DeepSeek Suspended My Account Three Times. My Archive Didn't Care.

说明与用途

作者将127条对话（820万字符）导出到本地ChromaDB，构建了自定义的摄取和检索工具，尽管DeepSeek账户被暂停三次，仍保留了310,963个块，零损失。

问题

DeepSeek suspended the author’s account three times without stated cause, threatening access to conversations.

结果

All 310,963 chunks of the author’s conversations were preserved locally, with zero losses, despite three platform suspensions.

工作流

• Schedule export of conversations to local storage.
• Export 127 conversations (8.2 million characters) to ChromaDB on local MacBook Air.
• Verify ingest and receipt of all chunks.
• Use custom ingest suite (Scribe, Warden, Hand) and msgvault adapter for email archives.
• Employ hybrid retrieval CLI (vector + SQL + dates) for access.
• Reconstruct documents if needed via document reconstruction tool.
• Orchestrate with four named workers to maintain local workflow.
• Keep all tooling AGPL and receipted for auditability.

证据

DeepSeek suspended my account three times. No cause stated. No appeal outcome. September 25. October 13. October 14 — and each one escalated: the first left my conversations visible, the second and third closed the door entirely.

来源

On September 22 — three days before the first suspension — a scheduled export ran. 127 conversations. 8.2 million characters. It went into a local ChromaDB store on an 8GB MacBook Air, embedded locally via Ollama, no cloud. The corpus survived the platform.

来源

Since then, I built the tooling to make every future suspension equally irrelevant: an ingest suite (Scribe, Warden, Hand), a msgvault adapter that reads email archives natively, a hybrid retrieval CLI (vector + SQL + dates), a document reconstruction tool, and an orchestrator with four named workers. All local. All AGPL. All receipted.

来源

Three suspensions proved the difference. 310,963 chunks. Zero losses.

来源