dsh-thinking-effort

dsh-thinking-effort

A DSH (DeepSeek Harness) plugin that adds configurable reasoning effort levels to hand-declared llm-pi-ai models and sets a default reasoning effort for subagents. 中文 README 日本語 README 한국어 README Installation guide 中文安装指南 日本語インストールガイド 한국어 설치 안내 Changelog 日本語 changelog 한국어 changelog Compatibility boundaries: DSH Runtime compatibility covers the Settings transport only: modern DSH exposes remote.settings, while legacy DSH exposes connection.api.settings. The plugin detects the available runtime capability and keeps the legacy fallback optional, so the settings page does not require a Remote provider on older DSH builds. Gateway Protocol compatibility is a separate layer. When the DSH schema exposes them, the plugin supports 18 common scalar llm-pi-ai.compat fields, grouped into role/reasoning, format/output, streaming/tools, and storage/cache. Boolean fields offer Auto, supported, and unsupported; enum fields offer Auto and their concrete values; number fields take Auto or an integer. Every supported DSH release — 0.1.7-alpha.1 through 0.2.2 — exposes all 18 of them when the schema supports them. The optional dsh-llm-openai-completions transport can take over eligible custom OpenAI-c

A gateway compat field can be configured only when the DSH version, runtime schema, and route's api protocol all support it. Unsupported fields stay hidden and are not written to Settings. Among these 18 fields, openai-completions supports all but supportsMaxOutputTokens, while openai-responses, azure-openai-responses, and openai-codex-responses support only supportsDeveloperRole, supportsStrictMode, supportsLongCacheRetention, and supportsMaxOutputTokens. If api is missing or unrecognized, the runtime schema and DSH validation remain the final authority.

DSH 0.1.7 and later derive each settings form from the Loader entry's own Config schema (the entry-config model); a plugin that exports none gets no form at all. This plugin exports that schema, so its section is the Loader entry id thinking-effort. subagentEffort and the subagent default route live in that section, and the llm-pi-ai location is not a fallback: that section's schema declares only providers, so the Host refuses a write to any other path and drops undeclared keys from the user layer it reports. Settings are stored in the