PRODUCT UPDATES

What’s new in ChatGrowing.

New features, improvements, and fixes — every version, newest first.

Released

ChatGrowing 0.4.10 — 批量视频传输与发布状态修复

ChatGrowing 0.4.10 改进 Codex 本地视频上传：支持批量路径、断点续传、自适应分块和两个文件并发传输。视频传到 ChatGrowing 后，继续通过现有统一 Gateway 批量提交到 YouTube；已发布视频与尚未核实的 YouTube 合成内容声明分别呈现，避免把声明回读缺失误报为失败或成功。

已用正式 MCP 完成 3 条私密视频的传输、批量提交、YouTube 回读与删除。部署中的 Gateway 保持 106 个工具，原有 OAuth resource、client 和 scope 不变。插件无需 Git 客户端，首次安装的本地运行环境由 chatgrowing.com 官网提供，不要求用户直连 GitHub、PyPI 或安装 FFmpeg；当前一次冷启动重试遇到官网 Cloudflare 522 或下载缓慢，已安装且运行环境就绪的用户更新插件时可以复用现有运行环境。OAuth 自动续期的长期稳定性仍需独立观察。

本版本没有启用 Meta/TikTok 发布，也不把 YouTube 合成内容声明缺失解释为已生效。浏览器上传路径的前端新版尚未作为本次发布的一部分部署。

GitHub Release ↗

Released

ChatGrowing 0.4.7 — YouTube 批量发布与文件接收

ChatGrowing 0.4.7 更新 YouTube 素材操作 Skill 和公开 Gateway 工具清单。

  • 新版 Skill 使用批量发布清单预览与单次提交：用户指令已明确覆盖文件、频道和发布字段时，不再重复要求授权；旧 Host 工具快照仍可使用兼容提交入口。
  • 用户明确指定视频删除时，精确预览后可执行原操作，不要求重复确认；结果未知时只对账，不重新发起删除。
  • 可用时优先通过 Host 正式文件参数将本地 MP4 临时接收到 ChatGrowing 服务端，再发布到 YouTube；本地文件助手保留兼容在途任务。
  • 发布元数据与当前生产 Gateway 的 106 个工具一致，包含文件接收与新版批量提交入口。Codex 桌面版 0.155.0-alpha.9 的新会话已验证工具发现、授权查询、越权拒绝、资源桥、本地助手和文件交接。

已知限制：生产 OAuth 自动续期尚未完成两次真实到期周期验收。本版不宣称修复 Token expired 问题。当前已安装的插件不会自动升级；请按 INSTALL.md 更新插件，并新建 Codex 任务以刷新工具列表。更新插件不要求重新授权 YouTube。

GitHub Release ↗

Released

ChatGrowing 0.4.6 — 安装与单登录素材交接修复

本次修复本地素材助手的安装与单登录文件交接。账户查询、频道读取继续复用现有 ChatGrowing 企业登录和资源权限。

  • 新安装支持 HTTPS 快照入口，避免因系统 Git 触发 Apple 开发工具安装。
  • macOS 素材助手使用固定版本的独立运行环境，无需另装系统 Python、Homebrew 或 Xcode；安装中断及残缺目录可以重试修复。
  • 本地文件通过现有 ChatGrowing 登录完成任务级交接，不再额外登录素材服务；上传仍需权限、目标确认及审计。
  • 广告查询和频道读取不依赖本地素材组件；操作指引避免循环重登、临时 OAuth 桥和提取 Host 凭据。

已验证：当前成员的账户/频道发现、受控查询入口、越权拒绝、Apple Silicon 本地助手启动与文件检查、同一登录下文件登记和幂等重试。查询返回的数据缺失仍按 partial 表达，不代表数据完整性验收。

已知限制：生产 OAuth 自动续期仍在独立验收，本版本不宣称根治 token expired；Intel 尚未实机验收；本轮没有执行真实 YouTube 视频上传或删除。

现有用户需显式更新插件到 0.4.6 才获得本地助手与随包指引修复。已经生效的服务端及 Cloudflare 接入修复不要求更新插件或重新授权 Google。网站保留全部历史版本记录。

GitHub Release ↗

Released

ChatGrowing 0.4.5 — Minimal public client package

ChatGrowing 0.4.5 reduces the public local material helper to its required client code.

Changes

  • Isolated file inspection, manifest encoding, local authentication and transfer into a small client package.
  • Removed advertising domain contracts, report models, tenant routing and server-side material storage/registration implementations from the current installable package.
  • Replaced recursive dependency bundling with an explicit seven-file Python allowlist and import checks that reject private domain modules and dynamic import loaders.
  • Preserved the existing unified gateway, YouTube workflow and server-side permissions. This update adds no provider access or second login requirement.

Update

Explicitly update the installed plugin to 0.4.5 and open a new task. Existing organization connections remain valid. See INSTALL.md.

Scope

This hardening changes the current package. It does not rewrite previous public commits/tags or revoke copies already downloaded. Server business logic was not deployed or changed by this plugin release.

Requires Codex 0.144.5 or later. Previous public version: 0.4.4.

GitHub Release ↗

Released

ChatGrowing 0.4.4 — Unified gateway and YouTube workflows

ChatGrowing 0.4.4 brings advertising analysis and permitted YouTube operations into one ChatGrowing agent connection.

What changed

  • One remote gateway for advertising reads and YouTube material operations. Members reuse their ChatGrowing session and existing organization channel connections, subject to their permissions.
  • Added YouTube material workflow guidance for channel discovery, video lookup, upload, editing, deletion and recovery. Uploads and destructive operations still require explicit confirmation.
  • Retained the bundled local material helper for user-selected files; it does not require a second ChatGrowing sign-in.
  • Preserved the existing advertising analysis capabilities and server-side organization/resource access controls.

Update

Refresh the ChatGrowing marketplace, then explicitly update the installed plugin and open a new task. Refreshing the marketplace alone does not update an existing installation. Follow INSTALL.md.

An already connected YouTube channel does not need another Google consent merely because of this plugin update. A new channel or missing provider permissions may still require its owner to connect or complete authorization.

Validation and scope

The unified production gateway previously completed a private YouTube upload, readback and confirmed deletion. This release additionally verifies fresh Codex Host discovery, direct read access, recovery-contract discovery and denied resource access. This release does not activate the proposed new Google Ads collection architecture or new advertising write capabilities.

Codex CLI/Desktop 0.144.5 or later is required. Previous public version: 0.4.3.

GitHub Release ↗

Marketplace commit

Google sign-in callback correction

Corrected the Material OAuth callback client used by the 0.4.3 plugin.

Original marketplace record ↗

Marketplace commit

Analysis with partial data

Added guidance for explaining available observations when data is partial and discovering sources dynamically.

Original marketplace record ↗

Marketplace commit

Event and user counts together

Allowed event counts and user counts to be analyzed together while preserving their distinct meanings.

Original marketplace record ↗

Marketplace commit

Material operations and local files

Introduced the Material Actions connection and a bundled helper for user-selected local files. The separate Material login used by this version is superseded by 0.4.4.

Original marketplace record ↗

Marketplace commit

Advertising analysis plugin

Published the read-only advertising analysis plugin, organization-scoped access and installation instructions.

Original marketplace record ↗

Archived · Local release candidate

Branded plugin packaging

Prepared an immutable local ChatGrowing plugin package with the branded installation flow and Resource Bridge recovery contract.

This was a local candidate; public marketplace release was not confirmed in the historical record.

Archived changelog source ↗

Archived · Release candidate

ChatGrowing 0.3.0

A new identity and a simpler path from an advertising question to a governed answer inside Codex.

  • Introduced the ChatGrowing name, visual identity, Plugin namespace, OAuth resource, and customer-facing product language.
  • Separated everyday queries from long-lived Artifacts. Users can ask ordinary questions and continue drilling down without first publishing an Evidence Artifact.
  • Kept explicit Tool dependencies and added a discoverable Resource Bridge recovery contract for compatible Codex sessions where custom Tools are not exposed.
  • Consolidated the public Remote surface around 13 governed read-only Tools and seven intent-level Remote Skills.
  • Preserved request-scoped organization and resource authorization. The release does not modify campaigns, budgets, bids, status, or creatives.

0.3.0 is currently a release candidate and has not yet been published to the public Marketplace.

Archived changelog source ↗

Archived · Unpublished candidate

ChatGrowing 0.2.3

A recovery path for Codex sessions where custom Tools are unavailable.

  • Added Resource Bridge access backed by the same read-only authorization and query implementation.
  • Published a fixed recovery contract that compatible Hosts can discover through MCP Resources.
  • Allowed approved read-only queries to run through parameterized Resource Templates without creating a separate query engine.
  • Kept authorization, account scope, input validation, and evidence behavior identical to normal Tool calls.
  • Added protocol observability to distinguish initialization, Tool discovery, Resource discovery, and query execution failures.

The server-side recovery capability was deployed, but the 0.2.3 Plugin was not publicly released.

Archived changelog source ↗

Archived · Public release

ChatGrowing 0.2.2

More reliable Tool discovery in Codex.

  • Declared the remote Ads Read Tool dependency for every published Skill.
  • Improved how Codex connects analysis, monitoring, configuration, and reporting Skills to the remote MCP.
  • Added release checks for the expected server name, Streamable HTTP transport, and Remote MCP URL.
  • Kept all seven published Skills on the same governed Ads Read capability instead of duplicating query logic inside each Skill.

Archived changelog source ↗

Archived · Public release

ChatGrowing 0.2.1

Simpler authentication and evidence-first custom reports.

  • Moved Codex authentication to one allowlisted CIMD OAuth client.
  • Added user-defined reports based on explicitly published evidence.
  • Preserved account scope and metric definitions from query to rendered report.
  • Added report preview, Report Run, rendered asset, and Feishu projection-plan outputs without adding advertising write access.
  • Required every report input to resolve to resources visible to the current signed-in member.

Archived changelog source ↗

Archived · Public release

ChatGrowing 0.2.0

Server-driven reports and shareable report images.

  • Added server-managed report definitions and guidance.
  • Added long-image rendering for governed reports.
  • Kept report availability and formats up to date without changing the thin Plugin.
  • Added binary report-resource reading so rendered images could be retrieved through the governed MCP flow.
  • Established the server-driven bootstrap pattern used to deliver current capability and limitation guidance.

Archived changelog source ↗

Archived · Public release

ChatGrowing 0.1.9

Flexible analysis beyond fixed questions.

  • Added governed follow-up analysis and dynamic continuation.
  • Added cross-source compatibility checks.
  • Improved multi-account exploration while preserving authorization scope.
  • Added capability context and Catalog guidance so queries could be planned from available fields, metrics, grains, and breakdowns.
  • Added constrained SQL and Python analysis over authorized query results for calculations not covered by a fixed summary.

Archived changelog source ↗

Archived · Public release

ChatGrowing 0.1.8

Native Codex authentication without a fixed local callback.

  • Removed the previously fixed OAuth client and callback assumptions.
  • Added Authorization Code with PKCE for public-client authentication.
  • Allowed the Codex Host to register the callback used by each connection.
  • Hardened issuer, audience, resource, and scope validation for the Remote MCP.

This historical dynamic-registration approach was later replaced by the single CIMD client model in 0.2.1.

Archived changelog source ↗

Archived · Public release

ChatGrowing 0.1.7

More dependable sessions across the web product and Codex Plugin.

  • Stabilized OAuth login and session handling for Remote MCP requests.
  • Improved access checks when moving between Dashboard, ad-management, and Plugin workflows.
  • Hardened the public release builder and authentication configuration validation.
  • Reduced false authorization failures caused by session transitions.

Archived changelog source ↗

Archived · Public release

ChatGrowing 0.1.6

Session recovery for interrupted or expired authenticated requests.

  • Added a controlled retry path for requests that encounter an expired API session.
  • Improved authenticated fetch behavior so users could recover without restarting the entire workflow.
  • Pinned the then-current Codex OAuth configuration to reduce client mismatch.

Archived changelog source ↗

Archived · Public release

ChatGrowing 0.1.5

Stricter access control and more dependable advertising semantics.

  • Hardened organization membership, resource binding, and account-scope enforcement.
  • Added stronger checks around app and advertiser selection.
  • Improved semantic profiles for metric definitions and source-specific interpretation.
  • Made unavailable, unauthorized, missing, partial, and genuine-zero results easier to distinguish.
  • Added release gates covering the combined access and semantic surface.

Archived changelog source ↗

Archived · First public Plugin

ChatGrowing 0.1.4

Made the existing 0.1 product available as the first publicly installable thin Plugin.

  • Published the Plugin through a versioned public Git Marketplace.
  • Moved customer installation to a thin package containing stable Skills and Remote MCP configuration.
  • Kept private application code, credentials, tokens, and advertising data out of the public bundle.
  • Added immutable release checks and an explicit rollback version.

Archived changelog source ↗

Archived · Private candidate

ChatGrowing 0.1.3

The first versioned Codex Plugin candidate for invited teammates.

  • Established the Plugin manifest, versioned Marketplace packaging, and Remote MCP connection.
  • Documented installation, explicit upgrade behavior, and teammate onboarding.
  • Added controlled private distribution before the first public thin-Plugin release.
  • Confirmed that Marketplace updates do not silently replace an already installed Plugin.

Archived changelog source ↗

Archived · Product improvement

ChatGrowing 0.1.2

Improved the reporting and governed paid-growth workflows introduced in 0.1.0.

  • Strengthened the governed paid-growth analysis flow and corrected early evidence-handling gaps.
  • Improved the Dashboard reporting workflow from source data to a reviewable output.
  • Added basic daily-report automation on top of the existing report foundation.
  • Expanded validation around report composition, delivery state, and operational reliability.

Archived changelog source ↗

Archived · Initial release

ChatGrowing 0.1.0

The foundation of ChatGrowing. Most of the product’s core capabilities were established in this first version; later releases focused on making them more flexible, reliable, secure, and easier to distribute.

Advertising data in one governed layer

  • Connected the core data sources. Brought Meta Ads, Google Ads, TikTok Ads, and AppsFlyer into one read-only advertising data layer.
  • Unified delivery and attribution evidence. Used advertising platforms for spend, impressions, clicks, object status, budget, and bidding evidence, while AppsFlyer remained the attribution baseline for conversion outcomes.
  • Preserved source differences. Kept platform-specific hierarchy, metric grain, currency, status, and attribution meaning instead of flattening every source into one ambiguous table.

Core product functions

  • Natural-language advertising questions. Users could ask about spend, conversions, CPI/CPS, pass rate, account performance, campaigns, delivery, and changes over time.
  • Cross-channel summaries and comparisons. The system could compare platforms, accounts, apps, campaigns, and date windows using governed metric definitions.
  • Object-level drill-down. Users could move from a high-level result into provider-native Campaign, AdGroup or Ad Set, Ad, placement, asset, and other available evidence.
  • Performance diagnosis. The analysis flow separated what changed, possible explanations, supporting evidence, counter-evidence, and what still could not be concluded.
  • Configuration inspection. The product could read account hierarchy, delivery status, budget, bid, mapping, and available configuration evidence without changing the advertising platform.
  • Monitoring foundation. Data freshness, account status, delivery risk, balance or policy signals, and report-delivery conditions could be inspected and explained.
  • Report foundation. The same governed data and metric definitions could be composed into repeatable advertising summaries and operational reports.

Evidence and data-quality rules

  • Evidence before interpretation. Answers were grounded in a defined source, resource scope, date range, grain, metric contract, and freshness state.
  • Unknown was not treated as zero. Missing data, unavailable fields, incomplete mapping, insufficient permission, synchronization failure, and a real zero result remained different states.
  • Attribution dates stayed explicit. Actual event dates and D0/D1/D3 cohort views were not silently mixed.
  • Partial evidence stayed partial. The product did not promote incomplete hierarchy, asset, or attribution evidence into a confident conclusion.

Access and safety boundaries

  • Queries were restricted to the organization, resources, apps, and advertising accounts available to the current user.
  • The advertising MCP was read-only and did not modify campaigns, budgets, bids, status, targeting, or creatives.
  • The model did not receive direct database, production-server, credential, or secret access.
  • Recommendations remained reviewable suggestions; no advertising action was applied automatically.

Archived changelog source ↗

New release notes synchronize from GitHub. Earlier website records retain their original dates and status; historical candidate notes describe their status at that time.