openclaw

Microsoft ｜ Agent 與工作流 ｜ 原文 ｜ MIT

SkillOpt-Sleep 的 OpenClaw 參考改編，只能拿來研究或移植

---
name: skillopt-sleep
description: SkillOpt-Sleep 的 OpenClaw 改編版，僅供參考。拿來研究或移植別人貢獻的 DeepSeek wrapper，不是能直接執行的安裝版本。
---

# SkillOpt-Sleep OpenClaw 參考改編版

這個目錄是別人貢獻的**參考範例**，不是受支援、可直接插上就用的 OpenClaw 整合。它示範一種做法：把共用的 `skillopt_sleep` 週期，接到自訂的 DeepSeek Chat Completions backend，以及一組跟特定環境綁定的任務 fixture。

不要原封不動地執行或排程這些檔案。有幾個 script 和範例設定保留了貢獻者原本那台機器上的假設，而且 wrapper 有部分還沒移植到目前共用引擎的介面。先看這個目錄的 [README.md](README.md)，它才是權威的狀態說明和改編指南。

## 包含的內容

- `skillopt_sleep_openclaw.py`：貢獻者寫的 DeepSeek backend 原型。裡面還有一個 Ollama embedding helper，但那個 helper 沒有接到目前共用的 sleep 週期。
- `run_sleep.py`：自訂的週期 wrapper，含有跟環境綁定的路徑，以及一個 backend 註冊的 shim。
- `slash_sleep.py`：實驗性的指令 helper，是針對舊版 staging manifest 的格式寫的。
- `run_sleep_cron.sh`：跟特定機器綁定的分類執行器，不是可攜的 cron 安裝程式。
- `config.json`：範例設定，不是有保證或強制執行的 runtime 限制。
- `tests/*.json`：來自某一個環境的範例任務 fixture，不是通用的 OpenClaw benchmark。

## 已知的移植缺口

在把它當成整合之前，維護者至少要：

1. 把每一個絕對路徑（workspace、repository、state、skill、log、任務）都換成明確的使用者設定。
2. 更新自訂 backend 的 factory，符合目前 `get_backend` 的呼叫契約（包含專案目錄），並把 backend 的方法和 edit record 更新成目前的協定。
3. 把實驗性的採用邏輯，換成目前的 staging manifest 和 `skillopt_sleep.staging.adopt` 的行為。目前的 staging 產物是 `proposed_SKILL.md` / `proposed_CLAUDE.md`、`manifest.json` 和報告檔；它們不再提供舊的 `manifest.proposed_skill` 欄位。
4. 決定怎麼把真實的 OpenClaw transcript 轉成受支援的 session 格式。把 `claude_home` 指向任意的 agent 目錄，並不會讓裡面的檔案自動變成 Claude Code 相容的 JSONL。
5. 圍繞改編過的 wrapper 建立排程。共用的 scheduler 啟動的是共用的 CLI；它不會自動保留這個自訂 backend 或它的分類任務檔流程。
6. 加上獨立的端對端測試，涵蓋 dry-run、接受/拒絕的關卡、staging、採用與備份、憑證失敗，以及排程執行。

在這些缺口解決之前，要測試 SkillOpt-Sleep 本身，請使用受支援的共用 `python -m skillopt_sleep` CLI 搭配 `--backend mock`，並且只把這個目錄當成未來 OpenClaw 移植的原始素材。

## 共用引擎的功能不等於 wrapper 的功能

在這個版本，受支援的共用 CLI backend 有 `mock`、`claude`、`codex`、`copilot`、`handoff` 和 `azure_openai`；[plugin 整合參考](../README.md#supported-cli-surface)是權威的清單。共用引擎可以整合選定的 skill 和專案的 `CLAUDE.md` 記憶（由 `evolve_skill` 和 `evolve_memory` 控制），它的 `schedule` / `unschedule` 動作會管理共用引擎的 cron 項目。這些能力**不會**讓自訂的 OpenClaw wrapper 變得可攜：共用的 scheduler 不會去呼叫這個原型 backend 或它的分類 fixture。這些功能請看共用文件，不要看這份參考用的 SKILL.md。

## 資料與憑證的界線

原型的 DeepSeek backend 會把任務、skill、記憶、回應、rubric 和反思的內容，送到它所設定的 Chat Completions endpoint。它的原始碼裡還有一個 helper，如果未來的移植版把那個 helper 接進週期，就可以把文字送到 Ollama 服務。這兩條路徑，都不應該假設已經去除了所有的 secret 或私人細節。

在任何移植版用真實資料測試之前：

- 使用獨立的、合成的，或經過明確審查的任務檔；
- 替換範例裡的商家名稱、個人參照、URL 和機器路徑；
- 透過操作者的 secret 管理機制載入憑證；
- 對每個遠端 endpoint 驗證 TLS 和資料保留政策；
- 採用之前，檢查所有 staging 的產物。

附帶的 fixture 只是範例。它們的分數和任何舊的成本估算，都不能證明在其他 OpenClaw 部署上的成效、安全性，或穩定的每晚價格。

## 更多資訊

- [OpenClaw README](README.md)：目前的參考狀態和改編檢查清單
- [plugin 整合參考](../README.md)：受支援的共用引擎 CLI 範圍與資料界線
- [SkillOpt-Sleep 文件](../../docs/sleep/README.md)：概念、結果與限制

想把這份參考變成可攜整合的貢獻，應該加上測試，並同步更新這三份文件。

---
name: skillopt-sleep
description: Reference-only OpenClaw adaptation of SkillOpt-Sleep. Use it to study or port the contributed DeepSeek wrapper, not as a ready-to-run installation.
---

# SkillOpt-Sleep OpenClaw reference adaptation

This directory is a contributed **reference**, not a supported, plug-and-play
OpenClaw integration. It illustrates one way to connect the shared
`skillopt_sleep` cycle to a custom DeepSeek Chat Completions backend and a set of
environment-specific task fixtures.

Do not run or schedule the files unchanged. Several scripts and the sample
configuration preserve assumptions from the contributor's original machine,
and parts of the wrapper have not yet been ported to the current shared-engine
interfaces. Start with the directory's [README.md](README.md), which is the
authoritative status and adaptation guide.

## What is included

- `skillopt_sleep_openclaw.py` — a contributed DeepSeek backend prototype. It
  also contains an Ollama embedding helper, but that helper is not wired into
  the current shared sleep cycle.
- `run_sleep.py` — a custom cycle wrapper with environment-specific paths and a
  backend-registration shim.
- `slash_sleep.py` — an experimental command helper written for an older
  staging-manifest shape.
- `run_sleep_cron.sh` — a machine-specific category runner, not a portable cron
  installer.
- `config.json` — a sample configuration, not a set of guaranteed or enforced
  runtime limits.
- `tests/*.json` — example task fixtures from one environment, not a universal
  OpenClaw benchmark.

## Known porting gaps

Before treating this as an integration, a maintainer must at least:

1. Replace every absolute workspace, repository, state, skill, log, and task
   path with explicit user configuration.
2. Update the custom backend factory to the current `get_backend` call contract,
   including the project directory, and update its backend methods and edit
   records to the current protocol.
3. Replace the experimental adoption logic with the current staging manifest
   and `skillopt_sleep.staging.adopt` behavior. Current staging artifacts use
   `proposed_SKILL.md` / `proposed_CLAUDE.md`, `manifest.json`, and report files;
   they do not expose the old `manifest.proposed_skill` field.
4. Decide how real OpenClaw transcripts are converted into a supported session
   format. Pointing `claude_home` at an arbitrary agent directory does not by
   itself make its files Claude Code-compatible JSONL.
5. Build scheduling around the adapted wrapper. The shared scheduler launches
   the shared CLI; it does not automatically preserve this custom backend or
   its category task-file flow.
6. Add isolated end-to-end tests for dry-run, accepted/rejected gates, staging,
   adoption and backup, credential failure, and scheduled execution.

Until those gaps are resolved, use the supported shared
`python -m skillopt_sleep` CLI with `--backend mock` to test SkillOpt-Sleep itself,
and treat this directory only as source material for a future OpenClaw port.

## Shared-engine features are not wrapper features

At this revision the supported shared CLI backends are `mock`, `claude`,
`codex`, `copilot`, `handoff`, and `azure_openai`; the
[plugin integration reference](../README.md#supported-cli-surface) is the
authoritative list. The shared engine can consolidate a selected skill and
project `CLAUDE.md` memory (controlled by `evolve_skill` and `evolve_memory`),
and its `schedule` / `unschedule` actions manage shared-engine cron entries.
Those capabilities do **not** make the custom OpenClaw wrapper portable: the
shared scheduler will not invoke the prototype backend or its category
fixtures. Use the shared documentation for those features, not this reference
SKILL.

## Data and credential boundary

The prototype DeepSeek backend sends task, skill, memory, response, rubric, and
reflection content to its configured Chat Completions endpoint. Its source also
contains a helper that can send text to an Ollama service if a future port wires
that helper into the cycle. Neither path should be assumed to remove every
secret or private detail.

Before any port is tested with real data:

- use isolated, synthetic or explicitly reviewed task files;
- replace sample business names, personal references, URLs, and machine paths;
- load credentials through the operator's secret-management mechanism;
- verify TLS and retention policy for every remote endpoint; and
- inspect all staged artifacts before adoption.

The bundled fixtures are examples only. Their scores and any old cost estimates
do not establish effectiveness, safety, or a stable nightly price for another
OpenClaw deployment.

## Further information

- [OpenClaw README](README.md) — current reference status and adaptation checklist
- [plugin integration reference](../README.md) — supported shared-engine CLI
  surface and data boundary
- [SkillOpt-Sleep documentation](../../docs/sleep/README.md) — concepts,
  results, and limitations

Contributions that turn this reference into a portable integration should add
tests and update all three documents together.