mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
A goal round reporting complete or blocked used to conclude the turn at the tool result, so the model never spoke after the call and sessions ended on a bare update_goal card. The terminal update now defers one plugin-sourced <goal_complete>/<goal_blocked> instruction onto its result asking for a grounded closing message without further tool calls; the turn then ends through the ordinary no-tool-calls stop. Direct-human mutations stay uninstructed. Wording chosen by A/B sampling on deepseek-v4-pro; one extra request per goal lifecycle. New keyless ACP snapshot goal-wrapup drives the shipped app through create -> round one -> autonomous complete and pins the injection, the same-turn closing message, and the completed turn end.
14 lines
339 B
JSON
14 lines
339 B
JSON
{
|
|
"steps": [
|
|
{ "op": "initialize" },
|
|
{ "op": "newSession" },
|
|
{
|
|
"op": "promptAndWaitForAgentMessage",
|
|
"text": "Create a durable goal for the wrap-up snapshot, then report readiness.",
|
|
"waitForText": "GOAL READY"
|
|
},
|
|
{ "op": "waitForTurnStart", "minimumTurn": 2 },
|
|
{ "op": "waitForTurnEnd" }
|
|
]
|
|
}
|