TWTang Weigangindoramagic.hashnode.dev·1d ago · 1 min readFastMCP: tool discovery is not authorizationFastMCP makes it easy to expose Python functions as MCP tools, resources, and prompts. The production risk is not discovery itself; it is what a discovered capability is allowed to trigger. I validate00
TWTang Weigangindoramagic.hashnode.dev·3d ago · 3 min readBefore an AI agent touches a repo, give it a verifiable context packI published one Doramagic internal tool as a public repository: https://github.com/tangweigang-jpg/doramagic-ai-context-pack-benchmark The project is not trying to make an AI read more code. It is try00
TWTang Weigangindoramagic.hashnode.dev·3d ago · 7 min readBefore Adopting OpenAI Agents SDK, Write the Runtime Contract FirstOpenAI Agents SDK is easy to misread as a faster way to build "more agents." That is the shallow interpretation. The more useful reason to evaluate it is that it puts agents, tools, handoffs, guardrai00
TWTang Weigangindoramagic.hashnode.dev·6d ago · 4 min readBefore Adopting DSPy, Prove the LM Program ContractDSPy is easy to undersell. If you describe it as "a nicer way to write prompts", you will probably test the wrong thing. The better first test is this: can your language-model workflow be expressed as00
TWTang Weigangindoramagic.hashnode.dev·6d ago · 8 min readBefore Adopting LlamaIndex, Split Ingestion, Retrieval, Agents, and AuditLlamaIndex should not be judged by whether a five-line RAG demo returns a fluent answer. That only proves that one happy path can run. It does not prove that your data remains traceable, that retrieva00
