gitea_admin/agent-builder
Archived
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Use sandbox client for builder validation
All checks were successful
build / build (push) Successful in 14s
Details

Browse Source
This commit is contained in:
robert
2026-06-06 20:24:38 -03:00
parent 5d03074fa4
commit 137f84be6a
11 changed files with 92 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
agent_builder/skills/deepagent-agent-design/SKILL.md
View File

@@ -1,6 +1,6 @@
---
name: deepagent-agent-design
description: Design generated A2A agents around DeepAgents skills, subagents, durable workspace backends, and ctx.llm-backed reasoning. Use whenever building or modifying an agent, deciding whether to add tools, creating skill bundles, wiring create_deep_agent, or avoiding shallow fake tools.
description: Design generated A2A agents around DeepAgents skills, subagents, durable workspace backends, and ctx.llm-backed reasoning. Use whenever building or modifying an agent, deciding whether to add tools, creating skill bundles, wiring create_a2a_deep_agent, or avoiding shallow fake tools.
---
# DeepAgent Agent Design
@@ -13,8 +13,8 @@ planning, file work, skill selection, and subagent delegation.
Use this shape for non-trivial generated agents:
1. Keep one or two public A2A `@skill` methods with clear typed parameters.
2. Inside each method, read `ctx.llm`, verify credentials are available before
constructing `ChatOpenAI`, and build a DeepAgent with `create_deep_agent`.
2. Inside each method, read `ctx.llm`, verify credentials are available, and
build a DeepAgent with `create_a2a_deep_agent`.
3. Pass `backend=ctx.workspace_backend()` so DeepAgents file tools write to the
caller's durable workspace instead of LangGraph state.
4. Seed project skills into the current grant's write prefix and pass
@@ -44,7 +44,7 @@ linked from `SKILL.md`.
Project `skills/` files are source files in the agent image. DeepAgents loads
skills from its backend, so seed those files into the invocation workspace
before `create_deep_agent`:
before `create_a2a_deep_agent`:
```python
from pathlib import Path
@@ -84,8 +84,9 @@ Then:
```python
backend = ctx.workspace_backend()
skill_sources = _seed_runtime_skills(backend, ctx)
return create_deep_agent(
model=model,
return create_a2a_deep_agent(
ctx,
creds=creds,
backend=backend,
skills=skill_sources or None,
tools=[small_deterministic_tool],