@arizeai/phoenix-client 6.11.0 → 6.11.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/esm/__generated__/api/v1.d.ts +52 -0
- package/dist/esm/__generated__/api/v1.d.ts.map +1 -1
- package/dist/esm/testing/phoenix-test-tracking.d.ts +2 -2
- package/dist/esm/testing/phoenix-test-tracking.js +4 -4
- package/dist/esm/testing/phoenix-test-tracking.js.map +1 -1
- package/dist/esm/testing/runner.js +1 -1
- package/dist/esm/testing/runner.js.map +1 -1
- package/dist/esm/testing/types.d.ts +1 -1
- package/dist/esm/tsconfig.esm.tsbuildinfo +1 -1
- package/dist/esm/utils/formatPromptMessages.d.ts.map +1 -1
- package/dist/esm/utils/getPromptBySelector.d.ts.map +1 -1
- package/dist/src/__generated__/api/v1.d.ts +52 -0
- package/dist/src/__generated__/api/v1.d.ts.map +1 -1
- package/dist/src/testing/phoenix-test-tracking.d.ts +2 -2
- package/dist/src/testing/phoenix-test-tracking.js +4 -4
- package/dist/src/testing/phoenix-test-tracking.js.map +1 -1
- package/dist/src/testing/runner.js +1 -1
- package/dist/src/testing/runner.js.map +1 -1
- package/dist/src/testing/types.d.ts +1 -1
- package/dist/src/utils/formatPromptMessages.d.ts.map +1 -1
- package/dist/src/utils/getPromptBySelector.d.ts.map +1 -1
- package/dist/tsconfig.tsbuildinfo +1 -1
- package/docs/ci-evals-vitest.mdx +1 -1
- package/docs/ci-evals.mdx +2 -2
- package/package.json +1 -1
- package/src/__generated__/api/v1.ts +52 -0
- package/src/testing/phoenix-test-tracking.ts +4 -4
- package/src/testing/runner.ts +1 -1
- package/src/testing/types.ts +1 -1
package/docs/ci-evals-vitest.mdx
CHANGED
|
@@ -90,7 +90,7 @@ px.describe("my suite", () => { ... }, {
|
|
|
90
90
|
| `client` | `PhoenixClient` | Pre-configured `@arizeai/phoenix-client` instance. |
|
|
91
91
|
| `repetitions` | `number` | Run each test in the suite this many times (default `1`; `PHOENIX_TEST_REPETITIONS` overrides the default). Per-test `repetitions` wins. |
|
|
92
92
|
| `acceptanceCriteria` | `AcceptanceCriterion[]` | Aggregate annotation thresholds that fail the suite after all tests run. |
|
|
93
|
-
| `dryRun` | `boolean` | Run the whole suite locally — no dataset, experiment, runs, or annotations are created in Phoenix. Same effect as `
|
|
93
|
+
| `dryRun` | `boolean` | Run the whole suite locally — no dataset, experiment, runs, or annotations are created in Phoenix. Same effect as `PHOENIX_TEST_TRACKING=false`, scoped to this suite. |
|
|
94
94
|
|
|
95
95
|
### `test(name, params, fn, timeout?)`
|
|
96
96
|
|
package/docs/ci-evals.mdx
CHANGED
|
@@ -97,7 +97,7 @@ standard Phoenix env vars.
|
|
|
97
97
|
| `PHOENIX_HOST` | Phoenix base URL |
|
|
98
98
|
| `PHOENIX_API_KEY` | Bearer token for Phoenix |
|
|
99
99
|
| `PHOENIX_CLIENT_HEADERS` | Optional JSON headers forwarded to the Phoenix client and tracer |
|
|
100
|
-
| `
|
|
100
|
+
| `PHOENIX_TEST_TRACKING=false` | Disable sync to Phoenix for the current run (tracing is on by default) |
|
|
101
101
|
| `PHOENIX_TEST_REPETITIONS` | Default number of times to run each test |
|
|
102
102
|
| `PHOENIX_TEST_REPORTER=verbose` | Show every test row plus per-test `output:` detail (default is the compact view) |
|
|
103
103
|
| `PHOENIX_TEST_REPORTER_MAX_ROWS` | Max test rows shown per suite in compact mode (default `10`; failures are never hidden) |
|
|
@@ -123,7 +123,7 @@ Dry-run executes test bodies (and tracing, when a tracer is attached) but
|
|
|
123
123
|
creates no dataset, experiment, run, or annotations in Phoenix. The
|
|
124
124
|
reporter still prints a local summary.
|
|
125
125
|
|
|
126
|
-
- **Whole process** — `
|
|
126
|
+
- **Whole process** — `PHOENIX_TEST_TRACKING=false`.
|
|
127
127
|
- **One suite** — `describe(name, fn, { dryRun: true })`.
|
|
128
128
|
- **One test** — `test(name, { input, dryRun: true }, fn)`; that case runs
|
|
129
129
|
as an ordinary local test, with no dataset example and nothing uploaded,
|
package/package.json
CHANGED
|
@@ -1298,6 +1298,23 @@ export interface paths {
|
|
|
1298
1298
|
patch?: never;
|
|
1299
1299
|
trace?: never;
|
|
1300
1300
|
};
|
|
1301
|
+
"/agents/server/sessions/{session_id}/chat": {
|
|
1302
|
+
parameters: {
|
|
1303
|
+
query?: never;
|
|
1304
|
+
header?: never;
|
|
1305
|
+
path?: never;
|
|
1306
|
+
cookie?: never;
|
|
1307
|
+
};
|
|
1308
|
+
get?: never;
|
|
1309
|
+
put?: never;
|
|
1310
|
+
/** Run Server Agent */
|
|
1311
|
+
post: operations["run_server_agent_agents_server_sessions__session_id__chat_post"];
|
|
1312
|
+
delete?: never;
|
|
1313
|
+
options?: never;
|
|
1314
|
+
head?: never;
|
|
1315
|
+
patch?: never;
|
|
1316
|
+
trace?: never;
|
|
1317
|
+
};
|
|
1301
1318
|
"/agents/{agent_id}/sessions/{session_id}/chat": {
|
|
1302
1319
|
parameters: {
|
|
1303
1320
|
query?: never;
|
|
@@ -9288,6 +9305,41 @@ export interface operations {
|
|
|
9288
9305
|
};
|
|
9289
9306
|
};
|
|
9290
9307
|
};
|
|
9308
|
+
run_server_agent_agents_server_sessions__session_id__chat_post: {
|
|
9309
|
+
parameters: {
|
|
9310
|
+
query?: never;
|
|
9311
|
+
header?: never;
|
|
9312
|
+
path: {
|
|
9313
|
+
session_id: string;
|
|
9314
|
+
};
|
|
9315
|
+
cookie?: never;
|
|
9316
|
+
};
|
|
9317
|
+
requestBody: {
|
|
9318
|
+
content: {
|
|
9319
|
+
"application/json": components["schemas"]["ChatRequest"];
|
|
9320
|
+
};
|
|
9321
|
+
};
|
|
9322
|
+
responses: {
|
|
9323
|
+
/** @description Successful Response */
|
|
9324
|
+
200: {
|
|
9325
|
+
headers: {
|
|
9326
|
+
[name: string]: unknown;
|
|
9327
|
+
};
|
|
9328
|
+
content: {
|
|
9329
|
+
"application/json": unknown;
|
|
9330
|
+
};
|
|
9331
|
+
};
|
|
9332
|
+
/** @description Validation Error */
|
|
9333
|
+
422: {
|
|
9334
|
+
headers: {
|
|
9335
|
+
[name: string]: unknown;
|
|
9336
|
+
};
|
|
9337
|
+
content: {
|
|
9338
|
+
"application/json": components["schemas"]["HTTPValidationError"];
|
|
9339
|
+
};
|
|
9340
|
+
};
|
|
9341
|
+
};
|
|
9342
|
+
};
|
|
9291
9343
|
chat_agents__agent_id__sessions__session_id__chat_post: {
|
|
9292
9344
|
parameters: {
|
|
9293
9345
|
query?: never;
|
|
@@ -37,14 +37,14 @@ function isFalsyFlag(value: string | undefined): boolean {
|
|
|
37
37
|
* Decide whether tests should sync to Phoenix.
|
|
38
38
|
*
|
|
39
39
|
* Tracing is enabled by default. It can be disabled globally by setting
|
|
40
|
-
* `
|
|
40
|
+
* `PHOENIX_TEST_TRACKING=false`, or per suite via `SuiteConfig.dryRun`.
|
|
41
41
|
*/
|
|
42
42
|
export function isTrackingEnabled(suite?: SuiteState): {
|
|
43
43
|
enabled: boolean;
|
|
44
44
|
reason?: string;
|
|
45
45
|
} {
|
|
46
|
-
if (isFalsyFlag(process.env.
|
|
47
|
-
return { enabled: false, reason: "
|
|
46
|
+
if (isFalsyFlag(process.env.PHOENIX_TEST_TRACKING)) {
|
|
47
|
+
return { enabled: false, reason: "PHOENIX_TEST_TRACKING is disabled" };
|
|
48
48
|
}
|
|
49
49
|
if (suite?.config.dryRun) {
|
|
50
50
|
return { enabled: false, reason: "suite configured dryRun" };
|
|
@@ -177,7 +177,7 @@ function buildLinks(
|
|
|
177
177
|
* Initialize the suite: upload the dataset, create the experiment, and
|
|
178
178
|
* register the OpenInference tracer.
|
|
179
179
|
*
|
|
180
|
-
* If tracing is disabled (no Phoenix env vars, or
|
|
180
|
+
* If tracing is disabled (no Phoenix env vars, or PHOENIX_TEST_TRACKING=false),
|
|
181
181
|
* this populates a no-op tracer and exits without making any network calls.
|
|
182
182
|
*/
|
|
183
183
|
export async function initializeSuite(suite: SuiteState): Promise<void> {
|
package/src/testing/runner.ts
CHANGED
|
@@ -148,7 +148,7 @@ export function declareTest<Input extends KVMap, Expected extends KVMap>(
|
|
|
148
148
|
|
|
149
149
|
// A per-test `dryRun` opts the case out of Phoenix entirely: no dataset
|
|
150
150
|
// example, no experiment run, no annotations — it runs as an ordinary
|
|
151
|
-
// local test. Suite-level dryRun (or
|
|
151
|
+
// local test. Suite-level dryRun (or PHOENIX_TEST_TRACKING=false) is
|
|
152
152
|
// handled in `initializeSuite`, which never uploads anything anyway.
|
|
153
153
|
const isDryRun = !!params.dryRun;
|
|
154
154
|
|
package/src/testing/types.ts
CHANGED
|
@@ -241,7 +241,7 @@ export interface SuiteConfig {
|
|
|
241
241
|
/**
|
|
242
242
|
* When `true`, the whole suite runs as ordinary local tests — no dataset
|
|
243
243
|
* is uploaded and no experiment, runs, or annotations are created in
|
|
244
|
-
* Phoenix. Equivalent to `
|
|
244
|
+
* Phoenix. Equivalent to `PHOENIX_TEST_TRACKING=false` scoped to this
|
|
245
245
|
* suite. The reporter still prints a local summary.
|
|
246
246
|
*/
|
|
247
247
|
dryRun?: boolean;
|