. Check the PR description and commit messages for keywords:
+
+```bash
+PAGER=cat GH_PAGER=cat gh pr view <PR-NUMBER> --json body,commits
+```
+
+Look for patterns like:
+- `Closes #XX`, `Fixes #XX`, `Resolves #XX` (in description or commit bodies)
+- `#XX` mentioned as "related to" or "addresses"
+
+**Manual input**: If issue links are not in the PR, ask the user which issue(s) this PR resolves.
+
+Extract all issue numbers into a list: `[#48, #52, ...]`
+
+### Step 3 — Select Merge Strategy
+
+Offer the user three options:
+
+| Strategy | Git Behavior | Use Case |
+|----------|-------------|----------|
+| **Squash** | All commits squashed into one commit on main | Clean history, recommended for release PRs |
+| **Rebase** | Linear history, no merge commit | Preserve commit granularity |
+| **Merge** | Merge commit created | Preserve full PR context |
+
+**Recommendation for release PRs**: Use `--squash` to create a single clean commit.
+
+If user doesn't specify, default to `--squash`.
+
+### Step 4 — Prepare Merge Commit Message
+
+If using `--squash`, craft a single comprehensive commit message:
+
+**Format** (Conventional Commits + Github linking):
+```
+type(scope): description
+
+- Bullet point 1
+- Bullet point 2
+
+Closes #48
+Closes #52
+```
+
+The `Closes #XX` keyword tells GitHub to automatically close those issues when the commit lands on `main`.
+
+Example:
+```
+feat(pipes,filters): release Copilot SDK Pipe v0.8.0 and Files Filter v0.1.3
+
+- Implement P1~P4 conditional tool filtering system
+- Fix file publishing reliability across all storage backends
+- Add strict file URL validation
+- Update bilingual documentation
+
+Closes #48
+```
+
+### Step 5 — Execute Merge
+
+```bash
+gh pr merge <PR-NUMBER> \
+  --squash \
+  --delete-branch \
+  -m "type(scope): description" \
+  -b "- Bullet 1\n- Bullet 2\n\nCloses #48"
+```
+
+**Key flags:**
+- `--squash`: Squash commits (recommended for releases)
+- `--delete-branch`: Delete the feature branch after merge
+- `-m`: Commit subject
+- `-b`: Commit body (supports `\n` for newlines)
+
+Confirm the merge is successful; GitHub will automatically close related issues with `Closes #XX` keyword.
+
+### Step 6 — Verify Auto-Close
+
+GitHub automatically closes issues when a commit with `Closes #XX` lands on the default branch (`main`).
+
+To verify:
+```bash
+PAGER=cat GH_PAGER=cat gh issue view <ISSUE-NUMBER> --json state
+```
+
+Should show `state: CLOSED`.
+
+### Step 7 — Post Closing Message (Optional but Recommended)
+
+For better UX, manually post a summary comment to **each issue** before it auto-closes (since auto-close happens silently):
+
+```bash
+gh issue comment <ISSUE-NUMBER> --body "
+This has been fixed in PR #<PR-NUMBER>, which is now merged to main.
+
+**Solution Summary:**
+- <Key fix 1>
+- <Key fix 2>
+
+The fix will be available in the next plugin release. Thank you for reporting! ⭐
+"
+```
+
+### Step 8 — (Optional) Regenerate Release Notes
+
+If the merge revealed any final tweaks to release notes:
+
+```bash
+# Re-export release notes from merged commit
+git log --oneline -1 <merged-commit-sha>
+```
+
+If needed, create a follow-up PR with doc polish (do NOT force-push the merged commit).
+
+---
+
+## Merge Strategy Decision Tree
+
+```
+Is this a patch/hotfix release?
+├─ YES → Use --squash
+└─ NO → Multi-feature release?
+     ├─ YES → Use --squash (cleaner history)
+     └─ NO → Preserve detail? 
+          ├─ YES → Use --rebase
+          └─ NO → Use --merge (preserve PR context)
+```
+
+---
+
+## Issue Auto-Close Keywords
+
+These keywords in commit/PR messages will auto-close issues when merged to `main`:
+
+- `Closes #XX`
+- `Fixes #XX`
+- `Resolves #XX`
+- `close #XX` (case-insensitive)
+- `fix #XX`
+- `resolve #XX`
+
+**Important**: The keyword must be on the **final commit that lands on** `main`. For squash merges, it must be in the squash commit message body.
+
+---
+
+## Anti-Patterns to Avoid
+
+- ❌ Do NOT merge if any status checks are PENDING or FAILED
+- ❌ Do NOT merge if there are blocking reviews (reviewDecision: `CHANGES_REQUESTED`)
+- ❌ Do NOT merge without verifying the Conventional Commits format in the merge message
+- ❌ Do NOT merge without including `Closes #XX` keywords for all related issues
+- ❌ Do NOT assume issues will auto-close silently — post a courtesy comment first
+- ❌ Do NOT delete the branch if it might be needed for cherry-pick or hotfixes later
+
+---
+
+## Troubleshooting
+
+### Issue did not auto-close after merge
+- Verify the `Closes #XX` keyword is in the **final commit message** (use `git log` to check)
+- Ensure the commit is on the `main` branch
+- GitHub sometimes takes a few seconds to process; refresh the issue page
+
+### Multiple issues to close
+- List all in separate `Closes #XX` lines in the commit body
+- Each one will be independently auto-closed
+
+### Want to close issue without merge?
+- Use `gh issue close <ISSUE-NUMBER>` manually
+- Only recommended if the PR was manually reverted or deemed invalid

.agent/skills/release-prep/SKILL.md

@@ -0,0 +1,157 @@
+---
+name: release-prep
+description: Orchestrates the full release preparation flow for a plugin — version sync across 7+ files, bilingual release notes creation, and commit message drafting. Use before submitting a PR. Does NOT push or create a PR; that is handled by pr-submitter.
+---
+
+# Release Prep
+
+## Overview
+
+This skill drives the complete pre-PR release pipeline. It enforces the repository rule that every release must synchronize the version number and changelog across **at least 7 locations** before a commit is created.
+
+## Scope
+
+This skill covers:
+1. Version sync (delegates detail to `version-bumper` if needed)
+2. Bilingual release notes file creation
+3. 7-location consistency verification
+4. Conventional Commits message drafting
+5. `git add -A && git commit` execution
+
+It **stops before** `git push` or `gh pr create`. Use the `pr-submitter` skill for those steps.
+
+### Temporary File Convention
+
+Any temporary files created during release prep (e.g., draft changelogs) must:
+- Be written to the project's `.temp/` directory, **NOT** system `/tmp`
+- Be cleaned up before commit using `rm -f .temp/file_name`
+- Never be committed to git (add `.temp/` to `.gitignore`)
+
+---
+
+## Workflow
+
+### Step 1 — Collect Release Info
+
+Ask the user (or infer from current state) the following:
+- **Plugin name** and **type** (actions / filters / pipes / tools)
+- **New version number** (e.g., `0.8.0`)
+- **Key changes** in English and Chinese (1-5 bullet points each)
+
+If a `What's New` section already exists in README.md, extract it as the source of truth.
+
+### Step 2 — Sync Version Across 7 Locations
+
+Verify AND update the version string in all of the following. Mark each as ✅ or ❌:
+
+| # | File | Location |
+|---|------|----------|
+| 1 | `plugins/{type}/{name}/{name}.py` | `version:` in docstring |
+| 2 | `plugins/{type}/{name}/README.md` | `**Version:** x.x.x` metadata line |
+| 3 | `plugins/{type}/{name}/README_CN.md` | `**Version:** x.x.x` metadata line |
+| 4 | `docs/plugins/{type}/{name}.md` | `**Version:** x.x.x` metadata line |
+| 5 | `docs/plugins/{type}/{name}.zh.md` | `**Version:** x.x.x` metadata line |
+| 6 | `docs/plugins/{type}/index.md` | version badge for this plugin |
+| 7 | `docs/plugins/{type}/index.zh.md` | version badge for this plugin |
+
+Additionally update the root-level **updated date badge** in:
+- `README.md` — `![updated](https://img.shields.io/badge/YYYY--MM--DD-gray?style=flat)`
+- `README_CN.md` — same badge format
+
+Use today's date (`YYYY-MM-DD`) for the badge.
+
+### Step 3 — Update What's New (All 4 Doc Files)
+
+The `What's New` / `最新更新` section must contain **only the most recent release's changes**. Previous entries should be removed from this section (they live in CHANGELOG or release notes files).
+
+Update these 4 files' `What's New` / `最新更新` block consistently:
+- `plugins/{type}/{name}/README.md`
+- `plugins/{type}/{name}/README_CN.md`
+- `docs/plugins/{type}/{name}.md`
+- `docs/plugins/{type}/{name}.zh.md`
+
+### Step 4 — Create Bilingual Release Notes Files
+
+Create two versioned release notes files:
+
+**Path**: `plugins/{type}/{name}/v{version}.md`
+**Path**: `plugins/{type}/{name}/v{version}_CN.md`
+
+#### Required Sections
+
+Each file must include:
+1. **Title**: `# v{version} Release Notes` (EN) / `# v{version} 版本发布说明` (CN)
+2. **Overview**: One paragraph summarizing this release
+3. **New Features** / **新功能**: Bulleted list of features
+4. **Bug Fixes** / **问题修复**: Bulleted list of fixes
+5. **Migration Notes** / **迁移说明**: Breaking changes or Valve key renames (omit section if none)
+6. **Companion Plugins** / **配套插件** (optional): If a companion plugin was updated
+
+If a release notes file already exists for this version, update it rather than creating a new one.
+
+#### Full Coverage Rule (Mandatory)
+
+Release notes must cover **all updates in the current release scope** and not only headline features.
+
+Minimum required coverage in both EN/CN files:
+- New features and capability enhancements
+- Bug fixes and reliability fixes
+- Documentation/README/doc-mirror updates that affect user understanding or usage
+- Terminology/i18n/wording fixes that change visible behavior or messaging
+
+Before commit, cross-check release notes against `git diff` and ensure no meaningful update is omitted.
+
+### Step 5 — Verify Consistency (Pre-Commit Check)
+
+Run the consistency check script:
+
+```bash
+python3 scripts/check_version_consistency.py
+```
+
+If issues are found, fix them before proceeding. Do not commit with inconsistencies.
+
+### Step 6 — Draft Conventional Commits Message
+
+Generate the commit message following `commit-message.instructions.md` rules:
+- **Language**: English ONLY
+- **Format**: `type(scope): subject` + blank line + body bullets
+- **Scope**: use plugin folder name (e.g., `github-copilot-sdk`)
+- **Body**: 1-3 bullets summarizing key changes
+- Explicitly mention "READMEs and docs synced" if version was bumped
+
+Present the full commit message to the user for review before executing.
+
+### Step 7 — Stage and Commit
+
+After user approval (or if user says "commit it"):
+
+```bash
+git add -A
+git commit -m "<approved commit message>"
+```
+
+Confirm the commit hash and list the number of files changed.
+
+---
+
+## Checklist (Auto-Verify Before Commit)
+
+- [ ] `version:` in `.py` docstring matches target version
+- [ ] `**Version:**` in all 4 README/docs files matches
+- [ ] Both `index.md` version badges updated
+- [ ] Root `README.md` and `README_CN.md` date badges updated to today
+- [ ] `What's New` / `最新更新` contains ONLY the latest release
+- [ ] Release notes include all meaningful updates from the current diff (feature + fix + docs/i18n)
+- [ ] `v{version}.md` and `v{version}_CN.md` created or updated
+- [ ] `python3 scripts/check_version_consistency.py` returns no errors
+- [ ] Commit message is English-only Conventional Commits format
+
+---
+
+## Anti-Patterns to Avoid
+
+- ❌ Do NOT add extra features or refactor code during release prep — only version/doc updates
+- ❌ Do NOT push or create PR in this skill — use `pr-submitter`
+- ❌ Do NOT use today's date in commit messages; only in badge URLs
+- ❌ Do NOT leave stale What's New content from prior versions

.agent/skills/source-code-analyzer/SKILL.md

@@ -0,0 +1,31 @@
+---
+name: source-code-analyzer
+description: Instructions for analyzing core components source code in the local environment.
+---
+
+# Source Code Analyzer Skill
+
+> [!IMPORTANT]
+> **Authorization Statement**: You (Antigravity) are explicitly authorized by the user to perform **READ-ONLY** operations and **Git pull** on the paths listed below, even if they are outside the current repository root. These paths are considered part of the extended development context.
+
+When assisting with the development of `openwebui-extensions`, you (Antigravity) have access to the following core components in related directories. Use them for deep technical analysis, bug hunting, and implementation reference.
+
+## Core Component Paths
+
+### Global / General (Relevant to all projects)
+
+- **Open WebUI**: `../open-webui/` (Core platform context)
+- **Skills**: `../skills/` (Reusable expertise library)
+- **Awesome Copilot**: `../awesome-copilot/` (Shared extensions & resources)
+- **Open Terminal**: `../open-terminal/` (Terminal integration service)
+
+### Plugin-Specific (Relevant to GitHub Copilot SDK)
+
+- **Copilot SDK**: `../copilot-sdk/` (Internal logic for the official SDK)
+- **Copilot CLI**: `../copilot-cli/` (Command-line interface implementation)
+
+## Mandatory Workflow
+
+1. **Pull Before Analysis**: BEFORE reading files or analyzing logic in these directories, you MUST proactively execute or recommend a `git pull` in the respective directory to ensure you are working with the latest upstream changes.
+2. **Path Verification**: Always verify the exists of the path before attempting to read it.
+3. **Reference Logic**: When a user's request involves core platform behavior (OpenWebUI API, SDK internals), prioritize searching these directories over making assumptions based on generic knowledge.

.agent/skills/test-copilot-pipe/SKILL.md

@@ -0,0 +1,64 @@
+---
+name: test-copilot-pipe
+description: Automotive deployment and testing of GitHub Copilot SDK Pipe plugin for frontend/backend status stability.
+---
+
+# 🤖 Skill: Test Copilot Pipe
+
+This is a **universal testing framework** for publishing the latest `github_copilot_sdk.py` (Pipe) code to a local OpenWebUI instance and verifying it via an automated agent (`browser_subagent`).
+
+## 🎯 Core Principles
+
+- **Fixed Infrastructure**: The deployment script and the test entry URL are always static.
+- **Dynamic Test Planning**: Specific test prompts and expectations (acceptance criteria) **must** be dynamically planned by you based on the code changes or specific user requests before execution.
+
+---
+
+## 🛠️ Static Environment Info
+
+| Attribute | Fixed Value |
+|------|--------|
+| **Deployment Script** | `/Users/fujie/app/python/oui/openwebui-extensions/scripts/deploy_pipe.py` |
+| **Python Path** | `/opt/homebrew/Caskroom/miniconda/base/envs/ai/bin/python3` |
+| **Test URL** | `http://localhost:3003/?model=github_copilot_official_sdk_pipe.github_copilot_sdk-gpt-4.1` |
+
+---
+
+## 📋 Standard Workflow
+
+### Step 1: Analyze Changes & Plan Test (Plan)
+
+Before triggering the test, you must define the purpose of this test turn.
+Example: *Modified tool calling logic -> Test prompt should trigger a specific tool; observe if the tool executes and returns the correct result.*
+
+### Step 2: Deploy Latest Code (Deploy)
+
+Use the `run_command` tool to execute the fixed update task:
+
+```bash
+/opt/homebrew/Caskroom/miniconda/base/envs/ai/bin/python3 /Users/fujie/app/python/oui/openwebui-extensions/scripts/deploy_pipe.py
+```
+
+> **Mechanism**: `deploy_pipe.py` automatically loads the API Key from `scripts/.env` in the same directory.
+> **Verification**: Look for `✅ Successfully updated... version X.X.X` or `✅ Successfully created...`. If a 401 error occurs, remind the user to generate a new API Key in OpenWebUI and update `.env`.
+
+### Step 3: Verify via Browser Subagent (Verify)
+
+Use the `browser_subagent` tool. **You must fill in the `[Dynamic Content]` slots based on Step 1**:
+
+```text
+Task:
+1. Access The Fixed URL: http://localhost:3003/?model=github_copilot_official_sdk_pipe.github_copilot_sdk-gpt-4.1
+2. RELIABILITY WAIT: Wait until the page fully loads. Wait until the chat input text area (`#chat-input`) is present in the DOM.
+3. ACTION - FAST INPUT: Use the `execute_browser_javascript` tool to instantly inject the query and submit it. Use exactly this script format to ensure stability:
+   `const input = document.getElementById('chat-input'); input.value = "[YOUR_DYNAMIC_TEST_PROMPT]"; input.dispatchEvent(new Event('input', { bubbles: true })); const e = new KeyboardEvent('keydown', { key: 'Enter', code: 'Enter', keyCode: 13, which: 13, bubbles: true }); input.dispatchEvent(e);`
+4. WAITING: Wait patiently for the streaming response to stop completely. You should wait for the Stop button to disappear, or wait for the system to settle (approximately 10-15 seconds depending on the query).
+5. CHECK THE OUTCOME: [List the phenomena you expect to see, e.g., status bar shows specific text, tool card appears, result contains specific keywords, etc.]
+6. CAPTURE: Take a screenshot of the settled state to prove the outcome.
+7. REPORT: Report the EXACT outcome matching the criteria from step 5.
+```
+
+### Step 4: Evaluate & Iterate (Evaluate)
+
+- **PASS**: Screenshot and phenomena match expectations. Report success to the user.
+- **FAIL**: Analyze the issue based on screenshots/logs (e.g., race condition reappeared, API error). Modify the code and **re-run the entire skill workflow**.

.agent/skills/version-bumper/SKILL.md

@@ -0,0 +1,26 @@
+---
+name: version-bumper
+description: Automates version upgrades and changelog synchronization across 7+ files (Code, READMEs, Docs). Use when a plugin is ready for release to ensure version consistency.
+---
+
+# Version Bumper
+
+## Overview
+This skill ensures that every version upgrade is synchronized across the entire repository, following the strict "Documentation Sync" rule in GEMINI.md.
+
+## Workflow
+1. **Prepare Info**: Gather the new version number and brief changelogs in both English and Chinese.
+2. **Auto-Patch**: The skill will help you identify and update:
+   - `plugins/.../name.py` (docstring version)
+   - `plugins/.../README.md` (metadata & What's New)
+   - `plugins/.../README_CN.md` (metadata & 最新更新)
+   - `docs/plugins/...md` (mirrors)
+   - `docs/plugins/index.md` (version badge)
+   - `README.md` (updated date badge)
+3. **Verify**: Check the diffs to ensure no formatting was broken.
+
+## Tool Integration
+Execute the bump script (draft):
+```bash
+python3 scripts/bump.py <version> "<message_en>" "<message_zh>"
+```

.agent/skills/version-bumper/scripts/bump.py

@@ -0,0 +1,70 @@
+#!/usr/bin/env python3
+import sys
+import os
+import re
+from datetime import datetime
+
+def patch_file(file_path, old_pattern, new_content, is_regex=False):
+    if not os.path.exists(file_path):
+        print(f"Warning: File not found: {file_path}")
+        return False
+    
+    with open(file_path, 'r', encoding='utf-8') as f:
+        content = f.read()
+    
+    if is_regex:
+        new_content_result = re.sub(old_pattern, new_content, content, flags=re.MULTILINE)
+    else:
+        new_content_result = content.replace(old_pattern, new_content)
+    
+    if new_content_result != content:
+        with open(file_path, 'w', encoding='utf-8') as f:
+            f.write(new_content_result)
+        print(f"✅ Patched: {file_path}")
+        return True
+    else:
+        print(f"ℹ️ No change needed: {file_path}")
+        return False
+
+def bump_version(plugin_type, plugin_name, new_version, msg_en, msg_zh):
+    print(f"🚀 Bumping {plugin_name} ({plugin_type}) to {new_version}...")
+    
+    today = datetime.now().strftime("%Y-%m-%d")
+    today_badge = today.replace("-", "--")
+    
+    # 1. Patch Plugin Python File
+    py_file = f"plugins/{plugin_type}/{plugin_name}/{plugin_name}.py"
+    patch_file(py_file, r"version: \d+\.\d+\.\d+", f"version: {new_version}", is_regex=True)
+    
+    # 2. Patch Plugin READMEs
+    readme_en = f"plugins/{plugin_type}/{plugin_name}/README.md"
+    readme_zh = f"plugins/{plugin_type}/{plugin_name}/README_CN.md"
+    
+    # Update version in metadata
+    patch_file(readme_en, r"\*\*Version:\*\* \d+\.\d+\.\d+", f"**Version:** {new_version}", is_regex=True)
+    patch_file(readme_zh, r"\*\*版本:\*\* \d+\.\d+\.\d+", f"**版本:** {new_version}", is_regex=True)
+    
+    # Update What's New (Assuming standard headers)
+    patch_file(readme_en, r"## 🔥 What's New in v.*?\n", f"## 🔥 What's New in v{new_version}\n\n* {msg_en}\n", is_regex=True)
+    patch_file(readme_zh, r"## 🔥 最新更新 v.*?\n", f"## 🔥 最新更新 v{new_version}\n\n* {msg_zh}\n", is_regex=True)
+    
+    # 3. Patch Docs Mirrors
+    doc_en = f"docs/plugins/{plugin_type}/{plugin_name}.md"
+    doc_zh = f"docs/plugins/{plugin_type}/{plugin_name}.zh.md"
+    patch_file(doc_en, r"\*\*Version:\*\* \d+\.\d+\.\d+", f"**Version:** {new_version}", is_regex=True)
+    patch_file(doc_zh, r"\*\*版本:\*\* \d+\.\d+\.\d+", f"**版本:** {new_version}", is_regex=True)
+    
+    # 4. Patch Root READMEs (Updated Date Badge)
+    patch_file("README.md", r"badge/202\d--\d\d--\d\d-gray", f"badge/{today_badge}-gray", is_regex=True)
+    patch_file("README_CN.md", r"badge/202\d--\d\d--\d\d-gray", f"badge/{today_badge}-gray", is_regex=True)
+
+    print("\n✨ All synchronization tasks completed.")
+    return True
+
+if __name__ == "__main__":
+    if len(sys.argv) < 6:
+        print("Usage: bump.py <type> <name> <version> <msg_en> <msg_zh>")
+        print("Example: bump.py filters markdown_normalizer 1.2.8 'Fix bug' '修复错误'")
+        sys.exit(1)
+    
+    bump_version(sys.argv[1], sys.argv[2], sys.argv[3], sys.argv[4], sys.argv[5])

.agent/workflows/plugin-development.md

@@ -4,23 +4,25 @@ description: OpenWebUI Plugin Development & Release Workflow
 
 # OpenWebUI Plugin Development Workflow
 
-This workflow outlines the standard process for developing, documenting, and releasing plugins for OpenWebUI, ensuring compliance with project standards and CI/CD requirements.
+This workflow outlines the standard process for developing, documenting, and releasing plugins for OpenWebUI. **Crucially, the default goal of this workflow is "Preparation" (updating all relevant files) rather than automatic "Submission" (git commit/push), unless a release is explicitly requested.**
 
 ## 1. Development Standards
 
 Reference: `.github/copilot-instructions.md`
 
 ### Bilingual Requirement
-Every plugin **MUST** have bilingual versions for both code and documentation:
 
-- **Code**:
-  - English: `plugins/{type}/{name}/{name}.py`
-  - Chinese: `plugins/{type}/{name}/{name_cn}.py` (or `中文名.py`)
+Every plugin **MUST** have a single internationalized code file and bilingual documentation:
+
+- **Code (i18n)**:
+  - `plugins/{type}/{name}/{name}.py`
+  - The single `.py` file must implement internal i18n (e.g., using `navigator.language` or backend headers) to support multiple languages natively, rather than splitting into separate files.
 - **README**:
   - English: `plugins/{type}/{name}/README.md`
   - Chinese: `plugins/{type}/{name}/README_CN.md`
 
 ### Code Structure
+
 - **Docstring**: Must include `title`, `author`, `version`, `description`, etc.
 - **Valves**: Use `pydantic` for configuration.
 - **Database**: Re-use `open_webui.internal.db` shared connection.
@@ -32,8 +34,9 @@ Every plugin **MUST** have bilingual versions for both code and documentation:
   - Use Chat Persistence API for database storage
   - Always update both `messages[]` and `history.messages`
 
-### Commit Messages
-- **Language**: **English ONLY**. Do not use Chinese in commit messages.
+### Commit Messages & Release Notes
+
+- **Language**: **English ONLY**. Do not use Chinese in commit messages or release notes.
 - **Format**: Conventional Commits (e.g., `feat:`, `fix:`, `docs:`).
 
 ## 2. Documentation Updates
@@ -41,10 +44,16 @@ Every plugin **MUST** have bilingual versions for both code and documentation:
 When adding or updating a plugin, you **MUST** update the following documentation files to maintain consistency:
 
 ### Plugin Directory
-- `README.md`: Update version, description, and usage. **Explicitly describe new features in a prominent position at the beginning.**
-- `README_CN.md`: Update version, description, and usage. **Explicitly describe new features in a prominent position at the beginning.**
+
+- `README.md`: Update version, description, and usage.
+  - **Key Capabilities**: **MUST** include ALL core functionalities and features. This is a cumulative section. Every release **MUST** verify that basic core descriptions are NOT lost or overwritten by new feature lists.
+  - **What's New**: Explicitly describe only the latest changes/updates in a prominent position at the beginning. This section is dynamic and changes with versions.
+- `README_CN.md`: Update version, description, and usage.
+  - **核心功能 (Key Capabilities)**: **必须**包含所有核心功能和特性。这是一个累积性的部分，每次版本更新**必须**确认基础核心功能的描述没有丢失或被新功能列表覆盖。
+  - **最新更新 (What's New)**: 在开头显眼位置明确描述最新的更改/更新。此部分是动态的，随版本变化。
 
 ### Global Documentation (`docs/`)
+
 - **Index Pages**:
   - `docs/plugins/{type}/index.md`: Add/Update list item with **correct version**.
   - `docs/plugins/{type}/index.zh.md`: Add/Update list item with **correct version**.
@@ -53,6 +62,7 @@ When adding or updating a plugin, you **MUST** update the following documentatio
   - `docs/plugins/{type}/{name}.zh.md`: Ensure content matches README_CN.
 
 ### Root README
+
 - `README.md`: Add to "Featured Plugins" if applicable.
 - `README_CN.md`: Add to "Featured Plugins" if applicable.
 
@@ -61,40 +71,59 @@ When adding or updating a plugin, you **MUST** update the following documentatio
 Reference: `.github/workflows/release.yml`
 
 ### Version Bumping
+
 - **Rule**: Version bump is required **ONLY when the user explicitly requests a release**. Regular code changes do NOT require version bumps.
 - **Format**: Semantic Versioning (e.g., `1.0.0` -> `1.0.1`).
 - **When to Bump**: Only update the version when:
   - User says "发布" / "release" / "bump version"
   - User explicitly asks to prepare for release
-- **Agent Initiative**: After completing significant changes (new features, bug fixes, or multiple code modifications), the agent **SHOULD proactively ask** the user if they want to release a new version. If confirmed, update all version-related files.
+- **Agent Initiative**: After completing significant changes (new features, bug fixes, or multiple code modifications), the agent **SHOULD proactively ask** the user if they want to **prepare a new version** for release.
+- **Release Information Compliance**: When a release is requested, the agent must generate a standard release summary (English commit title + bilingual bullet points) as defined in Section 3 & 5.
+- **Default Action (Prepare Only)**: When performing a version bump or update, the agent should update all files locally but **STOP** before committing. Present the changes and the **proposed Release/Commit Message** to the user and wait for explicit confirmation to commit/push.
 - **Consistency**: When bumping, update version in **ALL** locations:
-  1. English Code (`.py`)
-  2. Chinese Code (`.py`)
-  3. English README (`README.md`)
-  4. Chinese README (`README_CN.md`)
-  5. Docs Index (`docs/.../index.md`)
-  6. Docs Index CN (`docs/.../index.zh.md`)
-  7. Docs Detail (`docs/.../{name}.md`)
-  8. Docs Detail CN (`docs/.../{name}.zh.md`)
+  1. Code (`.py`)
+  2. English README (`README.md`)
+  3. Chinese README (`README_CN.md`)
+  4. Docs Index (`docs/.../index.md`)
+  5. Docs Index CN (`docs/.../index.zh.md`)
+  6. Docs Detail (`docs/.../{name}.md`)
+  7. Docs Detail CN (`docs/.../{name}.zh.md`)
 
 ### Automated Release Process
-1.  **Trigger**: Push to `main` branch with changes in `plugins/**/*.py`.
-2.  **Detection**: `scripts/extract_plugin_versions.py` detects changed plugins and compares versions.
-3.  **Release**:
+
+1. **Trigger**: Push to `main` branch with changes in `plugins/**/*.py`.
+2. **Detection**: `scripts/extract_plugin_versions.py` detects changed plugins and compares versions.
+3. **Release**:
     - Generates release notes based on changes.
     - Creates a GitHub Release tag (e.g., `v2024.01.01-1`).
     - Uploads individual `.py` files of **changed plugins only** as assets.
-4.  **Market Publishing**:
+4. **Market Publishing**:
     - Workflow: `.github/workflows/publish_plugin.yml`
     - Trigger: Release published.
     - Action: Automatically updates the plugin code and metadata on OpenWebUI.com using `scripts/publish_plugin.py`.
     - **Auto-Sync**: If a local plugin has no ID but matches an existing published plugin by **Title**, the script will automatically fetch the ID, update the local file, and proceed with the update.
     - Requirement: `OPENWEBUI_API_KEY` secret must be set.
     - **README Link**: When announcing a release, always include the GitHub README URL for the plugin:
-      - Format: `https://github.com/Fu-Jie/awesome-openwebui/blob/main/plugins/{type}/{name}/README.md`
-      - Example: `https://github.com/Fu-Jie/awesome-openwebui/blob/main/plugins/filters/folder-memory/README.md`
+      - Format: `https://github.com/Fu-Jie/openwebui-extensions/blob/main/plugins/{type}/{name}/README.md`
+      - Example: `https://github.com/Fu-Jie/openwebui-extensions/blob/main/plugins/filters/folder-memory/README.md`
+
+### Release Content Standard
+
+When the user confirms a release, the agent **MUST** follow these content standards:
+
+1. **Commit Message**:
+   - **Language**: English ONLY.
+   - **Format**: `type(scope): description` (e.g., `feat(pipes): add streaming support for Copilot SDK`).
+   - **Body**: List 1-3 key changes in bullet points.
+2. **Release Summary (for user review)**:
+   - Before committing, present a "Release Draft" containing:
+     - **Title**: e.g., `Release v0.1.1: [Plugin Name] - [Brief Summary]`
+     - **Changelog**: English-only list of commits since the last release, including hashes (e.g., `896de02 docs(config): reorder antigravity model alias example`).
+     - **Verification Status**: Confirm all 7+ files have been updated and synced.
+3. **Internal Documentation**: Ensure "What's New" sections in READMEs and `docs/` match exactly the changes being released.
 
 ### Pull Request Check
+
 - Workflow: `.github/workflows/plugin-version-check.yml`
 - Checks if plugin files are modified.
 - **Fails** if version number is not updated.
@@ -104,15 +133,27 @@ Reference: `.github/workflows/release.yml`
 
 Before committing:
 
-- [ ] Code is bilingual and functional?
+- [ ] Code is internal i18n supported (`.py`) and fully functional?
 - [ ] Docstrings have updated version?
 - [ ] READMEs are updated and bilingual?
+- [ ] **Key Capabilities** in READMEs still cover all legacy core features + new features?
 - [ ] `docs/` index and detail pages are updated?
 - [ ] Root `README.md` is updated?
 - [ ] All version numbers match exactly?
+- [ ] Any non-obvious findings saved to `.agent/learnings/{topic}.md`?
 
 ## 5. Git Operations (Agent Rules)
 
-Strictly follow the rules defined in `.github/copilot-instructions.md` → **Git Operations (Agent Rules)** section.
+1. **Prepare-on-Demand**: Focus on file modifications and local verification first.
+2. **No Auto-Commit**: Never `git commit`, `git push`, or `create_pull_request` automatically after file updates unless the user explicitly says "commit this" or "release now".
+3. **Draft Mode**: If available, use PRs as drafts first.
+4. **Reference**: Strictly follow the rules defined in `.github/copilot-instructions.md` → **Git Operations (Agent Rules)** section.
 
+## 6. Knowledge Capture (Mandatory)
 
+Whenever you discover a non-obvious behaviour, internal API contract, or workaround
+during plugin development, **document it in `.agent/learnings/{topic}.md`** before
+ending the session.
+
+- Browse `.agent/learnings/` **first** at the start of a session to reuse existing knowledge.
+- Format: see `.agent/learnings/README.md`.

.all-contributorsrc

@@ -45,12 +45,21 @@
       "contributions": [
         "ideas"
       ]
+    },
+    {
+      "login": "abaroni",
+      "name": "Alessandro Baroni",
+      "avatar_url": "https://avatars.githubusercontent.com/u/21365486?v=4",
+      "profile": "https://github.com/abaroni",
+      "contributions": [
+        "ideas"
+      ]
     }
   ],
   "contributorsPerLine": 7,
   "skipCi": true,
   "repoType": "github",
   "repoHost": "https://github.com",
-  "projectName": "awesome-openwebui",
+  "projectName": "openwebui-extensions",
   "projectOwner": "Fu-Jie"
-}
+}

.cursorrules

@@ -0,0 +1,8 @@
+# 🤖 Cursor/Gemini Multi-Agent Protocol
+
+1. **STATUS CHECK**: Always run `python3 scripts/agent_sync.py status` first.
+2. **REGISTRATION**: Run `python3 scripts/agent_sync.py register gemini-id "Gemini" "Current task"`.
+3. **LOCKING**: Never edit without `python3 scripts/agent_sync.py lock gemini-id <path>`.
+4. **STANDARDS**: Refer to `.agent/rules/plugin_standards.md` for coding guidelines.
+
+Full details in `COOPERATION.md`.

.gemini/skills/README.md

@@ -0,0 +1,71 @@
+# Agent Skills Index
+
+This folder contains reusable Agent Skills for GitHub Copilot / VS Code custom agent workflows.
+
+## Available Skills
+
+- **community-announcer**
+  - Purpose: Generate community announcement content and related assets.
+  - Entry: `community-announcer/SKILL.md`
+
+- **doc-mirror-sync**
+  - Purpose: Sync mirrored documentation content and helper scripts.
+  - Entry: `doc-mirror-sync/SKILL.md`
+
+- **gh-issue-replier**
+  - Purpose: Draft standardized issue replies with templates.
+  - Entry: `gh-issue-replier/SKILL.md`
+
+- **gh-issue-scheduler**
+  - Purpose: Schedule and discover unanswered issues for follow-up.
+  - Entry: `gh-issue-scheduler/SKILL.md`
+
+- **i18n-validator**
+  - Purpose: Validate translation key consistency across i18n dictionaries.
+  - Entry: `i18n-validator/SKILL.md`
+
+- **plugin-scaffolder**
+  - Purpose: Scaffold OpenWebUI plugin boilerplate with repository standards.
+  - Entry: `plugin-scaffolder/SKILL.md`
+
+- **version-bumper**
+  - Purpose: Assist with semantic version bumping workflows.
+  - Entry: `version-bumper/SKILL.md`
+
+- **xlsx-single-file**
+  - Purpose: Single-file spreadsheet operations workflow without LibreOffice.
+  - Entry: `xlsx-single-file/SKILL.md`
+
+---
+
+## Release Pipeline Skills
+
+These four skills form a complete release pipeline and are designed to be used in sequence:
+
+```
+release-prep  →  pr-submitter  →  pr-reviewer  →  release-finalizer
+ (prepare)       (push & PR)      (respond to review)  (merge & close issue)
+```
+
+- **release-prep**
+  - Purpose: Full release preparation — version sync across 7+ files, bilingual release notes creation, consistency check, and commit.
+  - Entry: `release-prep/SKILL.md`
+
+- **pr-submitter**
+  - Purpose: Shell-escape-safe PR submission — writes body to temp file, validates sections, pushes branch, creates PR via `gh pr create --body-file`.
+  - Entry: `pr-submitter/SKILL.md`
+
+- **pr-reviewer**
+  - Purpose: Fetch PR review comments, categorize feedback, implement fixes, commit and push, reply to reviewers.
+  - Entry: `pr-reviewer/SKILL.md`
+
+- **release-finalizer**
+  - Purpose: Merge release PR to main with proper commit message, auto-link and close related issues, post closing messages.
+  - Entry: `release-finalizer/SKILL.md`
+
+## Notes
+
+- Skill definitions follow the expected location pattern:
+  - `.github/skills/<skill-name>/SKILL.md`
+- Each skill may include optional `assets/`, `references/`, and `scripts/` folders.
+- This directory mirrors `.gemini/skills` for compatibility.

.gemini/skills/community-announcer/SKILL.md

@@ -0,0 +1,23 @@
+---
+name: community-announcer
+description: Drafts engaging English and Chinese update announcements for the OpenWebUI Community and other social platforms. Use when a new version is released.
+---
+
+# Community Announcer
+
+## Overview
+Automates the drafting of high-impact update announcements.
+
+## Workflow
+1. **Source Intel**: Read the latest version's `What's New` section from `README.md`.
+2. **Drafting**: Create two versions:
+   - **Community Post**: Professional, structured, technical.
+   - **Catchy Short**: For Discord/Twitter, use emojis and bullet points.
+3. **Multi-language**: Generate BOTH English and Chinese versions automatically.
+
+## Announcement Structure (Recommended)
+- **Headline**: "Update vX.X.X - [Main Feature]"
+- **Introduction**: Brief context.
+- **Key Highlights**: Bulleted list of fixes/features.
+- **Action**: "Download from [Market Link]"
+- **Closing**: Thanks and Star request.

.gemini/skills/doc-mirror-sync/SKILL.md

@@ -0,0 +1,50 @@
+---
+name: doc-mirror-sync
+description: Automatically synchronizes plugin READMEs to the official documentation directory (docs/). Use after editing a plugin's local documentation to keep the MkDocs site up to date.
+---
+
+# Doc Mirror Sync
+
+## Overview
+Automates the mirroring of `plugins/{type}/{name}/README.md` to `docs/plugins/{type}/{name}.md`.
+
+## Docs-Only Mode (No Release Changes)
+Use this mode when the request is "only sync docs".
+
+- Only update documentation mirror files under `docs/plugins/**`.
+- Do **not** bump plugin version.
+- Do **not** modify plugin code (`plugins/**.py`) unless explicitly requested.
+- Do **not** update root badges/dates for release.
+- Do **not** run release preparation steps.
+
+## Workflow
+1. Identify changed READMEs.
+2. Copy content to corresponding mirror paths.
+3. Update version badges in `docs/plugins/{type}/index.md`.
+
+## Commands
+
+### Sync all mirrors (EN + ZH)
+
+```bash
+python .github/skills/doc-mirror-sync/scripts/sync.py
+```
+
+### Sync only one plugin (EN only)
+
+```bash
+cp plugins/<type>/<name>/README.md docs/plugins/<type>/<name>.md
+```
+
+### Sync only one plugin (EN + ZH)
+
+```bash
+cp plugins/<type>/<name>/README.md docs/plugins/<type>/<name>.md
+cp plugins/<type>/<name>/README_CN.md docs/plugins/<type>/<name>.zh.md
+```
+
+## Notes
+
+- If asked for English-only update, sync only `README.md` -> `.md` mirror.
+- If both languages are requested, sync both `README.md` and `README_CN.md`.
+- After syncing, verify git diff only contains docs file changes.

.gemini/skills/doc-mirror-sync/scripts/sync.py

@@ -0,0 +1,38 @@
+#!/usr/bin/env python3
+import os
+import shutil
+import re
+
+def sync_mirrors():
+    plugins_root = "plugins"
+    docs_root = "docs/plugins"
+    
+    types = ["actions", "filters", "pipes", "pipelines", "tools"]
+    
+    for t in types:
+        src_type_dir = os.path.join(plugins_root, t)
+        dest_type_dir = os.path.join(docs_root, t)
+        
+        if not os.path.exists(src_type_dir): continue
+        os.makedirs(dest_type_dir, exist_ok=True)
+        
+        for name in os.listdir(src_type_dir):
+            plugin_dir = os.path.join(src_type_dir, name)
+            if not os.path.isdir(plugin_dir): continue
+            
+            # Sync README.md -> docs/plugins/{type}/{name}.md
+            src_readme = os.path.join(plugin_dir, "README.md")
+            if os.path.exists(src_readme):
+                dest_readme = os.path.join(dest_type_dir, f"{name}.md")
+                shutil.copy(src_readme, dest_readme)
+                print(f"✅ Mirrored: {t}/{name} (EN)")
+            
+            # Sync README_CN.md -> docs/plugins/{type}/{name}.zh.md
+            src_readme_cn = os.path.join(plugin_dir, "README_CN.md")
+            if os.path.exists(src_readme_cn):
+                dest_readme_zh = os.path.join(dest_type_dir, f"{name}.zh.md")
+                shutil.copy(src_readme_cn, dest_readme_zh)
+                print(f"✅ Mirrored: {t}/{name} (ZH)")
+
+if __name__ == "__main__":
+    sync_mirrors()

.gemini/skills/gh-issue-replier/SKILL.md

@@ -0,0 +1,51 @@
+---
+name: gh-issue-replier
+description: Professional English replier for GitHub issues. Use when a task is completed, a bug is fixed, or more info is needed from the user. Automates replying using the 'gh' CLI tool.
+---
+
+# Gh Issue Replier
+
+## Overview
+
+The `gh-issue-replier` skill enables Gemini CLI to interact with GitHub issues professionally. It enforces English for all communications and leverages the `gh` CLI to post comments.
+
+## Workflow
+
+1.  **Identify the Issue**: Find the issue number (e.g., #49).
+2.  **Check Star Status**: Run the bundled script to check if the author has starred the repo.
+    *   Command: `bash scripts/check_star.sh <issue-number>`
+    *   Interpretation: 
+        *   Exit code **0**: User has starred. Use "Already Starred" templates.
+        *   Exit code **1**: User has NOT starred. Include "Star Request" in the reply.
+3.  **Select a Template**: Load [templates.md](references/templates.md) to choose a suitable English response pattern.
+4.  **Draft the Reply**: Compose a concise message based on the star status.
+5.  **Post the Comment**: Use the `gh` tool to submit the reply.
+
+## Tool Integration
+
+### Check Star Status
+```bash
+bash scripts/check_star.sh <issue-number>
+```
+
+### Post Comment
+```bash
+gh issue comment <issue-number> --body "<message-body>"
+```
+
+Example (if user has NOT starred):
+```bash
+gh issue comment 49 --body "This has been fixed in v1.2.7. If you find this helpful, a star on the repo would be much appreciated! ⭐"
+```
+
+Example (if user HAS starred):
+```bash
+gh issue comment 49 --body "This has been fixed in v1.2.7. Thanks for your support!"
+```
+
+## Guidelines
+
+-   **Language**: ALWAYS use English for the comment body, even if the system prompt or user conversation is in another language.
+-   **Tone**: Professional, helpful, and appreciative.
+-   **Precision**: When announcing a fix, mention the specific version or the logic change (e.g., "Updated regex pattern").
+-   **Closing**: If the issue is resolved and you have permission, you can also use `gh issue close <number>`.

.gemini/skills/gh-issue-replier/references/example_reference.md

@@ -0,0 +1,17 @@
+# Reference Documentation for Gh Issue Replier
+
+This is a placeholder for detailed reference documentation.
+Replace with actual reference content or delete if not needed.
+
+## Structure Suggestions
+
+### API Reference Example
+- Overview
+- Authentication
+- Endpoints with examples
+- Error codes
+
+### Workflow Guide Example
+- Prerequisites
+- Step-by-step instructions
+- Best practices

.gemini/skills/gh-issue-replier/references/templates.md

@@ -0,0 +1,45 @@
+# Issue Reply Templates
+
+Use these templates to craft professional English replies. Adjust placeholders like `@username`, `v1.2.x`, and `[commit hash]` as needed.
+
+## 1. Acknowledging a New Issue
+Use when you first see an issue and want to let the user know you are working on it.
+
+- "Thank you for reporting this! I'm looking into it right now."
+- "Thanks for bringing this to my attention. I'll try to reproduce this behavior and get back to you shortly."
+
+## 2. Requesting More Information
+Use when you need logs or specific details to fix the bug.
+
+- "Could you please provide the **'Original'** vs **'Normalized'** content from your browser console logs (F12)? It would help a lot in debugging."
+- "It would be very helpful if you could share the specific Markdown text that triggered this issue."
+
+## 3. Announcing a Fix
+Use when you have pushed the fix to the repository.
+
+- "This has been fixed in version **v1.2.x**. You can update the plugin to resolve it."
+- "I've just pushed a fix for this in [commit hash]. Please let me know if it works for you after updating."
+- "The issue was caused by a greedy regex pattern. I've updated it to use a tempered greedy token to prevent incorrect merging."
+
+## 4. Guiding to Official Market
+Always provide the official market link to ensure the user gets the latest verified version.
+
+- "The fix is now live! You can download the latest version from the official OpenWebUI Community page here: [Plugin Market Link]. Simply update the function in your OpenWebUI instance to apply the changes."
+- "I recommend getting the updated version from the official store: [Link]. It includes the fix for the spacing issue we discussed."
+
+## 5. Closing the Issue
+Use when the issue is confirmed resolved.
+
+- "Glad to hear it's working now! Closing this for now. Feel free to reopen it if the problem persists."
+- "Since this is resolved, I'm closing this issue. Thanks again for your feedback!"
+
+## 5. Pro-tip: Star Request
+Gently handle star requests based on the user's current status.
+
+### If User has NOT starred:
+- "If you find this plugin helpful, a star on the repo would be much appreciated! ⭐"
+- "We'd love your support! If this fixed your issue, please consider starring the repository. ⭐"
+
+### If User HAS already starred:
+- "Thanks again for starring the project and for your continuous support!"
+- "I appreciate your support and for being a stargazer of this project!"

.gemini/skills/gh-issue-replier/scripts/check_star.sh

@@ -0,0 +1,31 @@
+#!/usr/bin/env bash
+
+# Robust Star Checker v2
+# Usage: ./check_star.sh <issue_number>
+
+ISSUE_NUM=$1
+if [ -z "$ISSUE_NUM" ]; then exit 2; fi
+
+# 1. Get Repo and Author info
+REPO_FULL=$(gh repo view --json owner,name -q ".owner.login + \"/\" + .name")
+USER_LOGIN=$(gh issue view "$ISSUE_NUM" --json author -q ".author.login")
+
+# 2. Use GraphQL for high precision (Detects stars even when REST 404s)
+IS_STARRED=$(gh api graphql -f query='
+query($owner:String!, $repo:String!, $user:String!) {
+  repository(owner:$owner, name:$repo) {
+    stargazers(query:$user, first:1) {
+      nodes {
+        login
+      }
+    }
+  }
+}' -f owner="${REPO_FULL%/*}" -f repo="${REPO_FULL#*/}" -f user="$USER_LOGIN" -q ".data.repository.stargazers.nodes[0].login")
+
+if [ "$IS_STARRED" == "$USER_LOGIN" ]; then
+    echo "Confirmed: @$USER_LOGIN HAS starred $REPO_FULL. ⭐"
+    exit 0
+else
+    echo "Confirmed: @$USER_LOGIN has NOT starred $REPO_FULL."
+    exit 1
+fi

.gemini/skills/gh-issue-scheduler/SKILL.md

@@ -0,0 +1,42 @@
+---
+name: gh-issue-scheduler
+description: Finds all open GitHub issues that haven't been replied to by the owner, summarizes them, and generates a solution plan. Use when the user wants to audit pending tasks or plan maintenance work.
+---
+
+# Gh Issue Scheduler
+
+## Overview
+
+The `gh-issue-scheduler` skill helps maintainers track community feedback by identifying unaddressed issues and drafting actionable technical plans to resolve them.
+
+## Workflow
+
+1.  **Identify Unanswered Issues**: Run the bundled script to fetch issues without owner replies.
+    *   Command: `bash scripts/find_unanswered.sh`
+2.  **Analyze and Summarize**: For each identified issue, summarize the core problem and the user's intent.
+3.  **Generate Solution Plans**: Draft a technical "Action Plan" for each issue, including:
+    *   **Root Cause Analysis** (if possible)
+    *   **Proposed Fix/Implementation**
+    *   **Verification Strategy**
+4.  **Present to User**: Display a structured report of all pending issues and their respective plans.
+
+## Tool Integration
+
+### Find Unanswered Issues
+```bash
+bash scripts/find_unanswered.sh
+```
+
+## Report Format
+
+When presenting the summary, use the following Markdown structure:
+
+### 📋 Unanswered Issues Audit
+
+#### Issue #[Number]: [Title]
+- **Author**: @username
+- **Summary**: Concise description of the problem.
+- **Action Plan**:
+    1. Step 1 (e.g., Investigate file X)
+    2. Step 2 (e.g., Apply fix Y)
+    3. Verification (e.g., Run test Z)

.gemini/skills/gh-issue-scheduler/scripts/find_unanswered.sh

@@ -0,0 +1,42 @@
+#!/usr/bin/env bash
+
+# Fetch all open issues and filter for those without responses from the owner/collaborators.
+# Uses 'gh' CLI.
+
+REPO_FULL=$(gh repo view --json owner,name -q ".owner.login + "/" + .name")
+OWNER=${REPO_FULL%/*}
+
+# 1. Get all open issues
+OPEN_ISSUES=$(gh issue list --state open --json number,title,author,createdAt --limit 100)
+
+echo "Analysis for repository: $REPO_FULL"
+echo "------------------------------------"
+
+# Process each issue
+echo "$OPEN_ISSUES" | jq -c '.[]' | while read -r issue; do
+    NUMBER=$(echo "$issue" | jq -r '.number')
+    TITLE=$(echo "$issue" | jq -r '.title')
+    AUTHOR=$(echo "$issue" | jq -r '.author.login')
+    
+    # Check comments for owner responses
+    # We look for comments where the author is the repo owner
+    COMMENTS=$(gh issue view "$NUMBER" --json comments -q ".comments[].author.login" 2>/dev/null)
+    
+    HAS_OWNER_REPLY=false
+    for COMMENT_AUTHOR in $COMMENTS; do
+        if [ "$COMMENT_AUTHOR" == "$OWNER" ]; then
+            HAS_OWNER_REPLY=true
+            break
+        fi
+    done
+    
+    if [ "$HAS_OWNER_REPLY" == "false" ]; then
+        echo "ISSUE_START"
+        echo "ID: $NUMBER"
+        echo "Title: $TITLE"
+        echo "Author: $AUTHOR"
+        echo "Description:"
+        gh issue view "$NUMBER" --json body -q ".body"
+        echo "ISSUE_END"
+    fi
+done

.gemini/skills/i18n-validator/SKILL.md

@@ -0,0 +1,14 @@
+---
+name: i18n-validator
+description: Validates multi-language consistency in the TRANSLATIONS dictionary of a plugin. Use to check if any language keys are missing or if translations need updating.
+---
+
+# I18n Validator
+
+## Overview
+Ensures all 12 supported languages (en-US, zh-CN, etc.) have aligned translation keys.
+
+## Features
+- Detects missing keys in non-English dictionaries.
+- Suggests translations using the core AI engine.
+- Validates the `fallback_map` for variant redirects.

.gemini/skills/i18n-validator/scripts/validate_i18n.py

@@ -0,0 +1,54 @@
+#!/usr/bin/env python3
+import sys
+import ast
+import os
+
+def check_i18n(file_path):
+    if not os.path.exists(file_path):
+        print(f"Error: File not found {file_path}")
+        return
+    
+    with open(file_path, 'r', encoding='utf-8') as f:
+        tree = ast.parse(f.read())
+    
+    translations = {}
+    for node in tree.body:
+        if isinstance(node, ast.Assign):
+            for target in node.targets:
+                if isinstance(target, ast.Name) and target.id == "TRANSLATIONS":
+                    translations = ast.literal_eval(node.value)
+                    break
+    
+    if not translations:
+        print("⚠️ No TRANSLATIONS dictionary found.")
+        return
+
+    # Base keys from English
+    base_lang = "en-US"
+    if base_lang not in translations:
+        print(f"❌ Error: {base_lang} missing in TRANSLATIONS.")
+        return
+    
+    base_keys = set(translations[base_lang].keys())
+    print(f"🔍 Analyzing {file_path}...")
+    print(f"Standard keys ({len(base_keys)}): {', '.join(sorted(base_keys))}
+")
+
+    for lang, keys in translations.items():
+        if lang == base_lang: continue
+        lang_keys = set(keys.keys())
+        missing = base_keys - lang_keys
+        extra = lang_keys - base_keys
+        
+        if missing:
+            print(f"❌ {lang}: Missing {len(missing)} keys: {', '.join(missing)}")
+        if extra:
+            print(f"⚠️ {lang}: Has {len(extra)} extra keys: {', '.join(extra)}")
+        if not missing and not extra:
+            print(f"✅ {lang}: Aligned.")
+
+if __name__ == "__main__":
+    if len(sys.argv) < 2:
+        print("Usage: validate_i18n.py <path_to_plugin.py>")
+        sys.exit(1)
+    check_i18n(sys.argv[1])

.gemini/skills/openwebui-community-publisher/SKILL.md

@@ -0,0 +1,59 @@
+---
+name: openwebui-community-publisher
+description: Automatically publishes plugin update posts to openwebui.com. 
+---
+
+# OpenWebUI Community Publisher
+
+## Overview
+
+This skill automates the process of creating **new** plugin release notes and announcements directly on the OpenWebUI Community (openwebui.com).
+
+**Note**: This skill is exclusively for **new post creation**. Do NOT use this for updating existing posts, as updates are managed separately via dedicated scripts.
+
+## Prerequisites
+
+- User must be logged into [openwebui.com](https://openwebui.com) in the browser session.
+- The content must be prepared in Markdown format (typically following the structure of the plugin's changelog or a dedicated release `.md` file).
+
+## Execution Workflow
+
+### 1. Verification
+
+- Use `browser_subagent` to navigate to `https://openwebui.com`.
+- Verify the logged-in user status (look for profile icons or "@Fu-Jie").
+
+### 2. Post Creation
+
+- Navigate to `https://openwebui.com/post`.
+- **Post Type Selection**:
+  - Choose the appropriate tab based on content:
+    - **Text**: General announcements and documentation.
+    - **Tool**: Standalone tool plugins.
+    - **Function**: Pipes, Filters, or Actions.
+    - **Prompt**: Chat prompt templates.
+    - **Model**: GGUF/Ollama model files.
+  - Unless otherwise specified, default to **Text** for general release introductions.
+- **Community Selection**:
+  - For general OpenWebUI related posts, select **o/openwebui**.
+  - For specialized topics, select the relevant community (e.g., **o/ollama** for models).
+- **Metadata Mapping**:
+  - **Title**: Use the main header from the source file.
+  - **Content/Description**: Paste the Markdown body.
+  - **Source Code (for Function/Pipe)**: If publishing a `Function`, retrieve the corresponding `.py` file content and paste it into the code area.
+- **Tags**: Leave empty by default unless relevant keywords are explicitly provided.
+- **Media**: Optional, only attach if provided.
+- **Settings**: Ensure "Adult content" is unchecked.
+
+### 3. Submission & Validation
+
+- Click the "Create" (创建) button.
+- Wait for redirection to the final post URL.
+- **CRITICAL**: Use `capture_browser_screenshot` to verify the rendering.
+- Return the final URL to the user.
+
+## Design Standards
+
+- **Rich Aesthetics**: Use emojis in titles.
+- **Structured Data**: Ensure tables and code blocks in the Markdown are preserved.
+- **Internal Linking**: Link back to the OpenWebUI market or GitHub repository where applicable.

.gemini/skills/plugin-scaffolder/SKILL.md

@@ -0,0 +1,19 @@
+---
+name: plugin-scaffolder
+description: Generates a standardized single-file i18n Python plugin template based on project standards. Use when starting a new plugin development to skip boilerplate writing.
+---
+
+# Plugin Scaffolder
+
+## Overview
+Generates compliant OpenWebUI plugin templates with built-in i18n, common utility methods, and required docstring fields.
+
+## Usage
+1. Provide the **Plugin Name** and **Type** (action/filter/pipe).
+2. The skill will generate the `.py` file and the bilingual `README` files.
+
+## Template Standard
+- `Valves(BaseModel)` with `UPPER_SNAKE_CASE`
+- `_get_user_context` with JS fallback and timeout
+- `_emit_status` and `_emit_debug_log` methods
+- Standardized docstring metadata

.gemini/skills/plugin-scaffolder/assets/README_template.md

@@ -0,0 +1,34 @@
+# {{TITLE}}
+
+**Author:** [Fu-Jie](https://github.com/Fu-Jie/openwebui-extensions) | **Version:** 0.1.0 | **Project:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **License:** MIT
+
+{{DESCRIPTION}}
+
+## 🔥 What's New in v0.1.0
+
+* Initial release of {{TITLE}}.
+
+## 🌐 Multilingual Support
+
+Supports automatic interface and status switching for the following languages:
+`English`, `简体中文`, `繁體中文 (香港)`, `繁體中文 (台灣)`, `한국어`, `日本語`, `Français`, `Deutsch`, `Español`, `Italiano`, `Tiếng Việt`, `Bahasa Indonesia`.
+
+## ✨ Core Features
+
+* Feature 1
+* Feature 2
+
+## How to Use 🛠️
+
+1. Install the plugin in Open WebUI.
+2. Configure settings in Valves.
+
+## Configuration (Valves) ⚙️
+
+| Parameter | Default | Description |
+| :--- | :--- | :--- |
+| `priority` | `50` | Execution priority. |
+
+## ⭐ Support
+
+If this plugin has been useful, a star on [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) is a big motivation for me. Thank you for the support.

.gemini/skills/plugin-scaffolder/assets/template.py

@@ -0,0 +1,80 @@
+"""
+title: {{TITLE}}
+author: Fu-Jie
+author_url: https://github.com/Fu-Jie/openwebui-extensions
+funding_url: https://github.com/open-webui
+version: 0.1.0
+description: {{DESCRIPTION}}
+"""
+
+import asyncio
+import logging
+import json
+from typing import Optional, Dict, Any, List, Callable, Awaitable
+from pydantic import BaseModel, Field
+from fastapi import Request
+
+# Configure logging
+logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s")
+logger = logging.getLogger(__name__)
+
+TRANSLATIONS = {
+    "en-US": {"status_starting": "Starting {{TITLE}}..."},
+    "zh-CN": {"status_starting": "正在启动 {{TITLE}}..."},
+    "zh-HK": {"status_starting": "正在啟動 {{TITLE}}..."},
+    "zh-TW": {"status_starting": "正在啟動 {{TITLE}}..."},
+    "ko-KR": {"status_starting": "{{TITLE}} 시작 중..."},
+    "ja-JP": {"status_starting": "{{TITLE}} を起動中..."},
+    "fr-FR": {"status_starting": "Démarrage de {{TITLE}}..."},
+    "de-DE": {"status_starting": "{{TITLE}} wird gestartet..."},
+    "es-ES": {"status_starting": "Iniciando {{TITLE}}..."},
+    "it-IT": {"status_starting": "Avvio di {{TITLE}}..."},
+    "vi-VN": {"status_starting": "Đang khởi động {{TITLE}}..."},
+    "id-ID": {"status_starting": "Memulai {{TITLE}}..."},
+}
+
+class {{CLASS_NAME}}:
+    class Valves(BaseModel):
+        priority: int = Field(default=50, description="Priority level (lower = earlier).")
+        show_status: bool = Field(default=True, description="Show status updates in UI.")
+
+    def __init__(self):
+        self.valves = self.Valves()
+        self.fallback_map = {
+            "zh": "zh-CN", "en": "en-US", "ko": "ko-KR", "ja": "ja-JP",
+            "fr": "fr-FR", "de": "de-DE", "es": "es-ES", "it": "it-IT",
+            "vi": "vi-VN", "id": "id-ID"
+        }
+
+    def _get_translation(self, lang: str, key: str, **kwargs) -> str:
+        target_lang = lang
+        if target_lang not in TRANSLATIONS:
+            base = target_lang.split("-")[0]
+            target_lang = self.fallback_map.get(base, "en-US")
+        
+        lang_dict = TRANSLATIONS.get(target_lang, TRANSLATIONS["en-US"])
+        text = lang_dict.get(key, TRANSLATIONS["en-US"].get(key, key))
+        return text.format(**kwargs) if kwargs else text
+
+    async def _get_user_context(self, __user__: Optional[dict], __event_call__: Optional[Callable] = None, __request__: Optional[Request] = None) -> dict:
+        user_data = __user__ if isinstance(__user__, dict) else {}
+        user_language = user_data.get("language", "en-US")
+        if __event_call__:
+            try:
+                js = "try { return (document.documentElement.lang || localStorage.getItem('locale') || navigator.language || 'en-US'); } catch (e) { return 'en-US'; }"
+                frontend_lang = await asyncio.wait_for(__event_call__({"type": "execute", "data": {"code": js}}), timeout=2.0)
+                if frontend_lang: user_language = frontend_lang
+            except: pass
+        return {"user_language": user_language}
+
+    async def {{METHOD_NAME}}(self, body: dict, __user__: Optional[dict] = None, __event_emitter__=None, __event_call__=None, __request__: Optional[Request] = None) -> dict:
+        if self.valves.show_status and __event_emitter__:
+            user_ctx = await self._get_user_context(__user__, __event_call__, __request__)
+            msg = self._get_translation(user_ctx["user_language"], "status_starting")
+            await __event_emitter__({"type": "status", "data": {"description": msg, "done": False}})
+        
+        # Implement core logic here
+        
+        if self.valves.show_status and __event_emitter__:
+            await __event_emitter__({"type": "status", "data": {"description": "Done", "done": True}})
+        return body

.gemini/skills/plugin-scaffolder/assets/template.py.j2

@@ -0,0 +1,80 @@
+"""
+title: {{TITLE}}
+author: Fu-Jie
+author_url: https://github.com/Fu-Jie/openwebui-extensions
+funding_url: https://github.com/open-webui
+version: 0.1.0
+description: {{DESCRIPTION}}
+"""
+
+import asyncio
+import logging
+import json
+from typing import Optional, Dict, Any, List, Callable, Awaitable
+from pydantic import BaseModel, Field
+from fastapi import Request
+
+# Configure logging
+logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s")
+logger = logging.getLogger(__name__)
+
+TRANSLATIONS = {
+    "en-US": {"status_starting": "Starting {{TITLE}}..."},
+    "zh-CN": {"status_starting": "正在启动 {{TITLE}}..."},
+    "zh-HK": {"status_starting": "正在啟動 {{TITLE}}..."},
+    "zh-TW": {"status_starting": "正在啟動 {{TITLE}}..."},
+    "ko-KR": {"status_starting": "{{TITLE}} 시작 중..."},
+    "ja-JP": {"status_starting": "{{TITLE}} を起動中..."},
+    "fr-FR": {"status_starting": "Démarrage de {{TITLE}}..."},
+    "de-DE": {"status_starting": "{{TITLE}} wird gestartet..."},
+    "es-ES": {"status_starting": "Iniciando {{TITLE}}..."},
+    "it-IT": {"status_starting": "Avvio di {{TITLE}}..."},
+    "vi-VN": {"status_starting": "Đang khởi động {{TITLE}}..."},
+    "id-ID": {"status_starting": "Memulai {{TITLE}}..."},
+}
+
+class {{CLASS_NAME}}:
+    class Valves(BaseModel):
+        priority: int = Field(default=50, description="Priority level (lower = earlier).")
+        show_status: bool = Field(default=True, description="Show status updates in UI.")
+
+    def __init__(self):
+        self.valves = self.Valves()
+        self.fallback_map = {
+            "zh": "zh-CN", "en": "en-US", "ko": "ko-KR", "ja": "ja-JP",
+            "fr": "fr-FR", "de": "de-DE", "es": "es-ES", "it": "it-IT",
+            "vi": "vi-VN", "id": "id-ID"
+        }
+
+    def _get_translation(self, lang: str, key: str, **kwargs) -> str:
+        target_lang = lang
+        if target_lang not in TRANSLATIONS:
+            base = target_lang.split("-")[0]
+            target_lang = self.fallback_map.get(base, "en-US")
+        
+        lang_dict = TRANSLATIONS.get(target_lang, TRANSLATIONS["en-US"])
+        text = lang_dict.get(key, TRANSLATIONS["en-US"].get(key, key))
+        return text.format(**kwargs) if kwargs else text
+
+    async def _get_user_context(self, __user__: Optional[dict], __event_call__: Optional[Callable] = None, __request__: Optional[Request] = None) -> dict:
+        user_data = __user__ if isinstance(__user__, dict) else {}
+        user_language = user_data.get("language", "en-US")
+        if __event_call__:
+            try:
+                js = "try { return (document.documentElement.lang || localStorage.getItem('locale') || navigator.language || 'en-US'); } catch (e) { return 'en-US'; }"
+                frontend_lang = await asyncio.wait_for(__event_call__({"type": "execute", "data": {"code": js}}), timeout=2.0)
+                if frontend_lang: user_language = frontend_lang
+            except: pass
+        return {"user_language": user_language}
+
+    async def {{METHOD_NAME}}(self, body: dict, __user__: Optional[dict] = None, __event_emitter__=None, __event_call__=None, __request__: Optional[Request] = None) -> dict:
+        if self.valves.show_status and __event_emitter__:
+            user_ctx = await self._get_user_context(__user__, __event_call__, __request__)
+            msg = self._get_translation(user_ctx["user_language"], "status_starting")
+            await __event_emitter__({"type": "status", "data": {"description": msg, "done": False}})
+        
+        # Implement core logic here
+        
+        if self.valves.show_status and __event_emitter__:
+            await __event_emitter__({"type": "status", "data": {"description": "Done", "done": True}})
+        return body

.gemini/skills/plugin-scaffolder/scripts/scaffold.py

@@ -0,0 +1,66 @@
+#!/usr/bin/env python3
+import sys
+import os
+
+
+def scaffold(p_type, p_name, title, desc):
+    target_dir = f"plugins/{p_type}/{p_name}"
+    os.makedirs(target_dir, exist_ok=True)
+
+    class_name = (
+        "Action"
+        if p_type == "actions"
+        else (
+            "Filter"
+            if p_type == "filters"
+            else "Tools" if p_type == "tools" else "Pipe"
+        )
+    )
+    method_name = (
+        "action"
+        if p_type == "actions"
+        else (
+            "outlet"
+            if p_type == "filters"
+            else "execute" if p_type == "tools" else "pipe"
+        )
+    )
+
+    replacements = {
+        "{{TITLE}}": title,
+        "{{DESCRIPTION}}": desc,
+        "{{CLASS_NAME}}": class_name,
+        "{{METHOD_NAME}}": method_name,
+    }
+
+    # Files to generate
+    templates = [
+        ("assets/template.py.j2", f"{p_name}.py"),
+        ("assets/README_template.md", "README.md"),
+        ("assets/README_template.md", "README_CN.md"),
+    ]
+
+    # Path relative to skill root
+    skill_root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+
+    for t_path, t_name in templates:
+        template_file = os.path.join(skill_root, t_path)
+        if not os.path.exists(template_file):
+            print(f"⚠️ Warning: Template not found {template_file}")
+            continue
+
+        with open(template_file, "r") as f:
+            content = f.read()
+        for k, v in replacements.items():
+            content = content.replace(k, v)
+
+        with open(os.path.join(target_dir, t_name), "w") as f:
+            f.write(content)
+        print(f"✅ Generated: {target_dir}/{t_name}")
+
+
+if __name__ == "__main__":
+    if len(sys.argv) < 5:
+        print("Usage: scaffold.py <type> <name> <title> <desc>")
+        sys.exit(1)
+    scaffold(sys.argv[1], sys.argv[2], sys.argv[3], sys.argv[4])

.gemini/skills/pr-reviewer/SKILL.md

@@ -0,0 +1,180 @@
+---
+name: pr-reviewer
+description: Fetches PR review comments, analyzes requested changes, implements fixes, commits and pushes the resolution. Use after a reviewer has left comments on an open PR to close the feedback loop efficiently.
+---
+
+# PR Reviewer
+
+## Overview
+
+This skill automates the response cycle for code review. When a reviewer leaves comments on a Pull Request, this skill fetches all pending feedback, categorizes issues by severity, implements fixes, and submits a follow-up commit with appropriate review response comments.
+
+## Prerequisites
+
+- An open PR exists with pending review comments
+- The local branch matches the PR's head branch
+- `gh` CLI is authenticated
+
+---
+
+## Workflow
+
+### Step 1 — Fetch Review State
+
+Retrieve all review comments and overall review status:
+
+```bash
+# Get overall review decisions
+PAGER=cat GH_PAGER=cat gh pr view <PR-NUMBER> --json reviews,reviewDecision,headRefName \
+  --jq '{decision: .reviewDecision, reviews: [.reviews[] | {author: .author.login, state: .state, body: .body}]}'
+
+# Get inline code comments (specific line comments)
+PAGER=cat GH_PAGER=cat gh api repos/Fu-Jie/openwebui-extensions/pulls/<PR-NUMBER>/comments \
+  --jq '[.[] | {path: .path, line: .line, body: .body, author: .user.login, id: .id}]'
+
+# Get general issue comments
+PAGER=cat GH_PAGER=cat gh issue view <PR-NUMBER> --comments --json comments \
+  --jq '[.comments[] | {author: .author.login, body: .body}]'
+```
+
+Confirm the current local branch matches the PR head:
+```bash
+git branch --show-current
+```
+If mismatched, checkout the correct branch first.
+
+### Step 2 — Categorize Review Feedback
+
+Group feedback into categories:
+
+| Category | Examples | Action |
+|----------|---------|--------|
+| **Code Bug** | Logic error, incorrect variable, broken condition | Fix code immediately |
+| **Style / Formatting** | Indentation, naming convention, missing blank line | Fix code |
+| **Documentation** | Missing i18n key, wrong version in README, typo | Fix docs |
+| **Design Question** | Suggestion to restructure, alternative approach | Discuss with user before implementing |
+| **Nitpick / Optional** | Minor style preferences reviewer marked as optional | Fix if quick; document if skipped |
+| **Blocking** | Reviewer explicitly blocks merge | Must fix before proceeding |
+
+Present the full categorized list to the user and confirm the resolution plan.
+
+### Step 3 — Implement Fixes
+
+For each accepted fix:
+
+1. Read the affected file at the commented line for context:
+   ```bash
+   sed -n '<line-5>,<line+10>p' <file-path>
+   ```
+2. Apply the fix using appropriate file edit tools
+3. After editing, verify the specific area looks correct
+
+**For code changes that might affect behavior:**
+- Check if tests exist: `ls tests/test_*.py`
+- If tests exist, run them: `python -m pytest tests/ -v`
+
+**For documentation fixes:**
+- If modifying README.md, check if `docs/` mirror needs the same fix
+- Apply the same fix to both locations
+
+### Step 4 — Run Consistency Checks
+
+After all fixes are applied:
+
+```bash
+# Version consistency (if any version files were touched)
+python3 scripts/check_version_consistency.py
+
+# Quick syntax check for Python files
+python3 -m py_compile plugins/{type}/{name}/{name}.py && echo "✅ Syntax OK"
+```
+
+### Step 5 — Stage and Commit
+
+Create a new commit (do NOT amend if the branch has already been pushed, to avoid force-push):
+
+```bash
+git add -A
+git status
+```
+
+Draft a Conventional Commits message for the fixup:
+
+Format: `fix(scope): address review feedback`
+
+Body should list what was fixed, referencing reviewer concerns:
+```
+fix(github-copilot-sdk): address review feedback from @reviewer
+
+- Fix X per review comment on line Y of file Z
+- Update README to clarify auth requirement
+- Correct edge case in _parse_mcp_servers logic
+```
+
+```bash
+git commit -m "<fixup commit message>"
+```
+
+### Step 6 — Push the Fix Commit
+
+```bash
+git push origin $(git branch --show-current)
+```
+
+**Force-push policy:**
+- Use `git push` (non-force) by default
+- Only use `git push --force-with-lease` if:
+  1. The user explicitly requests it, AND
+  2. The only change is an amended commit squash (cosmetic, no logic change)
+  3. Never use `--force` (without `--lease`)
+
+### Step 7 — Respond to Reviewers
+
+For each addressed review comment, post a reply:
+
+```bash
+# Reply to inline comment
+gh api repos/Fu-Jie/openwebui-extensions/pulls/<PR-NUMBER>/comments/<COMMENT-ID>/replies \
+  -X POST -f body="Fixed in commit <SHORT-SHA>. <Brief explanation of what was changed.>"
+
+# General comment to summarize all fixes
+gh issue comment <PR-NUMBER> --body "All review feedback addressed in commit <SHORT-SHA>:
+- Fixed: <item 1>
+- Fixed: <item 2>
+Ready for re-review. 🙏"
+```
+
+### Step 8 — Re-Request Review (Optional)
+
+If the reviewer had submitted a `CHANGES_REQUESTED` review, request a new review after fixes:
+
+```bash
+PAGER=cat GH_PAGER=cat gh api repos/Fu-Jie/openwebui-extensions/pulls/<PR-NUMBER>/requested_reviewers \
+  -X POST -f reviewers[]='<reviewer-login>'
+```
+
+---
+
+## Decision Guide
+
+### When NOT to implement a suggestion immediately
+
+- **Design questions**: "Should this be a separate class?" — Present to user for decision
+- **Optional nitpicks**: Reviewer marked as `nit:` — Ask user if they want to include it
+- **Large refactors**: If fix would require changing >50 lines, propose a separate follow-up issue instead
+
+### When to ask the user before proceeding
+
+- Any fix involving behavioral changes to plugin logic
+- Renaming Valve keys (breaking change — requires migration notes)
+- Changes that affect the bilingual release notes already committed
+
+---
+
+## Anti-Patterns to Avoid
+
+- ❌ Do NOT `git commit --amend` on a pushed commit without user approval for force-push
+- ❌ Do NOT silently skip a reviewer's comment; always acknowledge it (implement or explain why not)
+- ❌ Do NOT use `--force` (only `--force-with-lease` when absolutely necessary)
+- ❌ Do NOT make unrelated changes in the fixup commit; keep scope focused on review feedback
+- ❌ Do NOT respond to reviewer comments in Chinese if the PR language context is English

.gemini/skills/pr-submitter/SKILL.md

@@ -0,0 +1,179 @@
+---
+name: pr-submitter
+description: Submits a feature branch as a Pull Request with a validated, properly formatted bilingual PR body. Handles shell-escape-safe body writing via temp files. Use after release-prep has committed all changes.
+---
+
+# PR Submitter
+
+## Overview
+
+This skill handles the final step of pushing a feature branch and creating a validated Pull Request on GitHub. Its primary purpose is to avoid the shell-escaping pitfalls (backticks, special characters in `gh pr create --body`) by always writing the PR body to a **temp file** first.
+
+## Prerequisites
+
+- All changes are committed (use `release-prep` skill first)
+- The `gh` CLI is authenticated (`gh auth status`)
+- Current branch is NOT `main` or `master`
+
+---
+
+## Workflow
+
+### Step 1 — Pre-Flight Checks
+
+Run these checks before any push:
+
+```bash
+# 1. Confirm not on protected branch
+git branch --show-current
+
+# 2. Verify there are commits to push
+git log origin/$(git branch --show-current)..HEAD --oneline 2>/dev/null || echo "No remote tracking branch yet"
+
+# 3. Check gh CLI auth
+gh auth status
+```
+
+If any check fails, stop and report clearly.
+
+### Step 2 — Collect PR Metadata
+
+Gather:
+- **PR Title**: Must follow Conventional Commits format, English only (e.g., `feat(github-copilot-sdk): release v0.8.0 with conditional tool filtering`)
+- **Target base branch**: Default is `main`
+- **Plugin name + version** (to build body sections)
+- **Key changes** (reuse from release-prep or the latest What's New section)
+
+### Step 3 — Build PR Body File (Shell-Escape-Safe)
+
+**Always write the body to a temp file.** Never embed multi-line markdown with special characters directly in a shell command.
+
+```bash
+cat > /tmp/pr_body.md << 'HEREDOC'
+## Summary
+
+Brief one-sentence description of what this PR accomplishes.
+
+## Changes
+
+### New Features
+- Feature 1 description
+- Feature 2 description
+
+### Bug Fixes
+- Fix 1 description
+
+## Plugin Version
+- `PluginName` bumped to `vX.X.X`
+
+## Documentation
+- README.md / README_CN.md updated
+- docs/ mirrors synced
+
+## Testing
+- [ ] Tested locally in OpenWebUI
+- [ ] i18n validated (all language keys present)
+- [ ] Version consistency check passed (`python3 scripts/check_version_consistency.py`)
+
+---
+
+## 变更摘要（中文）
+
+简要描述本次 PR 的改动内容。
+
+### 新功能
+- 功能1描述
+- 功能2描述
+
+### 问题修复
+- 修复1描述
+HEREDOC
+```
+
+**Critical rules for the body file:**
+- Use `<< 'HEREDOC'` (quoted heredoc) to prevent variable expansion
+- Keep all backticks literal — they are safe inside a heredoc
+- Paths like `/api/v1/files/` are safe too since heredoc doesn't interpret them as commands
+
+### Step 4 — Validate PR Body
+
+Before submitting, verify the body file contains expected sections:
+
+```bash
+# Check key sections exist
+grep -q "## Summary" /tmp/pr_body.md && echo "✅ Summary" || echo "❌ Summary missing"
+grep -q "## Changes" /tmp/pr_body.md && echo "✅ Changes" || echo "❌ Changes missing"
+grep -q "## 变更摘要" /tmp/pr_body.md && echo "✅ CN Section" || echo "❌ CN Section missing"
+
+# Preview the body
+cat /tmp/pr_body.md
+```
+
+Ask the user to confirm the body content before proceeding.
+
+### Step 5 — Push Branch
+
+```bash
+git push -u origin $(git branch --show-current)
+```
+
+If push is rejected (non-fast-forward), report to user and ask whether to force-push. **Do NOT force-push without explicit confirmation.**
+
+### Step 6 — Create Pull Request
+
+```bash
+gh pr create \
+  --base main \
+  --head $(git branch --show-current) \
+  --title "<PR title from Step 2>" \
+  --body-file /tmp/pr_body.md
+```
+
+Always use `--body-file`, never `--body` with inline markdown.
+
+### Step 7 — Verify PR Creation
+
+```bash
+PAGER=cat GH_PAGER=cat gh pr view --json number,url,title,body --jq '{number: .number, url: .url, title: .title, body_preview: .body[:200]}'
+```
+
+Confirm:
+- PR number and URL
+- Title matches intended Conventional Commits format
+- Body preview includes key sections (not truncated/corrupted)
+
+If the body appears corrupted (empty sections, missing backtick content), use edit:
+
+```bash
+gh pr edit <PR-NUMBER> --body-file /tmp/pr_body.md
+```
+
+### Step 8 — Cleanup
+
+```bash
+rm -f /tmp/pr_body.md
+```
+
+Report final PR URL to the user.
+
+---
+
+## Shell-Escape Safety Rules
+
+| Risk | Safe Approach |
+|------|--------------|
+| Backticks in `--body` | Write to file, use `--body-file` |
+| Paths like `/api/...` | Safe in heredoc; risky in inline `--body` |
+| Newlines in `--body` | File-based only |
+| `$variable` expansion | Use `<< 'HEREDOC'` (quoted) |
+| Double quotes in body | Safe in heredoc file |
+
+---
+
+## Anti-Patterns to Avoid
+
+- ❌ Never use `--body "..."` with multi-line content directly in shell command
+- ❌ Never interpolate variables directly into heredoc without quoting the delimiter
+- ❌ Never force-push (`--force`) without explicit user confirmation
+- ❌ Never target `main` as the source branch (only as base)
+- ❌ Never skip the body validation step — a PR with empty body is worse than a delayed PR

.gemini/skills/release-finalizer/SKILL.md

@@ -0,0 +1,208 @@
+---
+name: release-finalizer
+description: Merges a release PR, associates it with resolved issues, replies to issue reporters, and closes issues. Use after PR review is complete and ready for merge. Closes the release cycle.
+---
+
+# Release Finalizer
+
+## Overview
+
+This skill completes the final step of the release cycle: merging the release PR to `main`, replying to all related issues with solutions, and automatically closing them using GitHub's issue linking mechanism.
+
+## Prerequisites
+
+- The PR is in `OPEN` state and ready to merge
+- All status checks have passed (CI green)
+- All review feedback has been addressed
+- The PR relates to one or more GitHub issues (either in PR description or through commits)
+
+---
+
+## Workflow
+
+### Step 1 — Pre-Merge Verification
+
+Verify that the PR is ready:
+
+```bash
+PAGER=cat GH_PAGER=cat gh pr view <PR-NUMBER> --json state,statusCheckRollup,reviewDecision
+```
+
+Checklist:
+- ✅ `state` is `OPEN`
+- ✅ `statusCheckRollup` all have `conclusion: SUCCESS`
+- ✅ `reviewDecision` is `APPROVED` or empty (no blocking reviews)
+
+If any check fails, **do NOT merge**. Report the issue to the user.
+
+### Step 2 — Identify Related Issues
+
+Issues can be linked to a PR in multiple ways. Check the PR description and commit messages for keywords:
+
+```bash
+PAGER=cat GH_PAGER=cat gh pr view <PR-NUMBER> --json body,commits
+```
+
+Look for patterns like:
+- `Closes #XX`, `Fixes #XX`, `Resolves #XX` (in description or commit bodies)
+- `#XX` mentioned as "related to" or "addresses"
+
+**Manual input**: If issue links are not in the PR, ask the user which issue(s) this PR resolves.
+
+Extract all issue numbers into a list: `[#48, #52, ...]`
+
+### Step 3 — Select Merge Strategy
+
+Offer the user three options:
+
+| Strategy | Git Behavior | Use Case |
+|----------|-------------|----------|
+| **Squash** | All commits squashed into one commit on main | Clean history, recommended for release PRs |
+| **Rebase** | Linear history, no merge commit | Preserve commit granularity |
+| **Merge** | Merge commit created | Preserve full PR context |
+
+**Recommendation for release PRs**: Use `--squash` to create a single clean commit.
+
+If user doesn't specify, default to `--squash`.
+
+### Step 4 — Prepare Merge Commit Message
+
+If using `--squash`, craft a single comprehensive commit message:
+
+**Format** (Conventional Commits + Github linking):
+```
+type(scope): description
+
+- Bullet point 1
+- Bullet point 2
+
+Closes #48
+Closes #52
+```
+
+The `Closes #XX` keyword tells GitHub to automatically close those issues when the commit lands on `main`.
+
+Example:
+```
+feat(pipes,filters): release Copilot SDK Pipe v0.8.0 and Files Filter v0.1.3
+
+- Implement P1~P4 conditional tool filtering system
+- Fix file publishing reliability across all storage backends
+- Add strict file URL validation
+- Update bilingual documentation
+
+Closes #48
+```
+
+### Step 5 — Execute Merge
+
+```bash
+gh pr merge <PR-NUMBER> \
+  --squash \
+  --delete-branch \
+  -m "type(scope): description" \
+  -b "- Bullet 1\n- Bullet 2\n\nCloses #48"
+```
+
+**Key flags:**
+- `--squash`: Squash commits (recommended for releases)
+- `--delete-branch`: Delete the feature branch after merge
+- `-m`: Commit subject
+- `-b`: Commit body (supports `\n` for newlines)
+
+Confirm the merge is successful; GitHub will automatically close related issues with `Closes #XX` keyword.
+
+### Step 6 — Verify Auto-Close
+
+GitHub automatically closes issues when a commit with `Closes #XX` lands on the default branch (`main`).
+
+To verify:
+```bash
+PAGER=cat GH_PAGER=cat gh issue view <ISSUE-NUMBER> --json state
+```
+
+Should show `state: CLOSED`.
+
+### Step 7 — Post Closing Message (Optional but Recommended)
+
+For better UX, manually post a summary comment to **each issue** before it auto-closes (since auto-close happens silently):
+
+```bash
+gh issue comment <ISSUE-NUMBER> --body "
+This has been fixed in PR #<PR-NUMBER>, which is now merged to main.
+
+**Solution Summary:**
+- <Key fix 1>
+- <Key fix 2>
+
+The fix will be available in the next plugin release. Thank you for reporting! ⭐
+"
+```
+
+### Step 8 — (Optional) Regenerate Release Notes
+
+If the merge revealed any final tweaks to release notes:
+
+```bash
+# Re-export release notes from merged commit
+git log --oneline -1 <merged-commit-sha>
+```
+
+If needed, create a follow-up PR with doc polish (do NOT force-push the merged commit).
+
+---
+
+## Merge Strategy Decision Tree
+
+```
+Is this a patch/hotfix release?
+├─ YES → Use --squash
+└─ NO → Multi-feature release?
+     ├─ YES → Use --squash (cleaner history)
+     └─ NO → Preserve detail? 
+          ├─ YES → Use --rebase
+          └─ NO → Use --merge (preserve PR context)
+```
+
+---
+
+## Issue Auto-Close Keywords
+
+These keywords in commit/PR messages will auto-close issues when merged to `main`:
+
+- `Closes #XX`
+- `Fixes #XX`
+- `Resolves #XX`
+- `close #XX` (case-insensitive)
+- `fix #XX`
+- `resolve #XX`
+
+**Important**: The keyword must be on the **final commit that lands on** `main`. For squash merges, it must be in the squash commit message body.
+
+---
+
+## Anti-Patterns to Avoid
+
+- ❌ Do NOT merge if any status checks are PENDING or FAILED
+- ❌ Do NOT merge if there are blocking reviews (reviewDecision: `CHANGES_REQUESTED`)
+- ❌ Do NOT merge without verifying the Conventional Commits format in the merge message
+- ❌ Do NOT merge without including `Closes #XX` keywords for all related issues
+- ❌ Do NOT assume issues will auto-close silently — post a courtesy comment first
+- ❌ Do NOT delete the branch if it might be needed for cherry-pick or hotfixes later
+
+---
+
+## Troubleshooting
+
+### Issue did not auto-close after merge
+- Verify the `Closes #XX` keyword is in the **final commit message** (use `git log` to check)
+- Ensure the commit is on the `main` branch
+- GitHub sometimes takes a few seconds to process; refresh the issue page
+
+### Multiple issues to close
+- List all in separate `Closes #XX` lines in the commit body
+- Each one will be independently auto-closed
+
+### Want to close issue without merge?
+- Use `gh issue close <ISSUE-NUMBER>` manually
+- Only recommended if the PR was manually reverted or deemed invalid

.gemini/skills/release-prep/SKILL.md

@@ -0,0 +1,149 @@
+---
+name: release-prep
+description: Orchestrates the full release preparation flow for a plugin — version sync across 7+ files, bilingual release notes creation, and commit message drafting. Use before submitting a PR. Does NOT push or create a PR; that is handled by pr-submitter.
+---
+
+# Release Prep
+
+## Overview
+
+This skill drives the complete pre-PR release pipeline. It enforces the repository rule that every release must synchronize the version number and changelog across **at least 7 locations** before a commit is created.
+
+## Scope
+
+This skill covers:
+1. Version sync (delegates detail to `version-bumper` if needed)
+2. Bilingual release notes file creation
+3. 7-location consistency verification
+4. Conventional Commits message drafting
+5. `git add -A && git commit` execution
+
+It **stops before** `git push` or `gh pr create`. Use the `pr-submitter` skill for those steps.
+
+---
+
+## Workflow
+
+### Step 1 — Collect Release Info
+
+Ask the user (or infer from current state) the following:
+- **Plugin name** and **type** (actions / filters / pipes / tools)
+- **New version number** (e.g., `0.8.0`)
+- **Key changes** in English and Chinese (1-5 bullet points each)
+
+If a `What's New` section already exists in README.md, extract it as the source of truth.
+
+### Step 2 — Sync Version Across 7 Locations
+
+Verify AND update the version string in all of the following. Mark each as ✅ or ❌:
+
+| # | File | Location |
+|---|------|----------|
+| 1 | `plugins/{type}/{name}/{name}.py` | `version:` in docstring |
+| 2 | `plugins/{type}/{name}/README.md` | `**Version:** x.x.x` metadata line |
+| 3 | `plugins/{type}/{name}/README_CN.md` | `**Version:** x.x.x` metadata line |
+| 4 | `docs/plugins/{type}/{name}.md` | `**Version:** x.x.x` metadata line |
+| 5 | `docs/plugins/{type}/{name}.zh.md` | `**Version:** x.x.x` metadata line |
+| 6 | `docs/plugins/{type}/index.md` | version badge for this plugin |
+| 7 | `docs/plugins/{type}/index.zh.md` | version badge for this plugin |
+
+Additionally update the root-level **updated date badge** in:
+- `README.md` — `![updated](https://img.shields.io/badge/YYYY--MM--DD-gray?style=flat)`
+- `README_CN.md` — same badge format
+
+Use today's date (`YYYY-MM-DD`) for the badge.
+
+### Step 3 — Update What's New (All 4 Doc Files)
+
+The `What's New` / `最新更新` section must contain **only the most recent release's changes**. Previous entries should be removed from this section (they live in CHANGELOG or release notes files).
+
+Update these 4 files' `What's New` / `最新更新` block consistently:
+- `plugins/{type}/{name}/README.md`
+- `plugins/{type}/{name}/README_CN.md`
+- `docs/plugins/{type}/{name}.md`
+- `docs/plugins/{type}/{name}.zh.md`
+
+### Step 4 — Create Bilingual Release Notes Files
+
+Create two versioned release notes files:
+
+**Path**: `plugins/{type}/{name}/v{version}.md`
+**Path**: `plugins/{type}/{name}/v{version}_CN.md`
+
+#### Required Sections
+
+Each file must include:
+0. **Marketplace Badge**: A prominent button linking to the plugin on openwebui.com using shields.io (e.g., `[![](https://img.shields.io/badge/OpenWebUI%20Community-Get%20Plugin-blue?style=for-the-badge)](URL)`).
+1. **Overview Header**: Use `## Overview` as the first header.
+2. **Summary Paragraph**: A paragraph summarizing the release. **NEVER** include the version number as a title.
+3. **README Link**: Direct link to the plugin's README file on GitHub.
+4. **New Features** / **新功能**: Bulleted list of features
+5. **Bug Fixes** / **问题修复**: Bulleted list of fixes
+6. **Related Issues** / **相关 Issue**: Link to GitHub Issues. **ONLY** include if a specific issue is resolved. **NEVER use placeholders.**
+7. **Related PRs** / **相关 PR**: Link to the Pull Request. **ONLY** include if the PR is already created and the ID is known. **NEVER use placeholders.**
+8. **Migration Notes**: Breaking changes or Valve key renames (omit section if none)
+
+---
+
+## Language Standard
+
+- **Release Notes Files**: Use **English ONLY** for the final `.md` files to maintain professional consistency on GitHub. Avoid bilingual content in the release description.
+6. **Companion Plugins** / **配套插件** (optional): If a companion plugin was updated
+
+If a release notes file already exists for this version, update it rather than creating a new one.
+
+### Step 5 — Verify Consistency (Pre-Commit Check)
+
+Run the consistency check script:
+
+```bash
+python3 scripts/check_version_consistency.py
+```
+
+If issues are found, fix them before proceeding. Do not commit with inconsistencies.
+
+### Step 6 — Draft Conventional Commits Message
+
+Generate the commit message following `commit-message.instructions.md` rules:
+- **Language**: English ONLY
+- **Format**: `type(scope): subject` + blank line + body bullets
+- **Scope**: use plugin folder name (e.g., `github-copilot-sdk`)
+- **Body**: 
+    - 1-3 bullets summarizing key changes
+    - Explicitly mention "READMEs and docs synced" if version was bumped
+    - **MUST** end with `Closes #XX` or `Fixes #XX` if an issue is being resolved.
+
+Present the full commit message to the user for review before executing.
+
+### Step 7 — Stage and Commit
+
+After user approval (or if user says "commit it"):
+
+```bash
+git add -A
+git commit -m "<approved commit message>"
+```
+
+Confirm the commit hash and list the number of files changed.
+
+---
+
+## Checklist (Auto-Verify Before Commit)
+
+- [ ] `version:` in `.py` docstring matches target version
+- [ ] `**Version:**` in all 4 README/docs files matches
+- [ ] Both `index.md` version badges updated
+- [ ] Root `README.md` and `README_CN.md` date badges updated to today
+- [ ] `What's New` / `最新更新` contains ONLY the latest release
+- [ ] `v{version}.md` and `v{version}_CN.md` created or updated
+- [ ] `python3 scripts/check_version_consistency.py` returns no errors
+- [ ] Commit message is English-only Conventional Commits format
+
+---
+
+## Anti-Patterns to Avoid
+
+- ❌ Do NOT add extra features or refactor code during release prep — only version/doc updates
+- ❌ Do NOT push or create PR in this skill — use `pr-submitter`
+- ❌ Do NOT use today's date in commit messages; only in badge URLs
+- ❌ Do NOT leave stale What's New content from prior versions

.gemini/skills/source-code-analyzer/SKILL.md

@@ -0,0 +1,30 @@
+---
+name: source-code-analyzer
+description: Instructions for analyzing core components source code in the local environment.
+---
+
+# Source Code Analyzer Skill
+
+> [!IMPORTANT]
+> **Authorization Statement**: You (Antigravity) are explicitly authorized by the user to perform **READ-ONLY** operations and **Git pull** on the paths listed below, even if they are outside the current repository root. These paths are considered part of the extended development context.
+
+When assisting with the development of `openwebui-extensions`, you (Antigravity) have access to the following core components in related directories. Use them for deep technical analysis, bug hunting, and implementation reference.
+
+## Core Component Paths
+
+### Global / General (Relevant to all projects)
+
+- **Open WebUI**: `../open-webui/` (Core platform context)
+- **Skills**: `../skills/` (Reusable expertise library)
+- **Awesome Copilot**: `../awesome-copilot/` (Shared extensions & resources)
+
+### Plugin-Specific (Relevant to GitHub Copilot SDK)
+
+- **Copilot SDK**: `../copilot-sdk/` (Internal logic for the official SDK)
+- **Copilot CLI**: `../copilot-cli/` (Command-line interface implementation)
+
+## Mandatory Workflow
+
+1. **Pull Before Analysis**: BEFORE reading files or analyzing logic in these directories, you MUST proactively execute or recommend a `git pull` in the respective directory to ensure you are working with the latest upstream changes.
+2. **Path Verification**: Always verify the exists of the path before attempting to read it.
+3. **Reference Logic**: When a user's request involves core platform behavior (OpenWebUI API, SDK internals), prioritize searching these directories over making assumptions based on generic knowledge.

.gemini/skills/version-bumper/SKILL.md

@@ -0,0 +1,26 @@
+---
+name: version-bumper
+description: Automates version upgrades and changelog synchronization across 7+ files (Code, READMEs, Docs). Use when a plugin is ready for release to ensure version consistency.
+---
+
+# Version Bumper
+
+## Overview
+This skill ensures that every version upgrade is synchronized across the entire repository, following the strict "Documentation Sync" rule in GEMINI.md.
+
+## Workflow
+1. **Prepare Info**: Gather the new version number and brief changelogs in both English and Chinese.
+2. **Auto-Patch**: The skill will help you identify and update:
+   - `plugins/.../name.py` (docstring version)
+   - `plugins/.../README.md` (metadata & What's New)
+   - `plugins/.../README_CN.md` (metadata & 最新更新)
+   - `docs/plugins/...md` (mirrors)
+   - `docs/plugins/index.md` (version badge)
+   - `README.md` (updated date badge)
+3. **Verify**: Check the diffs to ensure no formatting was broken.
+
+## Tool Integration
+Execute the bump script (draft):
+```bash
+python3 scripts/bump.py <version> "<message_en>" "<message_zh>"
+```

.gemini/skills/version-bumper/scripts/bump.py

@@ -0,0 +1,70 @@
+#!/usr/bin/env python3
+import sys
+import os
+import re
+from datetime import datetime
+
+def patch_file(file_path, old_pattern, new_content, is_regex=False):
+    if not os.path.exists(file_path):
+        print(f"Warning: File not found: {file_path}")
+        return False
+    
+    with open(file_path, 'r', encoding='utf-8') as f:
+        content = f.read()
+    
+    if is_regex:
+        new_content_result = re.sub(old_pattern, new_content, content, flags=re.MULTILINE)
+    else:
+        new_content_result = content.replace(old_pattern, new_content)
+    
+    if new_content_result != content:
+        with open(file_path, 'w', encoding='utf-8') as f:
+            f.write(new_content_result)
+        print(f"✅ Patched: {file_path}")
+        return True
+    else:
+        print(f"ℹ️ No change needed: {file_path}")
+        return False
+
+def bump_version(plugin_type, plugin_name, new_version, msg_en, msg_zh):
+    print(f"🚀 Bumping {plugin_name} ({plugin_type}) to {new_version}...")
+    
+    today = datetime.now().strftime("%Y-%m-%d")
+    today_badge = today.replace("-", "--")
+    
+    # 1. Patch Plugin Python File
+    py_file = f"plugins/{plugin_type}/{plugin_name}/{plugin_name}.py"
+    patch_file(py_file, r"version: \d+\.\d+\.\d+", f"version: {new_version}", is_regex=True)
+    
+    # 2. Patch Plugin READMEs
+    readme_en = f"plugins/{plugin_type}/{plugin_name}/README.md"
+    readme_zh = f"plugins/{plugin_type}/{plugin_name}/README_CN.md"
+    
+    # Update version in metadata
+    patch_file(readme_en, r"\*\*Version:\*\* \d+\.\d+\.\d+", f"**Version:** {new_version}", is_regex=True)
+    patch_file(readme_zh, r"\*\*版本:\*\* \d+\.\d+\.\d+", f"**版本:** {new_version}", is_regex=True)
+    
+    # Update What's New (Assuming standard headers)
+    patch_file(readme_en, r"## 🔥 What's New in v.*?\n", f"## 🔥 What's New in v{new_version}\n\n* {msg_en}\n", is_regex=True)
+    patch_file(readme_zh, r"## 🔥 最新更新 v.*?\n", f"## 🔥 最新更新 v{new_version}\n\n* {msg_zh}\n", is_regex=True)
+    
+    # 3. Patch Docs Mirrors
+    doc_en = f"docs/plugins/{plugin_type}/{plugin_name}.md"
+    doc_zh = f"docs/plugins/{plugin_type}/{plugin_name}.zh.md"
+    patch_file(doc_en, r"\*\*Version:\*\* \d+\.\d+\.\d+", f"**Version:** {new_version}", is_regex=True)
+    patch_file(doc_zh, r"\*\*版本:\*\* \d+\.\d+\.\d+", f"**版本:** {new_version}", is_regex=True)
+    
+    # 4. Patch Root READMEs (Updated Date Badge)
+    patch_file("README.md", r"badge/202\d--\d\d--\d\d-gray", f"badge/{today_badge}-gray", is_regex=True)
+    patch_file("README_CN.md", r"badge/202\d--\d\d--\d\d-gray", f"badge/{today_badge}-gray", is_regex=True)
+
+    print("\n✨ All synchronization tasks completed.")
+    return True
+
+if __name__ == "__main__":
+    if len(sys.argv) < 6:
+        print("Usage: bump.py <type> <name> <version> <msg_en> <msg_zh>")
+        print("Example: bump.py filters markdown_normalizer 1.2.8 'Fix bug' '修复错误'")
+        sys.exit(1)
+    
+    bump_version(sys.argv[1], sys.argv[2], sys.argv[3], sys.argv[4], sys.argv[5])

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -0,0 +1,165 @@
+name: 🐛 Bug Report
+description: Report a bug or issue with OpenWebUI plugins
+title: "[BUG] "
+labels: ["bug"]
+assignees: []
+
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for reporting a bug! Please provide clear information to help us reproduce and fix the issue.
+
+  - type: dropdown
+    id: plugin-type
+    attributes:
+      label: Plugin Type
+      description: Which type of plugin is affected?
+      options:
+        - Action
+        - Filter
+        - Pipe
+        - Pipeline
+        - Tool
+        - Other
+    validations:
+      required: true
+
+  - type: dropdown
+    id: plugin-name
+    attributes:
+      label: Plugin Name
+      description: Which plugin has the issue?
+      options:
+        - "Select a plugin..."
+        - "Action - Deep Dive"
+        - "Action - Export to Word Enhanced"
+        - "Action - Export to Excel"
+        - "Action - Flash Card"
+        - "Action - Smart Infographic"
+        - "Action - Smart Mind Map"
+        - "Filter - Async Context Compression"
+        - "Filter - Context & Model Enhancement Filter"
+        - "Filter - Folder Memory"
+        - "Filter - GitHub Copilot SDK Files Filter"
+        - "Filter - Markdown Normalizer"
+        - "Filter - Gemini Multimodel Filter"
+        - "Pipeline - MOE Prompt Refiner"
+        - "Pipe - GitHub Copilot SDK"
+        - "Pipe - iFlow SDK"
+        - "Tool - OpenWebUI Skills Manager"
+        - "Tool - Smart Infographic Tool"
+        - "Tool - Smart Mind Map Tool"
+        - "Other / Not Listed"
+    validations:
+      required: true
+
+  - type: input
+    id: plugin-name-other
+    attributes:
+      label: Plugin Name (if not in list)
+      description: If you selected 'Other / Not Listed', please specify the plugin name
+      placeholder: "Plugin name"
+    validations:
+      required: false
+
+  - type: textarea
+    id: description
+    attributes:
+      label: Description
+      description: Clearly describe the bug. What went wrong? What did you expect?
+      placeholder: |
+        I tried to use [feature], but instead of [expected behavior], it [actual behavior].
+        
+        Error message (if any):
+    validations:
+      required: true
+
+  - type: textarea
+    id: steps
+    attributes:
+      label: Steps to Reproduce
+      description: How can we reproduce this issue?
+      placeholder: |
+        1. Click on...
+        2. Enter...
+        3. See error...
+    validations:
+      required: true
+
+  - type: input
+    id: openwebui-version
+    attributes:
+      label: OpenWebUI Version
+      description: What version of OpenWebUI are you using?
+      placeholder: "e.g., 0.3.0 or main"
+    validations:
+      required: true
+
+  - type: textarea
+    id: environment
+    attributes:
+      label: Operating System & Container
+      description: "Your operating system and deployment method"
+      placeholder: |
+        Example 1:
+        OS: macOS 14.3
+        Container: Docker (version 24.0.x)
+        
+        Example 2:
+        OS: Ubuntu 22.04 LTS
+        Deployment: Docker Compose
+    validations:
+      required: true
+
+  - type: markdown
+    attributes:
+      value: |
+        ## 📋 Debug Information (Optional)
+        
+        To help diagnose the issue faster, please provide relevant logs:
+        
+        **Frontend Console Logs** (Recommended):
+        1. Enable: Click avatar → Settings → General → Enable Plugin Debug Output
+        2. Open DevTools: Press `F12` (or `Cmd+Option+I` on Mac)
+        3. Go to Console tab and copy any error messages or `🛠️ Debug` output
+        
+        **Server-Side Logs**:
+        - Docker: `docker logs <container-id>`
+        - Local: Check terminal output or log files
+
+  - type: textarea
+    id: logs
+    attributes:
+      label: Error Logs (Optional)
+      description: "Paste frontend console or server logs that show the error"
+      placeholder: |
+        Error message from console:
+        [Your logs here]
+      render: bash
+    validations:
+      required: false
+
+  - type: textarea
+    id: additional
+    attributes:
+      label: Additional Information (Optional)
+      description: "Screenshots, related issues, or other helpful details"
+      placeholder: |
+        - Screenshots (if applicable)
+        - Related issues or discussions
+        - Steps you've already tried to fix it
+    validations:
+      required: false
+
+  - type: checkboxes
+    id: checklist
+    attributes:
+      label: Checklist
+      options:
+        - label: I have searched for duplicate issues
+          required: true
+        - label: I have provided clear reproduction steps
+          required: true
+        - label: I have mentioned OpenWebUI version and OS/container info
+          required: true

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,11 @@
+blank_issues_enabled: false
+contact_links:
+  - name: Documentation
+    url: https://docs.openwebui.com/
+    about: Official OpenWebUI documentation
+  - name: Discussions
+    url: https://github.com/Fu-Jie/openwebui-extensions/discussions
+    about: Ask questions and discuss with the community
+  - name: OpenWebUI Repository
+    url: https://github.com/open-webui/open-webui
+    about: Main OpenWebUI project

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -0,0 +1,104 @@
+name: ✨ Feature Request
+description: Suggest a new feature or improvement
+title: "[FEATURE] "
+labels: ["enhancement"]
+assignees: []
+
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for your suggestion! Please describe the feature you'd like to see.
+
+  - type: dropdown
+    id: plugin-type
+    attributes:
+      label: Plugin Type (Optional)
+      description: Is this for a specific plugin type?
+      options:
+        - Action
+        - Filter
+        - Pipe
+        - Pipeline
+        - Tool
+        - Core/General
+        - Documentation
+        - Other
+    validations:
+      required: false
+
+  - type: dropdown
+    id: plugin-name
+    attributes:
+      label: Plugin Name (Optional)
+      description: Which plugin would benefit from this feature?
+      options:
+        - "Select a plugin..."
+        - "Action - Deep Dive"
+        - "Action - Export to Word Enhanced"
+        - "Action - Export to Excel"
+        - "Action - Flash Card"
+        - "Action - Smart Infographic"
+        - "Action - Smart Mind Map"
+        - "Filter - Async Context Compression"
+        - "Filter - Context & Model Enhancement Filter"
+        - "Filter - Folder Memory"
+        - "Filter - GitHub Copilot SDK Files Filter"
+        - "Filter - Markdown Normalizer"
+        - "Filter - Gemini Multimodel Filter"
+        - "Pipeline - MOE Prompt Refiner"
+        - "Pipe - GitHub Copilot SDK"
+        - "Pipe - iFlow SDK"
+        - "Tool - OpenWebUI Skills Manager"
+        - "Tool - Smart Infographic Tool"
+        - "Tool - Smart Mind Map Tool"
+        - "Core/General Improvement"
+        - "Other / Not Listed"
+    validations:
+      required: false
+
+  - type: textarea
+    id: description
+    attributes:
+      label: Feature Description
+      description: Clearly describe the feature you're requesting
+      placeholder: |
+        What feature would you like to see?
+        How would it work?
+    validations:
+      required: true
+
+  - type: textarea
+    id: motivation
+    attributes:
+      label: Motivation & Use Case
+      description: Why is this feature important? What problem does it solve?
+      placeholder: |
+        What's the pain point this solves?
+        How would it improve your workflow?
+        Who else would benefit from this?
+    validations:
+      required: true
+
+  - type: textarea
+    id: additional
+    attributes:
+      label: Additional Information (Optional)
+      description: "Mockups, alternatives considered, references, or examples"
+      placeholder: |
+        - Links to related plugins or tools
+        - Screenshots or mockups
+        - Alternative approaches you've considered
+        - Code examples or references
+    validations:
+      required: false
+
+  - type: checkboxes
+    id: checklist
+    attributes:
+      label: Checklist
+      options:
+        - label: I have searched existing issues/discussions for similar requests
+          required: true
+        - label: This feature would be useful for multiple users
+          required: false

.github/TEMP_FILES_POLICY.md

@@ -0,0 +1,121 @@
+# Temporary Files Handling Policy
+
+**Last Updated**: 2026-02-26  
+**Status**: Active Guideline
+
+## Overview
+
+All temporary files created during skill execution or development workflows must follow this centralized policy to maintain project cleanliness and workspace isolation alignment.
+
+## Core Rule
+
+**Temporary files MUST be stored in the project's `.temp/` directory, NOT in system directories like `/tmp`.**
+
+## Rationale
+
+1. **Workspace Isolation**: Aligns with OpenWebUI's workspace-per-user model
+2. **Project Cohesion**: All project artifacts (temporary or permanent) stay within project boundaries
+3. **Multi-User Safety**: Avoids conflicts between multiple developers using the same system
+4. **Cleanup Traceability**: Easy to verify all temp files are cleaned up via single `.temp/` directory
+5. **Debugging**: Inspectable before deletion if issues occur
+
+## Usage Pattern
+
+### Creating Temp File
+
+```bash
+# Step 1: Ensure temp directory exists
+mkdir -p .temp
+
+# Step 2: Write temp file
+cat > .temp/my_temp_file.md << 'EOF'
+...content...
+EOF
+
+# Step 3: Use the file in your workflow
+# (e.g., pass to gh CLI, process with script, etc.)
+```
+
+### Cleanup After Use
+
+```bash
+# Remove individual temp files
+rm -f .temp/my_temp_file.md
+
+# Or full cleanup of entire temp directory
+rm -rf .temp/
+```
+
+## Skills Affected
+
+| Skill | Implementation | Status |
+|-------|----------------|--------|
+| `pr-submitter` | PR body file (`.temp/pr_body.md`) | ✅ Updated |
+| `release-prep` | Draft notes (if any) | ✅ Policy Added |
+| `version-bumper` | Backup files (if any) | ℹ️ Check needed |
+| Future skills | TBD | 📋 Must follow policy |
+
+## .gitignore Configuration
+
+The following entry in `.gitignore` ensures temp files are never committed:
+
+```
+# Temporary files
+.temp/
+.build/
+```
+
+## Examples
+
+### Example 1: PR Submitter Skill
+```bash
+# Create PR body in temp directory
+mkdir -p .temp
+cat > .temp/pr_body.md << 'EOF'
+## Summary
+New feature implementation
+EOF
+
+# Use with gh CLI
+gh pr create --body-file .temp/pr_body.md --title "feat: new feature"
+
+# Cleanup
+rm -f .temp/pr_body.md
+```
+
+### Example 2: Release Prepare Workflow
+```bash
+# Create draft changelog
+mkdir -p .temp
+cat > .temp/changelog_draft.md << 'EOF'
+# v1.0.0 Release Notes
+EOF
+
+# Edit, validate, then integrate into real files
+# ...
+
+# Cleanup
+rm -f .temp/changelog_draft.md
+```
+
+## Anti-Patterns (❌ Don't Do This)
+
+- ❌ Writing temp files to `/tmp` — will be lost/orphaned
+- ❌ Writing to root directory or `plugins/` — pollutes repo
+- ❌ Not cleaning up temp files — accumulates clutter
+- ❌ Committing `.temp/` files to git — defeats the purpose
+- ❌ Using absolute paths — breaks workflow portability
+
+## Enforcement
+
+1. **Code Review**: PRs should verify no `/tmp` references in scripts
+2. **CI/CD**: Setup can validate `.temp/` cleanup via git status before commit
+3. **Documentation**: All skill docs must reference this policy (link to this file)
+4. **Automated**: Consider adding pre-commit hook to ensure `.temp/` is not staged
+
+## Questions / Clarifications
+
+For questions about this policy, refer to:
+- `.github/skills/pr-submitter/SKILL.md` — Practical example
+- `.github/skills/release-prep/SKILL.md` — Policy integration
+- `/memories/repo/temp-file-handling-convention.md` — Internal notes

.github/agents/plugin-implementer.agent.md

@@ -0,0 +1,67 @@
+---
+name: Plugin Implementer
+description: Implement OpenWebUI plugin and docs updates with strict project standards
+argument-hint: Provide approved plan or feature request to implement
+tools: ['execute/getTerminalOutput', 'execute/runInTerminal', 'read/readFile', 'read/terminalSelection', 'read/terminalLastCommand', 'edit/createFile', 'edit/editFiles', 'search', 'web', 'web/fetch', 'web/githubRepo', 'agent']
+infer: true
+handoffs:
+  - label: Run Review
+    agent: Plugin Reviewer
+    prompt: Review the implementation for i18n, safety, and consistency issues.
+    send: false
+---
+You are the **implementation specialist** for the `openwebui-extensions` repository.
+
+## Execution Rules
+1. **Minimal diffs**: Change only what the approved plan specifies.
+2. **Single-file i18n**: Every plugin is one `.py` file with built-in `TRANSLATIONS` dict. Never create `_cn.py` split files.
+3. **Context helpers**: Always use `_get_user_context(__user__)` and `_get_chat_context(body, __metadata__)` — never access dict keys directly.
+4. **Emitter guards**: Every `await emitter(...)` must be guarded by `if emitter:`.
+5. **Logging**: Use `logging.getLogger(__name__)` — no bare `print()` in production code.
+6. **Async safety**: Wrap all `__event_call__` with `asyncio.wait_for(..., timeout=2.0)` + inner JS `try { ... } catch(e) { return fallback; }`.
+
+## Required Plugin Pattern
+```python
+# Docstring: title, author, author_url, funding_url, version, description
+# icon_url is REQUIRED for Action plugins (Lucide SVG, base64)
+
+class Action:  # or Filter / Pipe
+    class Valves(BaseModel):
+        SHOW_STATUS: bool = Field(default=True, description="...")
+        # All fields UPPER_SNAKE_CASE
+
+    def __init__(self):
+        self.valves = self.Valves()
+
+    def _get_user_context(self, __user__): ...   # always implement
+    def _get_chat_context(self, body, __metadata__=None): ...  # always implement
+    async def _emit_status(self, emitter, description, done=False): ...
+    async def _emit_notification(self, emitter, content, ntype="info"): ...
+```
+
+## Known Split-File Plugins (Legacy — Do NOT Add More)
+These still have `_cn.py` files. When touching any of them, migrate CN content into `TRANSLATIONS` dict:
+- `plugins/actions/deep-dive/deep_dive_cn.py`
+- `plugins/actions/export_to_docx/export_to_word_cn.py`
+- `plugins/actions/export_to_excel/export_to_excel_cn.py`
+- `plugins/actions/flash-card/flash_card_cn.py`
+- `plugins/actions/infographic/infographic_cn.py`
+- `plugins/filters/folder-memory/folder_memory_cn.py`
+
+## Version Bump Rule
+Only bump version when user explicitly says "发布" / "release" / "bump version".
+When bumping, update ALL 7+ files (code docstring + 2× README + 2× doc detail + 2× doc index + 2× root README date badge).
+
+## Git Policy
+- Never run `git commit`, `git push`, or create PRs automatically.
+- After all edits, list what changed and why, then stop.
+
+## Knowledge Capture (Mandatory)
+Before ending the session, if you discovered any non-obvious internal API behaviour,
+parameter injection quirk, or workaround, save it to `.agent/learnings/{topic}.md`.
+Also browse `.agent/learnings/` at the start to reuse existing knowledge.
+
+## Completion Output
+- Modified files (full relative paths, one-line descriptions)
+- Remaining manual checks
+- Suggested handoff to **Plugin Reviewer**

.github/agents/plugin-planner.agent.md

@@ -0,0 +1,78 @@
+---
+name: Plugin Planner
+description: Analyze requirements and produce a safe implementation plan for OpenWebUI plugins
+argument-hint: Describe the plugin goal, constraints, and target files
+tools: ['read/readFile', 'search', 'web', 'web/githubRepo', 'read/terminalLastCommand', 'read/terminalSelection', 'agent']
+handoffs:
+  - label: Start Implementation
+    agent: Plugin Implementer
+    prompt: Implement the approved plan step by step with minimal diffs.
+    send: false
+---
+You are the **planning specialist** for the `openwebui-extensions` repository.
+
+## Your Responsibilities
+1. Read existing plugin code and docs **before** proposing any change.
+2. Produce a **small, reversible** plan (one logical change per file per step).
+3. Clearly list all impacted files including the docs sync chain.
+4. Flag risks: breaking changes, release implications, version bumps needed.
+
+## Hard Rules
+- Never propose `git commit`, `git push`, or PR creation.
+- Every plan must end with an acceptance checklist for the user to approve before handing off.
+- Reference `.github/copilot-instructions.md` as the authoritative spec.
+- Browse `.agent/learnings/` **first** to reuse existing knowledge before researching anything.
+
+## Repository Plugin Inventory
+
+### Actions (`plugins/actions/`)
+| Dir | Main file | Version | i18n status |
+|-----|-----------|---------|-------------|
+| `deep-dive` | `deep_dive.py` | 1.0.0 | ⚠️ has `deep_dive_cn.py` split |
+| `export_to_docx` | `export_to_word.py` | 0.4.4 | ⚠️ has `export_to_word_cn.py` split |
+| `export_to_excel` | `export_to_excel.py` | 0.3.7 | ⚠️ has `export_to_excel_cn.py` split |
+| `flash-card` | `flash_card.py` | 0.2.4 | ⚠️ has `flash_card_cn.py` split |
+| `infographic` | `infographic.py` | 1.5.0 | ⚠️ has `infographic_cn.py` split |
+| `smart-mind-map` | `smart_mind_map.py` | 1.0.0 | ✅ single file |
+| `smart-mermaid` | _(empty stub)_ | — | — |
+
+### Filters (`plugins/filters/`)
+| Dir | Main file | Version | i18n status |
+|-----|-----------|---------|-------------|
+| `async-context-compression` | `async_context_compression.py` | 1.3.0 | ✅ |
+| `context_enhancement_filter` | `context_enhancement_filter.py` | 0.3 | ⚠️ non-SemVer version |
+| `copilot_files_preprocessor` | _(empty stub)_ | — | — |
+| `folder-memory` | `folder_memory.py` | 0.1.0 | ⚠️ has `folder_memory_cn.py` split |
+| `github_copilot_sdk_files_filter` | `github_copilot_sdk_files_filter.py` | 0.1.2 | ✅ |
+| `markdown_normalizer` | `markdown_normalizer.py` | 1.2.4 | ✅ |
+| `web_gemini_multimodel_filter` | `web_gemini_multimodel.py` | 0.3.2 | ✅ |
+
+### Pipes / Pipelines / Tools
+| Path | Main file | Version |
+|------|-----------|---------|
+| `pipes/github-copilot-sdk` | `github_copilot_sdk.py` | 0.7.0 |
+| `pipelines/moe_prompt_refiner` | `moe_prompt_refiner.py` | — |
+| `tools/workspace-file-manager` | `workspace_file_manager.py` | 0.2.0 |
+
+## Naming Conventions (Actual Mix)
+- Action dirs: some use **dashes** (`deep-dive`, `flash-card`, `smart-mind-map`), some **underscores** (`export_to_docx`, `export_to_excel`, `infographic`)
+- Filter dirs: similarly mixed — prefer underscores for new plugins
+- Main `.py` filenames always use **underscores**
+
+## Docs Sync Chain (for every plugin change)
+For `plugins/{type}/{name}/`, these 7+ files must stay in sync:
+1. `plugins/{type}/{name}/{name}.py` — version in docstring
+2. `plugins/{type}/{name}/README.md` — version + What's New
+3. `plugins/{type}/{name}/README_CN.md` — version + 最新更新
+4. `docs/plugins/{type}/{name}.md`
+5. `docs/plugins/{type}/{name}.zh.md`
+6. `docs/plugins/{type}/index.md` — version badge
+7. `docs/plugins/{type}/index.zh.md` — version badge
+8. Root `README.md` / `README_CN.md` — date badge
+
+## Output Format
+- **Scope summary**
+- **Affected files** (full relative paths)
+- **Step-by-step plan** (numbered, ≤10 steps)
+- **Risk flags** (version bump? breaking change? split-file migration needed?)
+- **Acceptance checklist** → user must approve before handoff to Implementer

.github/agents/plugin-reviewer.agent.md

@@ -0,0 +1,75 @@
+---
+name: Plugin Reviewer
+description: Perform strict repository-aligned code review for OpenWebUI plugin changes
+argument-hint: Share changed files or branch diff to review
+tools: ['search', 'read/readFile', 'web', 'web/fetch', 'web/githubRepo', 'execute/getTerminalOutput', 'read/terminalLastCommand', 'read/terminalSelection']
+infer: true
+handoffs:
+  - label: Prepare Release Draft
+    agent: Release Prep
+    prompt: Create a bilingual release draft and commit message based on reviewed changes.
+    send: false
+---
+You are the **review specialist** for the `openwebui-extensions` repository.
+
+Full review rules are in .github/instructions/code-review.instructions.md.
+
+## Review Checklist
+
+### 🔴 Blocking (must fix before release)
+
+**1. Single-file i18n Architecture**
+- [ ] No new `_cn.py` split files created.
+- [ ] All user-visible strings go through `TRANSLATIONS[lang].get(key, fallback)`.
+- [ ] `FALLBACK_MAP` covers at least `zh → zh-CN` and `en → en-US`.
+- [ ] `format(**kwargs)` on translations wrapped in `try/except KeyError`.
+
+**2. Context Helpers**
+- [ ] Uses `_get_user_context(__user__)` (not `__user__["name"]` directly).
+- [ ] Uses `_get_chat_context(body, __metadata__)` (not ad-hoc `body.get("chat_id")`).
+
+**3. Antigravity Safety**
+- [ ] Every `__event_call__` wrapped: `asyncio.wait_for(..., timeout=2.0)`.
+- [ ] JS code passed to `__event_call__` has `try { ... } catch(e) { return fallback; }`.
+- [ ] File path operations validated against workspace root (no traversal).
+- [ ] Upload paths have dual-channel fallback (API → DB/local).
+
+**4. Emitter Guards**
+- [ ] Every `await emitter(...)` guarded by `if emitter:`.
+- [ ] `_emit_status(done=False)` on start, `done=True` on success, `_emit_notification("error")` on failure.
+- [ ] No bare `print()` — use `logging.getLogger(__name__)`.
+
+**5. Filter Singleton Safety**
+- [ ] No mutable per-request state stored on `self` in Filter plugins.
+
+**6. Streaming Compatibility (OpenWebUI 0.8.x)**
+- [ ] `</think>` tag closed before any normal text or tool cards.
+- [ ] `<details type="tool_calls" ...>` attributes escape `"` as `&quot;`.
+- [ ] `<details ...>` block has newline immediately after `>`.
+
+**7. Version & Docs Sync**
+- [ ] Version bumped in docstring (if release).
+- [ ] `README.md` + `README_CN.md` updated (What's New + version).
+- [ ] `docs/plugins/{type}/{name}.md` and `.zh.md` match README.
+- [ ] `docs/plugins/{type}/index.md` and `.zh.md` version badges updated.
+- [ ] Root `README.md` / `README_CN.md` date badge updated.
+
+**8. Knowledge Capture**
+- [ ] Any non-obvious findings (API contracts, injection quirks, gotchas) documented in `.agent/learnings/{topic}.md`.
+
+### 🟡 Non-blocking (suggestions)
+- Copilot SDK tools: `params_type=MyParams` in `define_tool()`.
+- Long tasks (>3s): periodic `_emit_notification("info")` every 5s.
+- `icon_url` present for Action plugins (Lucide SVG, base64).
+
+## Known Pre-existing Issues (Don't block on unless the PR introduces new ones)
+- `_cn.py` splits in: `deep-dive`, `export_to_docx`, `export_to_excel`, `flash-card`, `infographic`, `folder-memory` — legacy, not new.
+- `context_enhancement_filter` version is `0.3` (non-SemVer) — pre-existing.
+- `copilot_files_preprocessor` and `smart-mermaid` are empty stubs — pre-existing.
+
+## Review Output
+- **Blocking issues** (file:line references)
+- **Non-blocking suggestions**
+- **Pass / Fail verdict**
+- **Knowledge captured?** (`.agent/learnings/` updated if any discoveries were made)
+- **Next step**: Pass → handoff to Release Prep; Fail → return to Implementer with fix list

.github/agents/release-prep.agent.md

@@ -0,0 +1,105 @@
+---
+name: Release Prep
+description: Prepare release-ready summaries and Conventional Commit drafts without pushing
+argument-hint: Provide final change list and target version (optional)
+tools: ['search', 'read/readFile', 'web', 'web/fetch', 'web/githubRepo', 'execute/getTerminalOutput', 'read/terminalLastCommand', 'read/terminalSelection']
+infer: true
+---
+You are the **release preparation specialist** for the `openwebui-extensions` repository.
+
+Full commit message rules: .github/instructions/commit-message.instructions.md
+Full release workflow: .agent/workflows/plugin-development.md
+
+## Responsibilities
+1. Generate a Conventional Commit message (English only).
+2. Draft bilingual release notes (EN + 中文).
+3. Verify ALL file sync locations are updated.
+4. **Stop before any commit or push** — wait for explicit user confirmation.
+
+## Commit Message Format
+```text
+type(scope): brief imperative description
+
+- Key change 1
+- Key change 2 (include migration note if needed)
+```
+- `type`: `feat` / `fix` / `docs` / `refactor` / `chore`
+- `scope`: plugin folder name (e.g., `smart-mind-map`, `github-copilot-sdk`, `folder-memory`)
+- Title ≤ 72 chars, imperative mood, no trailing period, no capital first letter
+
+## 9-File Sync Checklist (fill in for each changed plugin)
+```text
+Plugin: {type}/{name} → v{new_version}
+[ ] 1. plugins/{type}/{name}/{name}.py          → version in docstring
+[ ] 2. plugins/{type}/{name}/README.md          → version + What's New
+[ ] 3. plugins/{type}/{name}/README_CN.md       → version + 最新更新
+[ ] 4. docs/plugins/{type}/{name}.md            → mirrors README
+[ ] 5. docs/plugins/{type}/{name}.zh.md         → mirrors README_CN
+[ ] 6. docs/plugins/{type}/index.md             → version badge updated
+[ ] 7. docs/plugins/{type}/index.zh.md          → version badge updated
+[ ] 8. README.md (root)                         → date badge updated
+[ ] 9. README_CN.md (root)                      → date badge updated
+```
+
+## Current Plugin Versions (as of last audit — 2026-02-23)
+| Plugin | Type | Version | Note |
+|--------|------|---------|------|
+| deep-dive | action | 1.0.0 | has `_cn.py` split |
+| export_to_docx | action | 0.4.4 | has `_cn.py` split |
+| export_to_excel | action | 0.3.7 | has `_cn.py` split |
+| flash-card | action | 0.2.4 | has `_cn.py` split |
+| infographic | action | 1.5.0 | has `_cn.py` split |
+| smart-mind-map | action | 1.0.0 | ✅ |
+| async-context-compression | filter | 1.3.0 | ✅ |
+| context_enhancement_filter | filter | 0.3 | ⚠️ non-SemVer |
+| folder-memory | filter | 0.1.0 | has `_cn.py` split |
+| github_copilot_sdk_files_filter | filter | 0.1.2 | ✅ |
+| markdown_normalizer | filter | 1.2.4 | ✅ |
+| web_gemini_multimodel_filter | filter | 0.3.2 | ✅ |
+| github-copilot-sdk | pipe | 0.7.0 | ✅ |
+| workspace-file-manager | tool | 0.2.0 | ✅ |
+
+## Output Template
+
+### Commit Message
+```text
+{type}({scope}): {description}
+
+- {change 1}
+- {change 2}
+```
+
+### Change Summary (EN)
+- {bullet list of user-visible changes}
+
+### 变更摘要（中文）
+- {中文要点列表}
+
+### Verification Status
+{filled-in 9-file checklist for each changed plugin}
+
+## Post-Release: Batch Plugin Installation
+
+After release is published, users can quickly install all plugins:
+
+```bash
+# Clone the repository
+git clone https://github.com/Fu-Jie/openwebui-extensions.git
+cd openwebui-extensions
+
+# Setup API key and instance URL
+echo "api_key=sk-your-api-key-here" > scripts/.env
+echo "url=http://localhost:3000" >> scripts/.env
+
+# If using remote instance, configure the baseURL:
+# echo "url=http://192.168.1.10:3000" >> scripts/.env
+# echo "url=https://openwebui.example.com" >> scripts/.env
+
+# Install all plugins at once
+python scripts/install_all_plugins.py
+```
+
+See: [Deployment Guide](./scripts/DEPLOYMENT_GUIDE.md)
+
+---
+⚠️ **Waiting for user confirmation — no git operations will run until explicitly approved.**

.github/copilot-instructions.md

@@ -1,4 +1,4 @@
-# Copilot Instructions for awesome-openwebui
+# Copilot Instructions for openwebui-extensions
 
 本文档定义了 OpenWebUI 插件开发的标准规范和最佳实践。Copilot 在生成代码或文档时应遵循这些准则。
 
@@ -8,45 +8,57 @@ This document defines the standard conventions and best practices for OpenWebUI
 
 ## 🏗️ 项目结构与命名 (Project Structure & Naming)
 
-### 1. 双语版本要求 (Bilingual Version Requirements)
+### 1. 语言与代码规范 (Language & Code Requirements)
 
 #### 插件代码 (Plugin Code)
 
-每个插件必须提供两个版本：
+每个插件**必须**采用单文件国际化 (i18n) 设计。严禁为不同语言创建独立的源代码文件（如 `_cn.py`）。
 
-1. **英文版本**: `plugin_name.py` - 英文界面、提示词和注释
-2. **中文版本**: `plugin_name_cn.py` - 中文界面、提示词和注释
+1.  **单代码文件**: `plugins/{type}/{name}/{name}.py`
+2.  **内置 i18n**: 必须在代码中根据前端传来的用户语言（如 `__user__` 中的 `language` 或通过 `get_user_language` 脚本读取）动态切换界面显示、提示词和状态日志。
 
-示例：
+示例目录结构：
 ```
 plugins/actions/export_to_docx/
-├── export_to_word.py      # English version
-├── export_to_word_cn.py    # Chinese version
-├── README.md               # English documentation
-└── README_CN.md            # Chinese documentation
+├── export_to_word.py      # 单个代码文件，内置多语言支持
+├── README.md               # 英文文档 (English documentation)
+└── README_CN.md            # 中文文档
 ```
 
 #### 文档 (Documentation)
 
-每个插件目录必须包含双语 README 文件：
+尽管代码是合一的，但为了市场展示和 SEO，每个插件目录仍**必须**包含双语 README 文件：
 
 - `README.md` - English documentation
 - `README_CN.md` - 中文文档
 
+#### 文档交付与审阅 (Documentation Delivery for Review)
+
+当任务涉及文档类内容时，例如 README、Guide、Post、Release Notes、Announcement、Development Docs：
+
+- **必须**同时提供英文版与中文版，方便审阅与校对。
+- 若仓库最终只提交英文文件，也**必须**在对话中额外提供中文版草稿给维护者 review。
+- 若用户未明确指定只保留单语文件，默认按双语交付处理。
+- 中文版的目标是**便于审阅**，应忠实对应英文原意，可在表达上自然调整，但不得遗漏风险、限制、步骤或结论。
+
 #### README 结构规范 (README Structure Standard)
 
 所有插件 README 必须遵循以下统一结构顺序：
 
 1.  **标题 (Title)**: 插件名称，带 Emoji 图标
 2.  **元数据 (Metadata)**: 作者、版本、项目链接 (一行显示)
-    - 格式: `**Author:** [Fu-Jie](https://github.com/Fu-Jie) | **Version:** x.x.x | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)`
+    - 格式: `**Author:** [Fu-Jie](https://github.com/Fu-Jie) | **Version:** x.x.x | **Project:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions)`
     - **注意**: Author 和 Project 为固定值，仅需更新 Version 版本号
 3.  **描述 (Description)**: 一句话功能介绍
-4.  **最新更新 (What's New)**: **必须**放在描述之后，显著展示最新版本的变更点 (仅展示最近 3 次更新)
+4.  **最新更新 (What's New)**: **必须**放在描述之后，仅展示**最近 1 次**更新
 5.  **核心特性 (Key Features)**: 使用 Emoji + 粗体标题 + 描述格式
 6.  **使用方法 (How to Use)**: 按步骤说明
 7.  **配置参数 (Configuration/Valves)**: 使用表格格式，包含参数名、默认值、描述
-8.  **其他 (Others)**: 支持的模板类型、语法示例、故障排除等
+8.  **支持 (Support)**: **必须**包含，放在配置参数之后、故障排除之前
+    - English: `If this plugin has been useful, a star on [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) is a big motivation for me. Thank you for the support.`
+    - 中文: `如果这个插件对你有帮助，欢迎到 [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) 点个 Star，这将是我持续改进的动力，感谢支持。`
+9.  **其他 (Others)**: 支持的模板类型、语法示例、故障排除等
+    - **Changelog**: 统一指向 GitHub 项目历史，不在 README 中列出具体变更
 
 ### 2. 插件目录结构 (Plugin Directory Structure)
 
@@ -54,26 +66,47 @@ plugins/actions/export_to_docx/
 plugins/
 ├── actions/           # Action 插件 (用户触发的功能)
 │   ├── my_action/
-│   │   ├── my_action.py          # English version
-│   │   ├── 我的动作.py            # Chinese version
+│   │   ├── my_action.py          # 单文件，内置 i18n
 │   │   ├── README.md              # English documentation
 │   │   └── README_CN.md           # Chinese documentation
-│   ├── ACTION_PLUGIN_TEMPLATE.py      # English template
-│   ├── ACTION_PLUGIN_TEMPLATE_CN.py   # Chinese template
+│   ├── ACTION_PLUGIN_TEMPLATE.py      # 通用 i18n 模板
 │   └── README.md
 ├── filters/           # Filter 插件 (输入处理)
-│   ├── my_filter/
-│   │   ├── my_filter.py
-│   │   ├── 我的过滤器.py
-│   │   ├── README.md
-│   │   └── README_CN.md
-│   └── README.md
+│   └── ...
 ├── pipes/             # Pipe 插件 (输出处理)
 │   └── ...
-└── pipelines/         # Pipeline 插件
+├── pipelines/         # Pipeline 插件
     └── ...
+├── debug/             # 调试与开发工具 (Debug & Development Tools)
+│   ├── my_debug_tool/
+│   │   ├── debug_script.py
+│   │   └── notes.md
+│   └── ...
 ```
 
+#### 调试目录规范 (Debug Directory Standards)
+
+`plugins/debug/` 目录用于存放调试用的脚本、临时验证代码或开发笔记。
+
+**目录结构 (Directory Structure)**:
+应根据调试工具所属的插件或功能模块进行子目录分类，而非将文件散落在根目录。
+
+```
+plugins/debug/
+├── my_plugin_name/      # 特定插件的调试文件 (Debug files for specific plugin)
+│   ├── debug_script.py
+│   └── guides/
+├── common_tools/        # 通用调试工具 (General debug tools)
+│   └── ...
+└── ...
+```
+
+**规范说明 (Guidelines)**:
+- **不强制要求 README**: 该目录下的子项目不需要包含 `README.md`。
+- **发布豁免**: 该目录下的内容**绝不会**被发布脚本处理。
+- **内容灵活性**: 可以包含 Python 脚本、Markdown 文档、JSON 数据等。
+- **分类存放**: 任何调试产物（如 `test_*.py`, `inspect_*.py`）都不应直接存放在项目根目录，必须移动到此目录下相应的子文件夹中。
+
 ### 3. 文档字符串规范 (Docstring Standard)
 
 每个插件文件必须以标准化的文档字符串开头：
@@ -82,7 +115,7 @@ plugins/
 """
 title: 插件名称 (Plugin Name)
 author: Fu-Jie
-author_url: https://github.com/Fu-Jie/awesome-openwebui
+author_url: https://github.com/Fu-Jie/openwebui-extensions
 funding_url: https://github.com/open-webui
 version: 0.1.0
 icon_url: data:image/svg+xml;base64,<base64-encoded-svg>
@@ -97,7 +130,7 @@ description: 插件功能的简短描述。Brief description of plugin functiona
 |--------------|---------------------|----------------|
 | `title` | 插件显示名称 | `Export to Word` / `导出为 Word` |
 | `author` | 作者名称 | `Fu-Jie` |
-| `author_url` | 作者主页链接 | `https://github.com/Fu-Jie/awesome-openwebui` |
+| `author_url` | 作者主页链接 | `https://github.com/Fu-Jie/openwebui-extensions` |
 | `funding_url` | 赞助/项目链接 | `https://github.com/open-webui` |
 | `version` | 语义化版本号 | `0.1.0`, `1.2.3` |
 | `icon_url` | 图标 (Base64 编码的 SVG) | 仅 Action 插件**必须**提供。其他类型可选。 |
@@ -181,19 +214,56 @@ class Action:
 #### 用户上下文 (User Context)
 
 ```python
-def _get_user_context(self, __user__: Optional[Dict[str, Any]]) -> Dict[str, str]:
-    """安全提取用户上下文信息。"""
-    if isinstance(__user__, (list, tuple)):
-        user_data = __user__[0] if __user__ else {}
-    elif isinstance(__user__, dict):
-        user_data = __user__
-    else:
-        user_data = {}
+async def _get_user_context(
+    self,
+    __user__: Optional[dict],
+    __event_call__: Optional[callable] = None,
+    __request__: Optional[Request] = None,
+) -> dict:
+    """
+    Robust extraction of user context with multi-level fallback for language detection.
+    Priority: localStorage (via JS) > HTTP headers > User profile > en-US
+    """
+    user_data = __user__ if isinstance(__user__, dict) else {}
+    user_id = user_data.get("id", "unknown_user")
+    user_name = user_data.get("name", "User")
+    user_language = user_data.get("language", "en-US")
+
+    # 1. Fallback: HTTP Accept-Language header
+    if __request__ and hasattr(__request__, "headers"):
+        accept_lang = __request__.headers.get("accept-language", "")
+        if accept_lang:
+            user_language = accept_lang.split(",")[0].split(";")[0]
+
+    # 2. Priority: Frontend localStorage via JS (requires timeout protection)
+    if __event_call__:
+        try:
+            js_code = """
+                try {
+                    return (
+                        document.documentElement.lang ||
+                        localStorage.getItem('locale') || 
+                        navigator.language || 
+                        'en-US'
+                    );
+                } catch (e) {
+                    return 'en-US';
+                }
+            """
+            # MUST use wait_for with timeout (e.g., 2.0s) to prevent backend deadlock
+            frontend_lang = await asyncio.wait_for(
+                __event_call__({"type": "execute", "data": {"code": js_code}}),
+                timeout=2.0
+            )
+            if frontend_lang and isinstance(frontend_lang, str):
+                user_language = frontend_lang
+        except Exception:
+            pass # Fallback to existing language
 
     return {
-        "user_id": user_data.get("id", "unknown_user"),
-        "user_name": user_data.get("name", "User"),
-        "user_language": user_data.get("language", "en-US"),
+        "user_id": user_id,
+        "user_name": user_name,
+        "user_language": user_language,
     }
 ```
 
@@ -409,6 +479,277 @@ async def long_running_task_with_notification(self, event_emitter, ...):
         return task_future.result()
 ```
 
+### 7. 前端数据获取与交互规范 (Frontend Data Access & Interaction)
+
+#### 获取前端信息 (Retrieving Frontend Info)
+
+当需要获取用户浏览器的上下文信息（如语言、时区、LocalStorage）时，**必须**使用 `__event_call__` 的 `execute` 类型，而不是通过文件上传或复杂的 API 请求。
+
+```python
+async def _get_frontend_value(self, js_code: str) -> str:
+    """Helper to execute JS and get return value."""
+    try:
+        response = await __event_call__(
+            {
+                "type": "execute",
+                "data": {
+                    "code": js_code,
+                },
+            }
+        )
+        return str(response)
+    except Exception as e:
+        logger.error(f"Failed to execute JS: {e}")
+        return ""
+
+# 示例：获取界面语言 (Get UI Language)
+async def get_user_language(self):
+    js_code = """
+        return (
+            localStorage.getItem('locale') || 
+            localStorage.getItem('language') || 
+            navigator.language || 
+            'en-US'
+        );
+    """
+    return await self._get_frontend_value(js_code)
+```
+
+#### 适用场景与引导 (Usage Guidelines)
+
+- **语言适配**: 动态获取界面语言 (`ru-RU`, `zh-CN`) 自动切换输出语言和 UI 翻译。这对于单文件 i18n 插件至关重要。
+- **时区处理**: 获取 `Intl.DateTimeFormat().resolvedOptions().timeZone` 处理时间。
+- **客户端存储**: 读取 `localStorage` 中的用户偏好设置。
+- **硬件能力**: 获取 `navigator.clipboard` 或 `navigator.geolocation` (需授权)。
+
+**注意**: 即使插件有 `Valves` 配置，也应优先尝试自动探测，提升用户体验。
+
+### 8. 国际化 (i18n) 适配规范 (Internationalization Standards)
+
+开发供全球用户使用的插件时，必须预置多语言支持（如中文、英文等）。
+
+#### i18n 字典定义
+
+在文件顶部定义 `TRANSLATIONS` 字典存储多语言字符串：
+
+```python
+TRANSLATIONS = {
+    "en-US": {
+        "status_starting": "Smart Mind Map is starting...",
+    },
+    "zh-CN": {
+        "status_starting": "智能思维导图正在启动...",
+    },
+    # ... 其他语言
+}
+
+# 语言回退映射 (Fallback Map)
+FALLBACK_MAP = {
+    "zh": "zh-CN",
+    "zh-TW": "zh-CN",
+    "zh-HK": "zh-CN",
+    "en": "en-US",
+    "en-GB": "en-US"
+}
+```
+
+#### 获取当前用户真实语言 (Robust Language Detection)
+
+Open WebUI 的前端（localStorage）并未自动同步语言设置到后端数据库或通过标准 API 参数传递。为了获取精准的用户偏好语言，**必须**使用多层级回退机制（Multi-level Fallback）：
+`JS 动态探测 (localStorage)` > `HTTP 浏览器头 (Accept-Language)` > `用户 Profile 默认设置` > `en-US`
+
+> **注意！防卡死指南 (Anti-Deadlock Guide)**
+> 在通过 `__event_call__` 执行前端 JS 脚本时，如果前端脚本不慎抛出异常 (`Exception`) 会导致回调函数 `cb()` 永不执行，这会让后端的 `asyncio` 永远阻塞并卡死整个请求队列！
+> **必须**做两重防护：
+> 1. JS 内部包裹 `try...catch` 保证必须有 `return`。
+> 2. 后端使用 `asyncio.wait_for` 设置强制超时（建议 2 秒）。
+
+```python
+import asyncio
+from fastapi import Request
+
+async def _get_user_context(
+    self,
+    __user__: Optional[dict],
+    __event_call__: Optional[callable] = None,
+    __request__: Optional[Request] = None,
+) -> dict:
+    user_language = __user__.get("language", "en-US") if __user__ else "en-US"
+    
+    # 1st Fallback: HTTP Accept-Language header
+    if __request__ and hasattr(__request__, "headers") and "accept-language" in __request__.headers:
+        raw_lang = __request__.headers.get("accept-language", "")
+        if raw_lang:
+            user_language = raw_lang.split(",")[0].split(";")[0]
+
+    # 2nd Fallback (Best): Execute JS in frontend to read localStorage
+    if __event_call__:
+        try:
+            js_code = """
+                try {
+                    return (
+                        document.documentElement.lang ||
+                        localStorage.getItem('locale') || 
+                        navigator.language || 
+                        'en-US'
+                    );
+                } catch (e) {
+                    return 'en-US';
+                }
+            """
+            # 【致命！】必须设置 wait_for 防止前端无响应卡死后端
+            frontend_lang = await asyncio.wait_for(
+                __event_call__({"type": "execute", "data": {"code": js_code}}),
+                timeout=2.0
+            )
+            if frontend_lang and isinstance(frontend_lang, str):
+                user_language = frontend_lang
+        except Exception as e:
+            pass # fallback to accept-language or en-US
+
+    return {
+        "user_language": user_language,
+        # ... user_name, user_id etc.
+    }
+```
+
+#### 实际使用 (Usage in Action/Filter)
+ 
+```python
+async def action(self, body: dict, __user__: Optional[dict] = None, __event_call__: Optional[callable] = None, ...):
+    user_ctx = await self._get_user_context(__user__, __event_call__)
+    lang = user_ctx["user_language"]
+    
+    # Use helper to get localized string with optional formatting
+    msg = self._get_translation(lang, "status_starting", name=user_ctx["user_name"])
+    await self._emit_status(emitter, msg)
+```
+
+#### 提示词中的语言一致性 (Language Consistency in Prompts)
+
+在为 LLM 生成系统提示词时，必须包含“输出语言与输入保持一致”的指令，以确保 i18n 逻辑在 AI 生成环节也不断裂。
+
+**标准指令示例**:
+- `Language`: All output must be in the exact same language as the input text provided by the user.
+- `Format Consistency`: Even if this system prompt is in English, if the user input is in Chinese, your output must be in Chinese.
+
+#### CJK 脚本的特殊考量 (CJK Script Considerations)
+
+当涉及字符长度限制（如思维导图标题、卡片摘要）时，应区分 CJK（中日韩）和拉丁脚本。
+- **CJK (zh, ja, ko)**: 通常应设置更小的字符数限制（如 10 字以内）。
+- **Latin (en, es, fr)**: 可设置较长的字符限制（如 5-8 个词或 35 字符）。
+
+### 9. 智能代理文件交付规范 (Agent File Delivery Standards)
+
+在开发具备文件生成能力的智能代理插件（如 GitHub Copilot SDK 集成）时，必须遵循以下标准流程，以确保文件在不同存储后端（本地/S3）下的可用性并绕过不必要的 RAG 处理。
+
+#### 核心协议：三步交付法 (The 3-Step Delivery Protocol)
+
+1.  **本地写入 (Write Local)**:
+    - 代理必须在当前执行目录 (`.`) 下创建文件。
+    - **严禁**使用系统临时目录（如 `/tmp`）存放待发布的文件，因为这些路径在隔离的工作空间外不可见。
+2.  **显式发布 (Publish)**:
+    - 必须调用内建工具 `publish_file_from_workspace(filename='name.ext')`。
+    - 该工具负责将文件迁移至 Open WebUI 正式存储（自动适配 S3），并注入 `skip_rag` 元数据以防止触发向量化流程（RAG Bypass）。
+3.  **呈现链接 (Display Link)**:
+    - 获取工具返回的 `download_url`（正确格式为 `/api/v1/files/{id}/content`）。
+    - **必须**以 Markdown 链接形式（如 `[点击下载报告](url)`）展示给用户。
+
+#### 路径语义 (Path Semantics)
+- 代理应始终将“当前目录”视为其受保护所在的私有工作空间。
+- `publish_file_from_workspace` 的参数 `filename` 仅需传入相对于当前目录的文件名。
+
+### 10. Copilot SDK 插件工具定义规范 (Copilot SDK Tool Definition Standards)
+
+在为 GitHub Copilot SDK 开发自定义工具时，为了确保大模型能正确识别参数（避免生成空的 `properties` Schema），必须遵循以下定义模式：
+
+#### 显式参数模型 (Explicit Parameter Schema)
+**禁止**仅依赖函数签名和类型提示。**必须**定义一个继承自 `pydantic.BaseModel` 的类来描述参数，并在 `define_tool` 中通过 `params_type` 显式引用。
+
+```python
+from pydantic import BaseModel, Field
+from copilot import define_tool
+
+# 1. 定义参数模型
+class MyToolParams(BaseModel):
+    query: str = Field(..., description="搜索关键词")
+    limit: int = Field(default=10, description="返回结果数量限制")
+
+# 2. 实现工具逻辑
+async def my_custom_search(query: str, limit: int) -> dict:
+    # ... 逻辑实现 ...
+    return {"results": []}
+
+# 3. 注册工具（关键：使用 params_type）
+my_tool = define_tool(
+    name="my_custom_search",
+    description="在特定数据源中执行搜索",
+    params_type=MyToolParams,  # 显式传递参数模型以生成正确的 JSON Schema
+)(my_custom_search)
+```
+
+#### 关键要点 (Key Requirements)
+1.  **params_type**: 必须在 `define_tool` 中使用此参数。这是防止大模型幻觉认为工具“无参数”的唯一可靠方法。
+2.  **Field 描述**: 在 `BaseModel` 中使用 `Field(..., description="...")` 为每个参数提供详细的描述信息。
+3.  **Required vs Optional**: 明确标注必填项（无默认值）和可选项（带 `default`）。
+
+### 11. Copilot SDK 流式渲染与工具卡片规范 (Streaming & Tool Card Standards)
+
+在处理大模型的思维链（Reasoning）输出和工具调用（Tool Calls）时，为了确保能完美兼容 OpenWebUI 0.8.x 前端的 Markdown 解析器及原生折叠 UI 组件，必须遵循以下极度严格的输出格式规范。
+
+#### 思维链流式渲染 (Reasoning Streaming)
+
+为了让前端能够正确显示“Thinking...”的折叠框和 Spinner 动画，**必须**使用原生的 `<think>` 标签。
+
+- **正确的标签包裹**:
+  ```html
+  <think>
+  这里是思考过程...
+  </think>
+  ```
+- **关键细节**:
+  - **标签闭合检测**: 必须在代码内部维护状态（如 `state["thinking_started"]`）。当（1）正文内容即将开始输出，或（2）工具调用触发 (`tool.execution_start`) 时，**必须优先输出 `\n</think>\n` 强制闭合标签**。如果不闭合，后续的正文或工具面板会被全部吞进思考框内，导致页面完全崩坏！
+  - **不要手动拼装**: 严禁通过手动输出 `<details type="reasoning">` 等大段 HTML 来模拟思考过程，这种方式极易在流式片段发送中破坏前端 DOM 树并导致错位。
+
+#### 工具调用原生卡片 (Native Tool Calls Block)
+
+为了在对话界面中生成标准、原生的下拉折叠“工具调用”卡片，当 `event_type == "tool.execution_complete"` 时，必须向队列输出如下严格格式的 HTML：
+
+```python
+# 必须转义属性中的双引号为 &quot;
+args_for_attr = args_json_str.replace('"', "&quot;")
+result_for_attr = result_content.replace('"', "&quot;")
+
+tool_block = (
+    f'\\n<details type="tool_calls"'
+    f' id="{tool_call_id}"'
+    f' name="{tool_name}"'
+    f' arguments="{args_for_attr}"'
+    f' result="{result_for_attr}"'
+    f' done="true">\\n'
+    f"<summary>Tool Executed</summary>\\n"
+    f"</details>\\n\\n"
+)
+queue.put_nowait(tool_block)
+```
+
+- **致命避坑点 (Critical Pitfalls)**:
+  1. **属性转义 (Extremely Important)**: `<details>` 内的 `arguments` 和 `result` 属性**必须**将内部的所有双引号 `"` 替换为 `&quot;`。因为 OpenWebUI 前端提取这些数据的 Regex 是严格的 `="([^"]*)"`，一旦内容中出现原生双引号，就会被瞬间截断，导致参数被渲染为空并引发解析错误！
+  2. **换行符要求**: `<details ...>` 尖括号闭合后紧接着的内容**必须换行**（即 `>\\n`），否则 Markdown 扩展引擎无法将其识别为独立的 UI Block。
+  3. **去除冗余通知**: 不要在 `tool.execution_start` 事件中提前向对话流输出普通的 `🔧 Executing...` 纯文本块，这会导致最终页面上同时出现两块工具提示（一个文本，一个折叠卡片）。
+
+#### Debug 信息的解耦 (Decoupling Debug Logs)
+
+对于连接建立、运行环境、缓存加载等属于 *脚本自身运行状态* 的 Debug 信息：
+- **禁止**: 不要将这些内容 yield 到最终的回答数据流（或塞进 `<think>` 标签内），这会污染回答的纯粹性。
+- **推荐**: 统一使用 OpenWebUI 顶部的原生状态反馈气泡（Status Events）：
+  ```python
+  await __event_emitter__({
+      "type": "status",
+      "data": {"description": "连接建立，正在等待响应...", "done": True}
+  })
+  ```
+
 ---
 
 ## ⚡ Action 插件规范 (Action Plugin Standards)
@@ -806,8 +1147,7 @@ Filter 实例是**单例 (Singleton)**。
 
 ### 1. ✅ 开发检查清单 (Development Checklist)
 
-- [ ] 创建英文版插件代码 (`plugin_name.py`)
-- [ ] 创建中文版插件代码 (`plugin_name_cn.py`)
+- [ ] 代码实现了内置 i18n 逻辑 (`.py`)
 - [ ] 编写英文 README (`README.md`)
 - [ ] 编写中文 README (`README_CN.md`)
 - [ ] 包含标准化文档字符串
@@ -815,15 +1155,21 @@ Filter 实例是**单例 (Singleton)**。
 - [ ] 使用 Lucide 图标
 - [ ] 实现 Valves 配置
 - [ ] 使用 logging 而非 print
-- [ ] 测试双语界面
+- [ ] 测试 i18n 界面适配
 - [ ] **一致性检查**: 确保文档、代码、README 同步
+- [ ] **README 结构**: 
+    - **Key Capabilities** (英文) / **核心功能** (中文): 必须包含所有核心功能
+    - **What's New** (英文) / **最新更新** (中文): 仅包含最新版本的变更信息
+- [ ] **知识沉淀**: 开发过程中发现的非显而易见的规律、踩坑或内部 API 合约，必须记录到 `.agent/learnings/{topic}.md`
 
 ### 2. 🔄 一致性维护 (Consistency Maintenance)
 
 任何插件的**新增、修改或移除**，必须同时更新：
 1. **插件代码** (version)
-2. **项目文档** (`docs/`)
-3. **自述文件** (`README.md`)
+2. **插件自述文件** (`plugins/{type}/{name}/README.md` & `README_CN.md`)
+3. **项目文档** (`docs/plugins/{type}/{name}.md` & `.zh.md`)
+4. **项目文档索引** (`docs/plugins/{type}/index.md` & `index.zh.md` — 版本号)
+5. **项目根 README** (`README.md` & `README_CN.md` — 更新日期徽章 `![updated](https://img.shields.io/badge/YYYY--MM--DD-gray?style=flat)` 必须同步为发布当天日期)
 
 ### 3.  发布工作流 (Release Workflow)
 
@@ -853,21 +1199,45 @@ Filter 实例是**单例 (Singleton)**。
 - Update README/README_CN to include What's New section
 - Migration: default TITLE_SOURCE changed to chat_title
 
-### 4. 🤖 Git Operations (Agent Rules)
+#### 发布信息生成准则 (Release Summary Generation)
+当准备提交时，必须向用户展示以下格式的“发布草案”：
+1. **Commit Message**: 符合 Conventional Commits 的英文标题及摘要。
+2. **变更列表 (Bilingual Changes)**: 
+   - 英文: Clear descriptions of technical/functional changes.
+   - 中文: 清晰描述用户可见的功能改进或修复。
+3. **核查状态 (Verification)**: 确认版本号已在相关 7+ 处位置同步更新（1 个代码文件 + 2 个 README + 4 个 Docs 文件）。
 
-- **允许**: 创建功能分支 (`feature/xxx`)，推送到功能分支。
-- **禁止**: 直接推送到 `main`，自动合并到 `main`。
+### 4. 🤖 Git 提交与推送规范 (Git Operations & Push Rules)
+
+- **核心原则**: 默认仅进行**本地文件准备**（更新代码、READMEs、Docs、版本号），**严禁**在未获用户明确许可的情况下自动执行 `git commit` 或 `git push`。
+- **允许 (需确认)**: 只有在用户明确表示“发布”、“Commit it”、“Release”或“提交”后，才允许直接推送到 `main` 分支或创建 PR。
+- **功能分支**: 推荐在进行大规模重构或实验性功能开发时，创建功能分支 (`feature/xxx`) 进行隔离。
+- **PR 提交**: 必须使用 GitHub CLI (`gh`) 创建 Pull Request。示例：`gh pr create --title "feat: ..." --body "..."`。
 
 ### 5. 🤝 贡献者认可规范 (Contributor Recognition)
 
 使用 `@all-contributors please add @username for <type>` 指令。
 
+### 6. 📖 知识沉淀 Knowledge Capture (Mandatory)
+
+任何开发会话中发现的**非显而易见**的内部 API 行为、参数注入机制、Mock 对象要求或其他踩坑经验，
+**必须**在会话结束前记录到 `.agent/learnings/{topic}.md`。
+
+- **开始前**: 先浏览 `.agent/learnings/` 确认是否存在相关先验知识，避免重复调研。
+- **格式规范**: 参见 `.agent/learnings/README.md`。
+- **现有条目**: 见 `.agent/learnings/` 目录。
+
+典型需要记录的内容：
+- OpenWebUI 内部函数的参数注入机制
+- Pipe 调用 Tool 时必须提供的上下文字段
+- Mock Request 对象所需满足的接口契约
+- 模型 ID 在不同上下文中的解析规则
+
 ---
 
 ## 📚 参考资源 (Reference Resources)
 
-- [Action 插件模板 (英文)](plugins/actions/ACTION_PLUGIN_TEMPLATE.py)
-- [Action 插件模板 (中文)](plugins/actions/ACTION_PLUGIN_TEMPLATE_CN.py)
+- [Action 插件模板](plugins/actions/ACTION_PLUGIN_TEMPLATE.py)
 - [插件开发指南](plugins/actions/PLUGIN_DEVELOPMENT_GUIDE.md)
 - [Lucide Icons](https://lucide.dev/icons/)
 - [OpenWebUI 文档](https://docs.openwebui.com/)
@@ -877,8 +1247,9 @@ Filter 实例是**单例 (Singleton)**。
 ## Author
 
 Fu-Jie  
-GitHub: [Fu-Jie/awesome-openwebui](https://github.com/Fu-Jie/awesome-openwebui)
+GitHub: [Fu-Jie/openwebui-extensions](https://github.com/Fu-Jie/openwebui-extensions)
 
 ## License
 
 MIT License
+```

.github/gh-aw/README.md

@@ -0,0 +1,21 @@
+# gh-aw Support Files
+
+This directory stores repository-local support files for GitHub Agentic Workflows.
+
+## Purpose
+
+Keep review aids, policy notes, and human-facing mirrors out of `.github/workflows/` so only real gh-aw source workflows live there.
+
+## Structure
+
+- `review-mirrors/`: Chinese review mirrors and maintainer-facing explanations for workflow source files.
+
+## Current Files
+
+- `review-mirrors/aw-pr-maintainer-review.zh.md`: Chinese review mirror for `.github/workflows/aw-pr-maintainer-review.md`.
+- `review-mirrors/aw-release-preflight.zh.md`: Chinese review mirror for `.github/workflows/aw-release-preflight.md`.
+- `review-mirrors/aw-ci-audit.zh.md`: Chinese review mirror for `.github/workflows/aw-ci-audit.md`.
+
+## Rule
+
+Files in this directory are for maintainer review and documentation only. They are not gh-aw workflow source files and should not be compiled.

.github/gh-aw/review-mirrors/aw-ci-audit.zh.md

@@ -0,0 +1,249 @@
+# aw-ci-audit 中文对照
+
+对应源文件：`.github/workflows/aw-ci-audit.md`
+
+用途：这是一份给维护者 review 用的中文对照说明，不是 gh-aw 工作流源文件，也不参与 `gh aw compile`。
+
+## 工作流定位
+
+这个工作流的目标是做“CI / 自动化健康审计”。
+
+它不是日志转储器，也不是自动修复器，而是用于：
+
+- 检查近期仓库自动化是否出现可重复的失败模式
+- 分析 release、publish、stats 等关键工作流的薄弱点
+- 只在有新且可操作的诊断结论时，创建一条维护 issue
+
+如果没有新的可操作诊断，或者问题已经被现有 issue 覆盖，就执行 `noop`。
+
+## Frontmatter 对照
+
+### 触发方式
+
+- `schedule: daily`
+- `workflow_dispatch`
+- `roles: all`
+- `skip-bots`
+  - `github-actions`
+  - `copilot`
+  - `dependabot`
+  - `renovate`
+
+说明：这套设计更适合“定期体检 + 手动补查”，而不是直接绑到不确定的 workflow failure 事件上。
+
+### 权限
+
+当前设计为只读：
+
+- `contents: read`
+- `issues: read`
+- `pull-requests: read`
+- `actions: read`
+
+说明：工作流只做诊断分析，不改代码、不发 release、不创建 PR。
+
+### Safe Outputs
+
+已配置：
+
+- `create-issue`
+  - 标题前缀：`[ci-audit] `
+  - labels：`ci-audit`、`maintenance`
+  - 不自动关闭旧 issue
+
+最终只能二选一：
+
+- 有新且可操作的诊断时执行 `create_issue`
+- 无新问题时执行 `noop`
+
+### 工具
+
+- `github`
+  - `repos`
+  - `issues`
+  - `pull_requests`
+- `bash`
+  - 仅开放只读类命令，如 `pwd`、`ls`、`cat`、`rg`、`git diff`、`git show`
+
+## 正文指令对照
+
+## 主要目标
+
+要求代理审计：
+
+- release 相关 workflow 的失败或波动
+- 插件发布失败
+- 社区统计更新回归
+- 重复出现的 workflow 脆弱点
+- 维护者真正可以执行的下一步动作
+
+明确限制：
+
+- 只做诊断
+- 不改文件
+- 不推代码
+- 不开 PR
+- 不发 release
+
+## 高优先级依据文件
+
+在形成结论前，优先把这些文件当成“自动化规则源”：
+
+- `.github/copilot-instructions.md`
+- `.github/workflows/release.yml`
+- `.github/workflows/publish_plugin.yml`
+- `.github/workflows/publish_new_plugin.yml`
+- `.github/workflows/plugin-version-check.yml`
+- `.github/workflows/community-stats.yml`
+- `docs/development/gh-aw-integration-plan.md`
+- `docs/development/gh-aw-integration-plan.zh.md`
+
+## 重点关注的目标工作流
+
+优先检查：
+
+- `release.yml`
+- `publish_plugin.yml`
+- `publish_new_plugin.yml`
+- `plugin-version-check.yml`
+- `community-stats.yml`
+- `deploy.yml`
+
+如果这些没有明显问题，不要无限扩大范围。
+
+## 审查范围
+
+聚焦“近期失败或可疑自动化信号”，并优先给出基于本仓库结构的诊断，而不是泛泛的 CI 建议。
+
+它应该像“在看仓库自动化健康趋势的维护者”，而不是普通日志摘要机器人。
+
+## 重点检查项
+
+### 1. Release 与 Publish 失败
+
+检查近期失败是否指向这些可操作问题：
+
+- 版本提取或比较逻辑漂移
+- release note 打包缺口
+- publish 脚本的认证或环境问题
+- workflow 中的结构假设已经不匹配当前仓库
+- 如果不改仓库逻辑，就可能持续复现的失败
+
+### 2. Stats 与定时任务稳定性
+
+检查定时维护任务是否出现这些脆弱点：
+
+- community stats 该提交时不再提交
+- badge / docs 生成逻辑过时
+- 依赖外部 API 的任务反复因同类原因失败
+- schedule 驱动任务制造低价值噪音
+
+### 3. 维护者信号质量
+
+只有当结论“真的值得维护者处理”时，才创建 issue。
+
+适合开 issue 的情况：
+
+- 同类失败在多次运行中重复出现
+- workflow 逻辑与当前仓库结构不匹配
+- 大概率缺 secret / 权限 / 路径假设过时
+- 重复出现的低信号失败值得过滤或加固
+
+不要为一次性噪音失败开 issue，除非它很可能复发。
+
+### 4. 已有 Issue 感知
+
+在创建新 issue 前，先判断是否已有 open issue 覆盖同一类 CI 问题。
+
+如果已有 issue 已经足够覆盖，就优先 `noop`，避免制造重复单。
+
+## 严重级别
+
+只允许三档：
+
+- `High`
+  - 高概率重复发生，且会持续影响仓库自动化
+- `Medium`
+  - 建议尽快修，以降低维护成本或 workflow 漂移
+- `Low`
+  - 可选的稳健性增强或清理建议
+
+并且明确要求：
+
+- 不要为了开 issue 而硬造问题
+
+## Issue 格式
+
+如果要创建 issue，必须只有一条维护 issue。
+
+要求：
+
+- 英文
+- 简洁
+- 先写 findings，不写空泛表扬
+- 带可点击路径引用
+- 不用嵌套列表
+- 不要粘贴大段原始日志，除非短摘录确实必要
+
+固定结构：
+
+```markdown
+## CI Audit
+
+### Summary
+Short diagnosis of the failure pattern or automation risk.
+
+### Findings
+- `path/to/file`: specific problem or likely root cause
+
+### Suggested Next Steps
+- concrete maintainer action
+- concrete maintainer action
+
+### Notes
+- Mention whether this appears recurring, new, or already partially mitigated.
+```
+
+补充规则：
+
+- 正常情况下控制在约 300 词以内
+- 如果是相关联的问题，合并成一个 issue，不要拆多个
+- 优先提交“单个可执行诊断”，而不是大杂烩
+
+## No-Issue 规则
+
+如果没有值得报告的新诊断：
+
+- 不要创建状态汇报型 issue
+- 不要复述 workflows 看起来健康
+- 直接走 `noop`
+
+示例：
+
+```json
+{"noop": {"message": "No action needed: reviewed recent repository automation signals and found no new actionable CI diagnosis worth opening as a maintenance issue."}}
+```
+
+## 建议执行流程
+
+1. 检查近期仓库自动化上下文
+2. 优先检查目标工作流
+3. 识别可重复或仓库特定的失败模式
+4. 判断该问题是否已被 open issue 覆盖
+5. 只有在诊断“新且可操作”时，才起草最短有用的维护 issue
+6. 最终只执行一次 `create_issue` 或一次 `noop`
+
+## 额外约束
+
+- 不要为单次低信号瞬时失败开 issue
+- 除非失败模式非常明确，否则不要顺势要求大规模重构
+- 优先给出仓库特定原因，而不是泛泛的“重试试试”
+- 如果根因不确定，要把不确定性写明
+- 如果现有 issue 已经覆盖，优先 `noop` 而不是重复开单
+
+## 最终要求
+
+必须以且仅以一次 safe output 结束：
+
+- 有新且可操作的诊断：`create_issue`
+- 无新问题：`noop`

.github/gh-aw/review-mirrors/aw-pr-maintainer-review.zh.md

@@ -0,0 +1,268 @@
+# aw-pr-maintainer-review 中文对照
+
+对应源文件：`.github/workflows/aw-pr-maintainer-review.md`
+
+用途：这是一份给维护者 review 用的中文对照说明，不是 gh-aw 工作流源文件，也不参与 `gh aw compile`。
+
+## 工作流定位
+
+这个工作流的目标是对触发 PR 做一次“维护者语义审查”。
+
+它不是通用 code review 机器人，也不是自动修复器，而是用来检查以下问题：
+
+- 是否违反本仓库插件开发规范
+- 是否缺失应同步更新的 README / README_CN / docs 镜像文件
+- 是否存在发布准备层面的遗漏
+- 是否引入明显的高风险行为回归
+
+如果 PR 已经足够合规，没有可操作的维护者反馈，就不评论，而是执行 `noop`。
+
+## Frontmatter 对照
+
+### 触发方式
+
+- `pull_request`
+  - 类型：`opened`、`reopened`、`synchronize`、`ready_for_review`
+  - 路径限制：
+    - `plugins/**`
+    - `docs/**`
+    - `.github/**`
+    - `README.md`
+    - `README_CN.md`
+- `workflow_dispatch`
+- `roles: all`
+- `skip-bots`
+  - `github-actions`
+  - `copilot`
+  - `dependabot`
+  - `renovate`
+
+### 权限
+
+当前设计为只读：
+
+- `contents: read`
+- `issues: read`
+- `pull-requests: read`
+
+说明：工作流不会直接改代码，也不会提交 review comment 之外的写操作。
+
+### Safe Outputs
+
+已配置：
+
+- `add-comment`
+  - 目标：当前触发 PR
+  - 最多 1 条
+  - 隐藏旧评论
+  - 不加 footer
+
+同时要求最终必须二选一：
+
+- 有问题时执行 `add_comment`
+- 无问题时执行 `noop`
+
+### 工具
+
+- `github`
+  - `repos`
+  - `issues`
+  - `pull_requests`
+- `bash`
+  - 仅开放只读类命令，如 `pwd`、`ls`、`cat`、`rg`、`git diff`、`git show`
+
+## 正文指令对照
+
+## 主要目标
+
+要求代理审查：
+
+- 仓库标准合规性
+- 缺失的同步更新文件
+- 发布准备缺口
+- 文档漂移
+- 插件代码中的高风险回归
+
+明确限制：
+
+- 只做 review
+- 不改文件
+- 不推代码
+- 不创建 PR
+
+## 高优先级依据文件
+
+在形成结论前，优先把这些文件当成“本仓库规则源”：
+
+- `.github/copilot-instructions.md`
+- `.github/instructions/code-review.instructions.md`
+- `.github/instructions/commit-message.instructions.md`
+- `.github/skills/release-prep/SKILL.md`
+- `.github/skills/doc-mirror-sync/SKILL.md`
+- `docs/development/gh-aw-integration-plan.md`
+- `docs/development/gh-aw-integration-plan.zh.md`
+
+## 审查范围
+
+- 先看 PR diff 和 changed files
+- 只有在验证一致性时，才扩展读取关联文件
+- 优先遵循“仓库特定规则”，而不是泛泛的最佳实践
+
+换句话说，它应该像“熟悉本仓库的维护者”，而不是通用 lint bot。
+
+## 重点检查项
+
+### 1. 插件代码规范
+
+当 `plugins/**/*.py` 变化时，重点看：
+
+- 是否保持单文件 i18n 模式
+- 用户可见文本是否进入翻译字典
+- 是否使用 `_get_user_context` 和 `_get_chat_context`
+- `__event_call__` 的 JS 执行是否具备 timeout 防护和前端兜底
+- 是否引入 `print()` 到生产插件代码
+- emitter 是否安全判空
+- filter 插件是否把请求级可变状态塞到 `self`
+- Copilot SDK / OpenWebUI tool 定义是否仍符合仓库规范
+
+### 2. 版本与发布卫生
+
+当 `plugins/**/*.py` 改动时，检查是否“应该同步但没同步”：
+
+- 插件 docstring 的 `version:`
+- 插件目录下 `README.md`
+- 插件目录下 `README_CN.md`
+- `docs/plugins/**` 下的镜像页面
+- `docs/plugins/{type}/index.md` 等索引文件
+- 如果是明显 release-prep 类型 PR，再看根 `README.md` 和 `README_CN.md` 日期 badge
+
+这里的关键语义是：
+
+- 不是每个 PR 都必须当发布处理
+- 只有在“用户可见行为、元数据、版本化文档、发布面内容”发生变化时，才提示缺失同步
+
+### 3. 文档同步
+
+当插件 README 改动时，检查是否应同步 docs 镜像：
+
+- `plugins/actions/{name}/README.md` -> `docs/plugins/actions/{name}.md`
+- `plugins/actions/{name}/README_CN.md` -> `docs/plugins/actions/{name}.zh.md`
+- `plugins/filters/{name}/README.md` -> `docs/plugins/filters/{name}.md`
+- `plugins/filters/{name}/README_CN.md` -> `docs/plugins/filters/{name}.zh.md`
+- `plugins/pipes/{name}/README.md` -> `docs/plugins/pipes/{name}.md`
+- `plugins/pipes/{name}/README_CN.md` -> `docs/plugins/pipes/{name}.zh.md`
+- `plugins/pipelines/{name}/README.md` -> `docs/plugins/pipelines/{name}.md`
+- `plugins/pipelines/{name}/README_CN.md` -> `docs/plugins/pipelines/{name}.zh.md`
+- `plugins/tools/{name}/README.md` -> `docs/plugins/tools/{name}.md`
+- `plugins/tools/{name}/README_CN.md` -> `docs/plugins/tools/{name}.zh.md`
+
+如果是 docs-only 且明显有意为之，不要过度报错。
+
+### 4. PR 质量
+
+只在“确实让维护者审查变难”时，才指出 PR 描述缺失这些内容：
+
+- 改了什么
+- 为什么改
+- 是否需要迁移或重新配置
+
+## 严重级别
+
+只允许三档：
+
+- `Blocking`
+  - 大概率 bug、发布回归、缺少必需同步、严重规范破坏
+- `Important`
+  - 应该合并前修，但不一定是直接运行时错误
+- `Minor`
+  - 建议项，可选
+
+并且明确要求：
+
+- 不要为了留言而硬凑问题
+
+## 评论格式
+
+如果要评论，必须只有一条总结评论。
+
+要求：
+
+- 英文
+- 简洁
+- 先给 findings，不先夸赞
+- 带可点击路径引用
+- 不使用嵌套列表
+- 不要机械复述 diff
+
+固定结构：
+
+```markdown
+## PR Maintainer Review
+
+### Blocking
+- `path/to/file`: specific issue and why it matters
+
+### Important
+- `path/to/file`: specific issue and what sync/check is missing
+
+### Minor
+- `path/to/file`: optional improvement or consistency note
+
+### Merge Readiness
+- Ready after the items above are addressed.
+```
+
+补充规则：
+
+- 空 section 要省略
+- 如果只有一个严重级别，只保留那个 section 和 `Merge Readiness`
+- 正常情况下控制在约 250 词以内
+
+## No-Comment 规则
+
+如果没有有意义的维护者反馈：
+
+- 不要发“看起来不错”这类表扬评论
+- 不要复述 checks passed
+- 直接走 `noop`
+
+示例：
+
+```json
+{"noop": {"message": "No action needed: reviewed the PR diff and repository sync expectations, and found no actionable maintainer feedback."}}
+```
+
+## 建议执行流程
+
+1. 找出变更文件
+2. 读取高优先级规则文件
+3. 对照插件审查规范检查插件代码
+4. 对照 doc mirror 规则检查 README / docs
+5. 判断是否缺失 version sync 或 release-facing 文件
+6. 先起草最短但有用的维护者总结
+7. 最终只执行一次 `add_comment` 或一次 `noop`
+
+## 额外约束
+
+- 不要要求与本 PR 无关的大重构
+- 小型内部变更不要强拉成 release-prep
+- 明显是私有/内部改动时，不要强制要求 docs sync
+- 优先给出“仓库特定”的反馈，而不是通用 code review 废话
+- 如果你不确定某个同步文件是否必需，把级别降为 `Important`
+- 如果问题依赖 PR 意图但当前信息不足，要把表述写成“条件性判断”，不要装作确定
+
+## 最终要求
+
+必须以且仅以一次 safe output 结束：
+
+- 有可操作反馈：`add_comment`
+- 无可操作反馈：`noop`
+
+## Review 结论
+
+这份英文源工作流目前已经可以作为后续 `gh aw compile` 的候选源文件。
+
+中文镜像的目的只有两个：
+
+- 方便你逐段审阅策略是否符合预期
+- 避免把中文说明混进真正要编译的 workflow 源文件

.github/gh-aw/review-mirrors/aw-release-preflight.zh.md

@@ -0,0 +1,275 @@
+# aw-release-preflight 中文对照
+
+对应源文件：`.github/workflows/aw-release-preflight.md`
+
+用途：这是一份给维护者 review 用的中文对照说明，不是 gh-aw 工作流源文件，也不参与 `gh aw compile`。
+
+## 工作流定位
+
+这个工作流的目标是对触发变更做一次“发布前预检语义审查”。
+
+它不是发布执行器，也不是自动补版本工具，而是用于判断：
+
+- 这次改动是否真的在做 release-prep
+- 如果是在做 release-prep，版本同步是否完整
+- 双语 README、docs 镜像、release notes 是否齐全
+- 是否存在会影响发布质量的说明缺失或文档漂移
+
+如果当前变更并不是发布准备，或者已经足够一致、没有可操作反馈，就执行 `noop`。
+
+## Frontmatter 对照
+
+### 触发方式
+
+- `pull_request`
+  - 类型：`opened`、`reopened`、`synchronize`、`ready_for_review`
+  - 路径限制：
+    - `plugins/**/*.py`
+    - `plugins/**/README.md`
+    - `plugins/**/README_CN.md`
+    - `plugins/**/v*.md`
+    - `plugins/**/v*_CN.md`
+    - `docs/plugins/**/*.md`
+    - `README.md`
+    - `README_CN.md`
+    - `.github/**`
+- `workflow_dispatch`
+- `roles: all`
+- `skip-bots`
+  - `github-actions`
+  - `copilot`
+  - `dependabot`
+  - `renovate`
+
+### 权限
+
+当前设计为只读：
+
+- `contents: read`
+- `issues: read`
+- `pull-requests: read`
+
+说明：工作流不会发 release、不会推代码、不会改文件。
+
+### Safe Outputs
+
+已配置：
+
+- `add-comment`
+  - 目标：当前触发 PR
+  - 最多 1 条
+  - 隐藏旧评论
+  - 不加 footer
+
+最终只能二选一：
+
+- 有问题时执行 `add_comment`
+- 无问题时执行 `noop`
+
+### 工具
+
+- `github`
+  - `repos`
+  - `issues`
+  - `pull_requests`
+- `bash`
+  - 仅开放只读类命令，如 `pwd`、`ls`、`cat`、`rg`、`git diff`、`git show`
+
+## 正文指令对照
+
+## 主要目标
+
+要求代理检查：
+
+- 版本同步完整性
+- 双语 README 与 docs 一致性
+- release notes 完整性
+- 发布面索引或 badge 漂移
+- 用户可见发布是否缺失迁移说明或维护者上下文
+
+明确限制：
+
+- 只做 review
+- 不改文件
+- 不推代码
+- 不创建 release
+- 不创建 PR
+
+## 高优先级依据文件
+
+在形成结论前，优先把这些文件当成“发布规则源”：
+
+- `.github/copilot-instructions.md`
+- `.github/instructions/commit-message.instructions.md`
+- `.github/skills/release-prep/SKILL.md`
+- `.github/skills/doc-mirror-sync/SKILL.md`
+- `.github/workflows/release.yml`
+- `docs/development/gh-aw-integration-plan.md`
+- `docs/development/gh-aw-integration-plan.zh.md`
+
+## 审查范围
+
+- 从 PR diff 和 changed files 开始
+- 只有在验证发布同步时才扩展到相关 release-facing 文件
+- 优先遵循仓库既有 release-prep 规则，而不是泛泛的 release 建议
+
+换句话说，它应该像“合并前最后做一致性复核的维护者”。
+
+## 重点检查项
+
+### 1. 发布相关文件中的版本同步
+
+当某个插件明显在准备发版时，检查这些位置是否同步：
+
+- 插件 Python docstring 的 `version:`
+- 插件目录下 `README.md`
+- 插件目录下 `README_CN.md`
+- `docs/plugins/**` 英文镜像页
+- `docs/plugins/**/*.zh.md` 中文镜像页
+- `docs/plugins/{type}/index.md` 中该插件的条目或版本 badge
+- `docs/plugins/{type}/index.zh.md` 中该插件的条目或版本 badge
+
+但只有在“这次改动明显带有发布意图”时才提示，不要把所有 PR 都按发布处理。
+
+### 2. README 与 docs 镜像一致性
+
+当插件 README 变化时，检查 docs 镜像是否同步。
+
+路径映射：
+
+- `plugins/actions/{name}/README.md` -> `docs/plugins/actions/{name}.md`
+- `plugins/actions/{name}/README_CN.md` -> `docs/plugins/actions/{name}.zh.md`
+- `plugins/filters/{name}/README.md` -> `docs/plugins/filters/{name}.md`
+- `plugins/filters/{name}/README_CN.md` -> `docs/plugins/filters/{name}.zh.md`
+- `plugins/pipes/{name}/README.md` -> `docs/plugins/pipes/{name}.md`
+- `plugins/pipes/{name}/README_CN.md` -> `docs/plugins/pipes/{name}.zh.md`
+- `plugins/pipelines/{name}/README.md` -> `docs/plugins/pipelines/{name}.md`
+- `plugins/pipelines/{name}/README_CN.md` -> `docs/plugins/pipelines/{name}.zh.md`
+- `plugins/tools/{name}/README.md` -> `docs/plugins/tools/{name}.md`
+- `plugins/tools/{name}/README_CN.md` -> `docs/plugins/tools/{name}.zh.md`
+
+如果是纯文档调整、而且并非发版预备，不要过度报错。
+
+### 3. What's New 与 Release Notes 覆盖度
+
+当这次更新明显是发布面插件更新时，检查：
+
+- `What's New` 是否只反映最新版本
+- `最新更新` 是否与英文对应
+- 是否存在 `v{version}.md` 和 `v{version}_CN.md`
+- release notes 是否覆盖当前 diff 中有意义的功能、修复、文档或迁移变化
+
+对纯内部小改动，不要强制要求 release notes。
+
+### 4. 根 README 与发布面索引漂移
+
+当改动明显面向正式发布时，再检查：
+
+- 根 `README.md` 的日期 badge
+- 根 `README_CN.md` 的日期 badge
+- `docs/plugins/**/index.md`
+- `docs/plugins/**/index.zh.md`
+
+不要把这种检查强加给普通内部 PR。
+
+### 5. 维护者上下文与发布清晰度
+
+检查 PR 描述或发布面文案是否缺少关键上下文：
+
+- 这次到底发布了什么
+- 为什么这次发布值得做
+- 是否需要迁移或重新配置
+
+只有在缺失信息会明显增加 release review 成本时，才提示。
+
+## 严重级别
+
+只允许三档：
+
+- `Blocking`
+  - 高概率发布回归、缺少必要版本同步、发布面更新明显不完整
+- `Important`
+  - 合并前最好修，避免发布混乱或文档漂移
+- `Minor`
+  - 可选的发布面清理或一致性建议
+
+并且明确要求：
+
+- 不要为了留言而造问题
+
+## 评论格式
+
+如果要评论，必须只有一条总结评论。
+
+要求：
+
+- 英文
+- 简洁
+- 先给 findings，不先夸赞
+- 带可点击路径引用
+- 不使用嵌套列表
+- 不要机械复述 diff
+
+固定结构：
+
+```markdown
+## Release Preflight Review
+
+### Blocking
+- `path/to/file`: specific release-facing problem and why it matters
+
+### Important
+- `path/to/file`: missing sync or release-documentation gap
+
+### Minor
+- `path/to/file`: optional cleanup or consistency improvement
+
+### Release Readiness
+- Ready after the items above are addressed.
+```
+
+补充规则：
+
+- 空 section 要省略
+- 如果只有一个严重级别，只保留那个 section 和 `Release Readiness`
+- 正常情况下控制在约 250 词以内
+
+## No-Comment 规则
+
+如果没有有意义的发布前预检反馈：
+
+- 不要发“看起来不错”这类表扬评论
+- 不要复述 checks passed
+- 直接走 `noop`
+
+示例：
+
+```json
+{"noop": {"message": "No action needed: reviewed the release-facing diff, version-sync expectations, and bilingual documentation coverage, and found no actionable preflight feedback."}}
+```
+
+## 建议执行流程
+
+1. 判断这次改动是否真的带有发布意图
+2. 检查 PR diff 中的变更文件
+3. 读取仓库的 release-prep 规则文件
+4. 只有在存在发布意图时，才检查 plugin version sync
+5. 检查 README、README_CN、docs 镜像、索引和 release notes 是否漂移
+6. 起草最短但有用的维护者总结
+7. 最终只执行一次 `add_comment` 或一次 `noop`
+
+## 额外约束
+
+- 不要把完整 release-prep 要求硬套到微小内部改动上
+- 非明确发布型 PR，不要强制要求根 README 日期 badge 更新
+- 如果这次改动并不现实地构成发版预备，就不要强求 release notes
+- 优先给出仓库特定的同步反馈，而不是泛泛的发布建议
+- 如果不确定某个 release-facing 同步文件是否必需，把级别降为 `Important`
+- 如果问题依赖“推测出来的意图”，要用条件式表述，不要装作确定
+
+## 最终要求
+
+必须以且仅以一次 safe output 结束：
+
+- 有可操作反馈：`add_comment`
+- 无可操作反馈：`noop`

.github/instructions/code-review.instructions.md

@@ -0,0 +1,54 @@
+---
+name: Plugin Code Review
+description: Comprehensive OpenWebUI plugin review checklist covering i18n, context helpers, antigravity safety, and streaming compatibility
+applyTo: "plugins/**/*.py"
+---
+# Code Review Instructions — OpenWebUI Plugins
+
+You are an expert Senior Software Engineer reviewing OpenWebUI plugins for the `openwebui-extensions` repository.
+When reviewing plugin code, you MUST verify each point below to ensure the code meets the strict repository standards.
+
+## 1. Single-file i18n Pattern (CRITICAL)
+- **One File Rule**: One `.py` file per plugin. No `_cn.py` or language-split files.
+- **Translations**: All user-visible strings (status, notification, UI text) MUST go through a `TRANSLATIONS` dictionary and a `FALLBACK_MAP`.
+- **Safety**: `format(**kwargs)` calls on translated strings MUST be wrapped in `try/except KeyError` to prevent crashes if a translation is missing a placeholder.
+
+## 2. Context Helpers (CRITICAL)
+- **User Context**: MUST use `_get_user_context(__user__)` instead of direct `__user__["name"]` access. `__user__` can be a list, dict, or None.
+- **Chat Context**: MUST use `_get_chat_context(body, __metadata__)` instead of ad-hoc `body.get("chat_id")` calls.
+
+## 3. Event & Logging
+- **No Print**: No bare `print()` in production code. Use `logging.getLogger(__name__)`.
+- **Emitter Safety**: Every `await emitter(...)` call MUST be guarded by `if emitter:` (or equivalent).
+- **Status Lifecycle**: 
+  - `_emit_status(done=False)` at task start.
+  - `_emit_status(done=True)` on completion.
+  - `_emit_notification("error")` on failure.
+
+## 4. Antigravity Safety (CRITICAL)
+- **Timeout Guards**: All `__event_call__` JS executions MUST be wrapped with `asyncio.wait_for(..., timeout=2.0)`. Failure to do this can hang the entire backend.
+- **JS Fallbacks**: JS code executed via `__event_call__` MUST have an internal `try { ... } catch (e) { return fallback; }` block.
+- **Path Sandboxing**: File path operations MUST be validated against the workspace root (no directory traversal vulnerabilities).
+- **Upload Fallbacks**: Upload paths MUST have a dual-channel fallback (API → local/DB).
+
+## 5. Filter Singleton Safety
+- **No Mutable State**: Filter plugins are singletons. There MUST be NO request-scoped mutable state stored on `self` (e.g., `self.current_user = ...`).
+- **Statelessness**: Per-request values MUST be computed from `body` and context helpers on each call.
+
+## 6. Copilot SDK Tools
+- **Pydantic Models**: Tool parameters MUST be defined as a `pydantic.BaseModel` subclass.
+- **Explicit Params**: `define_tool(...)` MUST include `params_type=MyParams`.
+- **Naming**: Tool names MUST match `^[a-zA-Z0-9_-]+$` (ASCII only).
+
+## 7. Streaming Compatibility (OpenWebUI 0.8.x)
+- **Thinking Tags**: The `</think>` tag MUST be closed before any normal content or tool cards are emitted.
+- **Attribute Escaping**: Tool card `arguments` and `result` attributes MUST escape `"` as `&quot;`.
+- **Newline Requirement**: The `<details type="tool_calls" ...>` block MUST be followed by a newline immediately after `>`.
+
+## 8. Performance & Memory
+- **Streaming**: Large files or responses MUST be streamed, not loaded entirely into memory.
+- **Database Connections**: Plugins MUST reuse the OpenWebUI internal database connection (`owui_engine`, `owui_Session`) rather than creating new ones.
+
+## 9. HTML Injection (Action Plugins)
+- **Wrapper Template**: HTML output MUST use the standard `<!-- OPENWEBUI_PLUGIN_OUTPUT -->` wrapper.
+- **Idempotency**: The plugin MUST implement `_remove_existing_html` to ensure multiple runs do not duplicate the HTML output.

.github/instructions/commit-message.instructions.md

@@ -0,0 +1,90 @@
+---
+name: Commit Message
+description: Comprehensive Conventional Commits guidelines for openwebui-extensions
+---
+# Commit Message Instructions
+
+You are an expert developer generating commit messages for the `openwebui-extensions` repository. 
+Always adhere to the following strict guidelines based on the Conventional Commits specification.
+
+## 1. General Rules
+- **Language**: **English ONLY**. Never use Chinese or other languages in the commit title or body.
+- **Structure**:
+  ```text
+  <type>(<scope>): <subject>
+  <BLANK LINE>
+  <body>
+  <BLANK LINE>
+  <footer>
+  ```
+
+## 2. Type (`<type>`)
+Must be one of the following:
+- `feat`: A new feature or a new plugin.
+- `fix`: A bug fix.
+- `docs`: Documentation only changes (e.g., README, MkDocs).
+- `refactor`: A code change that neither fixes a bug nor adds a feature.
+- `perf`: A code change that improves performance.
+- `test`: Adding missing tests or correcting existing tests.
+- `chore`: Changes to the build process, CI/CD, or auxiliary tools/scripts.
+- `style`: Changes that do not affect the meaning of the code (white-space, formatting, etc.).
+
+## 3. Scope (`<scope>`)
+The scope should indicate the affected component or plugin.
+- **For Plugins**: Use the plugin's folder name or category (e.g., `actions`, `filters`, `pipes`, `export-to-docx`, `github-copilot-sdk`).
+- **For Docs**: Use `docs` or the specific doc section (e.g., `guide`, `readme`).
+- **For Infra**: Use `ci`, `scripts`, `deps`.
+- *Note*: Omit the scope if the change is global or spans too many components.
+
+## 4. Subject Line (`<subject>`)
+- **Length**: Keep it under 50-72 characters.
+- **Mood**: Use the imperative, present tense: "change" not "changed" nor "changes" (e.g., "add feature" instead of "added feature").
+- **Formatting**: Do not capitalize the first letter. Do not place a period `.` at the end.
+- **Clarity**: State exactly *what* changed. Avoid vague terms like "update code" or "fix bug".
+
+## 5. Body (`<body>`)
+- **When to use**: Highly recommended for `feat`, `fix`, and `refactor`.
+- **Content**: Explain *what* and *why* (motivation), not just *how* (the code diff shows the how).
+- **Format**: Use a bulleted list (1-3 points) for readability.
+- **Repo Specifics**: If the commit involves a plugin version bump, explicitly mention that the READMEs and docs were synced.
+
+## 6. Footer / Breaking Changes (`<footer>`)
+- If the commit introduces a breaking change (e.g., changing a Valve configuration key, altering a plugin's output format), append `!` after the scope/type: `feat(pipes)!: ...`
+- Add a `BREAKING CHANGE:` block in the footer explaining the migration path.
+
+## 7. Examples
+
+**Example 1: Feature with Body**
+```text
+feat(github-copilot-sdk): add antigravity timeout guards
+
+- Wrap all __event_call__ JS executions with asyncio.wait_for(timeout=2.0)
+- Add dual-channel upload fallback (API → local/DB)
+- Emit staged status events for tasks > 3 seconds
+```
+
+**Example 2: Bug Fix**
+```text
+fix(export-to-docx): resolve missing title fallback
+
+- Fallback to user_name + date when chat_title is empty
+- Prevent crash when metadata variables are missing
+```
+
+**Example 3: Documentation Sync**
+```text
+docs(plugins): sync bilingual READMEs for v1.2.0 release
+
+- Update What's New section for folder-memory plugin
+- Sync docs/plugins/filters/folder-memory.md
+```
+
+**Example 4: Breaking Change**
+```text
+refactor(core)!: rename global configuration valves
+
+- Standardize all valve keys to UPPER_SNAKE_CASE
+- Remove deprecated legacy_api_key field
+
+BREAKING CHANGE: Users must reconfigure their API keys in the UI as the old `api_key` field is no longer read.
+```

.github/instructions/plugin-documentation.instructions.md

@@ -0,0 +1,90 @@
+---
+name: Plugin Documentation
+description: Use when writing or updating plugin README files, mirrored docs pages, bilingual release notes, or other user-facing documentation for plugins.
+applyTo: "plugins/**/README*.md"
+---
+# Plugin Documentation Standards
+
+## Delivery Language
+
+- Plugin directories must keep both `README.md` and `README_CN.md`
+- When a task includes docs, guides, announcements, release notes, or development docs, prepare both English and Chinese versions for review unless the user explicitly asks for single-language delivery
+- Even if only English is committed, provide a Chinese review draft in the conversation when documentation is part of the work
+
+## README Structure
+
+Use this order for plugin READMEs:
+
+1. Title with icon
+2. README header
+3. One-sentence description
+4. `What's New` with only the latest update
+5. `Key Features`
+6. `How to Use`
+7. Configuration or Valves table
+8. Support section
+9. Other sections such as examples, template notes, troubleshooting, or changelog link
+
+## README Header
+
+Do not use the old pipe-separated metadata line.
+
+Use a compact two-part header:
+
+1. A full-width two-column line with author/version on the left and the star link on the right
+2. A single-row live badge table with no visible text header
+
+English example:
+
+`| By [Fu-Jie](https://github.com/Fu-Jie) · vx.y.z | [⭐ Star this repo](https://github.com/Fu-Jie/openwebui-extensions) |`
+
+`| :--- | ---: |`
+
+`| ![followers](...) | ![points](...) | ![top](...) | ![contributions](...) | ![downloads](...) | ![saves](...) | ![views](...) |`
+
+`| :---: | :---: | :---: | :---: | :---: | :---: | :---: |`
+
+Chinese example:
+
+`| 作者：[Fu-Jie](https://github.com/Fu-Jie) · vx.y.z | [⭐ 点个 Star 支持项目](https://github.com/Fu-Jie/openwebui-extensions) |`
+
+`| :--- | ---: |`
+
+`| ![followers](...) | ![points](...) | ![top](...) | ![contributions](...) | ![downloads](...) | ![saves](...) | ![views](...) |`
+
+`| :---: | :---: | :---: | :---: | :---: | :---: | :---: |`
+
+Guidelines:
+
+- Keep the author link pointing to `https://github.com/Fu-Jie`
+- Keep the star link pointing to the repository root
+- Put the version on the left-side author line as plain text (`vx.y.z`), not as a badge
+- Use live badges for followers, points, plugin contribution count, total plugin downloads, total plugin saves, and total plugin views
+- Keep the `Top` badge compact and use the project standard wording (`Top <1%`)
+- Do not add a visible label header row above the badges
+
+## Support Section
+
+Use the repository-standard support wording.
+
+English:
+`If this plugin has been useful, a star on [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) is a big motivation for me. Thank you for the support.`
+
+Chinese:
+`如果这个插件对你有帮助，欢迎到 [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) 点个 Star，这将是我持续改进的动力，感谢支持。`
+
+## Mirror and Sync Rules
+
+When plugin documentation changes, keep these layers aligned as needed:
+
+- Plugin-local README files under `plugins/`
+- Mirrored docs pages under `docs/plugins/`
+- Plugin index pages under `docs/plugins/<type>/index.md` and `index.zh.md`
+- Root `README.md` and `README_CN.md` date badge when preparing a release
+
+Use the `doc-mirror-sync` skill when the task includes mirroring plugin READMEs into `docs/`.
+
+## Changelog Handling
+
+- Keep detailed changelog history in GitHub release history or dedicated docs
+- In README files, keep `What's New` focused on the latest version only

.github/instructions/test-generation.instructions.md

@@ -0,0 +1,54 @@
+---
+name: Test Generation
+description: Comprehensive Pytest conventions, mocking strategies, and model usage rules for OpenWebUI plugins
+applyTo: "plugins/debug/**,tests/**"
+---
+# Test Generation Instructions
+
+You are an expert SDET (Software Development Engineer in Test) writing tests for the `openwebui-extensions` repository.
+Follow these comprehensive guidelines to ensure robust, reliable, and cost-effective testing.
+
+## 1. Test Structure & Placement
+- **Unit Tests**: Place in the `tests/` directory at the root of the repository. Name files `test_<module>.py`.
+- **Integration/Debug Scripts**: Place in `plugins/debug/<plugin_name>/`. Name files `debug_<feature>.py` or `inspect_<feature>.py`.
+- **Fixtures**: Use `conftest.py` for shared fixtures (e.g., mock users, mock emitters, mock database sessions).
+
+## 2. Model Usage & Cost Control (CRITICAL)
+When writing tests or debug scripts that actually invoke an LLM:
+- **Allowed Models**: You MUST use low-cost models: `gpt-5-mini` (Preferred) or `gpt-4.1`.
+- **Forbidden**: NEVER use expensive models (like `gpt-4-turbo`, `claude-3-opus`) in automated tests unless explicitly requested by the user.
+- **API Keys**: Never hardcode API keys. Always read from environment variables (`os.getenv("OPENAI_API_KEY")`) or a `.env` file.
+
+## 3. Mocking OpenWebUI Internals
+OpenWebUI plugins rely heavily on injected runtime variables. Your tests must mock these accurately:
+- **`__user__`**: Mock as a dictionary. Always test both with a full user object and an empty/None object to ensure fallback logic works.
+  ```python
+  mock_user_en = {"id": "u1", "name": "Alice", "language": "en-US"}
+  mock_user_zh = {"id": "u2", "name": "Bob", "language": "zh-CN"}
+  mock_user_none = None
+  ```
+- **`__event_emitter__`**: Mock as an async callable that records emitted events for assertion.
+  ```python
+  async def mock_emitter(event: dict):
+      emitted_events.append(event)
+  ```
+- **`__event_call__`**: Mock as an async callable. To test Antigravity timeout guards, you must occasionally mock this to sleep longer than the timeout (e.g., `await asyncio.sleep(3.0)`) to ensure `asyncio.wait_for` catches it.
+
+## 4. Testing Async Code
+- All OpenWebUI plugin entry points (`action`, `inlet`, `outlet`) are asynchronous.
+- Use `@pytest.mark.asyncio` for all test functions.
+- Ensure you `await` all plugin method calls.
+
+## 5. i18n (Internationalization) Testing
+Since all plugins must be single-file i18n:
+- **Mandatory**: Write parameterized tests to verify output in both English (`en-US`) and Chinese (`zh-CN`).
+- Verify that if an unsupported language is passed (e.g., `fr-FR`), the system correctly falls back to the default (usually `en-US`).
+
+## 6. Antigravity & Safety Testing
+- **Timeout Guards**: Explicitly test that frontend JS executions (`__event_call__`) do not hang the backend. Assert that a `TimeoutError` is caught and handled gracefully.
+- **State Leakage**: For `Filter` plugins (which are singletons), write tests that simulate concurrent requests from different users to ensure no state leaks across `self`.
+
+## 7. Assertions & Best Practices
+- Assert on **behavior and output**, not internal implementation details.
+- For HTML/Markdown generation plugins, use Regex or BeautifulSoup to assert the presence of required tags (e.g., `<!-- OPENWEBUI_PLUGIN_OUTPUT -->`) rather than exact string matching.
+- Keep tests isolated. Do not rely on the execution order of tests.

.github/skills/README.md

@@ -0,0 +1,71 @@
+# Agent Skills Index
+
+This folder contains reusable Agent Skills for GitHub Copilot / VS Code custom agent workflows.
+
+## Available Skills
+
+- **community-announcer**
+  - Purpose: Generate community announcement content and related assets.
+  - Entry: `community-announcer/SKILL.md`
+
+- **doc-mirror-sync**
+  - Purpose: Sync mirrored documentation content and helper scripts.
+  - Entry: `doc-mirror-sync/SKILL.md`
+
+- **gh-issue-replier**
+  - Purpose: Draft standardized issue replies with templates.
+  - Entry: `gh-issue-replier/SKILL.md`
+
+- **gh-issue-scheduler**
+  - Purpose: Schedule and discover unanswered issues for follow-up.
+  - Entry: `gh-issue-scheduler/SKILL.md`
+
+- **i18n-validator**
+  - Purpose: Validate translation key consistency across i18n dictionaries.
+  - Entry: `i18n-validator/SKILL.md`
+
+- **plugin-scaffolder**
+  - Purpose: Scaffold OpenWebUI plugin boilerplate with repository standards.
+  - Entry: `plugin-scaffolder/SKILL.md`
+
+- **version-bumper**
+  - Purpose: Assist with semantic version bumping workflows.
+  - Entry: `version-bumper/SKILL.md`
+
+- **xlsx-single-file**
+  - Purpose: Single-file spreadsheet operations workflow without LibreOffice.
+  - Entry: `xlsx-single-file/SKILL.md`
+
+---
+
+## Release Pipeline Skills
+
+These four skills form a complete release pipeline and are designed to be used in sequence:
+
+```
+release-prep  →  pr-submitter  →  pr-reviewer  →  release-finalizer
+ (prepare)       (push & PR)      (respond to review)  (merge & close issue)
+```
+
+- **release-prep**
+  - Purpose: Full release preparation — version sync across 7+ files, bilingual release notes creation, consistency check, and commit.
+  - Entry: `release-prep/SKILL.md`
+
+- **pr-submitter**
+  - Purpose: Shell-escape-safe PR submission — writes body to temp file, validates sections, pushes branch, creates PR via `gh pr create --body-file`.
+  - Entry: `pr-submitter/SKILL.md`
+
+- **pr-reviewer**
+  - Purpose: Fetch PR review comments, categorize feedback, implement fixes, commit and push, reply to reviewers.
+  - Entry: `pr-reviewer/SKILL.md`
+
+- **release-finalizer**
+  - Purpose: Merge release PR to main with proper commit message, auto-link and close related issues, post closing messages.
+  - Entry: `release-finalizer/SKILL.md`
+
+## Notes
+
+- Skill definitions follow the expected location pattern:
+  - `.github/skills/<skill-name>/SKILL.md`
+- Each skill may include optional `assets/`, `references/`, and `scripts/` folders.
+- This directory mirrors `.gemini/skills` for compatibility.

.github/skills/community-announcer/SKILL.md

@@ -0,0 +1,23 @@
+---
+name: community-announcer
+description: Drafts engaging English and Chinese update announcements for the OpenWebUI Community and other social platforms. Use when a new version is released.
+---
+
+# Community Announcer
+
+## Overview
+Automates the drafting of high-impact update announcements.
+
+## Workflow
+1. **Source Intel**: Read the latest version's `What's New` section from `README.md`.
+2. **Drafting**: Create two versions:
+   - **Community Post**: Professional, structured, technical.
+   - **Catchy Short**: For Discord/Twitter, use emojis and bullet points.
+3. **Multi-language**: Generate BOTH English and Chinese versions automatically.
+
+## Announcement Structure (Recommended)
+- **Headline**: "Update vX.X.X - [Main Feature]"
+- **Introduction**: Brief context.
+- **Key Highlights**: Bulleted list of fixes/features.
+- **Action**: "Download from [Market Link]"
+- **Closing**: Thanks and Star request.

.github/skills/doc-mirror-sync/SKILL.md

@@ -0,0 +1,50 @@
+---
+name: doc-mirror-sync
+description: Automatically synchronizes plugin READMEs to the official documentation directory (docs/). Use after editing a plugin's local documentation to keep the MkDocs site up to date.
+---
+
+# Doc Mirror Sync
+
+## Overview
+Automates the mirroring of `plugins/{type}/{name}/README.md` to `docs/plugins/{type}/{name}.md`.
+
+## Docs-Only Mode (No Release Changes)
+Use this mode when the request is "only sync docs".
+
+- Only update documentation mirror files under `docs/plugins/**`.
+- Do **not** bump plugin version.
+- Do **not** modify plugin code (`plugins/**.py`) unless explicitly requested.
+- Do **not** update root badges/dates for release.
+- Do **not** run release preparation steps.
+
+## Workflow
+1. Identify changed READMEs.
+2. Copy content to corresponding mirror paths.
+3. Update version badges in `docs/plugins/{type}/index.md`.
+
+## Commands
+
+### Sync all mirrors (EN + ZH)
+
+```bash
+python .github/skills/doc-mirror-sync/scripts/sync.py
+```
+
+### Sync only one plugin (EN only)
+
+```bash
+cp plugins/<type>/<name>/README.md docs/plugins/<type>/<name>.md
+```
+
+### Sync only one plugin (EN + ZH)
+
+```bash
+cp plugins/<type>/<name>/README.md docs/plugins/<type>/<name>.md
+cp plugins/<type>/<name>/README_CN.md docs/plugins/<type>/<name>.zh.md
+```
+
+## Notes
+
+- If asked for English-only update, sync only `README.md` -> `.md` mirror.
+- If both languages are requested, sync both `README.md` and `README_CN.md`.
+- After syncing, verify git diff only contains docs file changes.

.github/skills/doc-mirror-sync/scripts/sync.py

@@ -0,0 +1,38 @@
+#!/usr/bin/env python3
+import os
+import shutil
+import re
+
+def sync_mirrors():
+    plugins_root = "plugins"
+    docs_root = "docs/plugins"
+    
+    types = ["actions", "filters", "pipes", "pipelines", "tools"]
+    
+    for t in types:
+        src_type_dir = os.path.join(plugins_root, t)
+        dest_type_dir = os.path.join(docs_root, t)
+        
+        if not os.path.exists(src_type_dir): continue
+        os.makedirs(dest_type_dir, exist_ok=True)
+        
+        for name in os.listdir(src_type_dir):
+            plugin_dir = os.path.join(src_type_dir, name)
+            if not os.path.isdir(plugin_dir): continue
+            
+            # Sync README.md -> docs/plugins/{type}/{name}.md
+            src_readme = os.path.join(plugin_dir, "README.md")
+            if os.path.exists(src_readme):
+                dest_readme = os.path.join(dest_type_dir, f"{name}.md")
+                shutil.copy(src_readme, dest_readme)
+                print(f"✅ Mirrored: {t}/{name} (EN)")
+            
+            # Sync README_CN.md -> docs/plugins/{type}/{name}.zh.md
+            src_readme_cn = os.path.join(plugin_dir, "README_CN.md")
+            if os.path.exists(src_readme_cn):
+                dest_readme_zh = os.path.join(dest_type_dir, f"{name}.zh.md")
+                shutil.copy(src_readme_cn, dest_readme_zh)
+                print(f"✅ Mirrored: {t}/{name} (ZH)")
+
+if __name__ == "__main__":
+    sync_mirrors()

.github/skills/gh-issue-replier/SKILL.md

@@ -0,0 +1,51 @@
+---
+name: gh-issue-replier
+description: Professional English replier for GitHub issues. Use when a task is completed, a bug is fixed, or more info is needed from the user. Automates replying using the 'gh' CLI tool.
+---
+
+# Gh Issue Replier
+
+## Overview
+
+The `gh-issue-replier` skill enables Gemini CLI to interact with GitHub issues professionally. It enforces English for all communications and leverages the `gh` CLI to post comments.
+
+## Workflow
+
+1.  **Identify the Issue**: Find the issue number (e.g., #49).
+2.  **Check Star Status**: Run the bundled script to check if the author has starred the repo.
+    *   Command: `bash scripts/check_star.sh <issue-number>`
+    *   Interpretation: 
+        *   Exit code **0**: User has starred. Use "Already Starred" templates.
+        *   Exit code **1**: User has NOT starred. Include "Star Request" in the reply.
+3.  **Select a Template**: Load [templates.md](references/templates.md) to choose a suitable English response pattern.
+4.  **Draft the Reply**: Compose a concise message based on the star status.
+5.  **Post the Comment**: Use the `gh` tool to submit the reply.
+
+## Tool Integration
+
+### Check Star Status
+```bash
+bash scripts/check_star.sh <issue-number>
+```
+
+### Post Comment
+```bash
+gh issue comment <issue-number> --body "<message-body>"
+```
+
+Example (if user has NOT starred):
+```bash
+gh issue comment 49 --body "This has been fixed in v1.2.7. If you find this helpful, a star on the repo would be much appreciated! ⭐"
+```
+
+Example (if user HAS starred):
+```bash
+gh issue comment 49 --body "This has been fixed in v1.2.7. Thanks for your support!"
+```
+
+## Guidelines
+
+-   **Language**: ALWAYS use English for the comment body, even if the system prompt or user conversation is in another language.
+-   **Tone**: Professional, helpful, and appreciative.
+-   **Precision**: When announcing a fix, mention the specific version or the logic change (e.g., "Updated regex pattern").
+-   **Closing**: If the issue is resolved and you have permission, you can also use `gh issue close <number>`.

.github/skills/gh-issue-replier/references/example_reference.md

@@ -0,0 +1,17 @@
+# Reference Documentation for Gh Issue Replier
+
+This is a placeholder for detailed reference documentation.
+Replace with actual reference content or delete if not needed.
+
+## Structure Suggestions
+
+### API Reference Example
+- Overview
+- Authentication
+- Endpoints with examples
+- Error codes
+
+### Workflow Guide Example
+- Prerequisites
+- Step-by-step instructions
+- Best practices

.github/skills/gh-issue-replier/references/templates.md

@@ -0,0 +1,45 @@
+# Issue Reply Templates
+
+Use these templates to craft professional English replies. Adjust placeholders like `@username`, `v1.2.x`, and `[commit hash]` as needed.
+
+## 1. Acknowledging a New Issue
+Use when you first see an issue and want to let the user know you are working on it.
+
+- "Thank you for reporting this! I'm looking into it right now."
+- "Thanks for bringing this to my attention. I'll try to reproduce this behavior and get back to you shortly."
+
+## 2. Requesting More Information
+Use when you need logs or specific details to fix the bug.
+
+- "Could you please provide the **'Original'** vs **'Normalized'** content from your browser console logs (F12)? It would help a lot in debugging."
+- "It would be very helpful if you could share the specific Markdown text that triggered this issue."
+
+## 3. Announcing a Fix
+Use when you have pushed the fix to the repository.
+
+- "This has been fixed in version **v1.2.x**. You can update the plugin to resolve it."
+- "I've just pushed a fix for this in [commit hash]. Please let me know if it works for you after updating."
+- "The issue was caused by a greedy regex pattern. I've updated it to use a tempered greedy token to prevent incorrect merging."
+
+## 4. Guiding to Official Market
+Always provide the official market link to ensure the user gets the latest verified version.
+
+- "The fix is now live! You can download the latest version from the official OpenWebUI Community page here: [Plugin Market Link]. Simply update the function in your OpenWebUI instance to apply the changes."
+- "I recommend getting the updated version from the official store: [Link]. It includes the fix for the spacing issue we discussed."
+
+## 5. Closing the Issue
+Use when the issue is confirmed resolved.
+
+- "Glad to hear it's working now! Closing this for now. Feel free to reopen it if the problem persists."
+- "Since this is resolved, I'm closing this issue. Thanks again for your feedback!"
+
+## 5. Pro-tip: Star Request
+Gently handle star requests based on the user's current status.
+
+### If User has NOT starred:
+- "If you find this plugin helpful, a star on the repo would be much appreciated! ⭐"
+- "We'd love your support! If this fixed your issue, please consider starring the repository. ⭐"
+
+### If User HAS already starred:
+- "Thanks again for starring the project and for your continuous support!"
+- "I appreciate your support and for being a stargazer of this project!"

.github/skills/gh-issue-replier/scripts/check_star.sh

@@ -0,0 +1,31 @@
+#!/usr/bin/env bash
+
+# Robust Star Checker v2
+# Usage: ./check_star.sh <issue_number>
+
+ISSUE_NUM=$1
+if [ -z "$ISSUE_NUM" ]; then exit 2; fi
+
+# 1. Get Repo and Author info
+REPO_FULL=$(gh repo view --json owner,name -q ".owner.login + \"/\" + .name")
+USER_LOGIN=$(gh issue view "$ISSUE_NUM" --json author -q ".author.login")
+
+# 2. Use GraphQL for high precision (Detects stars even when REST 404s)
+IS_STARRED=$(gh api graphql -f query='
+query($owner:String!, $repo:String!, $user:String!) {
+  repository(owner:$owner, name:$repo) {
+    stargazers(query:$user, first:1) {
+      nodes {
+        login
+      }
+    }
+  }
+}' -f owner="${REPO_FULL%/*}" -f repo="${REPO_FULL#*/}" -f user="$USER_LOGIN" -q ".data.repository.stargazers.nodes[0].login")
+
+if [ "$IS_STARRED" == "$USER_LOGIN" ]; then
+    echo "Confirmed: @$USER_LOGIN HAS starred $REPO_FULL. ⭐"
+    exit 0
+else
+    echo "Confirmed: @$USER_LOGIN has NOT starred $REPO_FULL."
+    exit 1
+fi

.github/skills/gh-issue-scheduler/SKILL.md

@@ -0,0 +1,42 @@
+---
+name: gh-issue-scheduler
+description: Finds all open GitHub issues that haven't been replied to by the owner, summarizes them, and generates a solution plan. Use when the user wants to audit pending tasks or plan maintenance work.
+---
+
+# Gh Issue Scheduler
+
+## Overview
+
+The `gh-issue-scheduler` skill helps maintainers track community feedback by identifying unaddressed issues and drafting actionable technical plans to resolve them.
+
+## Workflow
+
+1.  **Identify Unanswered Issues**: Run the bundled script to fetch issues without owner replies.
+    *   Command: `bash scripts/find_unanswered.sh`
+2.  **Analyze and Summarize**: For each identified issue, summarize the core problem and the user's intent.
+3.  **Generate Solution Plans**: Draft a technical "Action Plan" for each issue, including:
+    *   **Root Cause Analysis** (if possible)
+    *   **Proposed Fix/Implementation**
+    *   **Verification Strategy**
+4.  **Present to User**: Display a structured report of all pending issues and their respective plans.
+
+## Tool Integration
+
+### Find Unanswered Issues
+```bash
+bash scripts/find_unanswered.sh
+```
+
+## Report Format
+
+When presenting the summary, use the following Markdown structure:
+
+### 📋 Unanswered Issues Audit
+
+#### Issue #[Number]: [Title]
+- **Author**: @username
+- **Summary**: Concise description of the problem.
+- **Action Plan**:
+    1. Step 1 (e.g., Investigate file X)
+    2. Step 2 (e.g., Apply fix Y)
+    3. Verification (e.g., Run test Z)

.github/skills/gh-issue-scheduler/scripts/find_unanswered.sh

@@ -0,0 +1,42 @@
+#!/usr/bin/env bash
+
+# Fetch all open issues and filter for those without responses from the owner/collaborators.
+# Uses 'gh' CLI.
+
+REPO_FULL=$(gh repo view --json owner,name -q ".owner.login + "/" + .name")
+OWNER=${REPO_FULL%/*}
+
+# 1. Get all open issues
+OPEN_ISSUES=$(gh issue list --state open --json number,title,author,createdAt --limit 100)
+
+echo "Analysis for repository: $REPO_FULL"
+echo "------------------------------------"
+
+# Process each issue
+echo "$OPEN_ISSUES" | jq -c '.[]' | while read -r issue; do
+    NUMBER=$(echo "$issue" | jq -r '.number')
+    TITLE=$(echo "$issue" | jq -r '.title')
+    AUTHOR=$(echo "$issue" | jq -r '.author.login')
+    
+    # Check comments for owner responses
+    # We look for comments where the author is the repo owner
+    COMMENTS=$(gh issue view "$NUMBER" --json comments -q ".comments[].author.login" 2>/dev/null)
+    
+    HAS_OWNER_REPLY=false
+    for COMMENT_AUTHOR in $COMMENTS; do
+        if [ "$COMMENT_AUTHOR" == "$OWNER" ]; then
+            HAS_OWNER_REPLY=true
+            break
+        fi
+    done
+    
+    if [ "$HAS_OWNER_REPLY" == "false" ]; then
+        echo "ISSUE_START"
+        echo "ID: $NUMBER"
+        echo "Title: $TITLE"
+        echo "Author: $AUTHOR"
+        echo "Description:"
+        gh issue view "$NUMBER" --json body -q ".body"
+        echo "ISSUE_END"
+    fi
+done

.github/skills/i18n-validator/SKILL.md

@@ -0,0 +1,14 @@
+---
+name: i18n-validator
+description: Validates multi-language consistency in the TRANSLATIONS dictionary of a plugin. Use to check if any language keys are missing or if translations need updating.
+---
+
+# I18n Validator
+
+## Overview
+Ensures all 12 supported languages (en-US, zh-CN, etc.) have aligned translation keys.
+
+## Features
+- Detects missing keys in non-English dictionaries.
+- Suggests translations using the core AI engine.
+- Validates the `fallback_map` for variant redirects.

.github/skills/i18n-validator/scripts/validate_i18n.py

@@ -0,0 +1,54 @@
+#!/usr/bin/env python3
+import sys
+import ast
+import os
+
+def check_i18n(file_path):
+    if not os.path.exists(file_path):
+        print(f"Error: File not found {file_path}")
+        return
+    
+    with open(file_path, 'r', encoding='utf-8') as f:
+        tree = ast.parse(f.read())
+    
+    translations = {}
+    for node in tree.body:
+        if isinstance(node, ast.Assign):
+            for target in node.targets:
+                if isinstance(target, ast.Name) and target.id == "TRANSLATIONS":
+                    translations = ast.literal_eval(node.value)
+                    break
+    
+    if not translations:
+        print("⚠️ No TRANSLATIONS dictionary found.")
+        return
+
+    # Base keys from English
+    base_lang = "en-US"
+    if base_lang not in translations:
+        print(f"❌ Error: {base_lang} missing in TRANSLATIONS.")
+        return
+    
+    base_keys = set(translations[base_lang].keys())
+    print(f"🔍 Analyzing {file_path}...")
+    print(f"Standard keys ({len(base_keys)}): {', '.join(sorted(base_keys))}
+")
+
+    for lang, keys in translations.items():
+        if lang == base_lang: continue
+        lang_keys = set(keys.keys())
+        missing = base_keys - lang_keys
+        extra = lang_keys - base_keys
+        
+        if missing:
+            print(f"❌ {lang}: Missing {len(missing)} keys: {', '.join(missing)}")
+        if extra:
+            print(f"⚠️ {lang}: Has {len(extra)} extra keys: {', '.join(extra)}")
+        if not missing and not extra:
+            print(f"✅ {lang}: Aligned.")
+
+if __name__ == "__main__":
+    if len(sys.argv) < 2:
+        print("Usage: validate_i18n.py <path_to_plugin.py>")
+        sys.exit(1)
+    check_i18n(sys.argv[1])

.github/skills/plugin-scaffolder/SKILL.md

@@ -0,0 +1,20 @@
+---
+name: plugin-scaffolder
+description: Generates a standardized single-file i18n Python plugin template based on project standards. Use when starting a new plugin development to skip boilerplate writing.
+---
+
+# Plugin Scaffolder
+
+## Overview
+Generates compliant OpenWebUI plugin templates with built-in i18n, common utility methods, and required docstring fields.
+
+## Usage
+1. Provide the **Plugin Name** and **Type** (action/filter/pipe).
+2. The skill will generate the `.py` file and the bilingual `README` files.
+
+## Template Standard
+- `Valves(BaseModel)` with `UPPER_SNAKE_CASE`
+- `_get_user_context` with JS fallback and timeout
+- `_emit_status` and `_emit_debug_log` methods
+- Standardized docstring metadata
+- README header must use a two-column line with `By/作者 + vX.Y.Z` on the left and the Star link on the right, followed by a compact live badge row for followers, points, top (`Top <1%`), plugin contributions (`📦`), plugin downloads, plugin saves, and plugin views

.github/skills/plugin-scaffolder/assets/README_template.md

@@ -0,0 +1,38 @@
+# {{TITLE}}
+
+| By [Fu-Jie](https://github.com/Fu-Jie) · v0.1.0 | [⭐ Star this repo](https://github.com/Fu-Jie/openwebui-extensions) |
+| :--- | ---: |
+
+| ![followers](https://img.shields.io/endpoint?url=https%3A%2F%2Fgist.githubusercontent.com%2FFu-Jie%2Fdb3d95687075a880af6f1fba76d679c6%2Fraw%2Fbadge_followers.json&label=%F0%9F%91%A5&style=flat) | ![points](https://img.shields.io/endpoint?url=https%3A%2F%2Fgist.githubusercontent.com%2FFu-Jie%2Fdb3d95687075a880af6f1fba76d679c6%2Fraw%2Fbadge_points.json&label=%E2%AD%90&style=flat) | ![top](https://img.shields.io/badge/%F0%9F%8F%86-Top%20%3C1%25-10b981?style=flat) | ![contributions](https://img.shields.io/endpoint?url=https%3A%2F%2Fgist.githubusercontent.com%2FFu-Jie%2Fdb3d95687075a880af6f1fba76d679c6%2Fraw%2Fbadge_contributions.json&label=%F0%9F%93%A6&style=flat) | ![downloads](https://img.shields.io/endpoint?url=https%3A%2F%2Fgist.githubusercontent.com%2FFu-Jie%2Fdb3d95687075a880af6f1fba76d679c6%2Fraw%2Fbadge_downloads.json&label=%E2%AC%87%EF%B8%8F&style=flat) | ![saves](https://img.shields.io/endpoint?url=https%3A%2F%2Fgist.githubusercontent.com%2FFu-Jie%2Fdb3d95687075a880af6f1fba76d679c6%2Fraw%2Fbadge_saves.json&label=%F0%9F%92%BE&style=flat) | ![views](https://img.shields.io/endpoint?url=https%3A%2F%2Fgist.githubusercontent.com%2FFu-Jie%2Fdb3d95687075a880af6f1fba76d679c6%2Fraw%2Fbadge_views.json&label=%F0%9F%91%81%EF%B8%8F&style=flat) |
+| :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+
+{{DESCRIPTION}}
+
+## 🔥 What's New in v0.1.0
+
+* Initial release of {{TITLE}}.
+
+## 🌐 Multilingual Support
+
+Supports automatic interface and status switching for the following languages:
+`English`, `简体中文`, `繁體中文 (香港)`, `繁體中文 (台灣)`, `한국어`, `日本語`, `Français`, `Deutsch`, `Español`, `Italiano`, `Tiếng Việt`, `Bahasa Indonesia`.
+
+## ✨ Core Features
+
+* Feature 1
+* Feature 2
+
+## How to Use 🛠️
+
+1. Install the plugin in Open WebUI.
+2. Configure settings in Valves.
+
+## Configuration (Valves) ⚙️
+
+| Parameter | Default | Description |
+| :--- | :--- | :--- |
+| `priority` | `50` | Execution priority. |
+
+## ⭐ Support
+
+If this plugin has been useful, a star on [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) is a big motivation for me. Thank you for the support.

.github/skills/plugin-scaffolder/assets/template.py

@@ -0,0 +1,80 @@
+"""
+title: {{TITLE}}
+author: Fu-Jie
+author_url: https://github.com/Fu-Jie/openwebui-extensions
+funding_url: https://github.com/open-webui
+version: 0.1.0
+description: {{DESCRIPTION}}
+"""
+
+import asyncio
+import logging
+import json
+from typing import Optional, Dict, Any, List, Callable, Awaitable
+from pydantic import BaseModel, Field
+from fastapi import Request
+
+# Configure logging
+logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s")
+logger = logging.getLogger(__name__)
+
+TRANSLATIONS = {
+    "en-US": {"status_starting": "Starting {{TITLE}}..."},
+    "zh-CN": {"status_starting": "正在启动 {{TITLE}}..."},
+    "zh-HK": {"status_starting": "正在啟動 {{TITLE}}..."},
+    "zh-TW": {"status_starting": "正在啟動 {{TITLE}}..."},
+    "ko-KR": {"status_starting": "{{TITLE}} 시작 중..."},
+    "ja-JP": {"status_starting": "{{TITLE}} を起動中..."},
+    "fr-FR": {"status_starting": "Démarrage de {{TITLE}}..."},
+    "de-DE": {"status_starting": "{{TITLE}} wird gestartet..."},
+    "es-ES": {"status_starting": "Iniciando {{TITLE}}..."},
+    "it-IT": {"status_starting": "Avvio di {{TITLE}}..."},
+    "vi-VN": {"status_starting": "Đang khởi động {{TITLE}}..."},
+    "id-ID": {"status_starting": "Memulai {{TITLE}}..."},
+}
+
+class {{CLASS_NAME}}:
+    class Valves(BaseModel):
+        priority: int = Field(default=50, description="Priority level (lower = earlier).")
+        show_status: bool = Field(default=True, description="Show status updates in UI.")
+
+    def __init__(self):
+        self.valves = self.Valves()
+        self.fallback_map = {
+            "zh": "zh-CN", "en": "en-US", "ko": "ko-KR", "ja": "ja-JP",
+            "fr": "fr-FR", "de": "de-DE", "es": "es-ES", "it": "it-IT",
+            "vi": "vi-VN", "id": "id-ID"
+        }
+
+    def _get_translation(self, lang: str, key: str, **kwargs) -> str:
+        target_lang = lang
+        if target_lang not in TRANSLATIONS:
+            base = target_lang.split("-")[0]
+            target_lang = self.fallback_map.get(base, "en-US")
+        
+        lang_dict = TRANSLATIONS.get(target_lang, TRANSLATIONS["en-US"])
+        text = lang_dict.get(key, TRANSLATIONS["en-US"].get(key, key))
+        return text.format(**kwargs) if kwargs else text
+
+    async def _get_user_context(self, __user__: Optional[dict], __event_call__: Optional[Callable] = None, __request__: Optional[Request] = None) -> dict:
+        user_data = __user__ if isinstance(__user__, dict) else {}
+        user_language = user_data.get("language", "en-US")
+        if __event_call__:
+            try:
+                js = "try { return (document.documentElement.lang || localStorage.getItem('locale') || navigator.language || 'en-US'); } catch (e) { return 'en-US'; }"
+                frontend_lang = await asyncio.wait_for(__event_call__({"type": "execute", "data": {"code": js}}), timeout=2.0)
+                if frontend_lang: user_language = frontend_lang
+            except: pass
+        return {"user_language": user_language}
+
+    async def {{METHOD_NAME}}(self, body: dict, __user__: Optional[dict] = None, __event_emitter__=None, __event_call__=None, __request__: Optional[Request] = None) -> dict:
+        if self.valves.show_status and __event_emitter__:
+            user_ctx = await self._get_user_context(__user__, __event_call__, __request__)
+            msg = self._get_translation(user_ctx["user_language"], "status_starting")
+            await __event_emitter__({"type": "status", "data": {"description": msg, "done": False}})
+        
+        # Implement core logic here
+        
+        if self.valves.show_status and __event_emitter__:
+            await __event_emitter__({"type": "status", "data": {"description": "Done", "done": True}})
+        return body

.github/skills/plugin-scaffolder/assets/template.py.j2

@@ -0,0 +1,80 @@
+"""
+title: {{TITLE}}
+author: Fu-Jie
+author_url: https://github.com/Fu-Jie/openwebui-extensions
+funding_url: https://github.com/open-webui
+version: 0.1.0
+description: {{DESCRIPTION}}
+"""
+
+import asyncio
+import logging
+import json
+from typing import Optional, Dict, Any, List, Callable, Awaitable
+from pydantic import BaseModel, Field
+from fastapi import Request
+
+# Configure logging
+logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s")
+logger = logging.getLogger(__name__)
+
+TRANSLATIONS = {
+    "en-US": {"status_starting": "Starting {{TITLE}}..."},
+    "zh-CN": {"status_starting": "正在启动 {{TITLE}}..."},
+    "zh-HK": {"status_starting": "正在啟動 {{TITLE}}..."},
+    "zh-TW": {"status_starting": "正在啟動 {{TITLE}}..."},
+    "ko-KR": {"status_starting": "{{TITLE}} 시작 중..."},
+    "ja-JP": {"status_starting": "{{TITLE}} を起動中..."},
+    "fr-FR": {"status_starting": "Démarrage de {{TITLE}}..."},
+    "de-DE": {"status_starting": "{{TITLE}} wird gestartet..."},
+    "es-ES": {"status_starting": "Iniciando {{TITLE}}..."},
+    "it-IT": {"status_starting": "Avvio di {{TITLE}}..."},
+    "vi-VN": {"status_starting": "Đang khởi động {{TITLE}}..."},
+    "id-ID": {"status_starting": "Memulai {{TITLE}}..."},
+}
+
+class {{CLASS_NAME}}:
+    class Valves(BaseModel):
+        priority: int = Field(default=50, description="Priority level (lower = earlier).")
+        show_status: bool = Field(default=True, description="Show status updates in UI.")
+
+    def __init__(self):
+        self.valves = self.Valves()
+        self.fallback_map = {
+            "zh": "zh-CN", "en": "en-US", "ko": "ko-KR", "ja": "ja-JP",
+            "fr": "fr-FR", "de": "de-DE", "es": "es-ES", "it": "it-IT",
+            "vi": "vi-VN", "id": "id-ID"
+        }
+
+    def _get_translation(self, lang: str, key: str, **kwargs) -> str:
+        target_lang = lang
+        if target_lang not in TRANSLATIONS:
+            base = target_lang.split("-")[0]
+            target_lang = self.fallback_map.get(base, "en-US")
+        
+        lang_dict = TRANSLATIONS.get(target_lang, TRANSLATIONS["en-US"])
+        text = lang_dict.get(key, TRANSLATIONS["en-US"].get(key, key))
+        return text.format(**kwargs) if kwargs else text
+
+    async def _get_user_context(self, __user__: Optional[dict], __event_call__: Optional[Callable] = None, __request__: Optional[Request] = None) -> dict:
+        user_data = __user__ if isinstance(__user__, dict) else {}
+        user_language = user_data.get("language", "en-US")
+        if __event_call__:
+            try:
+                js = "try { return (document.documentElement.lang || localStorage.getItem('locale') || navigator.language || 'en-US'); } catch (e) { return 'en-US'; }"
+                frontend_lang = await asyncio.wait_for(__event_call__({"type": "execute", "data": {"code": js}}), timeout=2.0)
+                if frontend_lang: user_language = frontend_lang
+            except: pass
+        return {"user_language": user_language}
+
+    async def {{METHOD_NAME}}(self, body: dict, __user__: Optional[dict] = None, __event_emitter__=None, __event_call__=None, __request__: Optional[Request] = None) -> dict:
+        if self.valves.show_status and __event_emitter__:
+            user_ctx = await self._get_user_context(__user__, __event_call__, __request__)
+            msg = self._get_translation(user_ctx["user_language"], "status_starting")
+            await __event_emitter__({"type": "status", "data": {"description": msg, "done": False}})
+        
+        # Implement core logic here
+        
+        if self.valves.show_status and __event_emitter__:
+            await __event_emitter__({"type": "status", "data": {"description": "Done", "done": True}})
+        return body

.github/skills/plugin-scaffolder/scripts/scaffold.py

@@ -0,0 +1,66 @@
+#!/usr/bin/env python3
+import sys
+import os
+
+
+def scaffold(p_type, p_name, title, desc):
+    target_dir = f"plugins/{p_type}/{p_name}"
+    os.makedirs(target_dir, exist_ok=True)
+
+    class_name = (
+        "Action"
+        if p_type == "actions"
+        else (
+            "Filter"
+            if p_type == "filters"
+            else "Tools" if p_type == "tools" else "Pipe"
+        )
+    )
+    method_name = (
+        "action"
+        if p_type == "actions"
+        else (
+            "outlet"
+            if p_type == "filters"
+            else "execute" if p_type == "tools" else "pipe"
+        )
+    )
+
+    replacements = {
+        "{{TITLE}}": title,
+        "{{DESCRIPTION}}": desc,
+        "{{CLASS_NAME}}": class_name,
+        "{{METHOD_NAME}}": method_name,
+    }
+
+    # Files to generate
+    templates = [
+        ("assets/template.py.j2", f"{p_name}.py"),
+        ("assets/README_template.md", "README.md"),
+        ("assets/README_template.md", "README_CN.md"),
+    ]
+
+    # Path relative to skill root
+    skill_root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+
+    for t_path, t_name in templates:
+        template_file = os.path.join(skill_root, t_path)
+        if not os.path.exists(template_file):
+            print(f"⚠️ Warning: Template not found {template_file}")
+            continue
+
+        with open(template_file, "r") as f:
+            content = f.read()
+        for k, v in replacements.items():
+            content = content.replace(k, v)
+
+        with open(os.path.join(target_dir, t_name), "w") as f:
+            f.write(content)
+        print(f"✅ Generated: {target_dir}/{t_name}")
+
+
+if __name__ == "__main__":
+    if len(sys.argv) < 5:
+        print("Usage: scaffold.py <type> <name> <title> <desc>")
+        sys.exit(1)
+    scaffold(sys.argv[1], sys.argv[2], sys.argv[3], sys.argv[4])

.github/skills/pr-reviewer/SKILL.md

@@ -0,0 +1,180 @@
+---
+name: pr-reviewer
+description: Fetches PR review comments, analyzes requested changes, implements fixes, commits and pushes the resolution. Use after a reviewer has left comments on an open PR to close the feedback loop efficiently.
+---
+
+# PR Reviewer
+
+## Overview
+
+This skill automates the response cycle for code review. When a reviewer leaves comments on a Pull Request, this skill fetches all pending feedback, categorizes issues by severity, implements fixes, and submits a follow-up commit with appropriate review response comments.
+
+## Prerequisites
+
+- An open PR exists with pending review comments
+- The local branch matches the PR's head branch
+- `gh` CLI is authenticated
+
+---
+
+## Workflow
+
+### Step 1 — Fetch Review State
+
+Retrieve all review comments and overall review status:
+
+```bash
+# Get overall review decisions
+PAGER=cat GH_PAGER=cat gh pr view <PR-NUMBER> --json reviews,reviewDecision,headRefName \
+  --jq '{decision: .reviewDecision, reviews: [.reviews[] | {author: .author.login, state: .state, body: .body}]}'
+
+# Get inline code comments (specific line comments)
+PAGER=cat GH_PAGER=cat gh api repos/Fu-Jie/openwebui-extensions/pulls/<PR-NUMBER>/comments \
+  --jq '[.[] | {path: .path, line: .line, body: .body, author: .user.login, id: .id}]'
+
+# Get general issue comments
+PAGER=cat GH_PAGER=cat gh issue view <PR-NUMBER> --comments --json comments \
+  --jq '[.comments[] | {author: .author.login, body: .body}]'
+```
+
+Confirm the current local branch matches the PR head:
+```bash
+git branch --show-current
+```
+If mismatched, checkout the correct branch first.
+
+### Step 2 — Categorize Review Feedback
+
+Group feedback into categories:
+
+| Category | Examples | Action |
+|----------|---------|--------|
+| **Code Bug** | Logic error, incorrect variable, broken condition | Fix code immediately |
+| **Style / Formatting** | Indentation, naming convention, missing blank line | Fix code |
+| **Documentation** | Missing i18n key, wrong version in README, typo | Fix docs |
+| **Design Question** | Suggestion to restructure, alternative approach | Discuss with user before implementing |
+| **Nitpick / Optional** | Minor style preferences reviewer marked as optional | Fix if quick; document if skipped |
+| **Blocking** | Reviewer explicitly blocks merge | Must fix before proceeding |
+
+Present the full categorized list to the user and confirm the resolution plan.
+
+### Step 3 — Implement Fixes
+
+For each accepted fix:
+
+1. Read the affected file at the commented line for context:
+   ```bash
+   sed -n '<line-5>,<line+10>p' <file-path>
+   ```
+2. Apply the fix using appropriate file edit tools
+3. After editing, verify the specific area looks correct
+
+**For code changes that might affect behavior:**
+- Check if tests exist: `ls tests/test_*.py`
+- If tests exist, run them: `python -m pytest tests/ -v`
+
+**For documentation fixes:**
+- If modifying README.md, check if `docs/` mirror needs the same fix
+- Apply the same fix to both locations
+
+### Step 4 — Run Consistency Checks
+
+After all fixes are applied:
+
+```bash
+# Version consistency (if any version files were touched)
+python3 scripts/check_version_consistency.py
+
+# Quick syntax check for Python files
+python3 -m py_compile plugins/{type}/{name}/{name}.py && echo "✅ Syntax OK"
+```
+
+### Step 5 — Stage and Commit
+
+Create a new commit (do NOT amend if the branch has already been pushed, to avoid force-push):
+
+```bash
+git add -A
+git status
+```
+
+Draft a Conventional Commits message for the fixup:
+
+Format: `fix(scope): address review feedback`
+
+Body should list what was fixed, referencing reviewer concerns:
+```
+fix(github-copilot-sdk): address review feedback from @reviewer
+
+- Fix X per review comment on line Y of file Z
+- Update README to clarify auth requirement
+- Correct edge case in _parse_mcp_servers logic
+```
+
+```bash
+git commit -m "<fixup commit message>"
+```
+
+### Step 6 — Push the Fix Commit
+
+```bash
+git push origin $(git branch --show-current)
+```
+
+**Force-push policy:**
+- Use `git push` (non-force) by default
+- Only use `git push --force-with-lease` if:
+  1. The user explicitly requests it, AND
+  2. The only change is an amended commit squash (cosmetic, no logic change)
+  3. Never use `--force` (without `--lease`)
+
+### Step 7 — Respond to Reviewers
+
+For each addressed review comment, post a reply:
+
+```bash
+# Reply to inline comment
+gh api repos/Fu-Jie/openwebui-extensions/pulls/<PR-NUMBER>/comments/<COMMENT-ID>/replies \
+  -X POST -f body="Fixed in commit <SHORT-SHA>. <Brief explanation of what was changed.>"
+
+# General comment to summarize all fixes
+gh issue comment <PR-NUMBER> --body "All review feedback addressed in commit <SHORT-SHA>:
+- Fixed: <item 1>
+- Fixed: <item 2>
+Ready for re-review. 🙏"
+```
+
+### Step 8 — Re-Request Review (Optional)
+
+If the reviewer had submitted a `CHANGES_REQUESTED` review, request a new review after fixes:
+
+```bash
+PAGER=cat GH_PAGER=cat gh api repos/Fu-Jie/openwebui-extensions/pulls/<PR-NUMBER>/requested_reviewers \
+  -X POST -f reviewers[]='<reviewer-login>'
+```
+
+---
+
+## Decision Guide
+
+### When NOT to implement a suggestion immediately
+
+- **Design questions**: "Should this be a separate class?" — Present to user for decision
+- **Optional nitpicks**: Reviewer marked as `nit:` — Ask user if they want to include it
+- **Large refactors**: If fix would require changing >50 lines, propose a separate follow-up issue instead
+
+### When to ask the user before proceeding
+
+- Any fix involving behavioral changes to plugin logic
+- Renaming Valve keys (breaking change — requires migration notes)
+- Changes that affect the bilingual release notes already committed
+
+---
+
+## Anti-Patterns to Avoid
+
+- ❌ Do NOT `git commit --amend` on a pushed commit without user approval for force-push
+- ❌ Do NOT silently skip a reviewer's comment; always acknowledge it (implement or explain why not)
+- ❌ Do NOT use `--force` (only `--force-with-lease` when absolutely necessary)
+- ❌ Do NOT make unrelated changes in the fixup commit; keep scope focused on review feedback
+- ❌ Do NOT respond to reviewer comments in Chinese if the PR language context is English

.github/skills/pr-submitter/SKILL.md

@@ -0,0 +1,194 @@
+---
+name: pr-submitter
+description: Submits a feature branch as a Pull Request with a validated, properly formatted bilingual PR body. Handles shell-escape-safe body writing via temp files. Use after release-prep has committed all changes.
+---
+
+# PR Submitter
+
+## Overview
+
+This skill handles the final step of pushing a feature branch and creating a validated Pull Request on GitHub. Its primary purpose is to avoid the shell-escaping pitfalls (backticks, special characters in `gh pr create --body`) by always writing the PR body to a **temp file** first.
+
+## Prerequisites
+
+- All changes are committed (use `release-prep` skill first)
+- The `gh` CLI is authenticated (`gh auth status`)
+- Current branch is NOT `main` or `master`
+
+---
+
+## Workflow
+
+### Step 0 — Initialize Temp Directory (Project-Based)
+
+For all temporary files, use the project's `.temp/` directory instead of system `/tmp`:
+
+```bash
+# Create temp directory if it doesn't exist
+mkdir -p .temp
+```
+
+**Why**: All temporary files stay within the project workspace, avoiding system `/tmp` pollution and better aligning with OpenWebUI workspace isolation principles.
+
+### Step 1 — Pre-Flight Checks
+
+Run these checks before any push:
+
+```bash
+# 1. Confirm not on protected branch
+git branch --show-current
+
+# 2. Verify there are commits to push
+git log origin/$(git branch --show-current)..HEAD --oneline 2>/dev/null || echo "No remote tracking branch yet"
+
+# 3. Check gh CLI auth
+gh auth status
+```
+
+If any check fails, stop and report clearly.
+
+### Step 2 — Collect PR Metadata
+
+Gather:
+- **PR Title**: Must follow Conventional Commits format, English only (e.g., `feat(github-copilot-sdk): release v0.8.0 with conditional tool filtering`)
+- **Target base branch**: Default is `main`
+- **Plugin name + version** (to build body sections)
+- **Key changes** (reuse from release-prep or the latest What's New section)
+
+### Step 3 — Build PR Body File (Shell-Escape-Safe)
+
+**Always write the body to a temp file in `.temp/` directory.** Never embed multi-line markdown with special characters directly in a shell command.
+
+```bash
+cat > .temp/pr_body.md << 'HEREDOC'
+## Summary
+
+Brief one-sentence description of what this PR accomplishes.
+
+## Changes
+
+### New Features
+- Feature 1 description
+- Feature 2 description
+
+### Bug Fixes
+- Fix 1 description
+
+## Plugin Version
+- `PluginName` bumped to `vX.X.X`
+
+## Documentation
+- README.md / README_CN.md updated
+- docs/ mirrors synced
+
+## Testing
+- [ ] Tested locally in OpenWebUI
+- [ ] i18n validated (all language keys present)
+- [ ] Version consistency check passed (`python3 scripts/check_version_consistency.py`)
+
+---
+
+## 变更摘要（中文）
+
+简要描述本次 PR 的改动内容。
+
+### 新功能
+- 功能1描述
+- 功能2描述
+
+### 问题修复
+- 修复1描述
+HEREDOC
+```
+
+**Critical rules for the body file:**
+- Use `<< 'HEREDOC'` (quoted heredoc) to prevent variable expansion
+- Keep all backticks literal — they are safe inside a heredoc
+- Paths like `/api/v1/files/` are safe too since heredoc doesn't interpret them as commands
+
+### Step 4 — Validate PR Body
+
+Before submitting, verify the body file contains expected sections:
+
+```bash
+# Check key sections exist
+grep -q "## Summary" .temp/pr_body.md && echo "✅ Summary" || echo "❌ Summary missing"
+grep -q "## Changes" .temp/pr_body.md && echo "✅ Changes" || echo "❌ Changes missing"
+grep -q "## 变更摘要" .temp/pr_body.md && echo "✅ CN Section" || echo "❌ CN Section missing"
+
+# Preview the body
+cat .temp/pr_body.md
+```
+
+Ask the user to confirm the body content before proceeding.
+
+### Step 5 — Push Branch
+
+```bash
+git push -u origin $(git branch --show-current)
+```
+
+If push is rejected (non-fast-forward), report to user and ask whether to force-push. **Do NOT force-push without explicit confirmation.**
+
+### Step 6 — Create Pull Request
+
+```bash
+gh pr create \
+  --base main \
+  --head $(git branch --show-current) \
+  --title "<PR title from Step 2>" \
+  --body-file .temp/pr_body.md
+```
+
+Always use `--body-file`, never `--body` with inline markdown.
+
+### Step 7 — Verify PR Creation
+
+```bash
+PAGER=cat GH_PAGER=cat gh pr view --json number,url,title,body --jq '{number: .number, url: .url, title: .title, body_preview: .body[:200]}'
+```
+
+Confirm:
+- PR number and URL
+- Title matches intended Conventional Commits format
+- Body preview includes key sections (not truncated/corrupted)
+
+If the body appears corrupted (empty sections, missing backtick content), use edit:
+
+```bash
+gh pr edit <PR-NUMBER> --body-file /tmp/pr_body.md
+```
+
+### Step 8 — Cleanup
+
+```bash
+rm -f .temp/pr_body.md
+```
+
+**Note**: The `.temp/` directory itself is preserved for reuse; only the individual PR body file is deleted. To fully clean up: `rm -rf .temp/`
+
+Report final PR URL to the user.
+
+---
+
+## Shell-Escape Safety Rules
+
+| Risk | Safe Approach |
+|------|--------------|
+| Backticks in `--body` | Write to file, use `--body-file` |
+| Paths like `/api/...` | Safe in heredoc; risky in inline `--body` |
+| Newlines in `--body` | File-based only |
+| `$variable` expansion | Use `<< 'HEREDOC'` (quoted) |
+| Double quotes in body | Safe in heredoc file |
+| Temp file storage | Use `.temp/` dir, not `/tmp` |
+| Cleanup after use | Always delete temp file (keep dir) |
+
+---
+
+## Anti-Patterns to Avoid
+
+- ❌ Never use `--body "..."` with multi-line content directly in shell command
+- ❌ Never interpolate variables directly into heredoc without quoting the delimiter
+- ❌ Never force-push (`--force`) without explicit user confirmation
+- ❌ Never target `main` as the source branch (only as base)
+- ❌ Never skip the body validation step — a PR with empty body is worse than a delayed PR