Remove AI config approval flow
This commit is contained in:
@@ -24,7 +24,7 @@ Plugin pages build execution requests with `createBridgeExecutionRequest` and ha
|
||||
|
||||
Execution responses use `requestId`, plugin/page/server scope, action, status, optional result refs, and optional safe errors. Use `parseBridgeExecutionResponse` before reading results so plugin code handles denied, deferred, and failed states uniformly.
|
||||
|
||||
AI requests use `createAIInvocationRequest` with an explicit manifest-declared purpose, prompt, and scoped context refs. Use `parseAIInvocationResponse` to consume recommendations, reviewable `diffId` metadata, and safe errors. Plugin code must not choose or receive provider API keys, provider base URLs, bearer tokens, or direct transport details. Config writes require a separate Platform operator approval.
|
||||
AI requests use `createAIInvocationRequest` with an explicit manifest-declared purpose, prompt, and scoped context refs. Use `parseAIInvocationResponse` to consume recommendations, optional `configExecution` job metadata, and safe errors. For config purposes Platform validates the current config and dispatches the bounded `config.write` job immediately; plugin code must not choose or receive provider API keys, provider base URLs, bearer tokens, or direct transport details.
|
||||
|
||||
Artifact open requests use `createArtifactOpenRequest` with an artifact ID that belongs to the current server/job scope. Use `parseArtifactReference` to consume the bridge result. Parsed references contain platform-owned download URLs, filename, content type, size, checksum, expiry, range support, and chunk size; they do not contain bytes or raw storage adapter locations.
|
||||
|
||||
|
||||
Reference in New Issue
Block a user