Skip to content
All tags

#error-handling

2 posts
ai deep-dive 跟成熟 coding agent 學設計

Learning Design from Mature Coding Agents (6): The ModelProvider Abstraction — Why Wrapping an SDK Is Not Enough

Wrapping an SDK directly buys you three walls within months: usage fields that don't agree, error semantics tied to SDK exception types, and tool-call formats that change per provider. All five reference projects separate 'wire protocol' from 'provider identity' as independent dimensions. Rivumi goes further with pydantic canonical contracts (Message/ToolCall/Usage/ModelTurn) plus six protocol adapters, forces the OpenAI SDK's built-in retries to zero, and routes every failure through a classified ProviderErrorKind before any retry policy sees it. Its provider table is deliberately copied from pi's packages/ai — lineage, not coincidence.

#coding-agent#harness-engineering#llm-api#provider-abstraction#error-handling#llm-agents
ai deep-dive 跟成熟 coding agent 學設計

Learning Design from Mature Coding Agents (7): Provider Retry Policy — From One 5xx to Bounded Retry and Fallback

Intermittent NVIDIA NIM 500s exposed Rivumi's early gap: classified errors with no retry consumer. SDK retries are now disabled; the harness gives each candidate up to five attempts with jittered exponential backoff and capped Retry-After handling, then can move to an explicitly configured fallback model. Both model.retry and model.fallback enter the event log.

#coding-agent#harness-engineering#llm-api#retry#error-handling#llm-agents