fix(eval): prevent RangeError on large eval table payloads #7716
There are no files selected for viewing
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
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -1270,6 +1270,7 @@ function ResultsTable({ | |
| evaluationId={evalId || undefined} | ||
| testCaseId={info.row.original.test?.metadata?.testCaseId || output.id} | ||
| isRedteam={isRedteam} | ||
| testVars={info.row.original.test?.vars} | ||
| /> | ||
| </ErrorBoundary> | ||
| ) : ( | ||
|
|
||
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -51,6 +51,27 @@ export async function fetchUserId(): Promise<string | null> { | |
| } | ||
| } | ||
|
|
||
| export interface CellDetailResponse { | ||
|
Contributor
There was a problem hiding this comment. DRY with |
||
| prompt: string; | ||
| response?: Record<string, unknown>; | ||
| testCase?: Record<string, unknown>; | ||
| } | ||
|
|
||
| export async function fetchCellDetail( | ||
|
Contributor
There was a problem hiding this comment. Document this function |
||
| evalId: string, | ||
| resultId: string, | ||
| ): Promise<CellDetailResponse | null> { | ||
| try { | ||
| const response = await callApi(`/eval/${evalId}/results/${resultId}/detail`); | ||
| if (!response.ok) { | ||
| return null; | ||
| } | ||
| return response.json(); | ||
| } catch { | ||
| return null; | ||
| } | ||
| } | ||
|
|
||
| export async function updateEvalAuthor( | ||
| evalId: string, | ||
| author: string, | ||
|
|
||
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -119,20 +119,31 @@ export function exportCommand(program: Command) { | |
|
|
||
| logger.info(`Eval with ID ${evalId} has been successfully exported to ${cmdObj.output}.`); | ||
| } else { | ||
| try { | ||
| const summary = await result.toEvaluateSummary(); | ||
| const metadata = createOutputMetadata(result); | ||
| const jsonData = JSON.stringify( | ||
| { | ||
| evalId: result.id, | ||
| results: summary, | ||
| config: result.config, | ||
| shareableUrl: null, | ||
| metadata, | ||
| }, | ||
| null, | ||
| 2, | ||
| ); | ||
| logger.info(jsonData); | ||
| } catch (error) { | ||
| if (error instanceof RangeError) { | ||
| logger.error( | ||
| `Eval too large to output to console. Use -o to export to a file instead:\n\n promptfoo export eval ${evalId} -o output.jsonl\n`, | ||
| ); | ||
| process.exitCode = 1; | ||
| return; | ||
| } | ||
| throw error; | ||
| } | ||
| } | ||
|
|
||
| telemetry.record('command_used', { | ||
|
|
||
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -9,6 +9,7 @@ import Eval, { EvalQueries } from '../../models/eval'; | |
| import EvalResult from '../../models/evalResult'; | ||
| import { EvalSchemas, EvalTableQuerySchema } from '../../types/api/eval'; | ||
| import { deleteEval, deleteEvals, updateResult, writeResultsToDatabase } from '../../util/database'; | ||
| import { trimTableCellForApi } from '../../util/exportToFile'; | ||
| import invariant from '../../util/invariant'; | ||
| import { setDownloadHeaders } from '../utils/downloadHelpers'; | ||
| import { | ||
|
|
@@ -324,20 +325,53 @@ evalRouter.get('/:id/table', async (req: Request, res: Response): Promise<void> | |
| } | ||
| } | ||
|
|
||
| // Trim cell data for the API response to prevent massive payloads. | ||
|
Contributor
There was a problem hiding this comment. "massive" is less useful than a precise definition |
||
| // Each cell's prompt (rendered template with base64 images) is stripped — the frontend | ||
| // fetches it on demand via GET /:evalId/results/:resultId/detail. | ||
| // Export/download formats return full data (they return early above). | ||
| for (const row of returnTable.body) { | ||
| row.outputs = row.outputs.map((output) => (output ? trimTableCellForApi(output) : output)); | ||
|
Contributor
There was a problem hiding this comment. How's the performance on this? |
||
| } | ||
|
|
||
| // Strip config.tests — unused by the frontend from this endpoint and potentially large. | ||
| const { tests: _tests, ...configWithoutTests } = eval_.config; | ||
|
|
||
| // Default response for table view | ||
| res.json({ | ||
| table: returnTable, | ||
| totalCount: table.totalCount, | ||
| filteredCount: table.filteredCount, | ||
| filteredMetrics, | ||
| config: configWithoutTests, | ||
| author: eval_.author || null, | ||
| version: eval_.version(), | ||
| id, | ||
| stats: eval_.getStats(), | ||
| } as EvalTableDTO); | ||
| }); | ||
|
|
||
| // Returns the full prompt, response, and testCase for a single result cell. | ||
| // The table endpoint strips these fields to keep payloads small; the frontend | ||
| // fetches them on demand when the user clicks "Show Prompt". | ||
| evalRouter.get( | ||
| '/:evalId/results/:resultId/detail', | ||
| async (req: Request, res: Response): Promise<void> => { | ||
| const { evalId, resultId } = EvalSchemas.ResultDetail.Params.parse(req.params); | ||
|
|
||
| const result = await EvalResult.findById(resultId); | ||
| if (!result || result.evalId !== evalId) { | ||
| res.status(404).json({ error: 'Result not found' }); | ||
| return; | ||
| } | ||
|
|
||
| res.json({ | ||
| prompt: result.prompt.raw, | ||
| response: result.response, | ||
| testCase: result.testCase, | ||
| }); | ||
| }, | ||
|
Comment on lines
+353
to
+372
Contributor
There was a problem hiding this comment. Wrap the result-detail handler with try/catch and {success,data/error} responses. Uncaught Zod parse or DB errors will bubble, and the response shape doesn’t match the API contract. 🛠 Suggested fixevalRouter.get(
'/:evalId/results/:resultId/detail',
async (req: Request, res: Response): Promise<void> => {
- const { evalId, resultId } = EvalSchemas.ResultDetail.Params.parse(req.params);
-
- const result = await EvalResult.findById(resultId);
- if (!result || result.evalId !== evalId) {
- res.status(404).json({ error: 'Result not found' });
- return;
- }
-
- res.json({
- prompt: result.prompt.raw,
- response: result.response,
- testCase: result.testCase,
- });
+ try {
+ const { evalId, resultId } = EvalSchemas.ResultDetail.Params.parse(req.params);
+ const result = await EvalResult.findById(resultId);
+ if (!result || result.evalId !== evalId) {
+ res.status(404).json({ success: false, error: 'Result not found' });
+ return;
+ }
+
+ res.json({
+ success: true,
+ data: {
+ prompt: result.prompt.raw,
+ response: result.response,
+ testCase: result.testCase,
+ },
+ });
+ } catch (error) {
+ if (error instanceof z.ZodError) {
+ res.status(400).json({ success: false, error: z.prettifyError(error) });
+ return;
+ }
+ logger.error('[GET /:evalId/results/:resultId/detail] Failed to fetch result detail', {
+ error,
+ evalId: req.params.evalId,
+ resultId: req.params.resultId,
+ });
+ res.status(500).json({ success: false, error: 'Failed to fetch result detail' });
+ }
},
);As per coding guidelines, "src/server/routes/**/*.{ts,tsx}: Validate requests with Zod schemas from src/types/api/, wrap all responses in { success, data/error } format, handle errors with try-catch blocks in async route handlers." 🤖 Prompt for AI Agents |
||
| ); | ||
|
|
||
| evalRouter.get('/:id/metadata-keys', async (req: Request, res: Response): Promise<void> => { | ||
| try { | ||
| const { id } = EvalSchemas.MetadataKeys.Params.parse(req.params); | ||
|
|
||
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -98,6 +98,15 @@ export const EvalTableQuerySchema = z.object({ | |
|
|
||
| export type EvalTableQuery = z.infer<typeof EvalTableQuerySchema>; | ||
|
|
||
| // GET /api/eval/:evalId/results/:resultId/detail | ||
|
|
||
| export const ResultDetailParamsSchema = z.object({ | ||
| evalId: z.string().min(1), | ||
| resultId: z.string().min(1), | ||
| }); | ||
|
|
||
| export type ResultDetailParams = z.infer<typeof ResultDetailParamsSchema>; | ||
|
|
||
| /** Grouped schemas for server-side validation. */ | ||
| export const EvalSchemas = { | ||
| UpdateAuthor: { | ||
|
|
@@ -123,4 +132,7 @@ export const EvalSchemas = { | |
| Table: { | ||
| Query: EvalTableQuerySchema, | ||
| }, | ||
| ResultDetail: { | ||
| Params: ResultDetailParamsSchema, | ||
| }, | ||
| } as const; | ||
Oops, something went wrong.
Oops, something went wrong.
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Seems like
output's type should be fixed upstream