This is an automated email from the ASF dual-hosted git repository.

davsclaus pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/camel-performance-tests.git


    from 0570fd9  README: point at the ai-benchmark harness
     new 8c2ddea  ai-benchmark: the tool allow-list names the shared authoring 
tools only (CAMEL-24712 removes the older per-kind ones)
     new eae5b3e  The stepwise ladder: the round-2 harness that scores one 
example step by step
     new 1b947aa  Round 2 of the one-shot suite: k runs, pass@k and pass^k, a 
held-out set and services
     new 39312f2  The ladder gives the model 20 tool calls per step, not 12
     new a9de890  The sql rung runs on Postgres with camel infra, as the 
example ships it

The 5 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails.  The revisions
listed as "add" were already present in the repository and have only
been added to this reference.


Summary of changes:
 ai-benchmark/.gitignore                            |   7 +
 ai-benchmark/README.md                             |  24 +-
 ai-benchmark/agent_local.py                        | 253 ++++++-
 ai-benchmark/agent_mcp_stepwise.py                 | 348 ++++++++-
 ai-benchmark/examples-intermediate.json            |  61 ++
 ai-benchmark/examples-ladder-10.json               | 235 ++++++
 ai-benchmark/examples-ladder-dry.json              | 109 +++
 ai-benchmark/examples-ladder.json                  | 508 +++++++++++++
 ai-benchmark/gen_ladder.py                         | 132 ++++
 ai-benchmark/gen_local.py                          |   7 +-
 ai-benchmark/gen_stepwise.py                       | 825 +++++++++++++++++++++
 ai-benchmark/passk.py                              |  38 +
 ai-benchmark/run-stepwise-ladder.sh                |  35 +
 ai-benchmark/run-suite.sh                          |  43 +-
 ai-benchmark/run_one.sh                            |   8 +-
 .../_peer-openapi-server/application.properties    |   1 +
 .../_peer-openapi-server/openapi-server.camel.yaml | 162 ++++
 .../seed/_peer-openapi-server/stock-api.json       | 201 +++++
 ai-benchmark/seed/_peer-openapi-server/stock.json  |   5 +
 .../samples/invoice-2001.json                      |   1 +
 .../samples/invoice-2002.json                      |   1 +
 .../samples/invoice-2003.json                      |   1 +
 .../samples/invoice-2004.json                      |   1 +
 .../connect-file-processing/samples/note-2005.txt  |   1 +
 .../connect-http-client/orders/order-1001.json     |   2 +
 .../connect-http-client/orders/order-1002.json     |   2 +
 .../connect-http-client/orders/order-1003.json     |   2 +
 ai-benchmark/seed/connect-http-client/stock.json   |   5 +
 .../connect-service-sql/orders/order-1001.json     |   2 +
 .../connect-service-sql/orders/order-1002.json     |   2 +
 .../connect-service-sql/orders/order-1003.json     |   2 +
 ai-benchmark/seed/connect-stock-api/stock.json     |   5 +
 .../orders/order-1001.json                         |   2 +
 .../orders/order-1002.json                         |   2 +
 .../orders/order-1003.json                         |   2 +
 .../seed/contracts-openapi-client/stock-api.json   | 201 +++++
 .../seed/contracts-openapi-server/stock-api.json   | 201 +++++
 .../seed/contracts-openapi-server/stock.json       |   5 +
 .../orders/order-1001.json                         |   2 +
 .../orders/order-1002.json                         |   2 +
 .../orders/order-1003.json                         |   2 +
 .../seed/openapi-client/examples/1001.json         |  18 +
 ai-benchmark/seed/openapi-client/petstore-api.json | 299 ++++++++
 .../.camel-jbang/camel-jbang-run.properties        |  40 +
 .../seed/openapi-server-ref/application.properties |  18 +
 .../openapi-server-ref/openapi-server.camel.yaml   | 162 ++++
 .../seed/openapi-server-ref/stock-api.json         | 201 +++++
 ai-benchmark/seed/openapi-server-ref/stock.json    |   5 +
 .../seed/openapi-server/examples/pet/1000.json     |  18 +
 ai-benchmark/seed/openapi-server/petstore-api.json | 299 ++++++++
 .../seed/route-aggregator/orders/order-1001.json   |   2 +
 .../seed/route-aggregator/orders/order-1002.json   |   2 +
 .../seed/route-aggregator/orders/order-1003.json   |   2 +
 .../orders/order-1001.json                         |   2 +
 .../orders/order-1002.json                         |   2 +
 .../orders/order-1003.json                         |   2 +
 .../orders/order-1001.json                         |   2 +
 .../orders/order-1002.json                         |   2 +
 .../orders/order-1003.json                         |   2 +
 .../seed/route-order-lines/orders/order-1001.json  |   2 +
 .../seed/route-order-lines/orders/order-1002.json  |   2 +
 .../seed/route-order-lines/orders/order-1003.json  |   2 +
 .../seed/transform-csv-to-json/inbox/invoices.csv  |   4 +
 .../seed/transform-data-mapping/order.json         |   3 +
 .../transform-data-mapping/shipment-mapping.groovy |  12 +
 .../seed/transform-groovy/order-bad-email.json     |   2 +
 ai-benchmark/seed/transform-groovy/order.json      |   2 +
 .../seed/transform-json-transform/order.json       |   3 +
 .../transform-xml-to-json/inbox/supplier-order.xml |   7 +
 .../seed/transform-xslt/inbox/supplier-order.xml   |   7 +
 ai-benchmark/seed/transform-xslt/packing-slip.xsl  |  15 +
 ai-benchmark/steps.json                            |   7 +-
 ai-benchmark/summarize_stepwise.py                 |  25 +
 73 files changed, 4544 insertions(+), 75 deletions(-)
 create mode 100644 ai-benchmark/examples-intermediate.json
 create mode 100644 ai-benchmark/examples-ladder-10.json
 create mode 100644 ai-benchmark/examples-ladder-dry.json
 create mode 100644 ai-benchmark/examples-ladder.json
 create mode 100755 ai-benchmark/gen_ladder.py
 create mode 100644 ai-benchmark/gen_stepwise.py
 create mode 100755 ai-benchmark/passk.py
 create mode 100755 ai-benchmark/run-stepwise-ladder.sh
 create mode 100644 
ai-benchmark/seed/_peer-openapi-server/application.properties
 create mode 100644 
ai-benchmark/seed/_peer-openapi-server/openapi-server.camel.yaml
 create mode 100644 ai-benchmark/seed/_peer-openapi-server/stock-api.json
 create mode 100644 ai-benchmark/seed/_peer-openapi-server/stock.json
 create mode 100644 
ai-benchmark/seed/connect-file-processing/samples/invoice-2001.json
 create mode 100644 
ai-benchmark/seed/connect-file-processing/samples/invoice-2002.json
 create mode 100644 
ai-benchmark/seed/connect-file-processing/samples/invoice-2003.json
 create mode 100644 
ai-benchmark/seed/connect-file-processing/samples/invoice-2004.json
 create mode 100644 
ai-benchmark/seed/connect-file-processing/samples/note-2005.txt
 create mode 100644 ai-benchmark/seed/connect-http-client/orders/order-1001.json
 create mode 100644 ai-benchmark/seed/connect-http-client/orders/order-1002.json
 create mode 100644 ai-benchmark/seed/connect-http-client/orders/order-1003.json
 create mode 100644 ai-benchmark/seed/connect-http-client/stock.json
 create mode 100644 ai-benchmark/seed/connect-service-sql/orders/order-1001.json
 create mode 100644 ai-benchmark/seed/connect-service-sql/orders/order-1002.json
 create mode 100644 ai-benchmark/seed/connect-service-sql/orders/order-1003.json
 create mode 100644 ai-benchmark/seed/connect-stock-api/stock.json
 create mode 100644 
ai-benchmark/seed/contracts-openapi-client/orders/order-1001.json
 create mode 100644 
ai-benchmark/seed/contracts-openapi-client/orders/order-1002.json
 create mode 100644 
ai-benchmark/seed/contracts-openapi-client/orders/order-1003.json
 create mode 100644 ai-benchmark/seed/contracts-openapi-client/stock-api.json
 create mode 100644 ai-benchmark/seed/contracts-openapi-server/stock-api.json
 create mode 100644 ai-benchmark/seed/contracts-openapi-server/stock.json
 create mode 100644 
ai-benchmark/seed/fail-well-error-handling/orders/order-1001.json
 create mode 100644 
ai-benchmark/seed/fail-well-error-handling/orders/order-1002.json
 create mode 100644 
ai-benchmark/seed/fail-well-error-handling/orders/order-1003.json
 create mode 100644 ai-benchmark/seed/openapi-client/examples/1001.json
 create mode 100644 ai-benchmark/seed/openapi-client/petstore-api.json
 create mode 100644 
ai-benchmark/seed/openapi-server-ref/.camel-jbang/camel-jbang-run.properties
 create mode 100644 ai-benchmark/seed/openapi-server-ref/application.properties
 create mode 100644 
ai-benchmark/seed/openapi-server-ref/openapi-server.camel.yaml
 create mode 100644 ai-benchmark/seed/openapi-server-ref/stock-api.json
 create mode 100644 ai-benchmark/seed/openapi-server-ref/stock.json
 create mode 100644 ai-benchmark/seed/openapi-server/examples/pet/1000.json
 create mode 100644 ai-benchmark/seed/openapi-server/petstore-api.json
 create mode 100644 ai-benchmark/seed/route-aggregator/orders/order-1001.json
 create mode 100644 ai-benchmark/seed/route-aggregator/orders/order-1002.json
 create mode 100644 ai-benchmark/seed/route-aggregator/orders/order-1003.json
 create mode 100644 
ai-benchmark/seed/route-content-based-router/orders/order-1001.json
 create mode 100644 
ai-benchmark/seed/route-content-based-router/orders/order-1002.json
 create mode 100644 
ai-benchmark/seed/route-content-based-router/orders/order-1003.json
 create mode 100644 
ai-benchmark/seed/route-filter-and-multicast/orders/order-1001.json
 create mode 100644 
ai-benchmark/seed/route-filter-and-multicast/orders/order-1002.json
 create mode 100644 
ai-benchmark/seed/route-filter-and-multicast/orders/order-1003.json
 create mode 100644 ai-benchmark/seed/route-order-lines/orders/order-1001.json
 create mode 100644 ai-benchmark/seed/route-order-lines/orders/order-1002.json
 create mode 100644 ai-benchmark/seed/route-order-lines/orders/order-1003.json
 create mode 100644 ai-benchmark/seed/transform-csv-to-json/inbox/invoices.csv
 create mode 100644 ai-benchmark/seed/transform-data-mapping/order.json
 create mode 100644 
ai-benchmark/seed/transform-data-mapping/shipment-mapping.groovy
 create mode 100644 ai-benchmark/seed/transform-groovy/order-bad-email.json
 create mode 100644 ai-benchmark/seed/transform-groovy/order.json
 create mode 100644 ai-benchmark/seed/transform-json-transform/order.json
 create mode 100644 
ai-benchmark/seed/transform-xml-to-json/inbox/supplier-order.xml
 create mode 100644 ai-benchmark/seed/transform-xslt/inbox/supplier-order.xml
 create mode 100644 ai-benchmark/seed/transform-xslt/packing-slip.xsl
 create mode 100644 ai-benchmark/summarize_stepwise.py

Reply via email to