@yunxiyang

Continue a DeepSeek Harness agent turn whose model narrated its next action but called no tool.

Web search provider for the DeepSeek Harness ctx.web seam via the LiteLLM proxy OpenAI Responses API (DeepSeek native server-side web_search)

Solidify DSH session history step by step: rewrite tool results in place to the facts the model actually kept, so long conversations stop re-sending noise every turn. Costs tokens and time: a ~770-character contract in every request, plus one extra full-context request and round-trip per step when stepSummary is on.

DSH web client plugin: pins the conversation column to a configurable percentage of its width (default full width) instead of the built-in 680-920px reading measure.