@mcowger/opencode-plexus 1.2.5 → 1.2.6
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +3 -3
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -105,7 +105,7 @@ To force a model refresh:
|
|
|
105
105
|
/plexus refresh
|
|
106
106
|
```
|
|
107
107
|
|
|
108
|
-
|
|
108
|
+
Select a Plexus model explicitly for the current session. With no model ID, Pi opens a selector; you can also pass the exact Plexus model ID directly. This explicit choice is not applied automatically when starting a new session:
|
|
109
109
|
|
|
110
110
|
```
|
|
111
111
|
/plexus set-default-model
|
|
@@ -163,7 +163,7 @@ export PLEXUS_API_KEY=your-api-key
|
|
|
163
163
|
|
|
164
164
|
```
|
|
165
165
|
~/.pi/agent/extensions/plexus/
|
|
166
|
-
config.json # base URL and
|
|
166
|
+
config.json # base URL and model preference metadata
|
|
167
167
|
plexus-models-cache.json # last-fetched model list (startup cache)
|
|
168
168
|
plexus-models-response.json # raw API response (diagnostics)
|
|
169
169
|
plexus.log # extension activity log
|
|
@@ -237,7 +237,7 @@ Models with a falsy `id` are skipped. Missing metadata falls back to safe defaul
|
|
|
237
237
|
|
|
238
238
|
## Adapter behavior
|
|
239
239
|
|
|
240
|
-
- **pi** refreshes on session start and through `/plexus refresh
|
|
240
|
+
- **pi** refreshes on session start and through `/plexus refresh`, without changing the model selected for the session. It accepts either root URLs or URLs ending in `/v1` and normalizes them before calling Plexus.
|
|
241
241
|
- **OpenCode** seeds the provider from the on-disk cache (or a placeholder model) once, during config loading — OpenCode's `provider.models` hook never fires for custom providers, so there is no live discovery at startup. Run `/plexus-refresh` to force a live fetch and rewrite the cache; because OpenCode has no way to hot-reload a custom provider's model list mid-session, a restart is required afterward to see the refreshed models in the picker.
|
|
242
242
|
- OpenCode models retain their upstream model ID, SDK dialect, release date, and reasoning metadata so OpenCode can generate its native GPT, Claude, Gemini, and OpenAI-compatible variants and apply its current request transforms. DeepSeek models also preserve `reasoning_content` across tool-call turns.
|
|
243
243
|
- OpenCode uses a 250K-token context window when Plexus supplies no context metadata; its output fallback remains 20% of that window.
|