Overview
dsh-claude-move
Community · Topic auto-analysis — Automatically discovered through the dsh-plugin GitHub Topic. Static checks verified a pinned public root bundle contract and committed files without executing third-party code. This is not a human review, security audit, runtime smoke test, publisher identity check, or official endorsement.
Install this bundle from GitHub
The CLI validates the bundle, invokes native DSH, then reports completion.
npx dshpub add PerryLink/dsh-claude-move --ref 1c00376ba5dab1351d07dbabe81b266fa302ff1bCapabilities
What it contributes
README / EN
Package documentation
Keep your Claude Code history when you move to DeepSeek Harness. One install copies every Claude session, memory, skill and CLAUDE.md into DSH as resumable sessions — organized into one workspace per Claude project.
LIMITATIONS
Known limitations
- Titles come from `custom-title`/`ai-title`/first prompt; Claude `summary` records are not used as titles. - `thinking` blocks are kept in the imported log as `reasoning` content, but never enter the resume handoff. - Permission-class records are counted, not imported; DSH permission-preset suggestions are generated in reports. - Transcripts larger than `maxTranscriptBytes` fail loudly instead of partial import (fidelity first); chunked streaming import is on the roadmap. - Sessions whose source directory was deleted still import, but workspace attach fails (left ungrouped; `workspace.attached: false` plus a `reason` in the report). - Interrupted batch imports can be safely re-run (idempotent, append-only): finished files are skipped, grown files append only the new turns. - If a transcript was truncated or reset in place (fewer turns than the recorded import), re-import skips it and reports `sourceShrunk`; use `force: true` for a fresh full copy. - The Web panel is a zero-build floating panel driven by the plugin's own JSON routes; it does not use the shell's internal UI slot system (kept independent of undocumented rc.6 internals).
