@botbotgo/agent-harness 0.0.67 → 0.0.68
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 +16 -0
- package/README.zh.md +16 -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
|
@@ -70,6 +70,7 @@ Boundary documents live in:
|
|
|
70
70
|
- `docs/feature-checklist.md`
|
|
71
71
|
- `docs/long-term-memory.md`
|
|
72
72
|
- `docs/app-task-pattern.md`
|
|
73
|
+
- `docs/coding-agent-guide.md`
|
|
73
74
|
|
|
74
75
|
## Why This Exists
|
|
75
76
|
|
|
@@ -350,6 +351,21 @@ There are three main configuration layers:
|
|
|
350
351
|
- reusable object catalogs in `config/*.yaml`
|
|
351
352
|
- agent assembly in `config/agents/*.yaml`
|
|
352
353
|
|
|
354
|
+
### Temporary LangChain v1 Notes
|
|
355
|
+
|
|
356
|
+
At the moment, the most stable path for complex production-style runs is `backend: deepagent`.
|
|
357
|
+
|
|
358
|
+
Current temporary limits on the `backend: langchain-v1` path are:
|
|
359
|
+
|
|
360
|
+
- approval-gated side-effect tools are less reliable than the DeepAgents path under real remote models
|
|
361
|
+
- long multi-agent or orchestration-heavy flows are not the recommended default path
|
|
362
|
+
- the repository now treats DeepAgents as the default execution path for complex runtime coverage, and LangChain v1 should be selected explicitly when a workspace truly wants that behavior
|
|
363
|
+
|
|
364
|
+
Practical guidance:
|
|
365
|
+
|
|
366
|
+
- use `backend: deepagent` for approvals, resume, multi-agent orchestration, rich memory flows, and heavier tool chains
|
|
367
|
+
- keep `backend: langchain-v1` for lighter direct-response or explicitly chosen V1 agent shapes while this upstream behavior settles
|
|
368
|
+
|
|
353
369
|
### `config/workspace.yaml`
|
|
354
370
|
|
|
355
371
|
Use this file for workspace-wide runtime policy.
|
package/README.zh.md
CHANGED
|
@@ -70,6 +70,7 @@
|
|
|
70
70
|
- `docs/feature-checklist.md`
|
|
71
71
|
- `docs/long-term-memory.md`
|
|
72
72
|
- `docs/app-task-pattern.md`
|
|
73
|
+
- `docs/coding-agent-guide.md`
|
|
73
74
|
|
|
74
75
|
## 为何需要它
|
|
75
76
|
|
|
@@ -348,6 +349,21 @@ await stop(runtime);
|
|
|
348
349
|
- `config/*.yaml` 中的可复用对象目录
|
|
349
350
|
- `config/agents/*.yaml` 中的 agent 装配
|
|
350
351
|
|
|
352
|
+
### LangChain v1 的暂时说明
|
|
353
|
+
|
|
354
|
+
当前对于复杂、生产化风格的运行链路，最稳定的路径仍然是 `backend: deepagent`。
|
|
355
|
+
|
|
356
|
+
目前 `backend: langchain-v1` 这条路径的暂时限制是：
|
|
357
|
+
|
|
358
|
+
- 在真实远端模型下，带 approval 的副作用工具调用稳定性弱于 DeepAgents 路径
|
|
359
|
+
- 不建议把它作为长链路、多 agent、重 orchestration 流程的默认执行路径
|
|
360
|
+
- 仓库当前已把 DeepAgents 作为复杂运行时覆盖的默认主路径；只有在工作区明确需要 V1 行为时，才应显式选择 LangChain v1
|
|
361
|
+
|
|
362
|
+
实际建议：
|
|
363
|
+
|
|
364
|
+
- approvals、resume、多 agent orchestration、复杂 memory 流、重工具链，优先使用 `backend: deepagent`
|
|
365
|
+
- `backend: langchain-v1` 先保留给轻量 direct-response 场景，或明确需要 V1 agent 语义的工作区
|
|
366
|
+
|
|
351
367
|
### `config/workspace.yaml`
|
|
352
368
|
|
|
353
369
|
用于工作区范围的运行时策略。
|
|
@@ -1 +1 @@
|
|
|
1
|
-
export declare const AGENT_HARNESS_VERSION = "0.0.
|
|
1
|
+
export declare const AGENT_HARNESS_VERSION = "0.0.67";
|
package/dist/package-version.js
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
export const AGENT_HARNESS_VERSION = "0.0.
|
|
1
|
+
export const AGENT_HARNESS_VERSION = "0.0.67";
|