dsh-openai-server-compaction
OpenAI Responses 适配器和适用于 DeepSeek Harness 的持久化服务端压缩包。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:ylxmf2005/dsh-openai-server-compaction#0ead5e705eda47695cd3900677133b0ca836df49Openai Server Compaction 以 dsh-openai-server-compaction 发布，当前版本为 0.4.0。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。
A native DeepSeek Harness plugin that adds Codex-style server compaction to
OpenAI Responses routes managed by DSH's built-in llm-pi-ai plugin.
It uses an API key. OAuth and the ChatGPT Codex backend are not implemented.
llm-pi-ai remains the single owner of provider connection and model data:
api: openai-responsesThis plugin stores only per-route compaction policy. For each enabled, explicitly configured Responses route it:
POST /v1/responses{ "type": "compaction_trigger" } to a normal
POST /v1/responses request and enables the remote_compaction_v2 featurecompaction item returned by the server, stores that native
replacement history outside session JSONL, and restores it after restartEnabled route requests are intentionally handled by this plugin's Responses adapter rather than passed to pi-ai. That is required to preserve and restore opaque Responses replay state that pi-ai does not understand. Disabled routes, non-Responses routes, and models not listed on an enabled route pass through to their normal adapter unchanged.
There is no silent Chat Completions fallback. Missing credentials, ambiguous legacy configuration, unsupported route facts, malformed Responses streams, missing state, and unsupported content fail explicitly.
dsh plugin --profile web add dsh-openai-server-compaction
For a Git checkout:
dsh plugin --profile web add https://github.com/ylxmf2005/dsh-openai-server-compaction.git
If pnpm reports ERR_PNPM_ADDING_TO_ROOT for a workspace-style profile,
repeat the command with -w immediately after add.
The bundle replaces compaction-basic, but it does not create or enable an
OpenAI route. It stays dormant until a route is configured in both namespaces.
Open DSH Settings -> Models and create or edit an llm-pi-ai provider
route. The route must explicitly use openai-responses and declare every
model that should support server compaction.
Equivalent settings YAML:
llm-pi-ai:
providers:
openai:
displayName: OpenAI Responses
api: openai-responses
baseURL: https://api.openai.com/v1
apiKeyEnv: OPENAI_API_KEY
models:
- id: gpt-5.6
name: GPT-5.6
contextWindow: 1050000
maxTokens: 128000
Store OPENAI_API_KEY through DSH's credentials UI/service or export it in
the environment that starts DSH. The key is never stored in this plugin's
settings.
An enabled route must provide an explicit api: openai-responses, a non-empty
baseURL and apiKeyEnv, at least one model, and a positive
contextWindow on each model (or an explicit provider
defaultContextWindow). The plugin refuses to guess these facts because an
incorrect context capacity would make the compaction threshold dishonest.
Open DSH Settings -> Plugins -> OpenAI Compaction. This native plugin tab
lists routes already configured as openai-responses. Enable the desired
route and choose its trigger threshold.
Equivalent settings YAML:
openai-server-compaction:
routes:
openai:
enabled: true
thresholdRatio: 0.7
The route key, openai in this example, must exactly match the key under
llm-pi-ai.providers.
Compaction policy is restart-applied. Restart DSH after changing this section.
The server compaction request does not send max_output_tokens, matching
Codex. Separately, the plugin creates a portable text checkpoint capped at
4,096 output tokens so a DSH session can still continue on another provider;
this internal cap is not a server-compaction output limit.
stateFile is operational composition configuration, not a user setting. The
bundle defaults it to:
$DSH_HOME/openai-server-compaction/state.json
The old llm-openai-server-compaction namespace mixed connection, model, and
policy data. It is not migrated silently because the destination route name is
ambiguous.
baseURL, apiKeyEnv, and models into
llm-pi-ai.providers.<route>.api: openai-responses to that provider profile.thresholdRatio into openai-server-compaction.routes.<route>, set
enabled: true, and remove the obsolete route-level maxTokens value.llm-openai-server-compaction section.The plugin refuses startup with these instructions while a non-empty legacy section remains.
DSH's compaction contract has no public field for adapter-private opaque
compaction items. The plugin therefore writes encrypted provider state to
stateFile and embeds only a UUID marker in the portable checkpoint.
Keep this file with the DSH session store and treat it as private application data. If it is lost, compatible OpenAI replay fails explicitly, while the portable summary remains usable by another provider. Opaque state is bound to the provider route and model that created it.
npm install
npm test
npm run check
npm run build
npm pack --dry-run
Automated tests use stubbed HTTP responses and never call a paid API. The live smoke test is separate, explicit, and billable:
OPENAI_API_KEY=... OPENAI_MODEL=... npm run smoke:live
docs/marketplace-entry.yml is a draft for awesome-dsh-plugin. Registry
submission still requires its repository-age, commit-count, and GitHub
dsh-plugin topic rules.
MIT