@aiwayds/dsh-model-sync

Usage

Configure the plugin under the dsh-model-sync settings entry — on dsh 0.1.7+ the entry id (the same stable id the bundle patch always mounted) is the settings namespace; edit it in the settings UI or your profile patch. Every key is optional, and every key is a volatile field, so edits apply without restarting the plugin. Upgrading from a pre-0.1.7 install: a legacy top-level model-sync: section in the old settings.yaml is imported once into the new entry automatically at the next plugin boot (the audit record lands in ~/.dsh/storages/dsh-model-sync/legacy-import.json):

Key	Default	Description
writeMode	'settings'	Zero-patch pipeline; 'overlay' (deprecated since dsh 0.2.1) for the legacy patched-adapter mode
intervalMinutes	240 (4h)	Auto-refresh interval in minutes; 0 = startup-only
startupDelaySeconds	5	Delay before the first auto refresh, so the llm adapter is ready
refreshTimeoutMs	120000	Abort budget for one refresh round's network request (min 1000)
managedRoutes	[]	Routes to sync; empty = the default pi.dev routes
keepBuiltinOnly	true	Keep built-in-only models not present on pi.dev (smooth migration)
dropUnserviceable	true	Drop unserviceable entries; false aborts the route instead
syncNotify	false	Notify on changes (logger + /model-sync report)
forceMaxReasoningEffort	false	Force max reasoning effort on models with a non-empty thinkingFormat
providerNativeFetch	true	Union each mapped provider's first-party /models listing into the pi.dev result (additions only)
keepDeprecatedBuiltin	false	Opt back into emitting builtin ids the official default model list dropped (dsh 0.1.7 removed deepseek-v4-flash / deepseek-v4-flash-vision-exp; dsh 0.2.0 removed omen-alpha on opencode-go and glm-4.7 / glm-5-turbo / glm-5.1 / glm-5.2 / glm-5.2-highspeed / glm-5v-turbo on zai-coding-cn; the snapshot keeps the data but no longer syncs them by default)

Example (settings section dsh-model-sync; a legacy settings.yaml model-sync: section is not auto-imported by the dsh 0.1.7 host itself — the plugin recovers it once at boot, see above):

dsh-model-sync:
  writeMode: settings
  intervalMinutes: 30
  managedRoutes:
    - opencode-go
    - zai-coding-cn

The plugin writes to the llm-pi-ai namespace (providers..models) — the same document the adapter consumes — and only for the routes it manages. During migration, keepBuiltinOnly preserves models that exist in your installed built-in catalog but aren't on pi.dev yet.

Capacity values are upper limits, not your runtime settings

Synced contextWindow / maxTokens describe what the model accepts at most, as advertised by the gateway listing — not what your deployment is configured for. dsh resolves the settings-written value over the installed catalog, and a written maxTokens becomes the request-level default. Pointing a route at a local or proxied endpoint that serves a smaller context (vLLM / Ollama and friends) while carrying catalog-sized capacities is a known recipe for the "output token limit reached" family of failures.

If you need a model to run under a smaller budget, set it in modelOverrides under the same route — the sync folds the fields into the synced list and re-applies them from its store every round:

providers:
  zai-coding-cn:
    modelOverrides:
      glm-5.3:
        contextWindow: 32768

Note that listing data itself can be noisy: values are sanity-gated (positive integers; maxTokens strictly below contextWindow), and stripped values show up in the sync report as DEGRADED lines with reasons.

Manual refresh: the /model-sync command

Type /model-sync in any interactive UI to force one sync round on the spot. The plugin registers the command in the shared command registry (@deepseek-ai/dsh-commands), and UIs discover it automatically. It returns the same report the scheduled rounds log. The sync scope is decided by managedRoutes; any arguments typed after the command are ignored. Hosts without a command registry degrade gracefully — the scheduled rounds and the modelSync service keep working.