@deepseek-ai/dsh-goal-round-driver 0.1.3-alpha.2 → 0.1.5-alpha.2

package/README.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write packages/goal/goal-round-driver/README.md
-README.md: 8e6a31fe3e5e131611067ed95034a8b8cebb493a
-README.zh.md: 5a70b585da727cb4f599495deeef4d860ff200b8
+README.md: c80def6393c0a119c20d59acf4b527856811f47c
+README.zh.md: 0695b8494cd83b05a63813a8e0caf9e6052004d3

package/README.md

@@ -9,7 +9,7 @@ English | [中文](README.zh.md)
 
 ## Summary
 
-`dsh-goal-round-driver` automatically continues an active goal in the same session: whenever the agent is idle with an active, armed goal and remaining round capacity, the driver starts the next goal round. Each round is one model turn toward the objective, driven by a retained goal-round prompt; only goal-sourced rounds count against the goal's round cap, and the goal records a blocker when the cap is exhausted. The driver has no configuration of its own — the round cap belongs to the goal definition and the model-facing blocked threshold belongs to `dsh-tool-goal`, so policy stays in one place. Mount it together with `dsh-goal` and `dsh-tool-goal` when a task should work itself toward completion across rounds; leave it out when every step needs human steering.
+`dsh-goal-round-driver` automatically continues an active goal in the same session while the agent is idle, continuation is armed, and the configured round allowance remains. Each round gives the model another turn toward the objective; only goal rounds that reach model history consume the allowance, and exhaustion records a blocker. The driver has no configuration: the goal defines the round limit, and `dsh-tool-goal` defines when repeated blocking stops continuation. Mount it with `dsh-goal` and `dsh-tool-goal` for unattended multi-round progress; omit it when each step requires human steering.
 
 ## Table of Contents
 

package/README.zh.md

@@ -9,7 +9,7 @@ kind: "package-reference"
 
 ## 概述
 
-`dsh-goal-round-driver` 会在同一会话中自动继续 active 的 goal：每当 agent 空闲且存在 active、已启用续行并有剩余容量的 goal 时，驱动器就会启动下一个 Goal Round。每一轮都是朝目标前进的一次模型轮次，由保留的 goal-round 提示词驱动；只有来源为 goal 的 Round 会计入 goal 的 Round 上限，上限耗尽时 goal 会记录一个 blocker。驱动器没有自己的配置——Round 上限属于 goal 定义，面向模型的阻塞阈值属于 `dsh-tool-goal`，策略因此只保留在一处。当任务应跨多轮自行推进时，与 `dsh-goal` 和 `dsh-tool-goal` 一起挂载它；当每一步都需要人工 steering（中途引导）时，不要挂载。
+`dsh-goal-round-driver` 会在同一会话内自动继续 active goal，但前提是 agent 已空闲、续行已启用且配置的 Round 额度仍有剩余。每个 Round 都让模型获得另一次推进目标的机会；只有进入模型历史的 goal Round 才消耗额度，额度耗尽时会记录 blocker。驱动器本身没有配置：goal 定义 Round 上限，`dsh-tool-goal` 定义重复受阻后何时停止续行。若任务需要无人值守的多轮推进，应与 `dsh-goal` 和 `dsh-tool-goal` 一起挂载；若每一步都需要人工 steering（中途引导），则不要挂载。
 
 ## 目录
 

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@deepseek-ai/dsh-goal-round-driver",
   "description": "Race-fenced same-session goal-round driver",
-  "version": "0.1.3-alpha.2",
+  "version": "0.1.5-alpha.2",
   "publishConfig": {
     "access": "public"
   },
@@ -32,24 +32,24 @@
   ],
   "license": "MIT",
   "peerDependencies": {
-    "@deepseek-ai/dsh-invariants": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-llm": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-goal": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-agent": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-session": "^0.1.3-alpha.2",
+    "@deepseek-ai/dsh-goal": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-llm": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-session": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-invariants": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-agent": "^0.1.5-alpha.2",
     "@deepseek-ai/cordis": "^4.0.2"
   },
   "devDependencies": {
-    "@deepseek-ai/dsh-agent-loop": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-agent": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-goal": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-agent-loop-testkit": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-llm": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-invariants": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-session": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-system-prompt": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-tools": "^0.1.3-alpha.2",
+    "@deepseek-ai/dsh-agent": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-agent-loop": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-agent-loop-testkit": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-goal": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-invariants": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-llm": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-session": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-system-prompt": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-tools": "^0.1.5-alpha.2",
     "@deepseek-ai/cordis": "^4.0.2",
-    "@deepseek-ai/dsh-session-projection": "^0.1.3-alpha.2"
+    "@deepseek-ai/dsh-session-projection": "^0.1.5-alpha.2"
   }
 }