agentx-python 0.6.36__py3-none-any.whl → 0.6.37__py3-none-any.whl

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.
Files changed (7) hide show
  1. agentx/version.py +1 -1
  2. {agentx_python-0.6.36.dist-info → agentx_python-0.6.37.dist-info}/METADATA +16 -1
  3. {agentx_python-0.6.36.dist-info → agentx_python-0.6.37.dist-info}/RECORD +7 -7
  4. {agentx_python-0.6.36.dist-info → agentx_python-0.6.37.dist-info}/WHEEL +0 -0
  5. {agentx_python-0.6.36.dist-info → agentx_python-0.6.37.dist-info}/entry_points.txt +0 -0
  6. {agentx_python-0.6.36.dist-info → agentx_python-0.6.37.dist-info}/licenses/LICENSE +0 -0
  7. {agentx_python-0.6.36.dist-info → agentx_python-0.6.37.dist-info}/top_level.txt +0 -0
agentx/version.py CHANGED
@@ -1 +1 @@
1
- VERSION = "0.6.36"
1
+ VERSION = "0.6.37"
{agentx_python-0.6.36.dist-info → agentx_python-0.6.37.dist-info}/METADATA RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: agentx-python
3
- Version: 0.6.36
3
+ Version: 0.6.37
4
4
  Summary: Official Python SDK for AgentX (https://www.agentx.so/)
5
5
  Home-page: https://github.com/AgentX-ai/AgentX-python
6
6
  Author: Robin Wang and AgentX Team
@@ -315,6 +315,21 @@ evaluator = client.monitor.online_evaluators.builder(
315
315
  client.monitor.online_evaluators.ratings(evaluator.id, window="7d")
316
316
  ```
317
317
 
318
+ An online evaluator and a dataset run's grading config are two profiles of one **LLM Judge Scorer**, and `client.monitor.judge_scorers` manages both in a single call - one rubric, one id, used offline and online:
319
+
320
+ ```python
321
+ scorer = client.monitor.judge_scorers.builder(
322
+ name="Helpfulness",
323
+ acceptance_criteria="Concrete, correct, cites the policy.",
324
+ live=True, sample_rate=0.1, alert_threshold=5, # the online profile
325
+ ).publish()
326
+
327
+ client.evaluations.run(dataset_id=dataset.id, subject={...}, scorer_id=scorer.id)
328
+ client.monitor.judge_scorers.ratings(scorer.id, window="7d")
329
+ ```
330
+
331
+ The two clients above are that entity's per-profile legacy views; they keep working and share the same ids. See [LLM Judge Scorers](EVALUATIONS.md#llm-judge-scorers---reusable-grading-configs) for the full surface, including which self-host engine builds serve it.
332
+
318
333
  An online evaluator can also judge **whole conversations** instead of single traces: pass `scope="session"` and the engine scores each multi-turn session once it's been idle for `idle_seconds`, re-scoring if the conversation resumes. And to close the loop with reality, two ground-truth streams feed the dashboard's Judge Calibration view (which measures how often AgentX's automated verdicts agree with what actually happened): `client.outcomes.report(...)` for after-the-fact system results (a reopened ticket, a human confirmation), and `client.feedback.report(...)` for end-user votes forwarded from your own app's UI - a "down" raises a "Negative user feedback" signal directly, no sampling or judge call involved. All self-host features.
319
334
 
320
335
  ```python
{agentx_python-0.6.36.dist-info → agentx_python-0.6.37.dist-info}/RECORD RENAMED
@@ -9,7 +9,7 @@ agentx/projects.py,sha256=JN-nhesELPjEb1P0m9F4-Qw-0eGR68kCtBN5zNhArt0,2540
9
9
  agentx/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
10
10
  agentx/traces.py,sha256=sz9gxutlDKNgf0fdCkyzKsGwK5eMAJuIEl3NIwGrsuo,2287
11
11
  agentx/util.py,sha256=lt2Kpg4Fj8whrSuAhLEahcPEIYRVpK9RCC5y9ShdTJs,703
12
- agentx/version.py,sha256=Vjh1dxR-kRQ3D_9qSk_EH1XFCc8RMkJ2gALg30ZZ0ns,19
12
+ agentx/version.py,sha256=g7pGZt_oul7X_1L_DT3FK5c0cxCir3JI2dVVgi_HWZA,19
13
13
  agentx/evaluations/__init__.py,sha256=Erv7RGFlRxGTG4rVb2uHhCqLLEX_iAWKqkZKzK6CumE,262
14
14
  agentx/evaluations/_term.py,sha256=WFpiNzdgDBeJJ-Gg-6X7TwwxllobuE4OqFUTuDQvS3Y,2529
15
15
  agentx/evaluations/client.py,sha256=Vo3pvD37f6Z8VgUm3DR0FzSmnO3qYcokGHmiTc8RzwU,27273
@@ -59,9 +59,9 @@ agentx/tracing/__init__.py,sha256=l2mIRILE-wWrCD0fekgrIOQUEvtDObzdrkgpQUtXroU,40
59
59
  agentx/tracing/ci_types.py,sha256=zFVcZGvc1qbVDdOlEPQ1i5R6terqJHxCzFF4ZjouxxI,1423
60
60
  agentx/tracing/ingest_client.py,sha256=5X6RyxtMq1XYgOzsMd3b2f2qpmYpsMnhKm7NB3oup00,17664
61
61
  agentx/tracing/tracer.py,sha256=6qLTrV4Fz_ONitlBMKiayRbeoV1dpkTwskTDP5oVt4I,51567
62
- agentx_python-0.6.36.dist-info/licenses/LICENSE,sha256=gZVsM-nLsE8vlaY6NXXsVoo6IlCClxkToAWmhgT3y_s,10762
63
- agentx_python-0.6.36.dist-info/METADATA,sha256=lqDEHXO2-wFeK4cx6hGiU1hI-cE_4t92idDVwvza8q8,20133
64
- agentx_python-0.6.36.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
65
- agentx_python-0.6.36.dist-info/entry_points.txt,sha256=rQqF1JTY3T1yfviBU1r8PU-5mBdfOk6P4bZ1L4BskIM,172
66
- agentx_python-0.6.36.dist-info/top_level.txt,sha256=s-q-HB9Gb_QdrZNacSeQyF_c25gQooMy7DlxzgLOHPk,7
67
- agentx_python-0.6.36.dist-info/RECORD,,
62
+ agentx_python-0.6.37.dist-info/licenses/LICENSE,sha256=gZVsM-nLsE8vlaY6NXXsVoo6IlCClxkToAWmhgT3y_s,10762
63
+ agentx_python-0.6.37.dist-info/METADATA,sha256=drZ9keYVnP0hr-vZY_xvBMDH3WEWG0XStturtpIR-EA,20993
64
+ agentx_python-0.6.37.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
65
+ agentx_python-0.6.37.dist-info/entry_points.txt,sha256=rQqF1JTY3T1yfviBU1r8PU-5mBdfOk6P4bZ1L4BskIM,172
66
+ agentx_python-0.6.37.dist-info/top_level.txt,sha256=s-q-HB9Gb_QdrZNacSeQyF_c25gQooMy7DlxzgLOHPk,7
67
+ agentx_python-0.6.37.dist-info/RECORD,,