dsh-cwl
CWL — DeepSeek Harness 的上下文窗口生命周期管理：结构化上下文驱逐（arXiv:2606.11213）。当上下文压力超过预算时，分级、确定性地清除探索/操作回合，无需 LLM；不会产生摘要损失，不会幻觉，且永不清除用户消息。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add dsh-cwl@0.2.1Cwl 以 dsh-cwl 发布，当前版本为 0.2.1。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
点击下方 Badge 复制 Markdown，粘贴到 README 即可。
验证 package.json 声明的 GitHub 仓库，即可管理这个公开页面。认领后，Hub 会优先安排当前版本的安全扫描，并在通过后公开展示结果。
认领这个 Plugin →CWL — Context Window Lifecycle for DeepSeek Harness: structured context eviction for long-horizon agents.
Paradigm: Beyond Compaction: Structured Context Eviction for Long-Horizon Agents (arXiv:2606.11213, Kiz8)
English | 简体中文
Compaction (the standard response to context pressure) summarizes history with an LLM. Four structural problems (per the CWL paper):
CWL treats the transcript as a structured record of work and evicts deterministically:
the agent's trajectory is inferred into a typed episode graph (exploration expl / action act,
with dependency edges), and when context pressure exceeds budget, a zero-LLM, deterministic policy
strips content in graduated levels — exploration episodes first (pure context, safest), then action
episodes whose effects are already persisted. User messages are never evicted.
expl for pure read/search — including read-only
bash like grep/cat — act for anything with side effects: edit/write/write-style bash).
Each user message closes the current episode (a turn boundary), and episodes are capped at
a batch limit, so even a single-request long autonomous run (dozens of tool calls) splits
into bounded, evictable segments instead of collapsing into one giant episode. An act
that touches files an earlier expl read gets a dependency edge.assistant/message usage events — tokenMeter.measure().totalTokens omits
cacheRead, which dominates long sessions).agent/pre-step waterfall (before every LLM call), from
fine to coarse:
expl episodes are rewritten
to a short stub first ([cwl-stub: …]) — structure kept, tokens cut, tool pairing intactexpl episodes first (pure context, one-line
"explored: …" marker), then completed act episodes; executed as positional blocks
in the surface (positions are the invariant that survives replaces — an eviction never
splits a tool-call/result pair into orphans)cwl_recall can restore file paths)dsh plugin --profile <name> add dsh-cwl # from npm
dsh plugin --profile <name> add github:kalifun/dsh-cwl # or from GitHub
Or vendor the directory and add to your composition:
- id: dsh-cwl
name: ./dsh-cwl/index.js
No configuration needed. It stays completely inert while context is under budget (default 80% of the model's context window), and starts evicting only when pressure exceeds budget.
# Optional: override the budget (tokens) — for testing pressure behavior
DSH_CWL_BUDGET=30000 dsh web
Eviction policy (deterministic cache-replay validation: eviction −24% cacheRead, strategy-independent; batch best mean −24.7%, consistent across 7 sessions → defaults below; override via env):
| Env var | Default | Values | Effect |
|---|---|---|---|
DSH_CWL_EVICT_ORDER | tail | tail / oldest | oldest evicts oldest episodes first |
DSH_CWL_EVICT_BATCH | on | 0 / false / off to disable | merge adjacent episodes into one surface replace (fewer cache breaks) |
DSH_CWL_EVICT_TAIL_WINDOW | 0 | N | only evict episodes whose end falls within the last N surface nodes |
DSH_CWL_STRIP | on | 0 to disable | fine-grained level: stub large tool-result content in expl episodes before whole-episode eviction (structure preserved) |
DSH_CWL_STRIP_THRESHOLD | 1500 | chars | minimum result text length to be stubbed |
# back to the conservative config (oldest, per-episode replaces)
DSH_CWL_EVICT_ORDER=oldest DSH_CWL_EVICT_BATCH=0 dsh web
Session analysis (per-round token breakdown + "cacheRead of the round after an eviction"):
node tools/analyze-session.mjs <session.jsonl>
Agent-facing tools:
| Tool | Purpose |
|---|---|
cwl_recall | list file paths touched by evicted episodes, to re-read on demand |
Observability:
| Endpoint | Purpose |
|---|---|
GET /api/cwl/evictions | eviction log (session → episodes evicted) |
POST /api/cwl/force | debug: force one eviction on a session |
node check.js # pure-function unit checks (episode inference, eviction policy, strip, pairing)
Live capability benchmarks (helmsman platform): BENCHMARKS.md — the fixed test plan (scenario A: 12-round long conversation; scenario B: single-request long autonomous task ×3) with per-version data rows, refreshed after every behavioral change.
Offline regression tools (run on your own local sessions — no data leaves your machine):
tools/cache-replay.mjs (deterministic cacheRead), tools/replay-real.mjs --apply (engine
apply-layer with real surface fold + tool-pairing assertion), tools/eval-episodes.mjs.
MIT