Pine/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases 1 Wiki Activity

Merge remote-tracking branch 'origin/master' into codex/pr239-parent-retarget-publish

Browse Source 
# Conflicts:
#	packages/core/tools/tests/gen-tool-catalog.spec.ts
This commit is contained in:
Tianyi Cui
2026-07-21 00:58:16 +08:00
parent 8c6ba1736f bb85b384f1
commit 3947312432
81 changed files with 2312 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/acp-agent/tests/snapshots/plan-mode/system-prompt.expected.md
+4
View File
@@ -24,6 +24,8 @@ Approval prompts are disabled in this session: actions that require approval are
Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.
Use the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.
<!-- request/header change 1 -->
You are an AI agent powered by the DeepSeek Harness SDK.
@@ -49,3 +51,5 @@ Approval prompts are disabled in this session: actions that require approval are
<!-- dsh-user-approval-policy:never -->
Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.
Use the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.