session-import-codex
Run the following command in DeepSeek Harness:
dsh plugin install xing01l/session-import-codex
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install xing01l/session-import-codex in DeepSeek Harness to install this plugin, available at https://github.com/xing01l/session-import-codex .
About this plugin
Many developers have accumulated substantial conversation context and engineering records in OpenAI Codex. When a team or individual moves to DeepSeek Harness, discarding that history means starting from scratch. session-import-codex exists to bridge this gap: it reads completed conversation turns from the official Codex App Server history endpoints, converts them into validated DSH session events, and persists them through the public services of the selected profile, automatically creating or reusing workspaces based on each session historical working directory.
The plugin is deliberately restrained in scope. It never reads Codex rollout files, desktop state, SQLite databases, or private JSONL files, and it never writes Harness persistence files directly. The import covers completed, interrupted, and failed turns, carrying only reasoning summaries by default rather than raw reasoning content. Active conversations are skipped, existing destination IDs are never overwritten, and reruns are safe and idempotent.
If you are planning to migrate your entire Codex workflow into DeepSeek Harness while preserving past conversation memory and engineering context, this plugin offers a low-cost, repeatable bridge. It requires no manual record tidying and no third-party parsing service; a single command completes the migration.
Use Cases
- Batch-import Codex conversation history into persistent DeepSeek Harness sessions
- Auto-create or reuse Harness workspaces from each session historical working directory
- Preserve full engineering context and reasoning summaries before switching toolchains
Best For
- Developers migrating from Codex to DeepSeek Harness
- Engineering teams that want to keep past conversation memory and records
- Engineers running local workflows or automated migration via PowerShell
Related Plugins
Memory layer for coding agents that indexes local session history and auto-recalls relevant context before edits, commands, and failures, with no manual search needed.
Traceable, searchable cross-session memory for AI agents that turns conversation knowledge into a typed knowledge graph and recalls relevant subgraphs instead of replaying full history, natively integrated with DeepSeek Harness.
Gives DSH AI cross-session long-term memory, to-do and skill management, plus multi-session orchestration, external AI delegation, and an infinite canvas that grows with you.
dsh-mnemon is a three-tier, pluggable, Agent-driven memory system for DeepSeek Harness, combining Runtime memory, Project Documents, and replaceable Memory Spaces with nine long-term providers.