fix(openai): fix responses reasoning token metric tracking support for openai>=1.66.0,<1.66.2
#14072
Conversation
sabrenner
added
the
changelog/no-changelog
|
|
Bootstrap import analysisComparison of import times between this PR and base. SummaryThe average import time from this PR is: 280 ± 3 ms. The average import time from base is: 283 ± 3 ms. The import time difference between this PR and base is: -2.9 ± 0.1 ms. Import time breakdownThe following import paths have grown:
|
…g/dd-trace-py into sabrenner/use-get-attr-token-util
Performance SLOsCandidate: sabrenner/use-get-attr-token-util (bec5b80) 🔵 No Baseline Data (24 suites)🔵 coreapiscenario - 12/12 (2 unstable)🔵 No baseline data available for this suite
|
sabrenner
removed
the
changelog/no-changelog
sabrenner
changed the title
sabrenner
changed the title
openai>=1.66.0,<1.66.2
…r `openai>=1.66.0,<1.66.2` (#14072) I discovered another instance of where we check object attributes when we should be checking dict attributes. This is specifically for older versions of the OpenAI SDK that have support for the Responses API (`openai==1.66.0,<1.66.2`). ## Checklist - [x] PR author has checked that all the criteria below are met - The PR description includes an overview of the change - The PR description articulates the motivation for the change - The change includes tests OR the PR description describes a testing strategy - The PR description notes risks associated with the change, if any - Newly-added code is easy to change - The change follows the [library release note guidelines](https://ddtrace.readthedocs.io/en/stable/releasenotes.html) - The change includes or references documentation updates if necessary - Backport labels are set (if [applicable](https://ddtrace.readthedocs.io/en/latest/contributing.html#backporting)) ## Reviewer Checklist - [x] Reviewer has checked that all the criteria below are met - Title is accurate - All changes are related to the pull request's stated goal - Avoids breaking [API](https://ddtrace.readthedocs.io/en/stable/versioning.html#interfaces) changes - Testing strategy adequately addresses listed risks - Newly-added code is easy to change - Release note makes sense to a user of the library - If necessary, author has acknowledged and discussed the performance implications of this PR as reported in the benchmarks PR comment - Backport labels are set in a manner that is consistent with the [release branch maintenance policy](https://ddtrace.readthedocs.io/en/latest/contributing.html#backporting) (cherry picked from commit b6939d1)
…r `openai>=1.66.0,<1.66.2` (#14072) I discovered another instance of where we check object attributes when we should be checking dict attributes. This is specifically for older versions of the OpenAI SDK that have support for the Responses API (`openai==1.66.0,<1.66.2`). ## Checklist - [x] PR author has checked that all the criteria below are met - The PR description includes an overview of the change - The PR description articulates the motivation for the change - The change includes tests OR the PR description describes a testing strategy - The PR description notes risks associated with the change, if any - Newly-added code is easy to change - The change follows the [library release note guidelines](https://ddtrace.readthedocs.io/en/stable/releasenotes.html) - The change includes or references documentation updates if necessary - Backport labels are set (if [applicable](https://ddtrace.readthedocs.io/en/latest/contributing.html#backporting)) ## Reviewer Checklist - [x] Reviewer has checked that all the criteria below are met - Title is accurate - All changes are related to the pull request's stated goal - Avoids breaking [API](https://ddtrace.readthedocs.io/en/stable/versioning.html#interfaces) changes - Testing strategy adequately addresses listed risks - Newly-added code is easy to change - Release note makes sense to a user of the library - If necessary, author has acknowledged and discussed the performance implications of this PR as reported in the benchmarks PR comment - Backport labels are set in a manner that is consistent with the [release branch maintenance policy](https://ddtrace.readthedocs.io/en/latest/contributing.html#backporting) (cherry picked from commit b6939d1)
…r `openai>=1.66.0,<1.66.2` [backport 3.11] (#14178) Backport b6939d1 from #14072 to 3.11. I discovered another instance of where we check object attributes when we should be checking dict attributes. This is specifically for older versions of the OpenAI SDK that have support for the Responses API (`openai==1.66.0,<1.66.2`). MLOB-3474 ## Checklist - [x] PR author has checked that all the criteria below are met - The PR description includes an overview of the change - The PR description articulates the motivation for the change - The change includes tests OR the PR description describes a testing strategy - The PR description notes risks associated with the change, if any - Newly-added code is easy to change - The change follows the [library release note guidelines](https://ddtrace.readthedocs.io/en/stable/releasenotes.html) - The change includes or references documentation updates if necessary - Backport labels are set (if [applicable](https://ddtrace.readthedocs.io/en/latest/contributing.html#backporting)) ## Reviewer Checklist - [x] Reviewer has checked that all the criteria below are met - Title is accurate - All changes are related to the pull request's stated goal - Avoids breaking [API](https://ddtrace.readthedocs.io/en/stable/versioning.html#interfaces) changes - Testing strategy adequately addresses listed risks - Newly-added code is easy to change - Release note makes sense to a user of the library - If necessary, author has acknowledged and discussed the performance implications of this PR as reported in the benchmarks PR comment - Backport labels are set in a manner that is consistent with the [release branch maintenance policy](https://ddtrace.readthedocs.io/en/latest/contributing.html#backporting) --------- Co-authored-by: Sam Brenner <[email protected]> Co-authored-by: Christophe Papazian <[email protected]> Co-authored-by: dd-octo-sts[bot] <200755185+dd-octo-sts[bot]@users.noreply.github.com> Co-authored-by: Christophe Papazian <[email protected]> Co-authored-by: Zachary Groves <[email protected]>
I discovered another instance of where we check object attributes when we should be checking dict attributes. This is specifically for older versions of the OpenAI SDK that have support for the Responses API (
openai==1.66.0,<1.66.2).MLOB-3474
Checklist
Reviewer Checklist