refactor: unify Gemini/Vertex error handling via handleAiSdkError() #11364
+121
−38
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Enrich handleAiSdkError() with optional HandleAiSdkErrorOptions to support telemetry capture and i18n message formatting without adding dependencies to the shared transform layer. Migrate gemini.ts and vertex.ts outer catch blocks (createMessage and completePrompt) from bespoke ApiProviderError + i18n patterns to the shared handleAiSdkError() with onError and formatMessage callbacks. All 23 migrated AI SDK providers now use handleAiSdkError() for their outer error path.
hannesrudolph
requested review from
cte,
daniel-lxs,
jr and
mrubens
as code owners
dosubot
bot
added
the
size:L
Contributor
Clean refactor. All issues resolved.
Mention @roomote in a comment to request specific changes to this pull request or fix all unresolved issues. |
![roomote[bot]](https://avatars.githubusercontent.com/in/1546624?s=60&v=4){kind=small}
Comment on lines
+743
to
+766
| export interface HandleAiSdkErrorOptions { | ||
| /** | ||
| * Called with the extracted error message and the original error before | ||
| * throwing. Use this to report to telemetry or structured logging. | ||
| * | ||
| * @example | ||
| * onError: (msg) => { | ||
| * TelemetryService.instance.captureException( | ||
| * new ApiProviderError(msg, providerName, modelId, "createMessage"), | ||
| * ) | ||
| * } | ||
| */ | ||
| onError?: (message: string, originalError: unknown) => void | ||
|
|
||
| /** | ||
| * Custom message formatter. When provided, the returned string is used | ||
| * as the thrown Error's message instead of the default | ||
| * `${providerName}: ${extractedMessage}` format. | ||
| * | ||
| * @example | ||
| * formatMessage: (msg) => t("common:errors.gemini.generate_stream", { error: msg }) | ||
| */ | ||
| formatMessage?: (message: string) => string | ||
| } |
Contributor
There was a problem hiding this comment.
The existing handleAiSdkError tests (lines 869-911) only cover the two-parameter signature. The new onError and formatMessage options have no test coverage. Worth adding a few cases to verify: (1) onError is called with the extracted message and original error, (2) formatMessage overrides the default ${providerName}: ${message} format, and (3) when neither option is provided, existing behavior is unchanged (already covered, but a combined test with both options would round things out).
Fix it with Roo Code or mention @roomote and request a fix.
Addresses review feedback — adds 4 tests: - onError callback receives extracted message and original error - formatMessage overrides default message format - combined onError + formatMessage with status preservation - default format unchanged when no options provided
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
Standardizes error handling across all migrated AI SDK providers by enriching
handleAiSdkError()with optional telemetry and i18n support, then migrating Gemini and Vertex to use it. These were the last two providers with bespoke outer-catch patterns.Changes
src/api/transform/ai-sdk.ts: AddedHandleAiSdkErrorOptionsinterface withonError(telemetry callback) andformatMessage(i18n formatter) hooks. The third parameter is fully optional — existing callers are unaffected.src/api/providers/gemini.ts: Replaced manualApiProviderError+TelemetryService+t()catch blocks increateMessageandcompletePromptwithhandleAiSdkError(error, providerName, { onError, formatMessage }).src/api/providers/vertex.ts: Same migration as Gemini.All 23 migrated AI SDK providers now use
handleAiSdkError()for their outer error path.Important
Refactor error handling in Gemini and Vertex providers to use
handleAiSdkError()with optional telemetry and i18n support.handleAiSdkError()inai-sdk.tsto include optionalonErrorandformatMessagehooks for telemetry and i18n.createMessageandcompletePromptingemini.tsandvertex.tsto usehandleAiSdkError().handleAiSdkError()inai-sdk.spec.tsto verifyonErrorandformatMessagefunctionality.handleAiSdkError()for error handling.This description was created by
for 265c24c. You can customize this summary. It will automatically update as commits are pushed.