feat(core): port v2 runtime fixes onto dev
Cherry-picks the packages/core changes from the v2 branch onto dev: - combined ordered stdout/stderr in AppProcess + bash structured output - edit/apply-patch return FileDiff info with status and line stats - ignore no-op model switches; record reasoning timestamps - return unexpected local tool defects to the model and continue - keep OAuth account metadata out of request bodies - nest OpenAI reasoning effort/summary options - load OpenCode provider config asynchronously; batch plugin boot - export latest public event manifest Includes the supporting schema reasoning time field and regenerated client/SDK types.
This commit is contained in:
parent
fab8ec4f54
commit
93159bccbf
28 changed files with 385 additions and 130 deletions
|
|
@ -400,7 +400,13 @@ export const layer = Layer.effect(
|
|||
})
|
||||
}),
|
||||
switchModel: Effect.fn("V2Session.switchModel")(function* (input) {
|
||||
yield* result.get(input.sessionID)
|
||||
const session = yield* result.get(input.sessionID)
|
||||
if (
|
||||
session.model?.providerID === input.model.providerID &&
|
||||
session.model.id === input.model.id &&
|
||||
(session.model.variant ?? "default") === (input.model.variant ?? "default")
|
||||
)
|
||||
return
|
||||
yield* events.publish(SessionEvent.ModelSwitched, {
|
||||
sessionID: input.sessionID,
|
||||
messageID: SessionMessage.ID.create(),
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue