@botbotgo/agent-harness 0.0.285 → 0.0.287
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +2 -0
- package/README.zh.md +2 -0
- package/dist/package-version.d.ts +1 -1
- package/dist/package-version.js +1 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -261,6 +261,7 @@ Start with these user-facing docs:
|
|
|
261
261
|
- `docs/development/release-notes.html`
|
|
262
262
|
- `docs/runtime-inspection-contract.md`
|
|
263
263
|
- `docs/tool-execution-policy.md`
|
|
264
|
+
- `docs/long-running-coding.md`
|
|
264
265
|
- `docs/long-term-memory.md`
|
|
265
266
|
- `docs/memory-policy-reference.md`
|
|
266
267
|
|
|
@@ -714,6 +715,7 @@ Example workspaces:
|
|
|
714
715
|
- `examples/06_repository-analysis/` is the Repository Analysis Example: repo analysis around one workspace-local tool plus embedding-backed indexing
|
|
715
716
|
- `examples/07_multi-agent-research/` is the Multi-Agent Research Example: the most complete multi-agent research workspace with reusable backends, skills, and local tools
|
|
716
717
|
- `examples/08_long-term-memory-learning/` is the Long-Term Memory Learning Example: repeated requests that store durable memory, inspect recall, and make later answers more context-aware
|
|
718
|
+
- `examples/09_long-running-coding-harness/` is the Long-Running Coding Harness Example: a host agent plus app-owned planning/evaluation roles, Playwright MCP wiring, and evaluation-bundle export for long coding sessions
|
|
717
719
|
|
|
718
720
|
Workspace-local tool modules in `resources/tools/` should be exported with `tool({...})`.
|
|
719
721
|
Any other local module shape is not supported, and unsupported shapes are rejected at load time.
|
package/README.zh.md
CHANGED
|
@@ -257,6 +257,7 @@ AI 让 agent 逻辑、工具调用和工作流代码更容易生成，真正更
|
|
|
257
257
|
- `docs/development/zh/release-notes.html`
|
|
258
258
|
- `docs/runtime-inspection-contract.md`
|
|
259
259
|
- `docs/tool-execution-policy.md`
|
|
260
|
+
- `docs/long-running-coding.md`
|
|
260
261
|
- `docs/long-term-memory.md`
|
|
261
262
|
- `docs/memory-policy-reference.md`
|
|
262
263
|
|
|
@@ -677,6 +678,7 @@ await stop(runtime);
|
|
|
677
678
|
- `examples/06_repository-analysis/` 是 Repository Analysis Example：围绕一个工作区本地 tool 和 embedding 索引的仓库分析示例
|
|
678
679
|
- `examples/07_multi-agent-research/` 是 Multi-Agent Research Example：最完整的多 agent 研究工作区，包含可复用 backend、skill 和本地 tool
|
|
679
680
|
- `examples/08_long-term-memory-learning/` 是 Long-Term Memory Learning Example：通过多次 request 写入 durable memory、检查 recall，并让后续回答更懂上下文
|
|
681
|
+
- `examples/09_long-running-coding-harness/` 是 Long-Running Coding Harness Example：用 host agent 加 app-owned planning/evaluation 角色，结合 Playwright MCP 与 evaluation bundle 承载长时 coding 会话
|
|
680
682
|
|
|
681
683
|
`resources/tools/` 下的工作区本地工具模块应统一用 `tool({...})` 导出。
|
|
682
684
|
不支持历史/兼容写法，任何不带该导出形式的工具模块都会在工作区加载时被拒绝。
|
|
@@ -1 +1 @@
|
|
|
1
|
-
export declare const AGENT_HARNESS_VERSION = "0.0.
|
|
1
|
+
export declare const AGENT_HARNESS_VERSION = "0.0.286";
|
package/dist/package-version.js
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
export const AGENT_HARNESS_VERSION = "0.0.
|
|
1
|
+
export const AGENT_HARNESS_VERSION = "0.0.286";
|