Most agent frameworks treat the runtime as scaffolding. You write tool definitions, wire up a prompt loop, and ship the agent. The harness is invisible infrastructure.
DeepSeek Harness (dsh
) flips that model. It treats the runtime itself as the product surface, exposing orchestration primitives, plugin boundaries, and execution state as first-class user-facing concepts. The result is an architecture where "everything is a plugin," including the parts you'd normally hard-code into the framework.
This is not a new LLM. It's a runtime that makes agent execution legible and composable at the infrastructure layer.
Most agent frameworks give you a loop: call the model, parse tool requests, execute tools, feed results back. The framework owns the loop. You own the tools.
A harness inverts the relationship. The runtime becomes a platform that plugins extend. The loop, the state manager, the tool executor, the context window policy, and the recovery logic are all swappable components.
DeepSeek Harness pushes this further than most:
This matters when agents run for hours, call dozens of tools, or spawn sub-agents. The harness becomes the control plane.
"Everything is a plugin" sounds like marketing. In practice, it means the runtime defines narrow interfaces and delegates everything else.
| Plugin Type | Responsibility | Example Use Case |
|---|---|---|
| Tool | ||
| Execute external actions | Call an API, run a shell command, query a database | |
| Context Manager | ||
| Decide what the model sees | Sliding window, summarization, retrieval-augmented context | |
| State Backend | ||
| Persist session data | Redis, SQLite, in-memory cache | |
| Delegation Handler | ||
| Spawn and coordinate sub-agents | Parallel research tasks, specialist agents | |
| Recovery Policy | ||
| Handle tool failures | Retry with backoff, fallback to human, skip and continue | |
| Observability Sink | ||
| Capture execution traces | OpenTelemetry, custom logs, audit trail |
Each plugin type has a defined contract. The runtime calls plugins at specific lifecycle hooks: before tool execution, after model response, on state checkpoint, on error.
When you run multiple agents concurrently, state isolation becomes critical. DeepSeek Harness uses session IDs to partition state. Each session gets its own context, tool registry, and execution history.
Plugins can share read-only state across sessions (like a global tool catalog) but write to session-scoped storage. This prevents one agent from corrupting another's state while still allowing shared infrastructure.
class ToolPlugin:
def execute(self, session_id: str, tool_name: str, args: dict):
state = self.state_backend.get(session_id)
result = self._run_tool(tool_name, args)
self.state_backend.update(session_id, result)
return result
runtime.register_plugin("http_tool", HTTPToolPlugin())
session_a = runtime.create_session()
session_b = runtime.create_session()
runtime.execute(session_a, "fetch_url", {"url": "https://api.example.com"})
runtime.execute(session_b, "fetch_url", {"url": "https://other.example.com"})
Because plugins are registered at runtime, you can swap implementations without restarting the agent. This is useful for A/B testing tool implementations, rolling out new context policies, or upgrading observability sinks.
Versioning happens at the plugin level. The runtime tracks which version of each plugin was active during a session. If you replay a session later, you can use the exact plugin versions that ran originally, or upgrade selectively.
Traditional agent frameworks log tool calls as side effects. DeepSeek Harness treats observability as a first-class concern.
Every plugin boundary emits structured events:
These events flow to observability plugins, which can write to OpenTelemetry, CloudWatch, or custom backends. You get distributed tracing across sub-agents, execution graphs for debugging, and audit trails for compliance.
The runtime also exposes a query API. You can ask "show me all tool calls in session X" or "what was the context window at turn 12" without parsing logs.
Agent failures fall into categories:
DeepSeek Harness handles each with explicit recovery policies:
The runtime wraps every tool call in a try-catch boundary. If a tool fails, the recovery plugin decides what happens next:
The model sees a structured error message, not a stack trace. This keeps the agent from hallucinating about internal errors.
If the model times out or returns invalid JSON, the runtime can:
State checkpoints happen at configurable intervals. If the state backend fails, the runtime can:
When agents delegate to sub-agents, the runtime tracks dependency graphs. If a sub-agent hangs, the parent can:
DeepSeek Harness can run as a library (embedded in your application) or as a standalone service (HTTP API or gRPC).
You import the runtime, register plugins, and call it directly from your code. This works for single-tenant applications where the agent runs in the same process as the rest of your app.
from deepseek_harness import Runtime
runtime = Runtime()
runtime.register_plugin("http_tool", HTTPToolPlugin())
runtime.register_plugin("state", RedisStateBackend(host="localhost"))
session = runtime.create_session()
result = runtime.run(session, initial_prompt="Fetch the latest stock price for AAPL")
You run the harness as a long-lived service. Clients send session creation requests, tool execution requests, and state queries over HTTP or gRPC.
This mode supports multi-tenancy. Each client gets isolated sessions. The service handles plugin lifecycle, connection pooling, and resource limits.
apiVersion: apps/v1
kind: Deployment
metadata:
name: deepseek-harness
spec:
replicas: 3
template:
spec:
containers:
- name: runtime
image: deepseek/harness:latest
env:
- name: STATE_BACKEND
value: "redis://redis-cluster:6379"
- name: OBSERVABILITY_SINK
value: "otlp://collector:4317"
resources:
limits:
memory: "4Gi"
cpu: "2"
In service mode, the runtime enforces:
Most agent frameworks hide the runtime. DeepSeek Harness exposes it.
This changes what you can build:
The runtime becomes the API. Plugins become the extension points. The agent itself is just configuration.
Use DeepSeek Harness when:
Avoid it when:
The plugin-first architecture is powerful but not free. You trade simplicity for composability. If your agent fits in a single Python file, a harness is overkill. If your agent needs to run in production, coordinate with other agents, and survive real-world failures, the runtime-as-product model starts to make sense.