The loop your agent can't see

说明与用途

模型无法检测自身循环导致上下文腐烂，导致设计反复迭代。解决方案采用无状态进程、磁盘状态、受限读取、结构化评审结果和确定性循环上限来消除此问题。

问题

AI development orchestrators can get stuck in a design loop due to context rot, where each model turn inherits errors from previous turns, causing endless revisions and wasted spend.

结果

The new architecture prevented context rot, eliminated the endless design loop, and reduced wasted model spend. Across 22 production runs, no repeated failures or build failures were observed, and the system reliably moved from design to code.

工作流

• 1. Start a new design turn with a fresh model invocation and empty context.
• 2. Load state from a workspace directory (design doc, decisions log, artifact stack).
• 3. Prompt the model with a bounded read‑set: only approved files, targeted symbols, and the previous turn’s verdict file.
• 4. Reviewer writes findings as a structured, schema‑checked file.
• 5. Orchestrator merges findings into a verdict file via plain Python, no model call.
• 6. Next turn reads only the verdict file and relevant design slices.
• 7. Apply deterministic loop caps: halt after three consecutive non‑terminal verdicts or a hard cap on design turns, routing to a human if needed.

证据

The loop cap we'd written never fired.

来源

We replaced the exempted counter with two that nothing can bypass.

来源

Across 22 runs and 38 code turns: Same set of change‑owned test failures, turn N and turn N−1 – 0 occurrences.

来源