Exports metadata-only DSH turn, model, tool, approval, retry, and error events to Tuning Engines for governed traces, policy evaluation, cost analysis, and Work Session review, with a disk-backed retry queue.
Install
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:cerebrixos-org/tuning-engines-cli#path:/packages/tuningengines-dsh-plugin
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).
README
Native DeepSeek Harness telemetry and tool governance for Tuning Engines. The plugin observes the Harness session event log, preserves turn/step/tool-call identity, and exports metadata-only traces through a durable local spool.
Install
export TE_API_KEY="your-tenant-token-or-inference-key"
dsh plugin --profile default add tuningengines-cli
dsh --profile default
Configuration
| Environment variable | Default | Purpose |
|---|---|---|
TE_API_KEY |
required | Tenant API token; TE_INFERENCE_KEY is also accepted |
TE_API_URL |
https://app.tuningengines.com |
TE control-plane URL |
TE_GOVERNANCE_MODE |
observe |
off, observe, or fail-closed enforce |
TE_TRACE_FLUSH_INTERVAL_MS |
2000 |
Background flush interval |
TE_TRACE_BATCH_SIZE |
64 |
Maximum locally spooled records per flush |
TE_TRACE_SPOOL_PATH |
~/.tuningengines/dsh-trace-spool.jsonl |
Durable queue path |
Data handling
The default and only v1 capture mode is metadata-only. Raw prompts, assistant content, tool arguments, tool results, credentials, and model reasoning are not exported. Tool arguments are represented by a SHA-256 fingerprint for stable correlation without content disclosure.
DeepSeek Harness remains the execution runtime. Tuning Engines supplies the governance, approvals, trace analytics, cost attribution, and review surfaces.
Links
More in this category
xmanrui/dsh-im★ 1548
Connect IM bots to DeepSeek Harness via QR codes or bot credentials (9 channels: Feishu, WeChat, DingTalk, WeCom, QQ, Slack, Telegram, Discord, and WhatsApp).
shaobeichen/dsh-pocket★ 1415
Remote phone access to the DSH Web UI: scan a QR code for LAN or public (cloudflared tunnel) access with real-time sync, a mobile-adaptive layout, and a settings tab.
inclusionAI/Avernet#deepseek-harness-channel-bcn★ 574
Connects DeepSeek Harness to Avernet's Bot Collaboration Network over WebSocket V2, with automatic onboarding, isolated agent sessions, tool-call events, and multi-bot routing tools.
omdsh-dev/dsh-notification★ 86
Desktop notifications for turn completions, with per-outcome controls and keyword rules.
whyihaveyou/dsh-suite#plugin-notify★ 57
IM webhook and local notifications on turn completion, errors, or approval (Feishu/WeCom/DingTalk/Slack/Discord/custom).
omdsh-dev/dsh-lark★ 55
Lark/Feishu bot channel for DeepSeek Harness: each chat drives its own agent, and tool approvals, model questions, and plan reviews return as cards answered by a button or a reply. Switch workspace and model from the chat (`/cd`, `/model`, `/new`), and run several bots that keep separate sessions and can hand turns to each other in one group.
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.