dsh-model-fix: Automatic DSH Model Parameter Population and Compatibility Optimization
The `dsh-model-fix` plugin is designed to address the cumbersome configuration of unofficial models in DSH. It automatically populates parameters such as reasoning levels and context from `models.dev`, and supports updates as well as compatibility writing (disabling the developer role). It includes a feature to remember reasoning levels, defaults to a high level, and supports visual settings, excluding specific providers, and offline caching. The plugin takes effect after installation and requires DSH version 0.1.7-rc.2 through 0.2.0-rc.2.
Read Moredsh-model-fix: Fix streaming finalization defects for opencode endpoints muse-spark and gpt-5.6-luna
`dsh-model-fix` is a DeepSeek Harness (DSH) plugin designed to fix an error that occurs at the end of streaming output when the aggregation endpoint fails to provide a `finish_reason` signal. By rewriting the ending state to `stop`, the plugin resolves compatibility issues with `muse-spark-1.2` and `gpt-5.6-luna`. Users can install it using the official command and enable it by configuring `modelPattern` and `providers` in `cordis.patch.yml`. Using this plugin does not require enabling the data training privacy switch, and it can effectively avoid unnecessary retries and token consumption.
Read More