Articles tagged "Sub agent model"

dsh-subagent-model: Enforce Subagent Model and Reasoning Effort

2026-10-12 DeepSeek Harness plugin DeepSeek Harness dsh-subagent-model DeepSeek plugin Sub agent model DSH

This plugin is designed to resolve the issue in DeepSeek Harness where subagents inherit the parent route, leading to unpredictable model usage. It provides a minimal forced-configuration approach that directly specifies the model and reasoning effort when invoking subagents, ensuring controlled execution. Core features include enforcing model selection, validating reasoning effort values, joining the current turn rather than waiting for the next one, and displaying the route in logs. Users can configure the allowlist and effort level via the UI or YAML. After installation, replace the delegation line in the preset and set `maxDepth` and `toolFilter` to prevent deep delegation.

dsh-submodel-change: Subagent Model Selector

2026-10-10 DeepSeek Harness plugin DeepSeek DSH plugin dsh-submodel-change Sub agent model model inference

The DeepSeek Harness plugin `dsh-submodel-change` lets users manually choose a model when the AI invokes subagents, addressing the need to distinguish between reasoning and summarization models in complex tasks. The plugin has zero dependencies and works only for `provider: spawn`. It supports GUI popup selection, reusing the previous selection, and nested inheritance. Installation requires restarting Desktop and supports automatic scripts or bundle methods. Configuration options allow customizing the reuse strategy and adding models. By using official extension points to intercept requests and inject model routing into the root session popup, the plugin enables fine-grained control over subtask execution under multi-model strategies.

dsh-task-models: Enhanced DeepSeek Harness Subagent Model and Reasoning Effort Selection

2026-09-14 DeepSeek Harness plugin DeepSeek DSH plugin dsh-task-models Sub agent model Reasoning power

The dsh-task-models plugin extends the native subagent tools in DeepSeek Harness (DSH), allowing you to specify a particular model and reasoning effort when invoking `subagent` and `subagent_fork`. By overriding the native tools to add `model` and `reasoning_effort` parameters, it supports both background sessions and one-shot foreground execution. In v0.2.0, the standalone `task` tool was removed and its functionality was merged into subagents. Note that this plugin is officially deprecated; you should confirm whether your current DSH version still requires it.