Files

T

Stéphane Tailland 67d7bffd1c Add implementation instructions

Design agreed in discussion, nothing built yet. Records the agent's role, its
scopes and MCP servers, its A2A surface, and the framework choice with its
reason — so the next session starts from the decisions rather than re-deriving
them.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

2026-08-26 15:14:41 +02:00

2.1 KiB

Raw Blame History

Catalogue — product management agent

Framework: PydanticAI + FastA2A · Mode: conversational · Client id: classic-models-agent-catalogue

Serves the product manager: create and update products and product lines, set prices, decide what to discontinue.

Scopes and MCP servers


MCP	catalog (`mcp-catalog-audience`), sales (`mcp-sales-audience`)
Scopes	`catalog:read`, `catalog:write`, `sales:read`

sales:read is there to answer "does this product actually sell?" before a pricing or discontinuation decision. Read only — this agent never touches orders.

A2A

Calls — Approvisionnement.check_availability, to know remaining stock and open orders before discontinuing a reference.

Exposes — nothing yet. Add skills only when another agent needs them.

Why PydanticAI here

Not arbitrary. This is the agent that writes structured data under constraints — prices, quantities, references, product line membership. Typed validation of the model's output earns its place here in a way it would not on a purely conversational agent.

FastA2A, not to_a2a()

Use FastA2A directly. Agent.to_a2a() still works in PydanticAI 1.x but emits a deprecation warning and is removed in v2.

FastA2A is framework-agnostic, so whatever is built here is also the natural basis for the A2A adapter in front of the n8n agents — see classic-models-agent-flows.

Before writing code

Read classic-models-agent-platform/CLAUDE.md first. It holds the identity model, the MCP and LLM endpoints, the token-exchange recipe and the known blockers. This file only covers what is specific to this agent.

Non-negotiables

Inference goes through the Kong AI gateway, https://llm-dev.sttlab.local/llm/v1/chat/completions. Calling a provider directly bypasses the rate limits and prompt guards.
One MCP client per conversation turn, built with freshly exchanged tokens. Do not hold a long-lived MCP connection with a fixed token.
A2A calls return answers, not data. Expose narrow decision-shaped skills, never a generic query.
Deliverables in English.

2.1 KiB Raw Blame History