michael/coding-agent-gitea
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: update AGENTS.md with respond tool and ModelRetry patterns

Browse Source
This commit is contained in:
Michael
2026-08-02 17:01:43 +02:00
parent 43fe0a284d
commit 4f7059788d
1 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
AGENTS.md
+3 -2
View File
@@ -43,14 +43,15 @@
- **Composable**: Write small, modular agents and tools with clear interfaces and dependency injection (`RunContext`). - **Composable**: Write small, modular agents and tools with clear interfaces and dependency injection (`RunContext`).
- **Unix-like**: Each agent or tool has a single responsibility and does one thing well. - **Unix-like**: Each agent or tool has a single responsibility and does one thing well.
- **Predictable**: Use structured outputs (`result_type` with Pydantic models) to eliminate ambiguous text responses. - **Predictable**: Require agents to submit final outputs via dedicated `reply` / `respond` tools accepting structured Pydantic models. Raise `ModelRetry` when inputs or tool usage fall short of the expected shape.
- **Idiomatic**: Follow modern Python type hints (`list[str]`, `dict[str, Any]`), standard Pydantic v2 schemas, and Pydantic AI idioms. - **Idiomatic**: Follow modern Python type hints (`list[str]`, `dict[str, Any]`), standard Pydantic v2 schemas, and Pydantic AI idioms.
- **Domain-based**: Structure code and data around domain concepts (`NotificationDecision`, `CoordinatorDecision`, `ExecutionPlan`) rather than LLM framework mechanics. - **Domain-based**: Structure code and data around domain concepts (`NotificationDecision`, `CoordinatorDecision`, `ExecutionPlan`) rather than LLM framework mechanics.
## Pydantic AI Integration Guidelines ## Pydantic AI Integration Guidelines
- Use `pydantic_ai.Agent` as the primary execution engine for all AI agents. - Use `pydantic_ai.Agent` as the primary execution engine for all AI agents.
- Define structured result schemas using Pydantic `BaseModel` for predictable output handling. - Require agents to provide structured decisions by calling a dedicated `respond` tool that takes the response Pydantic model as an argument.
- Use `ModelRetry` (from `pydantic_ai`) inside tools or validators to force the LLM to retry when it returns raw strings or incorrect parameter shapes.
- Pass runtime dependencies into tools using `pydantic_ai.RunContext` and typed dependency containers. - Pass runtime dependencies into tools using `pydantic_ai.RunContext` and typed dependency containers.
- Register tools using `@agent.tool` or modular toolsets for clean separation of concerns. - Register tools using `@agent.tool` or modular toolsets for clean separation of concerns.