docs: release v0.7.0 notes and update version artifacts

Publish scoped API keys, worker-pool governance, multi-instance storage, and the rest of the v0.7.0 feature set across CHANGELOG, READMEs, QA, Swagger, and version pins.
2026-08-29 02:04:30 +08:00 · 2026-07-17 14:41:27 +08:00
parent df21abe13b
commit e8dcbb07d0
14 changed files with 371 additions and 77 deletions
@@ -2,6 +2,65 @@

 All notable changes to this project will be documented in this file.

+## [0.7.0] - 2026-07-17
+
+### New Features
+
+- **NEW**: **Scoped Tenant API Keys & Principal Model** — the headline of this release. WeKnora now issues fine-grained, capability-scoped API keys that are first-class principals separate from human users (migrations `000064_principal_model`, `000065_tenant_api_keys`). Each key carries an explicit role plus capability grants (`manage_kbs` covering the full KB lifecycle, `manage_storage_backends`, member/space capabilities, etc.), can be restricted to specific knowledge bases, and updates its `last_used_at` under a throttle. Route-level guards (`DenyAPIKeyPrincipal`, `api_key_gate`) close IDOR/scope gaps, and a new **API Integration Playground** in the web UI lets owners mint, scope, and test keys interactively. MCP OAuth and embed sessions are now scoped per principal so external integrations stay isolated.
+- **NEW**: **Runtime Task Queue Observability & Worker-Pool Governance** — a system-admin **Runtime Queues** dashboard exposes live queue depth, per-model concurrency stats, failed-task inspection, manual retry, and cursor-paginated task listings. The ingestion pipeline moves from a single aggregate worker pool to guaranteed per-stage pools (core / post-process / enrichment / maintenance) plus a shared elastic pool, with per-model background concurrency governors (`model.max_concurrency`) wrapping chat, embedding, rerank, and VLM calls. Wiki generation runs in its own independently governed pool. See [`docs/worker-pool-governance.md`](./docs/worker-pool-governance.md).
+- **NEW**: **Multi-Instance Storage Backends** — each workspace can register multiple object/file storage instances (`local` / `minio` / `cos` / `tos` / `s3` / `oss` / `ks3` / `obs`) and bind different knowledge bases to different instances, with a workspace-level default (migration `000068_storage_backends`). Ships a full CRUD + connectivity-test API and settings UI, credential masking on read, and hardened image-source protection for storage backends. See [`docs/api/storage-backend.md`](./docs/api/storage-backend.md).
+- **NEW**: **Session-Scoped Temporary Attachments** — attach images and documents to a chat session for one-off Q&A with asynchronous parsing (migration `000070_temporary_documents`). Enforces a combined image + attachment limit, normalizes temporary attachment IDs, persists attachment content across turns, and adds a chat attachment preview drawer.
+- **NEW**: **Question & Follow-up Suggestions** — knowledge-grounded suggested questions plus after-answer follow-ups (migration `000067_question_suggestions`), with tag-scope aware generation, KB-scope preservation on click, and a dedicated follow-up rendering component.
+- **NEW**: **Stable Resource Registry & LLM-Context Alias Compaction** — a request-local resource registry (migration `000069_resource_registry`) assigns stable `res://` aliases to retrieved sources so LLM context stays compact and citations remain consistent; includes orphan-alias detection/logging and Markdown-based image context normalization.
+- **NEW**: **@Skill / @MCP Mentions with Scoped Agent Runtime** — mention skills and MCP services inline in chat to scope the agent runtime for a single turn, with hardened `@mention` scope resolution and consolidated per-turn scoping across knowledge tools.
+- **NEW**: **Mid-Conversation MCP OAuth** — MCP services can prompt for and resume OAuth authorization mid-chat, driven by `AuthType` with auto-detection on test, an OAuth skip endpoint, and in-chat OAuth interaction cards aligned with the agent tool timeline.
+- **NEW**: **QQBot & Lark (Feishu International) IM Integration** — new QQBot instant-messaging platform integration and support for Feishu's international edition (Lark), including region-aware routing and reply-in-thread via the Feishu reply-message API.
+- **NEW**: **`weknora` CLI v0.10** (BREAKING) — an agent-first CLI refresh: new `model`, `message`, `config`, and `skills` command groups; `doc reparse` / `doc update`; `kb config` / `kb config set`; `session resume` (renamed from `continue`) and `session tool-approval`; agent-first chat and `session ask` output modes; typed SDK errors/enums and KB model config; hardened SSE reliability; schema and exit-code contracts.
+- **NEW**: **Redis TLS Support** — TLS connections to Redis with config surfaced at startup and hardened TLS tests (#1930).
+- **NEW**: **New Providers** — Requesty added as an OpenAI-compatible model provider; Keenable added as a configurable web search provider.
+- **NEW**: **Tenantless Provisioning & Gated Self-Service Workspaces** — OIDC/login provisioning can create users without a tenant, with gated self-service workspace creation and a workspace onboarding flow, unified under a shared `default_tenant_mode` policy.
+- **NEW**: **Admin Password Reset & System Settings Tabs** — system admins can reset user passwords with session revocation and edit builtin model configs; system settings reorganized into tabbed sections. Password fields are sanitized in logs.
+- **NEW**: **Knowledge Base Duplicate Flow** — clone a knowledge base (config + structure) via a dedicated API and UI; custom instruction fields added to KB configuration with length validation.
+- **NEW**: **Per-Agent Citation Output Toggle** — agents can enable/disable citation output; retrieval references are still emitted to the references drawer even when in-answer citations are disabled.
+- **NEW**: **Chat References Drawer & UX Polish** — a dedicated references drawer with web/KB source distinction, inline session-title rename in the sidebar, chat reference links opening in new tabs, and native streaming loading placeholders.
+
+### Improvements
+
+- **IMPROVED**: **Security hardening (broad triage)** — closed numerous open GHSA findings and security-triage gaps: SSRF protection across web_fetch, datasource connectors, knowledge URL import (including redirect chains), MinerU, embedders, and model clients; secret redaction in login, tenant KV, integration-list, and initialization/parser-check responses; SQL-validator bypass closed in agent database tools; refresh-token validation hardened (blocked as bearer); MCP upload sandbox enforced across transports; wiki/IDOR KB-access enforcement; nginx iframe `X-Frame-Options`.
+- **IMPROVED**: **Wiki ingestion** — dedicated worker pool with concurrent claim-based batching; recovers stranded claims, prevents finalize double-run and cross-batch document races, and strips internal chunk aliases from page content.
+- **IMPROVED**: **Knowledge processing** — safe task recovery after server restart, chunking strategy propagated to parent-child splitter configs, richer error handling in knowledge spans, rune-aware span-name fitting with expanded name column, and processing-timeline status aligned with the knowledge row.
+- **IMPROVED**: **Terminology** — user-facing "tenant" labels renamed to "workspace" across the UI and i18n.
+- **IMPROVED**: **Chat streaming** — unified streaming wait indicators across chat and embed, follow-up suggestion loading and answer-toolbar timing polished, references drawer closed on session switch, and enforced retrieved-image output in answers.
+- **IMPROVED**: **Frontend resilience** — hardened settings `localStorage` load to prevent white-screen from corrupted state; shared document action menu and card-view components extracted; Wiki badge on KB cards; responsive doc filter bar.
+- **IMPROVED**: **Infrastructure config** — infrastructure host/port configurable via env vars in docker-compose; remote infrastructure supported via `.env.local`; `WEKNORA_MODEL_MAX_CONCURRENCY` defaulted to 32.
+- **IMPROVED**: **docreader** — SSRF utility and safe HTTP client added; legacy doc-payload detection; parser routing tests.
+
+### Bug Fixes
+
+- **FIXED**: Chat now emits retrieval references even when citation output is disabled.
+- **FIXED**: `/api/v1/tenants/kv/storage-engine-config` returned no Huawei OBS config, causing the KB-creation dialog to omit the OBS unavailable marker.
+- **FIXED**: Empty tenant `default_provider` fell back to `local` even when `local` was not in `STORAGE_ALLOW_LIST`, breaking KB creation.
+- **FIXED**: DingTalk file/image messages now ingest into the knowledge base with SSRF-checked downloads and `pictureDownloadCode` fallback (#1771).
+- **FIXED**: Feishu WebSocket long connection now actually closes when the channel is stopped; replies land in the original thread.
+- **FIXED**: Tag filters correctly applied to knowledge search; tag-scope resolution hardened (#1907).
+- **FIXED**: Scoped API keys can poll FAQ import progress; KB-scoped file proxy restricted to `exports/` paths while still serving shared KB images.
+- **FIXED**: Web-search controls gated by provider readiness; agent selector capability status chips polished.
+- **FIXED**: Manual knowledge editor publish flow; doc list reloads after tag rename in the manage drawer.
+- **FIXED**: Division-by-zero guard in FAQ import timing logs; VLM temperature made configurable.
+
+### Infrastructure & Build
+
+- **BUILD**: Migrations `000064_principal_model`, `000065_tenant_api_keys`, `000066_expand_knowledge_span_name`, `000067_question_suggestions`, `000068_storage_backends`, `000069_resource_registry`, `000070_temporary_documents`.
+- **BUILD**: Per-pool task-queue governance (core / post-process / enrichment / maintenance / shared / wiki); model concurrency limiter/governor package.
+- **BUILD**: Go client extended for scoped API keys, storage backends, message suggestions, KB duplicate, and streaming error types; resolved open Dependabot alerts across Go, npm, and pip.
+- **BUILD**: Swagger / API docs regenerated; `docs/api/storage-backend.md` added.
+
+### Documentation
+
+- **DOC**: `docs/worker-pool-governance.md` added; `docs/api/storage-backend.md` added.
+- **DOC**: `docs/QA.md`, wiki docs, and per-feature guides extended for scoped API keys, storage backends, runtime queues, temporary attachments, and MCP OAuth.
+- **DOC**: Architecture diagram updated for scoped API keys, multi-instance storage, and worker-pool governance.
+
 ## [0.6.3] - 2026-06-26

 ### New Features
@@ -28,7 +28,7 @@
        <img src="https://img.shields.io/badge/License-MIT-ffffff?labelColor=d4eaf7&color=2e6cc4" alt="License">
    </a>
    <a href="./CHANGELOG.md">
-        <img alt="Version" src="https://img.shields.io/badge/version-0.6.3-2e6cc4?labelColor=d4eaf7">
+        <img alt="Version" src="https://img.shields.io/badge/version-0.7.0-2e6cc4?labelColor=d4eaf7">
    </a>
 </p>

@@ -50,13 +50,14 @@

 [**WeKnora**](https://weknora.weixin.qq.com) is an open-source, LLM-powered knowledge framework built for enterprise-grade document understanding, semantic retrieval, and autonomous reasoning.

-It is organized around three core capabilities: **RAG-based Quick Q&A** for everyday lookups, a **ReAct Agent** that autonomously orchestrates retrieval, MCP tools and web search to handle complex multi-step tasks, and a brand-new **Wiki Mode** in which agents distill raw documents into a self-maintaining, interlinked markdown knowledge base with an interactive knowledge graph. Combined with multi-source ingestion (Feishu / Notion / Yuque / RSS, and growing), **website embed widgets** for publishing agents to external sites, 20+ LLM provider integrations, full Langfuse observability, **enterprise-ready multi-workspace RBAC** (4-tier role matrix + per-resource ownership + per-workspace audit log), and a fully self-hostable modular architecture, WeKnora turns scattered documents into a queryable, reasoning-capable, continuously evolving knowledge asset.
+It is organized around three core capabilities: **RAG-based Quick Q&A** for everyday lookups, a **ReAct Agent** that autonomously orchestrates retrieval, MCP tools and web search to handle complex multi-step tasks, and a brand-new **Wiki Mode** in which agents distill raw documents into a self-maintaining, interlinked markdown knowledge base with an interactive knowledge graph. Combined with multi-source ingestion (Feishu / Notion / Yuque / RSS, and growing), **website embed widgets** for publishing agents to external sites, **scoped API keys with a principal model** for programmatic integrations, **multi-instance storage backends** per workspace for flexible data placement, 20+ LLM provider integrations, full Langfuse observability plus a **runtime task-queue dashboard with worker-pool governance**, **enterprise-ready multi-workspace RBAC** (4-tier role matrix + per-resource ownership + per-workspace audit log), and a fully self-hostable modular architecture, WeKnora turns scattered documents into a queryable, reasoning-capable, continuously evolving knowledge asset.

 The framework supports auto-syncing knowledge from Feishu, Notion, and Yuque (more data sources coming soon), handles 10+ document formats including PDF, Word, images, and Excel, and can serve Q&A directly through IM channels like WeCom, Feishu, Slack, and Telegram. It is compatible with major LLM providers including OpenAI, DeepSeek, Qwen (Alibaba Cloud), Zhipu, Hunyuan, Gemini, MiniMax, NVIDIA, and Ollama. Its fully modular design allows swapping LLMs, vector databases, and storage backends, with support for local and private cloud deployment ensuring complete data sovereignty. WeKnora also integrates with **Langfuse** for comprehensive observability into agent reasoning, token usage, and pipeline tracing.


 ## ✨ Latest Updates

+- **v0.7.0** — Fine-grained **scoped API keys & principal model** (capability-level grants + per-KB restriction + API integration playground); **runtime task-queue observability dashboard & worker-pool governance** (per-stage pools + per-model concurrency governors + failed-task inspection/retry); **multi-instance storage backends** (multiple storage instances per workspace, per-KB binding, default instance); **session-scoped temporary attachments** (async image/doc parsing + combined limits); question & follow-up suggestions; stable resource registry with LLM-context alias compaction; `@Skill / @MCP` mentions with scoped agent runtime; mid-conversation MCP OAuth; QQBot & Lark (Feishu International) IM integration; Redis TLS; Requesty model provider + Keenable web search; tenantless provisioning & gated self-service workspaces; admin password reset; knowledge base duplicate flow; `weknora` CLI v0.10. Plus broad security hardening (SSRF, secret redaction, SQL validation, IDOR). See [`CHANGELOG.md`](./CHANGELOG.md).
 - **v0.6.3** — Website embed widget & Integrations Center (secure-mode token exchange + rate limits); chat experience overhaul (citation popovers, RAG pipeline progress, streaming markdown); document multi-tag & batch reparse; Wiki folders & hierarchy navigation; RSS data source; MCP OAuth2; EPUB / MHTML parsing; agent model-readiness checks; model test debugger; session source filter; workspace deletion UI. See [`CHANGELOG.md`](./CHANGELOG.md).
 - **v0.6.2** — Per-upload process configuration with upload-confirm dialog; document reparse with `process_config`; `weknora` CLI v0.9 (bundled Agent Skills, `session stop`, auth/profile harmonization); KB marquee multi-select; HNSW index for 1024-dim pgvector embeddings; chat resources store refactor; Langfuse-only tracing (Jaeger removed). See [`CHANGELOG.md`](./CHANGELOG.md).
 - **v0.6.1** — Document parsing trace timeline (Langfuse-style span tree with stage-by-stage progress + stop-parse); OpenSearch vector store driver; declarative built-in models via YAML; system admin & consolidated platform settings + audit log; new-user onboarding guide; settings UI redesign; `weknora` CLI v0.7 / v0.8 (agent-first wire contract, NDJSON, `--dry-run`); OpenDataLoader + PaddleOCR-VL parsers; MCP server multi-transport (stdio / SSE / HTTP); per-model thinking-mode config; Tencent LKEAP rerank + native Gemini embeddings + MiniMax-M3. See [`CHANGELOG.md`](./CHANGELOG.md).
@@ -108,11 +109,12 @@ Fully modular pipeline from document parsing, vectorization, and retrieval to LL
 | Intelligent Reasoning | ReACT progressive multi-step reasoning, autonomously orchestrating knowledge retrieval, MCP tools, and web search |
 | Quick Q&A | RAG-based Q&A over knowledge bases for fast and accurate answers |
 | Wiki Mode | Agent-driven auto-generation of structured, interlinked markdown Wiki pages from raw documents |
-| Tool Calling | Built-in tools, MCP tools (incl. OAuth2 remote services), web search |
-| Conversation Strategy | Online Prompt editing, retrieval threshold tuning, multi-turn context awareness |
-| Suggested Questions | Auto-generated question suggestions based on knowledge base content |
-| Citations & RAG Progress | Inline citation popovers, shared markdown rendering, and stage-by-stage RAG pipeline progress in chat |
-| Session Management | Filter and group sidebar sessions by source (Web / IM / Embed) |
+| Tool Calling | Built-in tools, MCP tools (incl. OAuth2 remote services, mid-conversation OAuth), web search; `@Skill / @MCP` mentions to scope the agent runtime per turn |
+| Conversation Strategy | Online Prompt editing, retrieval threshold tuning, multi-turn context awareness, per-agent citation output toggle |
+| Suggested Questions | Auto-generated question suggestions and after-answer follow-ups based on knowledge base content |
+| Temporary Attachments | Session-scoped image / document uploads with async parsing for one-off Q&A, with a combined image + attachment limit |
+| Citations & RAG Progress | Inline citation popovers and a references drawer (web / KB source distinction), shared markdown rendering, and stage-by-stage RAG pipeline progress in chat |
+| Session Management | Filter and group sidebar sessions by source (Web / IM / Embed), with inline session-title rename |

 **Knowledge Management**

@@ -131,13 +133,14 @@ Fully modular pipeline from document parsing, vectorization, and retrieval to LL

 | Capability | Details |
 |------------|---------|
-| LLMs | OpenAI / Azure OpenAI / Anthropic (Claude) / DeepSeek / Qwen (Alibaba Cloud) / Zhipu / Hunyuan / Doubao (Volcengine) / Gemini / MiniMax / NVIDIA / Novita AI / SiliconFlow / OpenRouter / Ollama |
+| LLMs | OpenAI / Azure OpenAI / Anthropic (Claude) / DeepSeek / Qwen (Alibaba Cloud) / Zhipu / Hunyuan / Doubao (Volcengine) / Gemini / MiniMax / NVIDIA / Novita AI / SiliconFlow / OpenRouter / Requesty / Ollama |
 | Embeddings | Ollama / BGE / GTE / Zhipu / OpenAI-compatible APIs |
 | Vector DBs | PostgreSQL (pgvector) / Elasticsearch / OpenSearch / Milvus / Weaviate / Qdrant / Apache Doris / Tencent VectorDB |
-| Object Storage | Local / MinIO / AWS S3 / Volcengine TOS / Alibaba Cloud OSS / Kingsoft Cloud KS3 / Huawei Cloud OBS |
-| IM Channels | WeCom / Feishu / Lark / Slack / Telegram / DingTalk / Mattermost / WeChat |
+| Object Storage | Local / MinIO / AWS S3 / Volcengine TOS / Alibaba Cloud OSS / Kingsoft Cloud KS3 / Huawei Cloud OBS; **multiple storage instances per workspace** with per-KB binding and a default instance |
+| IM Channels | WeCom / Feishu / Lark (Feishu International) / QQBot / Slack / Telegram / DingTalk / Mattermost / WeChat |
 | Website Embed | Publish agents via embed widget with domain allowlists, rate limits, and secure-mode token exchange |
-| Web Search | DuckDuckGo / Bing / Google / Tavily / Baidu / Ollama / SearXNG |
+| Web Search | DuckDuckGo / Bing / Google / Tavily / Baidu / Ollama / SearXNG / Keenable |
+| API Integration | Scoped API keys (capability-level grants + per-KB restriction + throttled last-used tracking) with an API integration playground; MCP OAuth and embed sessions isolated per principal |

 **Platform**

@@ -145,10 +148,10 @@ Fully modular pipeline from document parsing, vectorization, and retrieval to LL
 |------------|---------|
 | Deployment | Local / Docker / Kubernetes (Helm) with private and offline support |
 | UI | Web UI / RESTful API / CLI (`weknora`) / Chrome Extension / Website Embed Widget / WeChat Mini Program |
-| Access Control | Workspace RBAC with 4-tier role matrix (Owner / Admin / Contributor / Viewer), per-KB resource ownership, per-workspace audit log, invite-only workspaces, self-service workspace creation, cross-workspace superuser |
-| Security | AES-256-GCM at-rest encryption for API keys and MCP / data-source credentials with graceful key rotation; gRPC TLS + Token between app and docreader; SSRF-safe HTTP client; sandbox isolation for agent skills |
-| Observability | Integrated Langfuse (sole tracing backend) for ReAct loops, token tracking, tool calls, and pipeline tracing; built-in Langfuse-style document parsing trace timeline with stage-by-stage progress |
-| Task Management | MQ async tasks, automatic database migration on version upgrade |
+| Access Control | Workspace RBAC with 4-tier role matrix (Owner / Admin / Contributor / Viewer), per-KB resource ownership, per-workspace audit log, invite-only workspaces, tenantless provisioning & gated self-service workspace creation, admin password reset (session revocation), cross-workspace superuser, scoped API keys |
+| Security | AES-256-GCM at-rest encryption for API keys and MCP / data-source credentials with graceful key rotation; gRPC TLS + Token between app and docreader; Redis TLS; SSRF-safe HTTP client (data sources, URL import, redirect chains); secret redaction in responses; sandbox isolation for agent skills |
+| Observability | Integrated Langfuse (sole tracing backend) for ReAct loops, token tracking, tool calls, and pipeline tracing; built-in Langfuse-style document parsing trace timeline with stage-by-stage progress; system-admin runtime task-queue dashboard (queue depth, per-model concurrency, failed-task inspection & manual retry) |
+| Task Management | MQ async tasks with per-stage worker-pool governance (core / post-process / enrichment / maintenance + elastic shared pool, plus an independent Wiki pool) and per-model background concurrency governors; automatic database migration on version upgrade |
 | Model Management | Centralized config, declarative built-in models via YAML, per-knowledge-base model selection, per-model thinking-mode and embedding-dimension overrides, interactive model test debugger, multi-workspace built-in model sharing, WeKnora Cloud hosted models and parsing |

 ## 🧩 Chrome Extension
@@ -28,7 +28,7 @@
        <img src="https://img.shields.io/badge/License-MIT-ffffff?labelColor=d4eaf7&color=2e6cc4" alt="License">
    </a>
    <a href="./CHANGELOG.md">
-        <img alt="版本" src="https://img.shields.io/badge/version-0.6.3-2e6cc4?labelColor=d4eaf7">
+        <img alt="版本" src="https://img.shields.io/badge/version-0.7.0-2e6cc4?labelColor=d4eaf7">
    </a>
 </p>

@@ -50,12 +50,13 @@

 **[WeKnora（维娜拉）](https://weknora.weixin.qq.com)** 是一款开源的、基于大语言模型（LLM）的知识管理框架，专为企业级文档理解、语义检索与智能推理场景打造。

-框架围绕三大核心能力构建：**RAG 快速问答**适合日常知识查询，**ReAct Agent 智能推理**自主编排知识检索、MCP 工具与网络搜索完成复杂多步任务，全新的 **Wiki 模式**则让 Agent 从原始文档中自治生成相互链接的 Markdown 知识库与可视化知识图谱。结合多源数据接入（飞书 / Notion / 语雀 / RSS，更多持续接入中）、**网站嵌入 Widget** 将智能体发布到外部站点、二十余家主流模型厂商集成、Langfuse 全链路可观测性、**企业级多空间 RBAC（四级角色矩阵 + 资源归属 + 空间审计日志）**，以及完全可私有化部署的模块化架构，WeKnora 帮助团队把分散文档沉淀为可查询、可推理、可持续演进的专属知识资产。
+框架围绕三大核心能力构建：**RAG 快速问答**适合日常知识查询，**ReAct Agent 智能推理**自主编排知识检索、MCP 工具与网络搜索完成复杂多步任务，全新的 **Wiki 模式**则让 Agent 从原始文档中自治生成相互链接的 Markdown 知识库与可视化知识图谱。结合多源数据接入（飞书 / Notion / 语雀 / RSS，更多持续接入中）、**网站嵌入 Widget** 将智能体发布到外部站点、**权限范围 API Key 与 Principal 模型**面向程序化集成、**每空间多实例存储后端**灵活编排数据落地、二十余家主流模型厂商集成、Langfuse 全链路可观测性与**运行时任务队列面板 + Worker 池治理**、**企业级多空间 RBAC（四级角色矩阵 + 资源归属 + 空间审计日志）**，以及完全可私有化部署的模块化架构，WeKnora 帮助团队把分散文档沉淀为可查询、可推理、可持续演进的专属知识资产。

 框架支持从飞书、Notion 及语雀等外部平台自动同步知识（更多数据源持续接入中），覆盖 PDF、Word、图片、Excel 等十余种文档格式，并可通过企业微信、飞书、Slack、Telegram 等 IM 频道直接提供问答服务。模型层面兼容 OpenAI、DeepSeek、Qwen（阿里云）、智谱、混元、Gemini、MiniMax、NVIDIA、Ollama 等主流厂商。全流程模块化设计，大模型、向量数据库、存储等组件均可灵活替换，支持本地与私有云部署，数据完全自主可控。WeKnora 还无缝集成了 **Langfuse**，为 Agent 运行、Token 使用及任务流水线提供了全面的可观测性追踪。

 ## ✨ 最新更新

+- **v0.7.0** —— 细粒度**权限范围 API Key 与 Principal 模型**（能力级授权 + 按 KB 限制 + API 集成调试台）；**运行时任务队列可观测面板与 Worker 池治理**（分阶段独立池 + 按模型并发治理 + 失败任务排查/重试）；**多实例存储后端**（每空间多存储实例、按 KB 绑定、默认实例）；**会话级临时附件**（图片/文档异步解析 + 合并限额）；推荐问题与追问；稳定资源注册表与 LLM 上下文别名压缩；`@Skill / @MCP` 提及范围化 Agent 运行时；会话内 MCP OAuth 授权；QQBot 与 Lark（飞书国际版）IM 集成；Redis TLS；Requesty 模型厂商 + Keenable 网络搜索；无租户预置与受控自助创建工作区；管理员密码重置；知识库复制流程；`weknora` CLI v0.10。同时完成大范围安全加固（SSRF、密钥脱敏、SQL 校验、越权）。详见 [`CHANGELOG.md`](./CHANGELOG.md)。
 - **v0.6.3** —— 网站嵌入 Widget 与发布集成中心（安全模式 Token 交换 + 限流）；对话体验全面革新（引用浮层、RAG 流水线进度、流式 Markdown）；文档多标签与批量重新解析；Wiki 文件夹与层级导航；RSS 数据源；MCP OAuth2；EPUB / MHTML 解析；Agent 模型就绪校验；模型调试器；会话来源筛选；工作区删除 UI。详见 [`CHANGELOG.md`](./CHANGELOG.md)。
 - **v0.6.2** —— 按批次解析配置（`process_config`）+ 上传确认对话框；文档重新解析（reparse）支持覆盖配置；`weknora` CLI v0.9（内置 Agent Skills、`session stop`、auth/profile 统一）；知识库框选多选；pgvector 1024 维 HNSW 索引；对话资源 Store 重构；仅保留 Langfuse 追踪（移除 Jaeger）。详见 [`CHANGELOG.md`](./CHANGELOG.md)。
 - **v0.6.1** —— 文档解析追踪时间线（Langfuse 风格 Span 树，逐阶段进度展示 + 解析中止）；OpenSearch 向量库驱动；YAML 声明式内置模型配置；系统管理员与统一平台设置 + 审计日志；新用户引导；设置页 UI 重构；`weknora` CLI v0.7 / v0.8（Agent 优先线协议、NDJSON、`--dry-run`）；OpenDataLoader 与 PaddleOCR-VL 解析引擎；MCP Server 多传输（stdio / SSE / HTTP）；按模型的思考模式配置；腾讯云 LKEAP 重排 + 原生 Gemini Embedding + MiniMax-M3。详见 [`CHANGELOG.md`](./CHANGELOG.md)。
@@ -107,11 +108,12 @@
 | 智能推理 | ReACT 渐进式多步推理，自主编排知识检索、MCP 工具与网络搜索 |
 | 快速问答 | 基于知识库的 RAG 问答，快速准确地回答问题 |
 | Wiki 模式 | Agent 驱动从原始文档中自动生成并维护结构化、相互链接的 Markdown Wiki 知识页面 |
-| 工具调用 | 内置工具、MCP 工具（含 OAuth2 远程服务）、网络搜索 |
-| 对话策略 | 在线 Prompt 编辑、检索阈值调节、多轮上下文感知 |
-| 推荐问题 | 基于知识库内容自动生成推荐问题 |
-| 引用与 RAG 进度 | 对话内引用浮层、统一 Markdown 渲染、RAG 流水线分阶段进度展示 |
-| 会话管理 | 侧边栏按来源（Web / IM / 嵌入）筛选与分组会话 |
+| 工具调用 | 内置工具、MCP 工具（含 OAuth2 远程服务、会话内 OAuth 授权）、网络搜索；支持 `@Skill / @MCP` 提及以按轮次范围化 Agent 运行时 |
+| 对话策略 | 在线 Prompt 编辑、检索阈值调节、多轮上下文感知、按 Agent 引用输出开关 |
+| 推荐问题 | 基于知识库内容自动生成推荐问题与答后追问 |
+| 临时附件 | 会话级临时上传图片 / 文档，异步解析后用于一次性问答，支持图片与附件合并限额 |
+| 引用与 RAG 进度 | 对话内引用浮层与引用抽屉（区分网络 / 知识库来源）、统一 Markdown 渲染、RAG 流水线分阶段进度展示 |
+| 会话管理 | 侧边栏按来源（Web / IM / 嵌入）筛选与分组会话，支持会话标题内联重命名 |

 **知识管理**

@@ -130,13 +132,14 @@

 | 能力 | 详情 |
 |------|------|
-| 模型厂商 | OpenAI / Azure OpenAI / Anthropic（Claude）/ DeepSeek / Qwen（阿里云）/ 智谱 / 混元 / 豆包（火山引擎）/ Gemini / MiniMax / NVIDIA / Novita AI / SiliconFlow / OpenRouter / Ollama |
+| 模型厂商 | OpenAI / Azure OpenAI / Anthropic（Claude）/ DeepSeek / Qwen（阿里云）/ 智谱 / 混元 / 豆包（火山引擎）/ Gemini / MiniMax / NVIDIA / Novita AI / SiliconFlow / OpenRouter / Requesty / Ollama |
 | 向量数据库 | PostgreSQL (pgvector) / Elasticsearch / OpenSearch / Milvus / Weaviate / Qdrant / Apache Doris / 腾讯云 VectorDB |
 | Embedding | Ollama / BGE / GTE / 智谱 / OpenAI 兼容接口 |
-| 对象存储 | 本地 / 腾讯云COS / 火山引擎 TOS / MinIO / AWS S3 / 阿里云 OSS / 金山云 KS3 / 华为云 OBS |
-| IM 集成 | 企业微信 / 飞书 / Lark / Slack / Telegram / 钉钉 / Mattermost / 微信 |
+| 对象存储 | 本地 / 腾讯云COS / 火山引擎 TOS / MinIO / AWS S3 / 阿里云 OSS / 金山云 KS3 / 华为云 OBS；支持**每空间多实例存储后端**，不同知识库可绑定不同实例并设置默认实例 |
+| IM 集成 | 企业微信 / 飞书 / Lark（飞书国际版）/ QQBot / Slack / Telegram / 钉钉 / Mattermost / 微信 |
 | 网站嵌入 | 通过嵌入 Widget 发布智能体，支持域名白名单、限流与安全模式 Token 交换 |
-| 网络搜索 | DuckDuckGo / Bing / Google / Tavily / Baidu / Ollama / SearXNG |
+| 网络搜索 | DuckDuckGo / Bing / Google / Tavily / Baidu / Ollama / SearXNG / Keenable |
+| API 集成 | 权限范围 API Key（能力级授权 + 按 KB 限制 + 节流的 last_used 追踪）与 API 集成调试台；MCP OAuth 与嵌入会话按 Principal 隔离 |


 **平台能力**
@@ -145,10 +148,10 @@
 |------|------|
 | 部署 | 本地 / Docker / Kubernetes (Helm)，支持私有化离线部署 |
 | 界面 | Web UI / RESTful API / 命令行（`weknora`）/ Chrome Extension / 网站嵌入 Widget / 微信小程序 |
-| 权限控制 | 空间 RBAC 四级角色矩阵（Owner / Admin / Contributor / Viewer），按知识库的资源归属，每空间审计日志，invite-only 准入，自助创建工作区，跨空间超级管理员 |
-| 安全 | API Key 与 MCP / 数据源凭据 AES-256-GCM 静态加密、支持平滑密钥轮换；app ↔ docreader gRPC TLS + Token；防 SSRF HTTP 客户端；Agent 技能沙箱隔离 |
-| 可观测性 | 集成 Langfuse（唯一追踪后端）以追踪 ReAct 循环、Token 消耗、工具调用和任务流水线；内置 Langfuse 风格的文档解析追踪时间线，逐阶段展示解析进度 |
-| 任务管理 | MQ 异步任务，版本升级自动数据库迁移 |
+| 权限控制 | 空间 RBAC 四级角色矩阵（Owner / Admin / Contributor / Viewer），按知识库的资源归属，每空间审计日志，invite-only 准入，无租户预置与受控自助创建工作区，管理员密码重置（会话吊销），跨空间超级管理员，权限范围 API Key |
+| 安全 | API Key 与 MCP / 数据源凭据 AES-256-GCM 静态加密、支持平滑密钥轮换；app ↔ docreader gRPC TLS + Token；Redis TLS；防 SSRF HTTP 客户端（覆盖数据源、URL 导入、重定向链等）；密钥响应脱敏；Agent 技能沙箱隔离 |
+| 可观测性 | 集成 Langfuse（唯一追踪后端）以追踪 ReAct 循环、Token 消耗、工具调用和任务流水线；内置 Langfuse 风格的文档解析追踪时间线，逐阶段展示解析进度；系统管理员运行时任务队列面板（队列深度、按模型并发、失败任务排查与手动重试） |
+| 任务管理 | MQ 异步任务，分阶段独立 Worker 池治理（core / 后处理 / enrichment / maintenance + 弹性共享池，Wiki 独立池）与按模型后台并发治理；版本升级自动数据库迁移 |
 | 模型管理 | 集中配置，YAML 声明式内置模型配置，知识库级别模型选择，按模型思考模式与 Embedding 维度覆盖，交互式模型调试器，多空间共享内置模型，WeKnora Cloud 托管模型与文档解析 |

 ## 🧩 Chrome 插件
@@ -28,7 +28,7 @@
        <img src="https://img.shields.io/badge/License-MIT-ffffff?labelColor=d4eaf7&color=2e6cc4" alt="License">
    </a>
    <a href="./CHANGELOG.md">
-        <img alt="バージョン" src="https://img.shields.io/badge/version-0.6.3-2e6cc4?labelColor=d4eaf7">
+        <img alt="バージョン" src="https://img.shields.io/badge/version-0.7.0-2e6cc4?labelColor=d4eaf7">
    </a>
 </p>

@@ -50,12 +50,13 @@

 [**WeKnora（ウィーノラ）**](https://weknora.weixin.qq.com) は、大規模言語モデル（LLM）をベースとしたオープンソースのナレッジフレームワークで、エンタープライズ級の文書理解、セマンティック検索、自律推論シナリオ向けに設計されています。

-本フレームワークは **3 つのコア能力** を中心に構築されています：日常的な検索に最適な **RAG ベースのクイック Q&A**、ナレッジ検索・MCP ツール・Web 検索を自律的にオーケストレーションし複雑なマルチステップタスクを処理する **ReAct Agent 推論**、そして Agent が生のドキュメントから相互リンクされた Markdown ナレッジベースとインタラクティブなナレッジグラフを自律生成・維持する全く新しい **Wiki モード**。さらに、多様なデータソース連携（Feishu / Notion / Yuque / RSS、随時拡充中）、**ウェブサイト埋め込み Widget** による外部サイトへのエージェント公開、20 以上の LLM プロバイダー統合、Langfuse による全体可観測性、**エンタープライズ向けマルチテナント RBAC（4 階層ロールマトリクス + リソース所有権 + テナント監査ログ）**、完全セルフホスト可能なモジュラーアーキテクチャと組み合わせることで、WeKnora は散在する文書を「検索可能・推論可能・継続的に進化する」専用ナレッジ資産へと昇華させます。
+本フレームワークは **3 つのコア能力** を中心に構築されています：日常的な検索に最適な **RAG ベースのクイック Q&A**、ナレッジ検索・MCP ツール・Web 検索を自律的にオーケストレーションし複雑なマルチステップタスクを処理する **ReAct Agent 推論**、そして Agent が生のドキュメントから相互リンクされた Markdown ナレッジベースとインタラクティブなナレッジグラフを自律生成・維持する全く新しい **Wiki モード**。さらに、多様なデータソース連携（Feishu / Notion / Yuque / RSS、随時拡充中）、**ウェブサイト埋め込み Widget** による外部サイトへのエージェント公開、プログラム連携向けの**スコープ付き API キーと Principal モデル**、ワークスペースごとの**マルチインスタンスストレージバックエンド**、20 以上の LLM プロバイダー統合、Langfuse による全体可観測性と**ランタイムタスクキューダッシュボード + Worker プール統治**、**エンタープライズ向けマルチテナント RBAC（4 階層ロールマトリクス + リソース所有権 + テナント監査ログ）**、完全セルフホスト可能なモジュラーアーキテクチャと組み合わせることで、WeKnora は散在する文書を「検索可能・推論可能・継続的に進化する」専用ナレッジ資産へと昇華させます。

 Feishu、Notion、Yuqueなどの外部プラットフォームからのナレッジ自動同期（他のデータソースも順次対応中）に対応し、PDF、Word、画像、Excelなど10以上の文書フォーマットをサポート。WeChat Work、Feishu、Slack、TelegramなどのIMチャネルから直接Q&Aサービスを提供できます。モデル層ではOpenAI、DeepSeek、Qwen（Alibaba Cloud）、Zhipu、Hunyuan、Gemini、MiniMax、NVIDIA、Ollamaなど主要プロバイダーに対応。全プロセスをモジュラー設計し、大規模モデル、ベクトルデータベース、ストレージなどのコンポーネントを柔軟に差し替え可能。ローカルおよびプライベートクラウドデプロイに対応し、データは完全に自己管理可能です。さらにWeKnoraは **Langfuse** とシームレスに統合され、Agentの推論、トークン消費、パイプラインに対する包括的な可観測性（オブザーバビリティ）を提供します。

 ## ✨ 最新アップデート

+- **v0.7.0** — きめ細かい**スコープ付き API キーと Principal モデル**（能力単位の付与 + KB 単位の制限 + API 連携プレイグラウンド）；**ランタイムタスクキュー可観測ダッシュボードと Worker プール統治**（ステージ別プール + モデル別並行度ガバナー + 失敗タスクの調査/再試行）；**マルチインスタンスストレージバックエンド**（ワークスペースごとに複数のストレージインスタンス、KB 単位のバインド、デフォルトインスタンス）；**セッションスコープの一時添付**（画像/ドキュメントの非同期解析 + 合算上限）；推奨質問とフォローアップ；安定リソースレジストリと LLM コンテキストのエイリアス圧縮；`@Skill / @MCP` メンションによるスコープ化 Agent ランタイム；会話中の MCP OAuth；QQBot と Lark（Feishu 国際版）IM 連携；Redis TLS；Requesty モデルプロバイダー + Keenable Web 検索；テナントレスプロビジョニングと制御されたセルフサービスワークスペース；管理者パスワードリセット；ナレッジベース複製フロー；`weknora` CLI v0.10。加えて大規模なセキュリティ強化（SSRF、シークレットのマスキング、SQL 検証、IDOR）。詳細は [`CHANGELOG.md`](./CHANGELOG.md)。
 - **v0.6.3** — ウェブサイト埋め込み Widget と統合センター（セキュアモード Token 交換 + レート制限）；チャット体験の全面刷新（引用ポップオーバー、RAG パイプライン進捗、ストリーミング Markdown）；ドキュメント複数タグと一括 reparse；Wiki フォルダーと階層ナビゲーション；RSS データソース；MCP OAuth2；EPUB / MHTML 解析；Agent モデル準備状態チェック；モデルデバッガー；セッションソースフィルター；ワークスペース削除 UI。詳細は [`CHANGELOG.md`](./CHANGELOG.md)。
 - **v0.6.2** — アップロード単位の解析設定（`process_config`）+ アップロード確認ダイアログ；reparse 時の設定上書き；`weknora` CLI v0.9（同梱 Agent Skills、`session stop`、auth/profile 統合）；KB マーキー複数選択；pgvector 1024 次元 HNSW インデックス；チャットリソース Store 刷新；Langfuse のみのトレーシング（Jaeger 削除）。詳細は [`CHANGELOG.md`](./CHANGELOG.md)。
 - **v0.6.1** — ドキュメント解析トレースタイムライン（Langfuse 風の Span ツリー、ステージごとの進捗表示 + 解析中止）；OpenSearch ベクター DB ドライバー；YAML 宣言型ビルトインモデル設定；システム管理者と統合プラットフォーム設定 + 監査ログ；新規ユーザーオンボーディングガイド；設定 UI 刷新；`weknora` CLI v0.7 / v0.8（Agent ファースト ワイヤープロトコル、NDJSON、`--dry-run`）；OpenDataLoader と PaddleOCR-VL 解析エンジン；MCP サーバーのマルチトランスポート（stdio / SSE / HTTP）；モデル単位の思考モード設定；Tencent LKEAP リランク + ネイティブ Gemini Embedding + MiniMax-M3。詳細は [`CHANGELOG.md`](./CHANGELOG.md) を参照。
@@ -108,11 +109,12 @@ Feishu、Notion、Yuqueなどの外部プラットフォームからのナレッ
 | インテリジェント推論 | ReACT プログレッシブ・マルチステップ推論、ナレッジ検索・MCP ツール・Web 検索を自律的にオーケストレーション |
 | クイック Q&A | ナレッジベースベースの RAG Q&A、迅速かつ正確な回答 |
 | Wiki モード | Agent主導で生のドキュメントから構造化された相互リンク済みMarkdown Wikiページを自動生成・保守 |
-| ツール呼び出し | 組み込みツール、MCP ツール（OAuth2 リモートサービス含む）、Web 検索 |
-| 対話戦略 | オンライン Prompt 編集、検索閾値チューニング、マルチターン文脈認識 |
-| 推奨質問 | ナレッジベースの内容に基づく質問の自動生成 |
-| 引用と RAG 進捗 | インライン引用ポップオーバー、統一 Markdown レンダリング、RAG パイプラインの段階別進捗表示 |
-| セッション管理 | サイドバーでソース別（Web / IM / 埋め込み）にセッションをフィルター・グループ化 |
+| ツール呼び出し | 組み込みツール、MCP ツール（OAuth2 リモートサービス・会話中 OAuth 含む）、Web 検索；`@Skill / @MCP` メンションでターン単位に Agent ランタイムを範囲化 |
+| 対話戦略 | オンライン Prompt 編集、検索閾値チューニング、マルチターン文脈認識、Agent 単位の引用出力トグル |
+| 推奨質問 | ナレッジベースの内容に基づく質問の自動生成と回答後のフォローアップ |
+| 一時添付 | セッションスコープで画像 / ドキュメントをアップロードし、非同期解析して一回限りの Q&A に使用（画像 + 添付の合算上限） |
+| 引用と RAG 進捗 | インライン引用ポップオーバーと引用ドロワー（Web / KB ソースの区別）、統一 Markdown レンダリング、RAG パイプラインの段階別進捗表示 |
+| セッション管理 | サイドバーでソース別（Web / IM / 埋め込み）にセッションをフィルター・グループ化、セッションタイトルのインラインリネーム対応 |

 **ナレッジ管理**

@@ -131,13 +133,14 @@ Feishu、Notion、Yuqueなどの外部プラットフォームからのナレッ

 | 機能 | 詳細 |
 |------|------|
-| 大規模モデル | OpenAI / Azure OpenAI / Anthropic (Claude) / DeepSeek / Qwen (Alibaba Cloud) / Zhipu / Hunyuan / Doubao (Volcengine) / Gemini / MiniMax / NVIDIA / Novita AI / SiliconFlow / OpenRouter / Ollama |
+| 大規模モデル | OpenAI / Azure OpenAI / Anthropic (Claude) / DeepSeek / Qwen (Alibaba Cloud) / Zhipu / Hunyuan / Doubao (Volcengine) / Gemini / MiniMax / NVIDIA / Novita AI / SiliconFlow / OpenRouter / Requesty / Ollama |
 | Embedding | Ollama / BGE / GTE / OpenAI 互換 API |
 | ベクトル DB | PostgreSQL (pgvector) / Elasticsearch / OpenSearch / Milvus / Weaviate / Qdrant / Apache Doris / Tencent VectorDB |
-| オブジェクトストレージ | ローカル / MinIO / AWS S3 / 火山引擎 TOS / Alibaba Cloud OSS / 金山雲 KS3 |
-| IM 統合 | WeChat Work / Feishu / Lark / Slack / Telegram / DingTalk / Mattermost / WeChat |
+| オブジェクトストレージ | ローカル / MinIO / AWS S3 / 火山引擎 TOS / Alibaba Cloud OSS / 金山雲 KS3 / 華為雲 OBS；**ワークスペースごとに複数のストレージインスタンス**、KB 単位のバインドとデフォルトインスタンス |
+| IM 統合 | WeChat Work / Feishu / Lark（Feishu 国際版）/ QQBot / Slack / Telegram / DingTalk / Mattermost / WeChat |
 | ウェブ埋め込み | 埋め込み Widget でエージェントを公開、ドメイン許可リスト・レート制限・セキュアモード Token 交換 |
-| Web 検索 | DuckDuckGo / Bing / Google / Tavily / Baidu / Ollama / SearXNG |
+| Web 検索 | DuckDuckGo / Bing / Google / Tavily / Baidu / Ollama / SearXNG / Keenable |
+| API 連携 | スコープ付き API キー（能力単位の付与 + KB 単位の制限 + 節流付き last_used 追跡）と API 連携プレイグラウンド；MCP OAuth と埋め込みセッションを Principal 単位で分離 |

 **プラットフォーム**

@@ -145,8 +148,8 @@ Feishu、Notion、Yuqueなどの外部プラットフォームからのナレッ
 |------|------|
 | デプロイ | ローカル / Docker / Kubernetes (Helm)、プライベート化・オフラインデプロイ対応 |
 | UI | Web UI / RESTful API / CLI (`weknora`) / Chrome Extension / ウェブ埋め込み Widget / WeChat ミニプログラム |
-| 可観測性 | Langfuse（唯一のトレーシングバックエンド）で ReAct ループ・トークン消費・ツール呼び出し・パイプライン追跡；Langfuse 風のドキュメント解析トレースタイムラインを内蔵し、ステージごとの進捗を表示 |
-| タスク管理 | MQ 非同期タスク、バージョンアップ時の DB 自動マイグレーション |
+| 可観測性 | Langfuse（唯一のトレーシングバックエンド）で ReAct ループ・トークン消費・ツール呼び出し・パイプライン追跡；Langfuse 風のドキュメント解析トレースタイムラインを内蔵し、ステージごとの進捗を表示；システム管理者向けランタイムタスクキューダッシュボード（キュー深度・モデル別並行度・失敗タスクの調査と手動再試行） |
+| タスク管理 | MQ 非同期タスク、ステージ別 Worker プール統治（core / 後処理 / enrichment / maintenance + 弾性共有プール、Wiki は独立プール）とモデル別バックグラウンド並行度ガバナー；バージョンアップ時の DB 自動マイグレーション |
 | モデル管理 | 集中設定、YAML 宣言型ビルトインモデル設定、ナレッジベース単位のモデル選択、モデル単位の思考モード・Embedding 次元上書き、インタラクティブモデルデバッガー、マルチテナント組み込みモデル共有、WeKnora Cloud ホスティングモデルとドキュメント解析 |

 ## 🧩 Chrome 拡張機能
@@ -28,7 +28,7 @@
        <img src="https://img.shields.io/badge/License-MIT-ffffff?labelColor=d4eaf7&color=2e6cc4" alt="License">
    </a>
    <a href="./CHANGELOG.md">
-        <img alt="버전" src="https://img.shields.io/badge/version-0.6.3-2e6cc4?labelColor=d4eaf7">
+        <img alt="버전" src="https://img.shields.io/badge/version-0.7.0-2e6cc4?labelColor=d4eaf7">
    </a>
 </p>

@@ -50,12 +50,13 @@

 [**WeKnora**](https://weknora.weixin.qq.com)는 엔터프라이즈급 문서 이해, 시맨틱 검색, 자율 추론 시나리오를 위해 설계된 오픈소스 LLM 기반 지식 프레임워크입니다.

-본 프레임워크는 **세 가지 핵심 역량**을 중심으로 구성됩니다. 일상 검색에 최적화된 **RAG 기반 빠른 Q&A**, 지식 검색·MCP 도구·웹 검색을 자율적으로 오케스트레이션하여 복잡한 다단계 작업을 처리하는 **ReAct Agent 추론**, 그리고 Agent가 원본 문서에서 상호 연결된 마크다운 지식베이스와 인터랙티브 지식 그래프를 스스로 생성·유지하는 완전히 새로운 **Wiki 모드**입니다. 다양한 데이터 소스 연동(Feishu / Notion / Yuque / RSS, 지속 확장 중), **웹사이트 임베드 Widget**으로 외부 사이트에 에이전트 게시, 20개 이상의 LLM 프로바이더 통합, Langfuse 기반 풀스택 관측 가능성, **엔터프라이즈 멀티 테넌트 RBAC(4단계 역할 매트릭스 + 리소스 소유권 + 테넌트 감사 로그)**, 완전 셀프호스팅이 가능한 모듈형 아키텍처를 결합하여, WeKnora는 흩어진 문서를 검색·추론 가능하며 지속적으로 진화하는 전용 지식 자산으로 탈바꿈시킵니다.
+본 프레임워크는 **세 가지 핵심 역량**을 중심으로 구성됩니다. 일상 검색에 최적화된 **RAG 기반 빠른 Q&A**, 지식 검색·MCP 도구·웹 검색을 자율적으로 오케스트레이션하여 복잡한 다단계 작업을 처리하는 **ReAct Agent 추론**, 그리고 Agent가 원본 문서에서 상호 연결된 마크다운 지식베이스와 인터랙티브 지식 그래프를 스스로 생성·유지하는 완전히 새로운 **Wiki 모드**입니다. 다양한 데이터 소스 연동(Feishu / Notion / Yuque / RSS, 지속 확장 중), **웹사이트 임베드 Widget**으로 외부 사이트에 에이전트 게시, 프로그램 연동을 위한 **범위 지정 API 키 및 Principal 모델**, 워크스페이스별 **다중 인스턴스 스토리지 백엔드**, 20개 이상의 LLM 프로바이더 통합, Langfuse 기반 풀스택 관측 가능성과 **런타임 작업 큐 대시보드 + Worker 풀 거버넌스**, **엔터프라이즈 멀티 테넌트 RBAC(4단계 역할 매트릭스 + 리소스 소유권 + 테넌트 감사 로그)**, 완전 셀프호스팅이 가능한 모듈형 아키텍처를 결합하여, WeKnora는 흩어진 문서를 검색·추론 가능하며 지속적으로 진화하는 전용 지식 자산으로 탈바꿈시킵니다.

 Feishu, Notion, Yuque 등 외부 플랫폼에서 지식 자동 동기화를 지원하며(추가 데이터 소스 개발 중), PDF, Word, 이미지, Excel 등 10가지 이상의 문서 포맷을 처리합니다. WeChat Work, Feishu, Slack, Telegram 등의 IM 채널을 통해 Q&A 서비스를 직접 제공할 수 있습니다. 모델 레이어에서 OpenAI, DeepSeek, Qwen(Alibaba Cloud), Zhipu, Hunyuan, Gemini, MiniMax, NVIDIA, Ollama 등 주요 프로바이더를 지원합니다. 전체 프로세스가 모듈화 설계되어 LLM, 벡터 DB, 스토리지 등 구성 요소를 유연하게 교체 가능하며, 로컬 및 프라이빗 클라우드 배포를 지원하여 데이터 완전 자체 관리가 가능합니다. 또한 WeKnora는 **Langfuse**와 원활하게 통합되어 Agent 추론, 토큰 사용량 및 파이프라인에 대한 포괄적인 관측 가능성(Observability)을 제공합니다.

 ## ✨ 최신 업데이트

+- **v0.7.0** — 세분화된 **범위 지정 API 키 및 Principal 모델**(능력 단위 권한 + KB 단위 제한 + API 통합 플레이그라운드); **런타임 작업 큐 가시성 대시보드 및 Worker 풀 거버넌스**(단계별 풀 + 모델별 동시성 거버너 + 실패 작업 조사/재시도); **다중 인스턴스 스토리지 백엔드**(워크스페이스당 여러 스토리지 인스턴스, KB 단위 바인딩, 기본 인스턴스); **세션 범위 임시 첨부**(이미지/문서 비동기 파싱 + 통합 한도); 추천 질문 및 후속 질문; 안정적인 리소스 레지스트리 및 LLM 컨텍스트 별칭 압축; `@Skill / @MCP` 멘션 기반 범위 지정 Agent 런타임; 대화 중 MCP OAuth; QQBot 및 Lark(Feishu 국제판) IM 통합; Redis TLS; Requesty 모델 제공자 + Keenable 웹 검색; 테넌트리스 프로비저닝 및 제어된 셀프서비스 워크스페이스; 관리자 비밀번호 재설정; 지식 베이스 복제 플로우; `weknora` CLI v0.10. 또한 대규모 보안 강화(SSRF, 비밀 마스킹, SQL 검증, IDOR). 자세한 내용은 [`CHANGELOG.md`](./CHANGELOG.md).
 - **v0.6.3** — 웹사이트 임베드 Widget 및 통합 센터(보안 모드 Token 교환 + 속도 제한); 채팅 경험 전면 개편(인용 팝오버, RAG 파이프라인 진행, 스트리밍 Markdown); 문서 다중 태그 및 일괄 reparse; Wiki 폴더 및 계층 탐색; RSS 데이터 소스; MCP OAuth2; EPUB / MHTML 파싱; Agent 모델 준비 상태 검사; 모델 디버거; 세션 소스 필터; 워크스페이스 삭제 UI. 자세한 내용은 [`CHANGELOG.md`](./CHANGELOG.md).
 - **v0.6.2** — 업로드 단위 파싱 설정(`process_config`) + 업로드 확인 대화상자; reparse 시 설정 덮어쓰기; `weknora` CLI v0.9(번들 Agent Skills, `session stop`, auth/profile 통합); KB 마키 선택 다중 선택; pgvector 1024차원 HNSW 인덱스; 채팅 리소스 Store 리팩터; Langfuse 단일 추적(Jaeger 제거). 자세한 내용은 [`CHANGELOG.md`](./CHANGELOG.md).
 - **v0.6.1** — 문서 파싱 추적 타임라인(Langfuse 스타일 Span 트리, 단계별 진행 표시 + 파싱 중단); OpenSearch 벡터 저장소 드라이버; YAML 선언형 내장 모델 구성; 시스템 관리자와 통합 플랫폼 설정 + 감사 로그; 신규 사용자 온보딩 가이드; 설정 UI 리디자인; `weknora` CLI v0.7 / v0.8(Agent 우선 와이어 프로토콜, NDJSON, `--dry-run`); OpenDataLoader 및 PaddleOCR-VL 파싱 엔진; MCP 서버 멀티 트랜스포트(stdio / SSE / HTTP); 모델별 사고 모드 설정; Tencent LKEAP 리랭크 + 네이티브 Gemini 임베딩 + MiniMax-M3. 자세한 내용은 [`CHANGELOG.md`](./CHANGELOG.md) 참고.
@@ -117,11 +118,12 @@ Feishu, Notion, Yuque 등 외부 플랫폼에서 지식 자동 동기화를 지
 | 지능형 추론 | ReACT 점진적 멀티스텝 추론, 지식 검색·MCP 도구·웹 검색을 자율 오케스트레이션 |
 | 빠른 Q&A | 지식베이스 기반 RAG Q&A, 빠르고 정확한 답변 |
 | Wiki 모드 | Agent가 주도하여 원본 문서에서 구조화된 마크다운 Wiki 페이지를 자동 생성 및 유지 관리 |
-| 도구 호출 | 내장 도구, MCP 도구(OAuth2 원격 서비스 포함), 웹 검색 |
-| 대화 전략 | 온라인 프롬프트 편집, 검색 임계값 조정, 멀티턴 문맥 인식 |
-| 추천 질문 | 지식베이스 콘텐츠 기반 질문 자동 생성 |
-| 인용 및 RAG 진행 | 인라인 인용 팝오버, 통합 Markdown 렌더링, RAG 파이프라인 단계별 진행 표시 |
-| 세션 관리 | 사이드바에서 소스별(Web / IM / 임베드) 세션 필터 및 그룹화 |
+| 도구 호출 | 내장 도구, MCP 도구(OAuth2 원격 서비스·대화 중 OAuth 포함), 웹 검색; `@Skill / @MCP` 멘션으로 턴 단위 Agent 런타임 범위 지정 |
+| 대화 전략 | 온라인 프롬프트 편집, 검색 임계값 조정, 멀티턴 문맥 인식, Agent별 인용 출력 토글 |
+| 추천 질문 | 지식베이스 콘텐츠 기반 질문 자동 생성 및 답변 후 후속 질문 |
+| 임시 첨부 | 세션 범위로 이미지 / 문서를 업로드하고 비동기 파싱하여 일회성 Q&A에 사용(이미지 + 첨부 통합 한도) |
+| 인용 및 RAG 진행 | 인라인 인용 팝오버 및 인용 드로어(웹 / KB 소스 구분), 통합 Markdown 렌더링, RAG 파이프라인 단계별 진행 표시 |
+| 세션 관리 | 사이드바에서 소스별(Web / IM / 임베드) 세션 필터 및 그룹화, 세션 제목 인라인 이름 변경 지원 |

 **지식 관리**

@@ -140,13 +142,14 @@ Feishu, Notion, Yuque 등 외부 플랫폼에서 지식 자동 동기화를 지

 | 기능 | 상세 |
 |------|------|
-| LLM | OpenAI / Azure OpenAI / Anthropic (Claude) / DeepSeek / Qwen (Alibaba Cloud) / Zhipu / Hunyuan / Doubao (Volcengine) / Gemini / MiniMax / NVIDIA / Novita AI / SiliconFlow / OpenRouter / Ollama |
+| LLM | OpenAI / Azure OpenAI / Anthropic (Claude) / DeepSeek / Qwen (Alibaba Cloud) / Zhipu / Hunyuan / Doubao (Volcengine) / Gemini / MiniMax / NVIDIA / Novita AI / SiliconFlow / OpenRouter / Requesty / Ollama |
 | Embedding | Ollama / BGE / GTE / OpenAI 호환 API |
 | 벡터 DB | PostgreSQL (pgvector) / Elasticsearch / OpenSearch / Milvus / Weaviate / Qdrant / Apache Doris / Tencent VectorDB |
-| 오브젝트 스토리지 | 로컬 / MinIO / AWS S3 / Volcengine TOS / Alibaba Cloud OSS / Kingsoft Cloud KS3 |
-| IM 통합 | WeChat Work / Feishu / Lark / Slack / Telegram / DingTalk / Mattermost / WeChat |
+| 오브젝트 스토리지 | 로컬 / MinIO / AWS S3 / Volcengine TOS / Alibaba Cloud OSS / Kingsoft Cloud KS3 / Huawei Cloud OBS; **워크스페이스당 여러 스토리지 인스턴스**, KB 단위 바인딩 및 기본 인스턴스 |
+| IM 통합 | WeChat Work / Feishu / Lark(Feishu 국제판) / QQBot / Slack / Telegram / DingTalk / Mattermost / WeChat |
 | 웹사이트 임베드 | 임베드 Widget으로 에이전트 게시, 도메인 허용 목록·속도 제한·보안 모드 Token 교환 |
-| 웹 검색 | DuckDuckGo / Bing / Google / Tavily / Baidu / Ollama / SearXNG |
+| 웹 검색 | DuckDuckGo / Bing / Google / Tavily / Baidu / Ollama / SearXNG / Keenable |
+| API 통합 | 범위 지정 API 키(능력 단위 권한 + KB 단위 제한 + 스로틀링된 last_used 추적)와 API 통합 플레이그라운드; MCP OAuth 및 임베드 세션을 Principal 단위로 격리 |

 **플랫폼**

@@ -154,8 +157,8 @@ Feishu, Notion, Yuque 등 외부 플랫폼에서 지식 자동 동기화를 지
 |------|------|
 | 배포 | 로컬 / Docker / Kubernetes (Helm), 프라이빗/오프라인 배포 지원 |
 | UI | Web UI / RESTful API / CLI (`weknora`) / Chrome Extension / 웹사이트 임베드 Widget / WeChat 미니 프로그램 |
-| 관측 가능성 | Langfuse(단일 추적 백엔드)로 ReAct 루프·토큰 소비·도구 호출·파이프라인 추적; Langfuse 스타일의 문서 파싱 추적 타임라인 내장으로 단계별 진행 표시 |
-| 작업 관리 | MQ 비동기 작업, 버전 업그레이드 시 자동 DB 마이그레이션 |
+| 관측 가능성 | Langfuse(단일 추적 백엔드)로 ReAct 루프·토큰 소비·도구 호출·파이프라인 추적; Langfuse 스타일의 문서 파싱 추적 타임라인 내장으로 단계별 진행 표시; 시스템 관리자용 런타임 작업 큐 대시보드(큐 깊이·모델별 동시성·실패 작업 조사 및 수동 재시도) |
+| 작업 관리 | MQ 비동기 작업, 단계별 Worker 풀 거버넌스(core / 후처리 / enrichment / maintenance + 탄력적 공유 풀, Wiki 독립 풀)와 모델별 백그라운드 동시성 거버너; 버전 업그레이드 시 자동 DB 마이그레이션 |
 | 모델 관리 | 중앙 설정, YAML 선언형 내장 모델 구성, 지식베이스별 모델 선택, 모델별 사고 모드·Embedding 차원 덮어쓰기, 대화형 모델 디버거, 멀티테넌트 내장 모델 공유, WeKnora Cloud 호스팅 모델 및 문서 파싱 |

 ## 🧩 Chrome 확장 프로그램
@@ -1 +1 @@
-0.6.3
+0.7.0
@@ -317,5 +317,46 @@ Wiki 模式允许 Agent 根据原始文档自动生成并维护一套结构化

 0.6.3 在 Agent 选择器引入**模型就绪校验**：绑定的 LLM / Embedding / Rerank / VLM 缺失或配置无效时会阻断对话并给出修复指引。可在模型卡片打开 **调试抽屉** 先测试连通性；确认 KB 与 Agent 引用的模型均存在且可用。

+## 28. 如何创建并限制权限范围 API Key？
+
+0.7.0 引入**权限范围 API Key 与 Principal 模型**（迁移 `000064_principal_model`、`000065_tenant_api_keys`）。API Key 不再等同于某个人类用户，而是独立的 Principal，携带显式角色与能力（capability）授权：
+
+- 在 **设置 → API 集成**（Owner 可见）中创建 Key，可勾选能力（如 `manage_kbs` 覆盖 KB 全生命周期、`manage_storage_backends` 等），并可限制到指定知识库。
+- Key 的 `last_used_at` 按节流更新，避免高频写库。
+- 路由级守卫会拒绝越权访问；管理类接口对 API Key Principal 默认拒绝，请为集成使用具备对应能力的 Key，而非全权 Key。
+- MCP OAuth 与嵌入会话按 Principal 隔离，不同集成之间互不串号。
+
+## 29. 一个空间如何绑定多个对象存储实例？
+
+0.7.0 支持**多实例存储后端**（迁移 `000068_storage_backends`）。一个空间可注册多个存储实例（`local` / `minio` / `cos` / `tos` / `s3` / `oss` / `ks3` / `obs`），不同知识库绑定到不同实例，空间维度还有一个默认实例：
+
+- 在 **设置 → 存储后端** 创建/测试/设为默认（需 Admin+；API Key 需 `manage_storage_backends` 能力）。
+- 未显式绑定的新知识库使用空间默认实例；响应中的 `access_key_id` / `secret_access_key` 会被掩码，更新时提交掩码占位符不会覆盖库中真实凭据。
+- 若创建知识库时提示存储引擎不可用，请确认目标 provider 在 `STORAGE_ALLOW_LIST` 允许范围内。详见 [`docs/api/storage-backend.md`](./api/storage-backend.md)。
+
+## 30. 后台解析/入库任务积压或需要排查失败任务怎么办？
+
+0.7.0 新增系统管理员的**运行时任务队列面板**与 **Worker 池治理**。文档处理从单一聚合池改为分阶段独立池（core / 后处理 / enrichment / maintenance）+ 弹性共享池，Wiki 独立治理：
+
+- 在 **系统设置 → 运行时队列** 查看队列深度、按模型并发统计、失败任务详情，并可手动重试。
+- 可通过 `WEKNORA_ASYNQ_*_CONCURRENCY` 与 `asynq.*_concurrency` 系统设置调整各池并发（需重启服务）；`model.max_concurrency` 用于约束单模型后台并发。
+- 详见 [`docs/worker-pool-governance.md`](./worker-pool-governance.md)。注意：Worker 并发只是调度预算，仍受模型配额、DocReader 容量、向量库与数据库连接数限制。
+
+## 31. 对话中如何临时上传图片/文档做一次性问答？
+
+0.7.0 支持**会话级临时附件**（迁移 `000070_temporary_documents`）。在对话输入区上传图片或文档，系统异步解析后仅用于当前会话的问答，不会写入知识库。图片与附件共享一个合并数量上限；附件内容会在多轮对话中保留。
+
+## 32. 如何接入 QQBot / Lark（飞书国际版）？
+
+0.7.0 新增 **QQBot** 平台集成，并支持飞书国际版 **Lark**（区域感知路由）。在 **设置 → IM 集成** 添加对应渠道并填写凭据即可；飞书回复通过 reply-message 接口发送，回复会落在原消息线程内。
+
+## 33. 如何为 Redis 启用 TLS？
+
+0.7.0 支持 Redis 的 **TLS 连接**（#1930）。按环境变量启用 TLS 后，启动日志会打印 TLS 配置状态便于确认。若连接失败，请核对证书/CA 配置与 Redis 服务端是否要求 TLS。
+
+## 34. 升级到 0.7.0 后 `weknora` CLI 命令找不到或行为变化？
+
+0.7.0 随附 **CLI v0.10**（Agent 优先，破坏性变更）：新增 `model` / `message` / `config` / `skills` 命令组，`doc reparse` / `doc update`，`kb config` / `kb config set`；`session continue` 更名为 `session resume`，新增 `session tool-approval`；提供 agent-first 的 chat 与 `session ask` 输出模式，并强化了 SSE 可靠性与类型化错误。详见 [`cli/CHANGELOG.md`](../cli/CHANGELOG.md)。
+
 ## P.S.
 如果以上方式未解决问题，请在issue中描述您的问题，并提供必要的日志信息辅助我们进行问题排查
@@ -15092,10 +15092,33 @@ const docTemplate = `{
                    "description": "ASR model ID for audio transcription (optional)",
                    "type": "string"
                },
+                "attachment_image_understanding": {
+                    "description": "AttachmentImageUnderstanding enables VLM OCR fallback for image-only /\nscanned documents (PDF/PPT whose pages are images). Disabled by default\nbecause it materially increases parse latency; only triggers when the\nextracted text is below a threshold and a VLM model is configured.",
+                    "type": "boolean"
+                },
+                "attachment_ocr_max_pages": {
+                    "description": "AttachmentOCRMaxPages caps how many pages of a scanned / image-only\ndocument this agent sends to the VLM for OCR. 0 falls back to the global\ndefault (WEKNORA_CHAT_ATTACHMENT_OCR_MAX_PAGES). More pages means higher\ncoverage but slower parsing and more VLM cost.",
+                    "type": "integer"
+                },
+                "attachment_parse_wait_timeout_sec": {
+                    "description": "AttachmentParseWaitTimeoutSec bounds, in seconds, how long a chat turn\nwaits for this agent's still-parsing attachments before proceeding with\nonly the finished ones. 0 falls back to the global default\n(WEKNORA_CHAT_ATTACHMENT_WAIT_TIMEOUT_SEC).",
+                    "type": "integer"
+                },
                "audio_upload_enabled": {
                    "description": "Whether audio upload (ASR transcription) is enabled for this agent (default: false)",
                    "type": "boolean"
                },
+                "chat_parser_engine_rules": {
+                    "description": "===== Chat Attachment Parsing Settings =====\nChatParserEngineRules selects parser engines for session-scoped chat\nattachments by file type. Takes precedence over the tenant-level\nParserEngineConfig.ChatParserEngineRules; an explicit per-request\nparser_engine still overrides both.",
+                    "type": "array",
+                    "items": {
+                        "$ref": "#/definitions/github_com_Tencent_WeKnora_internal_types.ParserEngineRule"
+                    }
+                },
+                "citation_enabled": {
+                    "description": "Whether final answers include knowledge/web source citations. Nil defaults to true\nso agents saved before this option was introduced keep their existing behavior.",
+                    "type": "boolean"
+                },
                "context_template": {
                    "description": "Context template for normal mode (how to format retrieved chunks)",
                    "type": "string"
@@ -16819,7 +16842,7 @@ const docTemplate = `{
            ],
            "x-enum-comments": {
                "MatchTypeDataAnalysis": "数据分析匹配类型",
-                "MatchTypeDirectLoad": "直接加载匹配类型",
+                "MatchTypeDirectLoad": "Deprecated: reserved to preserve serialized enum values",
                "MatchTypeParentChunk": "父Chunk匹配类型",
                "MatchTypeRelationChunk": "关系Chunk匹配类型",
                "MatchTypeWebSearch": "网络搜索匹配类型"
@@ -16833,7 +16856,7 @@ const docTemplate = `{
                "关系Chunk匹配类型",
                "",
                "网络搜索匹配类型",
-                "直接加载匹配类型",
+                "Deprecated: reserved to preserve serialized enum values",
                "数据分析匹配类型"
            ],
            "x-enum-varnames": [
@@ -17009,6 +17032,10 @@ const docTemplate = `{
                    "description": "Extracted text content (for small text files)",
                    "type": "string"
                },
+                "content_mode": {
+                    "description": "full or selected_chunks",
+                    "type": "string"
+                },
                "file_name": {
                    "description": "Original filename",
                    "type": "string"
@@ -17021,6 +17048,10 @@ const docTemplate = `{
                    "description": "File extension (e.g., \".pdf\", \".docx\")",
                    "type": "string"
                },
+                "id": {
+                    "description": "Temporary document ID for session-scoped uploads",
+                    "type": "string"
+                },
                "is_truncated": {
                    "description": "Whether content was truncated",
                    "type": "boolean"
@@ -17029,9 +17060,17 @@ const docTemplate = `{
                    "description": "Total line count (for text files)",
                    "type": "integer"
                },
-                "url": {
-                    "description": "Storage URL (provider://path)",
-                    "type": "string"
+                "selected_chunks": {
+                    "description": "Chunks included in this message prompt",
+                    "type": "integer"
+                },
+                "token_count": {
+                    "description": "Approximate tokens in the parsed document",
+                    "type": "integer"
+                },
+                "total_chunks": {
+                    "description": "Total parsed chunks",
+                    "type": "integer"
                }
            }
        },
@@ -17456,6 +17495,13 @@ const docTemplate = `{
        "github_com_Tencent_WeKnora_internal_types.ParserEngineConfig": {
            "type": "object",
            "properties": {
+                "chat_parser_engine_rules": {
+                    "description": "ChatParserEngineRules selects parser engines for session-scoped chat\ndocuments. Knowledge bases keep their own rules in ChunkingConfig.",
+                    "type": "array",
+                    "items": {
+                        "$ref": "#/definitions/github_com_Tencent_WeKnora_internal_types.ParserEngineRule"
+                    }
+                },
                "mineru_api_key": {
                    "description": "MinerU 云 API Key",
                    "type": "string"
@@ -18106,6 +18152,12 @@ const docTemplate = `{
                "query_text": {
                    "type": "string"
                },
+                "scope_tag_ids": {
+                    "type": "array",
+                    "items": {
+                        "type": "string"
+                    }
+                },
                "skip_context_enrichment": {
                    "description": "SkipContextEnrichment skips fetching parent, nearby, and relation chunks\nin processSearchResults. Used by the chat pipeline where context assembly\nis handled separately in the merge stage.",
                    "type": "boolean"
@@ -21548,6 +21600,13 @@ const docTemplate = `{
                    "description": "Selected custom agent ID (backend resolves shared agent and its workspace from share relation)",
                    "type": "string"
                },
+                "attachment_ids": {
+                    "description": "Pre-uploaded session-scoped document IDs",
+                    "type": "array",
+                    "items": {
+                        "type": "string"
+                    }
+                },
                "attachment_uploads": {
                    "description": "Attached files (documents, audio, etc.)",
                    "type": "array",
@@ -15085,10 +15085,33 @@
                    "description": "ASR model ID for audio transcription (optional)",
                    "type": "string"
                },
+                "attachment_image_understanding": {
+                    "description": "AttachmentImageUnderstanding enables VLM OCR fallback for image-only /\nscanned documents (PDF/PPT whose pages are images). Disabled by default\nbecause it materially increases parse latency; only triggers when the\nextracted text is below a threshold and a VLM model is configured.",
+                    "type": "boolean"
+                },
+                "attachment_ocr_max_pages": {
+                    "description": "AttachmentOCRMaxPages caps how many pages of a scanned / image-only\ndocument this agent sends to the VLM for OCR. 0 falls back to the global\ndefault (WEKNORA_CHAT_ATTACHMENT_OCR_MAX_PAGES). More pages means higher\ncoverage but slower parsing and more VLM cost.",
+                    "type": "integer"
+                },
+                "attachment_parse_wait_timeout_sec": {
+                    "description": "AttachmentParseWaitTimeoutSec bounds, in seconds, how long a chat turn\nwaits for this agent's still-parsing attachments before proceeding with\nonly the finished ones. 0 falls back to the global default\n(WEKNORA_CHAT_ATTACHMENT_WAIT_TIMEOUT_SEC).",
+                    "type": "integer"
+                },
                "audio_upload_enabled": {
                    "description": "Whether audio upload (ASR transcription) is enabled for this agent (default: false)",
                    "type": "boolean"
                },
+                "chat_parser_engine_rules": {
+                    "description": "===== Chat Attachment Parsing Settings =====\nChatParserEngineRules selects parser engines for session-scoped chat\nattachments by file type. Takes precedence over the tenant-level\nParserEngineConfig.ChatParserEngineRules; an explicit per-request\nparser_engine still overrides both.",
+                    "type": "array",
+                    "items": {
+                        "$ref": "#/definitions/github_com_Tencent_WeKnora_internal_types.ParserEngineRule"
+                    }
+                },
+                "citation_enabled": {
+                    "description": "Whether final answers include knowledge/web source citations. Nil defaults to true\nso agents saved before this option was introduced keep their existing behavior.",
+                    "type": "boolean"
+                },
                "context_template": {
                    "description": "Context template for normal mode (how to format retrieved chunks)",
                    "type": "string"
@@ -16812,7 +16835,7 @@
            ],
            "x-enum-comments": {
                "MatchTypeDataAnalysis": "数据分析匹配类型",
-                "MatchTypeDirectLoad": "直接加载匹配类型",
+                "MatchTypeDirectLoad": "Deprecated: reserved to preserve serialized enum values",
                "MatchTypeParentChunk": "父Chunk匹配类型",
                "MatchTypeRelationChunk": "关系Chunk匹配类型",
                "MatchTypeWebSearch": "网络搜索匹配类型"
@@ -16826,7 +16849,7 @@
                "关系Chunk匹配类型",
                "",
                "网络搜索匹配类型",
-                "直接加载匹配类型",
+                "Deprecated: reserved to preserve serialized enum values",
                "数据分析匹配类型"
            ],
            "x-enum-varnames": [
@@ -17002,6 +17025,10 @@
                    "description": "Extracted text content (for small text files)",
                    "type": "string"
                },
+                "content_mode": {
+                    "description": "full or selected_chunks",
+                    "type": "string"
+                },
                "file_name": {
                    "description": "Original filename",
                    "type": "string"
@@ -17014,6 +17041,10 @@
                    "description": "File extension (e.g., \".pdf\", \".docx\")",
                    "type": "string"
                },
+                "id": {
+                    "description": "Temporary document ID for session-scoped uploads",
+                    "type": "string"
+                },
                "is_truncated": {
                    "description": "Whether content was truncated",
                    "type": "boolean"
@@ -17022,9 +17053,17 @@
                    "description": "Total line count (for text files)",
                    "type": "integer"
                },
-                "url": {
-                    "description": "Storage URL (provider://path)",
-                    "type": "string"
+                "selected_chunks": {
+                    "description": "Chunks included in this message prompt",
+                    "type": "integer"
+                },
+                "token_count": {
+                    "description": "Approximate tokens in the parsed document",
+                    "type": "integer"
+                },
+                "total_chunks": {
+                    "description": "Total parsed chunks",
+                    "type": "integer"
                }
            }
        },
@@ -17449,6 +17488,13 @@
        "github_com_Tencent_WeKnora_internal_types.ParserEngineConfig": {
            "type": "object",
            "properties": {
+                "chat_parser_engine_rules": {
+                    "description": "ChatParserEngineRules selects parser engines for session-scoped chat\ndocuments. Knowledge bases keep their own rules in ChunkingConfig.",
+                    "type": "array",
+                    "items": {
+                        "$ref": "#/definitions/github_com_Tencent_WeKnora_internal_types.ParserEngineRule"
+                    }
+                },
                "mineru_api_key": {
                    "description": "MinerU 云 API Key",
                    "type": "string"
@@ -18099,6 +18145,12 @@
                "query_text": {
                    "type": "string"
                },
+                "scope_tag_ids": {
+                    "type": "array",
+                    "items": {
+                        "type": "string"
+                    }
+                },
                "skip_context_enrichment": {
                    "description": "SkipContextEnrichment skips fetching parent, nearby, and relation chunks\nin processSearchResults. Used by the chat pipeline where context assembly\nis handled separately in the merge stage.",
                    "type": "boolean"
@@ -21541,6 +21593,13 @@
                    "description": "Selected custom agent ID (backend resolves shared agent and its workspace from share relation)",
                    "type": "string"
                },
+                "attachment_ids": {
+                    "description": "Pre-uploaded session-scoped document IDs",
+                    "type": "array",
+                    "items": {
+                        "type": "string"
+                    }
+                },
                "attachment_uploads": {
                    "description": "Attached files (documents, audio, etc.)",
                    "type": "array",
@@ -21790,4 +21849,4 @@
            "in": "header"
        }
    }
-}
+}
@@ -593,10 +593,46 @@ definitions:
      asr_model_id:
        description: ASR model ID for audio transcription (optional)
        type: string
+      attachment_image_understanding:
+        description: |-
+          AttachmentImageUnderstanding enables VLM OCR fallback for image-only /
+          scanned documents (PDF/PPT whose pages are images). Disabled by default
+          because it materially increases parse latency; only triggers when the
+          extracted text is below a threshold and a VLM model is configured.
+        type: boolean
+      attachment_ocr_max_pages:
+        description: |-
+          AttachmentOCRMaxPages caps how many pages of a scanned / image-only
+          document this agent sends to the VLM for OCR. 0 falls back to the global
+          default (WEKNORA_CHAT_ATTACHMENT_OCR_MAX_PAGES). More pages means higher
+          coverage but slower parsing and more VLM cost.
+        type: integer
+      attachment_parse_wait_timeout_sec:
+        description: |-
+          AttachmentParseWaitTimeoutSec bounds, in seconds, how long a chat turn
+          waits for this agent's still-parsing attachments before proceeding with
+          only the finished ones. 0 falls back to the global default
+          (WEKNORA_CHAT_ATTACHMENT_WAIT_TIMEOUT_SEC).
+        type: integer
      audio_upload_enabled:
        description: 'Whether audio upload (ASR transcription) is enabled for this
          agent (default: false)'
        type: boolean
+      chat_parser_engine_rules:
+        description: |-
+          ===== Chat Attachment Parsing Settings =====
+          ChatParserEngineRules selects parser engines for session-scoped chat
+          attachments by file type. Takes precedence over the tenant-level
+          ParserEngineConfig.ChatParserEngineRules; an explicit per-request
+          parser_engine still overrides both.
+        items:
+          $ref: '#/definitions/github_com_Tencent_WeKnora_internal_types.ParserEngineRule'
+        type: array
+      citation_enabled:
+        description: |-
+          Whether final answers include knowledge/web source citations. Nil defaults to true
+          so agents saved before this option was introduced keep their existing behavior.
+        type: boolean
      context_template:
        description: Context template for normal mode (how to format retrieved chunks)
        type: string
@@ -1918,7 +1954,7 @@ definitions:
    type: integer
    x-enum-comments:
      MatchTypeDataAnalysis: 数据分析匹配类型
-      MatchTypeDirectLoad: 直接加载匹配类型
+      MatchTypeDirectLoad: 'Deprecated: reserved to preserve serialized enum values'
      MatchTypeParentChunk: 父Chunk匹配类型
      MatchTypeRelationChunk: 关系Chunk匹配类型
      MatchTypeWebSearch: 网络搜索匹配类型
@@ -1931,7 +1967,7 @@ definitions:
    - 关系Chunk匹配类型
    - ""
    - 网络搜索匹配类型
-    - 直接加载匹配类型
+    - 'Deprecated: reserved to preserve serialized enum values'
    - 数据分析匹配类型
    x-enum-varnames:
    - MatchTypeEmbedding
@@ -2071,6 +2107,9 @@ definitions:
      content:
        description: Extracted text content (for small text files)
        type: string
+      content_mode:
+        description: full or selected_chunks
+        type: string
      file_name:
        description: Original filename
        type: string
@@ -2080,15 +2119,24 @@ definitions:
      file_type:
        description: File extension (e.g., ".pdf", ".docx")
        type: string
+      id:
+        description: Temporary document ID for session-scoped uploads
+        type: string
      is_truncated:
        description: Whether content was truncated
        type: boolean
      line_count:
        description: Total line count (for text files)
        type: integer
-      url:
-        description: Storage URL (provider://path)
-        type: string
+      selected_chunks:
+        description: Chunks included in this message prompt
+        type: integer
+      token_count:
+        description: Approximate tokens in the parsed document
+        type: integer
+      total_chunks:
+        description: Total parsed chunks
+        type: integer
    type: object
  github_com_Tencent_WeKnora_internal_types.MessageImage:
    properties:
@@ -2416,6 +2464,13 @@ definitions:
    type: object
  github_com_Tencent_WeKnora_internal_types.ParserEngineConfig:
    properties:
+      chat_parser_engine_rules:
+        description: |-
+          ChatParserEngineRules selects parser engines for session-scoped chat
+          documents. Knowledge bases keep their own rules in ChunkingConfig.
+        items:
+          $ref: '#/definitions/github_com_Tencent_WeKnora_internal_types.ParserEngineRule'
+        type: array
      mineru_api_key:
        description: MinerU 云 API Key
        type: string
@@ -2891,6 +2946,10 @@ definitions:
        type: array
      query_text:
        type: string
+      scope_tag_ids:
+        items:
+          type: string
+        type: array
      skip_context_enrichment:
        description: |-
          SkipContextEnrichment skips fetching parent, nearby, and relation chunks
@@ -5408,6 +5467,11 @@ definitions:
        description: Selected custom agent ID (backend resolves shared agent and its
          workspace from share relation)
        type: string
+      attachment_ids:
+        description: Pre-uploaded session-scoped document IDs
+        items:
+          type: string
+        type: array
      attachment_uploads:
        description: Attached files (documents, audio, etc.)
        items:
@@ -1,12 +1,12 @@
 {
  "name": "knowledage-base",
-  "version": "0.6.3",
+  "version": "0.7.0",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "knowledage-base",
-      "version": "0.6.3",
+      "version": "0.7.0",
      "dependencies": {
        "@microsoft/fetch-event-source": "^2.0.1",
        "@types/dompurify": "^3.2.0",
@@ -1,6 +1,6 @@
 {
  "name": "knowledage-base",
-  "version": "0.6.3",
+  "version": "0.7.0",
  "private": true,
  "type": "module",
  "scripts": {
@@ -5,7 +5,7 @@ description: |
  with document parsing, vector search, and LLM integration.
 type: application
 version: 0.1.0
-appVersion: "v0.6.3"
+appVersion: "v0.7.0"
 kubeVersion: ">=1.25.0-0"
 home: https://github.com/Tencent/WeKnora
 icon: https://raw.githubusercontent.com/Tencent/WeKnora/main/docs/images/logo.png
@@ -1 +1 @@
 .6.3
 .7.0