DESIGN.md@examples/optimization/eval_optimize_loopA
DESIGN.md@examples/optimization/eval_optimize_loop from trpc-group/trpc-agent-python is a DESIGN.md file: the design rules coding agents follow in that repo.
mdr add trpc-group/trpc-agent-python/examples/optimization/eval_optimize_loop/DESIGN.md@git:20260805.9e82694Pins git:20260805.9e82694 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- DESIGN.md file
- Repository
- trpc-group/trpc-agent-python
- Path
examples/optimization/eval_optimize_loop/DESIGN.md- Versions recorded
- 1
- Latest version
- git:20260805.9e82694, committed Aug 5, 2026
- Size
- 1,126 bytes
- Repository stars
- 147
- License
- a license file GitHub does not identify
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 设计边界 本示例把运行环境与替代组件分开描述。`offline`、`real`、`trace` 是三种 Pipeline 运行模式。`offline` 仍使用 SDK 的 `LlmAgent`、Runner 和独立 Session，只把 Agent 内部模型替换成 `DeterministicFakeModel`，并用确定性 Candidate Provider 代替真实优化器。它用于验证 Prompt 改变是否经过真实 Agent 编排影响输出。 `real` 使用真实业务模型生成回复，并由 `AgentOptimizer` 调用真实反思模型产生 Prompt 候选；只有 Gate 接受、源 Prompt 哈希未漂移且显式启用写回时，才允许更新源文件。 `trace` 直接评测预录制的 `actual_conversation`，不再次运行 Agent、Model 或 Candidate Provider。它适合复现工具轨迹和生产故障，但只能证明候选版本与轨迹的关联，不能证明 Prompt 导致了该轨迹。因此 Trace 即使获得 ACCEPT，也固定跳过源 Prompt 写回。 确定性 metric 负责精确匹配等硬规则。LLM Judge 若需要，应作为带 rubric 的评测指标显式配置；本示例不提供容易混淆职责的 `use_fake_judge` 开关。
Read the whole file at its exact version.
How to install
mdr add trpc-group/trpc-agent-python/examples/optimization/eval_optimize_loop/DESIGN.md@sha256:f61af41890a928f7The line at the top of this page pins the label git:20260805.9e82694, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_es4s56xs3j2bcexj)
9 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Aug 5, 2026.
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (1126 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
trpc-group/trpc-agent-python · 147 stars · license a license file GitHub does not identify · pushed 2026-11-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_es4s56xs3j2bcexj GET https://markdownregistry.com/api/v1/resolve?ref=trpc-group/trpc-agent-python/examples/optimization/eval_optimize_loop/DESIGN.md GET https://markdownregistry.com/api/v1/blob/f61af41890a928f7a11905d4a84d58008570c57ce538674bf95e2ed46880c220
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: what DESIGN.md is and how agents use it · which agent file does what.