Skip to content

Add pass fail metrics #432

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
bayger merged 2 commits into from
Jun 18, 2026
Merged

Add pass fail metrics #432

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c50788e
Add score and full pass stats to test run pass/fail tab
bayger Jun 18, 2026
99ff18d
Add pass rate column to test runs list view using backend testStatistics
bayger Jun 18, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
78 changes: 78 additions & 0 deletions src/api/generated/Api.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13604,6 +13604,19 @@ export class Api<
* @min 0
*/
errorCount: number;
/** Detailed test statistics for this run */
testStatistics: {
/**
* Total number of individual test assertions that passed across all conversations
* @min 0
*/
passedTests: number;
/**
* Total number of individual test assertions that failed across all conversations
* @min 0
*/
failedTests: number;
} | null;
/** Additional metadata */
metadata: Record<string, any>;
/** Version number for optimistic locking */
Expand Down Expand Up @@ -13697,6 +13710,19 @@ export class Api<
* @min 0
*/
errorCount: number;
/** Detailed test statistics for this run */
testStatistics: {
/**
* Total number of individual test assertions that passed across all conversations
* @min 0
*/
passedTests: number;
/**
* Total number of individual test assertions that failed across all conversations
* @min 0
*/
failedTests: number;
} | null;
/** Additional metadata */
metadata: Record<string, any>;
/** Version number for optimistic locking */
Expand Down Expand Up @@ -13775,6 +13801,19 @@ export class Api<
* @min 0
*/
errorCount: number;
/** Detailed test statistics for this run */
testStatistics: {
/**
* Total number of individual test assertions that passed across all conversations
* @min 0
*/
passedTests: number;
/**
* Total number of individual test assertions that failed across all conversations
* @min 0
*/
failedTests: number;
} | null;
/** Additional metadata */
metadata: Record<string, any>;
/** Version number for optimistic locking */
Expand Down Expand Up @@ -13853,6 +13892,19 @@ export class Api<
* @min 0
*/
errorCount: number;
/** Detailed test statistics for this run */
testStatistics: {
/**
* Total number of individual test assertions that passed across all conversations
* @min 0
*/
passedTests: number;
/**
* Total number of individual test assertions that failed across all conversations
* @min 0
*/
failedTests: number;
} | null;
/** Additional metadata */
metadata: Record<string, any>;
/** Version number for optimistic locking */
Expand Down Expand Up @@ -14013,6 +14065,19 @@ export class Api<
dataExtractionResults: Record<string, any>;
/** Post-processed data transformation results */
dataTransformationResults: Record<string, any>;
/** Detailed test statistics for this conversation */
testStatistics: {
/**
* Number of individual test assertions that passed
* @min 0
*/
passedTests: number;
/**
* Number of individual test assertions that failed
* @min 0
*/
failedTests: number;
} | null;
/** Additional metadata */
metadata: Record<string, any>;
/** Version number for optimistic locking */
Expand Down Expand Up @@ -14104,6 +14169,19 @@ export class Api<
dataExtractionResults: Record<string, any>;
/** Post-processed data transformation results */
dataTransformationResults: Record<string, any>;
/** Detailed test statistics for this conversation */
testStatistics: {
/**
* Number of individual test assertions that passed
* @min 0
*/
passedTests: number;
/**
* Number of individual test assertions that failed
* @min 0
*/
failedTests: number;
} | null;
/** Additional metadata */
metadata: Record<string, any>;
/** Version number for optimistic locking */
Expand Down
52 changes: 52 additions & 0 deletions src/api/generated/data-contracts.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9028,6 +9028,19 @@ export interface ScenarioRunResponse {
* @min 0
*/
errorCount: number;
/** Detailed test statistics for this run */
testStatistics: {
/**
* Total number of individual test assertions that passed across all conversations
* @min 0
*/
passedTests: number;
/**
* Total number of individual test assertions that failed across all conversations
* @min 0
*/
failedTests: number;
} | null;
/** Additional metadata */
metadata: Record<string, any>;
/** Version number for optimistic locking */
Expand Down Expand Up @@ -9066,6 +9079,19 @@ export interface ScenarioRunListResponse {
* @min 0
*/
errorCount: number;
/** Detailed test statistics for this run */
testStatistics: {
/**
* Total number of individual test assertions that passed across all conversations
* @min 0
*/
passedTests: number;
/**
* Total number of individual test assertions that failed across all conversations
* @min 0
*/
failedTests: number;
} | null;
/** Additional metadata */
metadata: Record<string, any>;
/** Version number for optimistic locking */
Expand Down Expand Up @@ -9134,6 +9160,19 @@ export interface ScenarioConversationResponse {
dataExtractionResults: Record<string, any>;
/** Post-processed data transformation results */
dataTransformationResults: Record<string, any>;
/** Detailed test statistics for this conversation */
testStatistics: {
/**
* Number of individual test assertions that passed
* @min 0
*/
passedTests: number;
/**
* Number of individual test assertions that failed
* @min 0
*/
failedTests: number;
} | null;
/** Additional metadata */
metadata: Record<string, any>;
/** Version number for optimistic locking */
Expand Down Expand Up @@ -9185,6 +9224,19 @@ export interface ScenarioConversationListResponse {
dataExtractionResults: Record<string, any>;
/** Post-processed data transformation results */
dataTransformationResults: Record<string, any>;
/** Detailed test statistics for this conversation */
testStatistics: {
/**
* Number of individual test assertions that passed
* @min 0
*/
passedTests: number;
/**
* Number of individual test assertions that failed
* @min 0
*/
failedTests: number;
} | null;
/** Additional metadata */
metadata: Record<string, any>;
/** Version number for optimistic locking */
Expand Down
Loading
Loading