DeepSeek Harness OpenTelemetry Monitoring

What is DeepSeek Harness Observability?

DeepSeek Harness (dsh) is DeepSeek's open-source agent harness. It has no OpenTelemetry export of its own, so instrumenting it means installing one plugin. Once installed, every turn becomes a trace: the agent loop, each reasoning round, each model call with its token counts and time to first token, and each tool execution.

With full DeepSeek Harness observability in SigNoz, you can see how much your team is spending in tokens and on which models, how many round trips a single request actually takes, which tools the agent reaches for, and where turns fail.

The plugin exports two metrics, gen_ai.client.operation.duration and gen_ai.client.token.usage, but neither carries a session, user, or error dimension. Everything worth grouping by lives on the spans, so this guide and the dashboard both work from traces.

Prerequisites

SigNoz setup (choose one):
- SigNoz Cloud account with an active ingestion key
- Self-hosted SigNoz instance
DeepSeek Harness 0.1.0-rc.6 or later, below 0.2.0. See the DeepSeek Harness repository
Node.js 22.19.0 or later
A DEEPSEEK_API_KEY, or another provider configured in your profile

Monitor DeepSeek Harness with OpenTelemetry

Instrumentation comes from @loongsuite/dsh-plugin, an Apache-2.0 plugin that hooks the harness lifecycle and exports OTLP over HTTP.

Step 1: Install the plugin into each profile you use

dsh plugin --profile headless add @loongsuite/dsh-plugin
dsh plugin --profile web add @loongsuite/dsh-plugin

Plugins are installed per profile, so a plugin added to headless does nothing when you launch web. Confirm it loaded:

dsh --profile headless --dump-config | grep loongsuite

You should see id: loongsuite-observability.

Step 2: Point the plugin at SigNoz

export OTEL_SERVICE_NAME=dsh-agent
export OTEL_EXPORTER_OTLP_ENDPOINT="https://ingest.<region>.signoz.cloud:443"
export OTEL_EXPORTER_OTLP_HEADERS="signoz-ingestion-key=<your-ingestion-key>"

Verify these values:

<region>: Your SigNoz Cloud region.
<your-ingestion-key>: Your SigNoz ingestion key.

The plugin appends /v1/traces and /v1/metrics to whatever you set. Adding a path yourself produces /v1/traces/v1/traces, and the export fails with no message in the terminal.

Step 3: Run the harness

dsh --profile headless "list the files in this directory and summarise the project"

Spans are batched, so allow a few seconds after the turn finishes before looking in SigNoz.

Every setting also lives in $DSH_HOME/profiles/<profile>/cordis.patch.yml (default ~/.dsh). Replace the empty [] with:

- id: loongsuite-observability
  config:
    endpoint: https://ingest.<region>.signoz.cloud:443
    serviceName: dsh-agent
    headers:
      signoz-ingestion-key: <your-ingestion-key>
    resourceAttributes:
      deployment.environment.name: production
    captureContent: false
    exportMetrics: true

This keeps the settings with the profile rather than the shell, at the cost of writing your ingestion key to disk.

Most steps are identical. To adapt this guide, update the endpoint and remove the ingestion key header as shown in Cloud → Self-Hosted.

View DeepSeek Harness Traces in SigNoz

Open the Traces explorer and filter on gen_ai.agent.system = 'deepseek-harness'. Each turn arrives as its own trace.

DeepSeek Harness traces in the SigNoz traces explorer — *Agent, step, model, and tool spans in the traces explorer*

Open any enter_ai_application_system span to see the full turn. The waterfall shows each reasoning round, the model call inside it, and every tool the agent executed.

A DeepSeek Harness turn expanded in the SigNoz trace detail view — *One turn: five reasoning rounds, nine tool calls, and a spawned subagent*

The plugin tags every span with gen_ai.span.kind, which is the attribute to filter and group by:

`gen_ai.span.kind`	Span name	What it covers
`ENTRY`	`enter_ai_application_system`	One turn, the root span
`AGENT`	`invoke_agent deepseek-harness`	The agent loop, with turn-level token totals
`STEP`	`react step`	One reasoning round
`LLM`	`chat <model>`	One model call, with tokens and time to first token
`TOOL`	`execute_tool <tool>`	One tool execution

Filter on gen_ai.span.kind rather than on the span name, since names embed the model and tool name and change per call.

The AGENT span repeats the sum of its own model calls. Summing gen_ai.usage.total_tokens across all spans therefore double counts exactly 2x. Add gen_ai.span.kind = 'LLM' to every token query.

Prompts and Responses Are Not Captured by Default

captureContent is false, so spans carry structure, timings, and token counts but no prompt or completion text. Enable it with captureContent: true in the profile config, or OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT=SPAN_ONLY.

Two things to weigh before turning it on. Anything in the context window, including source code and file contents, is written to your backend. And the payload grows sharply: the same single-tool turn measured 6,350 bytes with capture off and 73,078 bytes with it on, mostly because gen_ai.tool.definitions repeats the full schema of every registered tool on each model call.

Note that dsh.session.cwd records the absolute working directory on every span even with content capture off.

DeepSeek Harness Observability Dashboard

The DeepSeek Harness dashboard gives you token spend and cache efficiency, turn and session volume, model latency, tool activity, and error breakdown out of the box.

DeepSeek Harness dashboard in SigNoz — *The DeepSeek Harness dashboard template*

Troubleshooting DeepSeek Harness Observability

No data in SigNoz

An expired or wrong ingestion key fails silently. The harness prints a normal answer and exits successfully while the exporter receives a 401, so nothing in the terminal tells you anything is wrong. Test the key directly:

curl -i -X POST "https://ingest.<region>.signoz.cloud/v1/traces" \
  -H "content-type: application/json" \
  -H "signoz-ingestion-key: <your-ingestion-key>" \
  -d '{"resourceSpans":[]}'

A working key returns 200 with {"partialSuccess":{}}. An expired one returns 401 with Expired key.

The plugin does not appear in the config

Plugins are per profile. Run dsh --profile <profile> --dump-config | grep loongsuite for the profile you actually launch, and add the plugin to that profile if it is missing.

Subagent work is missing from the parent trace

A spawned subagent opens its own trace with its own root span, rather than nesting under the parent turn. There is no span link between them. Join them on attributes instead: the subagent's spans carry dsh.session.parent_id, dsh.session.origin = 'subagent', and dsh.session.delegation_depth.

A failing tool shows as a successful span

Only tools that report failure explicitly, such as an MCP tool returning isError, set the span status to error and add error.type = 'TOOL_ERROR'. A shell command exiting non-zero still records a successful span, so tool error counts based on span status will undercount.

Do not confuse this with the built-in telemetry plugin

DeepSeek Harness ships its own dsh-session-telemetry-otel plugin, disabled by default through DSH_TELEMETRY_MODE, which sends OTLP logs to DeepSeek's own endpoint. That is DeepSeek's product analytics and is unrelated to this setup.

Instrument the other AI coding agents your team runs, using the same OpenTelemetry pipeline:

Monitor Claude Code with OpenTelemetry - track token usage, cost, session activity, and tool decisions
OpenCode observability with OpenTelemetry - another agent that instruments through a plugin rather than natively
Monitor OpenAI Codex with OpenTelemetry - trace Codex runs from the IDE extension and the CLI
Grok Build observability with OpenTelemetry - token usage, tool activity, and startup latency from its native exporter
Monitor GitHub Copilot with OpenTelemetry - trace Copilot chat requests, models, and token spend

Browse all LLM observability integrations to instrument the rest of your stack.

DeepSeek Harness Observability & Monitoring with OpenTelemetry