Orkas is an open-source (MIT), local-first AI team for your desktop: a Commander turns your goal into to-dos and coordinates 16 built-in specialist agents plus Claude Code, Codex, OpenCode, OpenClaw and Hermes, with projects, scheduled automations and connectors. Free app for macOS & Windows; built-in models or your own keys.
JavaScript agent-collaborationagent-harnessagent-orchestrationagent-teamagent-workflowai-assistantai-automationai-employeeai-productivityai-teamai-workflowautonomous-agentsclaude-code-guiclaude-coworkdesktop-agentlocal-firstmulti-agentmulti-agent-systemself-evolving-agentstask-automation
Replace residual Chinese examples in the upstream-dependencies hard rule
wyt9727fff424b6
diff --git a/src/main/prompts/chat_commander.md b/src/main/prompts/chat_commander.mdindex c187758f..6ecd4a62 100644--- a/src/main/prompts/chat_commander.md+++ b/src/main/prompts/chat_commander.md@@ -137,7 +137,7 @@ plan_set({Variables that don't exist are left literal (handy for debugging).-**Hard rule for upstream dependencies**: when a later step needs data produced by an earlier one, the dependency MUST appear as `{{step_N.output_summary}}` / `{{step_N.output_files}}` inside that step's `input`. Prose like "对上一步采集到的数据 / based on the previous output" substitutes nothing — the assignee receives your literal text and the downstream agent re-prompts the user via `<agent-input-form>` for data the plan was supposed to thread automatically.+**Hard rule for upstream dependencies**: when a later step needs data produced by an earlier one, the dependency MUST appear as `{{step_N.output_summary}}` / `{{step_N.output_files}}` inside that step's `input`. Prose like "based on the previous output" / "use the data from step 1" substitutes nothing — the assignee receives your literal text and the downstream agent re-prompts the user via `<agent-input-form>` for data the plan was supposed to thread automatically.### Three typical shapes