[Search Playground] Fix the issue related to token count#246589
Merged
saikatsarkar056 merged 2 commits intoelastic:mainfrom Dec 17, 2025
Merged
[Search Playground] Fix the issue related to token count#246589saikatsarkar056 merged 2 commits intoelastic:mainfrom
saikatsarkar056 merged 2 commits intoelastic:mainfrom
Conversation
Contributor
🔍 Preview links for changed docs |
saikatsarkar056
force-pushed
the
token_count_issue
branch
from
37a3ffd to
2ee726e
Compare
Fix the issue related to token count
saikatsarkar056
force-pushed
the
token_count_issue
branch
from
d528481 to
ac9fe1f
Compare
saikatsarkar056
added
release_note:fix
Team:Search
backport:skip
saikatsarkar056
changed the title
TattdCodeMonkey
approved these changes
Dec 16, 2025
Contributor
Author
@TattdCodeMonkey Those test failures were caused by a previous commit. With the current changes, the conversational chain tests should pass. I’ll wait for the CI/CD pipeline to turn green. |
Contributor
|
Starting backport for target branches: 9.4 |
Contributor
💛 Build succeeded, but was flaky
Failed CI StepsTest Failures
Metrics [docs]Async chunks
History
|
Contributor
💔 All backports failed
Manual backportTo create the backport manually run: Questions ?Please refer to the Backport tool documentation |
Contributor
|
@saikatsarkar056 we should backport this to all the versions that the ai dep was backported too as well #244675 |
Contributor
Author
I will create the backport PRs. |
Contributor
Author
💚 All backports created successfully
Note: Successful backport PRs will be merged automatically after passing CI. Questions ?Please refer to the Backport tool documentation |
Contributor
Author
💚 All backports created successfully
Note: Successful backport PRs will be merged automatically after passing CI. Questions ?Please refer to the Backport tool documentation |
Contributor
Author
💚 All backports created successfully
Note: Successful backport PRs will be merged automatically after passing CI. Questions ?Please refer to the Backport tool documentation |
saikatsarkar056
added a commit
to saikatsarkar056/kibana
that referenced
this pull request
Dec 17, 2025
) ## Summary Fixes token count display showing "NaN / 200,000 tokens sent" in the Search Playground after the AI SDK v5 upgrade. The issue was on the client-side in `parseDataStream` (`api.ts`), where `messageAnnotations` was being reset to `undefined` when a `text-start` chunk was received. In AI SDK v5, annotations (including token counts) are sent *before* the `text-start` chunk, so this reset was clearing the already-collected token data. This PR removes that reset to preserve annotations across the stream, ensuring token counts are correctly attached to the final message and displayed in the UI. ### Before <img width="865" height="502" alt="Screenshot 2025-12-16 at 10 39 42 AM" src="https://github.com/user-attachments/assets/331d3c7c-1b3e-455e-b8d7-561e2832054c" /> ### After <img width="1008" height="519" alt="Screenshot 2025-12-16 at 9 56 13 AM" src="https://github.com/user-attachments/assets/ec507093-e382-4320-b610-cc3d53a74c3b" /> ### Checklist Check the PR satisfies following conditions. Reviewers should verify this PR satisfies this list as well. - [ ] Any text added follows [EUI's writing guidelines](https://elastic.github.io/eui/#/guidelines/writing), uses sentence case text and includes [i18n support](https://github.com/elastic/kibana/blob/main/src/platform/packages/shared/kbn-i18n/README.md) - [ ] [Documentation](https://www.elastic.co/guide/en/kibana/master/development-documentation.html) was added for features that require explanation or tutorials - [x] [Unit or functional tests](https://www.elastic.co/guide/en/kibana/master/development-tests.html) were updated or added to match the most common scenarios - [ ] If a plugin configuration key changed, check if it needs to be allowlisted in the cloud and added to the [docker list](https://github.com/elastic/kibana/blob/main/src/dev/build/tasks/os_packages/docker_generator/resources/base/bin/kibana-docker) - [ ] This was checked for breaking HTTP API changes, and any breaking changes have been approved by the breaking-change committee. The `release_note:breaking` label should be applied in these situations. - [ ] [Flaky Test Runner](https://ci-stats.kibana.dev/trigger_flaky_test_runner/1) was used on any tests changed - [x] The PR description includes the appropriate Release Notes section, and the correct `release_note:*` label is applied per the [guidelines](https://www.elastic.co/guide/en/kibana/master/contributing.html#kibana-release-notes-process) - [x] Review the [backport guidelines](https://docs.google.com/document/d/1VyN5k91e5OVumlc0Gb9RPa3h1ewuPE705nRtioPiTvY/edit?usp=sharing) and apply applicable `backport:*` labels. ### Identify risks Does this PR introduce any risks? For example, consider risks like hard to test bugs, performance regression, potential of data loss. Describe the risk, its severity, and mitigation for each identified risk. Invite stakeholders and evaluate how to proceed before merging. - [ ] [See some risk examples](https://github.com/elastic/kibana/blob/main/RISK_MATRIX.mdx) - [ ] ... ## Release note Fixes token count display showing "NaN" in Search Playground by preserving message annotations across the AI SDK v5 stream. (cherry picked from commit 6eae531)
saikatsarkar056
added a commit
to saikatsarkar056/kibana
that referenced
this pull request
Dec 17, 2025
) ## Summary Fixes token count display showing "NaN / 200,000 tokens sent" in the Search Playground after the AI SDK v5 upgrade. The issue was on the client-side in `parseDataStream` (`api.ts`), where `messageAnnotations` was being reset to `undefined` when a `text-start` chunk was received. In AI SDK v5, annotations (including token counts) are sent *before* the `text-start` chunk, so this reset was clearing the already-collected token data. This PR removes that reset to preserve annotations across the stream, ensuring token counts are correctly attached to the final message and displayed in the UI. ### Before <img width="865" height="502" alt="Screenshot 2025-12-16 at 10 39 42 AM" src="https://github.com/user-attachments/assets/331d3c7c-1b3e-455e-b8d7-561e2832054c" /> ### After <img width="1008" height="519" alt="Screenshot 2025-12-16 at 9 56 13 AM" src="https://github.com/user-attachments/assets/ec507093-e382-4320-b610-cc3d53a74c3b" /> ### Checklist Check the PR satisfies following conditions. Reviewers should verify this PR satisfies this list as well. - [ ] Any text added follows [EUI's writing guidelines](https://elastic.github.io/eui/#/guidelines/writing), uses sentence case text and includes [i18n support](https://github.com/elastic/kibana/blob/main/src/platform/packages/shared/kbn-i18n/README.md) - [ ] [Documentation](https://www.elastic.co/guide/en/kibana/master/development-documentation.html) was added for features that require explanation or tutorials - [x] [Unit or functional tests](https://www.elastic.co/guide/en/kibana/master/development-tests.html) were updated or added to match the most common scenarios - [ ] If a plugin configuration key changed, check if it needs to be allowlisted in the cloud and added to the [docker list](https://github.com/elastic/kibana/blob/main/src/dev/build/tasks/os_packages/docker_generator/resources/base/bin/kibana-docker) - [ ] This was checked for breaking HTTP API changes, and any breaking changes have been approved by the breaking-change committee. The `release_note:breaking` label should be applied in these situations. - [ ] [Flaky Test Runner](https://ci-stats.kibana.dev/trigger_flaky_test_runner/1) was used on any tests changed - [x] The PR description includes the appropriate Release Notes section, and the correct `release_note:*` label is applied per the [guidelines](https://www.elastic.co/guide/en/kibana/master/contributing.html#kibana-release-notes-process) - [x] Review the [backport guidelines](https://docs.google.com/document/d/1VyN5k91e5OVumlc0Gb9RPa3h1ewuPE705nRtioPiTvY/edit?usp=sharing) and apply applicable `backport:*` labels. ### Identify risks Does this PR introduce any risks? For example, consider risks like hard to test bugs, performance regression, potential of data loss. Describe the risk, its severity, and mitigation for each identified risk. Invite stakeholders and evaluate how to proceed before merging. - [ ] [See some risk examples](https://github.com/elastic/kibana/blob/main/RISK_MATRIX.mdx) - [ ] ... ## Release note Fixes token count display showing "NaN" in Search Playground by preserving message annotations across the AI SDK v5 stream. (cherry picked from commit 6eae531)
kibanamachine
added
the
backport missing
Contributor
|
Looks like this PR has backport PRs but they still haven't been merged. Please merge them ASAP to keep the branches relatively in sync. |
saikatsarkar056
added a commit
that referenced
this pull request
Dec 19, 2025
…) (#246766) # Backport This will backport the following commits from `main` to `9.2`: - [[Search Playground] Fix the issue related to token count (#246589)](#246589) <!--- Backport version: 10.2.0 --> ### Questions ? Please refer to the [Backport tool documentation](https://github.com/sorenlouv/backport) <!--BACKPORT [{"author":{"name":"Saikat Sarkar","email":"132922331+saikatsarkar056@users.noreply.github.com"},"sourceCommit":{"committedDate":"2025-12-17T00:27:12Z","message":"[Search Playground] Fix the issue related to token count (#246589)\n\n## Summary\n\nFixes token count display showing \"NaN / 200,000 tokens sent\" in the\nSearch Playground after the AI SDK v5 upgrade.\n\nThe issue was on the client-side in `parseDataStream` (`api.ts`), where\n`messageAnnotations` was being reset to `undefined` when a `text-start`\nchunk was received. In AI SDK v5, annotations (including token counts)\nare sent *before* the `text-start` chunk, so this reset was clearing the\nalready-collected token data. This PR removes that reset to preserve\nannotations across the stream, ensuring token counts are correctly\nattached to the final message and displayed in the UI.\n\n\n### Before\n<img width=\"865\" height=\"502\" alt=\"Screenshot 2025-12-16 at 10 39 42 AM\"\nsrc=\"https://github.com/user-attachments/assets/331d3c7c-1b3e-455e-b8d7-561e2832054c\"\n/>\n\n\n### After\n<img width=\"1008\" height=\"519\" alt=\"Screenshot 2025-12-16 at 9 56 13 AM\"\nsrc=\"https://github.com/user-attachments/assets/ec507093-e382-4320-b610-cc3d53a74c3b\"\n/>\n\n\n### Checklist\n\nCheck the PR satisfies following conditions. \n\nReviewers should verify this PR satisfies this list as well.\n\n- [ ] Any text added follows [EUI's writing\nguidelines](https://elastic.github.io/eui/#/guidelines/writing), uses\nsentence case text and includes [i18n\nsupport](https://github.com/elastic/kibana/blob/main/src/platform/packages/shared/kbn-i18n/README.md)\n- [ ]\n[Documentation](https://www.elastic.co/guide/en/kibana/master/development-documentation.html)\nwas added for features that require explanation or tutorials\n- [x] [Unit or functional\ntests](https://www.elastic.co/guide/en/kibana/master/development-tests.html)\nwere updated or added to match the most common scenarios\n- [ ] If a plugin configuration key changed, check if it needs to be\nallowlisted in the cloud and added to the [docker\nlist](https://github.com/elastic/kibana/blob/main/src/dev/build/tasks/os_packages/docker_generator/resources/base/bin/kibana-docker)\n- [ ] This was checked for breaking HTTP API changes, and any breaking\nchanges have been approved by the breaking-change committee. The\n`release_note:breaking` label should be applied in these situations.\n- [ ] [Flaky Test\nRunner](https://ci-stats.kibana.dev/trigger_flaky_test_runner/1) was\nused on any tests changed\n- [x] The PR description includes the appropriate Release Notes section,\nand the correct `release_note:*` label is applied per the\n[guidelines](https://www.elastic.co/guide/en/kibana/master/contributing.html#kibana-release-notes-process)\n- [x] Review the [backport\nguidelines](https://docs.google.com/document/d/1VyN5k91e5OVumlc0Gb9RPa3h1ewuPE705nRtioPiTvY/edit?usp=sharing)\nand apply applicable `backport:*` labels.\n\n### Identify risks\n\nDoes this PR introduce any risks? For example, consider risks like hard\nto test bugs, performance regression, potential of data loss.\n\nDescribe the risk, its severity, and mitigation for each identified\nrisk. Invite stakeholders and evaluate how to proceed before merging.\n\n- [ ] [See some risk\nexamples](https://github.com/elastic/kibana/blob/main/RISK_MATRIX.mdx)\n- [ ] ...\n\n\n## Release note\nFixes token count display showing \"NaN\" in Search Playground by\npreserving message annotations across the AI SDK v5 stream.","sha":"6eae531e0d82503feff37f1abebeb7d5b0e0907f","branchLabelMapping":{"^v9.3.0$":"main","^v(\\d+).(\\d+).\\d+$":"$1.$2"}},"sourcePullRequest":{"labels":["release_note:fix","Team:Search","backport:version","v9.3.0","v9.4.0"],"title":"[Search Playground] Fix the issue related to token count","number":246589,"url":"https://github.com/elastic/kibana/pull/246589","mergeCommit":{"message":"[Search Playground] Fix the issue related to token count (#246589)\n\n## Summary\n\nFixes token count display showing \"NaN / 200,000 tokens sent\" in the\nSearch Playground after the AI SDK v5 upgrade.\n\nThe issue was on the client-side in `parseDataStream` (`api.ts`), where\n`messageAnnotations` was being reset to `undefined` when a `text-start`\nchunk was received. In AI SDK v5, annotations (including token counts)\nare sent *before* the `text-start` chunk, so this reset was clearing the\nalready-collected token data. This PR removes that reset to preserve\nannotations across the stream, ensuring token counts are correctly\nattached to the final message and displayed in the UI.\n\n\n### Before\n<img width=\"865\" height=\"502\" alt=\"Screenshot 2025-12-16 at 10 39 42 AM\"\nsrc=\"https://github.com/user-attachments/assets/331d3c7c-1b3e-455e-b8d7-561e2832054c\"\n/>\n\n\n### After\n<img width=\"1008\" height=\"519\" alt=\"Screenshot 2025-12-16 at 9 56 13 AM\"\nsrc=\"https://github.com/user-attachments/assets/ec507093-e382-4320-b610-cc3d53a74c3b\"\n/>\n\n\n### Checklist\n\nCheck the PR satisfies following conditions. \n\nReviewers should verify this PR satisfies this list as well.\n\n- [ ] Any text added follows [EUI's writing\nguidelines](https://elastic.github.io/eui/#/guidelines/writing), uses\nsentence case text and includes [i18n\nsupport](https://github.com/elastic/kibana/blob/main/src/platform/packages/shared/kbn-i18n/README.md)\n- [ ]\n[Documentation](https://www.elastic.co/guide/en/kibana/master/development-documentation.html)\nwas added for features that require explanation or tutorials\n- [x] [Unit or functional\ntests](https://www.elastic.co/guide/en/kibana/master/development-tests.html)\nwere updated or added to match the most common scenarios\n- [ ] If a plugin configuration key changed, check if it needs to be\nallowlisted in the cloud and added to the [docker\nlist](https://github.com/elastic/kibana/blob/main/src/dev/build/tasks/os_packages/docker_generator/resources/base/bin/kibana-docker)\n- [ ] This was checked for breaking HTTP API changes, and any breaking\nchanges have been approved by the breaking-change committee. The\n`release_note:breaking` label should be applied in these situations.\n- [ ] [Flaky Test\nRunner](https://ci-stats.kibana.dev/trigger_flaky_test_runner/1) was\nused on any tests changed\n- [x] The PR description includes the appropriate Release Notes section,\nand the correct `release_note:*` label is applied per the\n[guidelines](https://www.elastic.co/guide/en/kibana/master/contributing.html#kibana-release-notes-process)\n- [x] Review the [backport\nguidelines](https://docs.google.com/document/d/1VyN5k91e5OVumlc0Gb9RPa3h1ewuPE705nRtioPiTvY/edit?usp=sharing)\nand apply applicable `backport:*` labels.\n\n### Identify risks\n\nDoes this PR introduce any risks? For example, consider risks like hard\nto test bugs, performance regression, potential of data loss.\n\nDescribe the risk, its severity, and mitigation for each identified\nrisk. Invite stakeholders and evaluate how to proceed before merging.\n\n- [ ] [See some risk\nexamples](https://github.com/elastic/kibana/blob/main/RISK_MATRIX.mdx)\n- [ ] ...\n\n\n## Release note\nFixes token count display showing \"NaN\" in Search Playground by\npreserving message annotations across the AI SDK v5 stream.","sha":"6eae531e0d82503feff37f1abebeb7d5b0e0907f"}},"sourceBranch":"main","suggestedTargetBranches":["9.4"],"targetPullRequestStates":[{"branch":"main","label":"v9.3.0","branchLabelMappingKey":"^v9.3.0$","isSourceBranch":true,"state":"MERGED","url":"https://github.com/elastic/kibana/pull/246589","number":246589,"mergeCommit":{"message":"[Search Playground] Fix the issue related to token count (#246589)\n\n## Summary\n\nFixes token count display showing \"NaN / 200,000 tokens sent\" in the\nSearch Playground after the AI SDK v5 upgrade.\n\nThe issue was on the client-side in `parseDataStream` (`api.ts`), where\n`messageAnnotations` was being reset to `undefined` when a `text-start`\nchunk was received. In AI SDK v5, annotations (including token counts)\nare sent *before* the `text-start` chunk, so this reset was clearing the\nalready-collected token data. This PR removes that reset to preserve\nannotations across the stream, ensuring token counts are correctly\nattached to the final message and displayed in the UI.\n\n\n### Before\n<img width=\"865\" height=\"502\" alt=\"Screenshot 2025-12-16 at 10 39 42 AM\"\nsrc=\"https://github.com/user-attachments/assets/331d3c7c-1b3e-455e-b8d7-561e2832054c\"\n/>\n\n\n### After\n<img width=\"1008\" height=\"519\" alt=\"Screenshot 2025-12-16 at 9 56 13 AM\"\nsrc=\"https://github.com/user-attachments/assets/ec507093-e382-4320-b610-cc3d53a74c3b\"\n/>\n\n\n### Checklist\n\nCheck the PR satisfies following conditions. \n\nReviewers should verify this PR satisfies this list as well.\n\n- [ ] Any text added follows [EUI's writing\nguidelines](https://elastic.github.io/eui/#/guidelines/writing), uses\nsentence case text and includes [i18n\nsupport](https://github.com/elastic/kibana/blob/main/src/platform/packages/shared/kbn-i18n/README.md)\n- [ ]\n[Documentation](https://www.elastic.co/guide/en/kibana/master/development-documentation.html)\nwas added for features that require explanation or tutorials\n- [x] [Unit or functional\ntests](https://www.elastic.co/guide/en/kibana/master/development-tests.html)\nwere updated or added to match the most common scenarios\n- [ ] If a plugin configuration key changed, check if it needs to be\nallowlisted in the cloud and added to the [docker\nlist](https://github.com/elastic/kibana/blob/main/src/dev/build/tasks/os_packages/docker_generator/resources/base/bin/kibana-docker)\n- [ ] This was checked for breaking HTTP API changes, and any breaking\nchanges have been approved by the breaking-change committee. The\n`release_note:breaking` label should be applied in these situations.\n- [ ] [Flaky Test\nRunner](https://ci-stats.kibana.dev/trigger_flaky_test_runner/1) was\nused on any tests changed\n- [x] The PR description includes the appropriate Release Notes section,\nand the correct `release_note:*` label is applied per the\n[guidelines](https://www.elastic.co/guide/en/kibana/master/contributing.html#kibana-release-notes-process)\n- [x] Review the [backport\nguidelines](https://docs.google.com/document/d/1VyN5k91e5OVumlc0Gb9RPa3h1ewuPE705nRtioPiTvY/edit?usp=sharing)\nand apply applicable `backport:*` labels.\n\n### Identify risks\n\nDoes this PR introduce any risks? For example, consider risks like hard\nto test bugs, performance regression, potential of data loss.\n\nDescribe the risk, its severity, and mitigation for each identified\nrisk. Invite stakeholders and evaluate how to proceed before merging.\n\n- [ ] [See some risk\nexamples](https://github.com/elastic/kibana/blob/main/RISK_MATRIX.mdx)\n- [ ] ...\n\n\n## Release note\nFixes token count display showing \"NaN\" in Search Playground by\npreserving message annotations across the AI SDK v5 stream.","sha":"6eae531e0d82503feff37f1abebeb7d5b0e0907f"}},{"branch":"9.4","label":"v9.4.0","branchLabelMappingKey":"^v(\\d+).(\\d+).\\d+$","isSourceBranch":false,"state":"NOT_CREATED"},{"url":"https://github.com/elastic/kibana/pull/246764","number":246764,"branch":"8.19","state":"OPEN"},{"url":"https://github.com/elastic/kibana/pull/246765","number":246765,"branch":"9.1","state":"OPEN"}]}] BACKPORT-->
saikatsarkar056
added a commit
that referenced
this pull request
Dec 19, 2025
…) (#246765) # Backport This will backport the following commits from `main` to `9.1`: - [[Search Playground] Fix the issue related to token count (#246589)](#246589) <!--- Backport version: 10.2.0 --> ### Questions ? Please refer to the [Backport tool documentation](https://github.com/sorenlouv/backport) <!--BACKPORT [{"author":{"name":"Saikat Sarkar","email":"132922331+saikatsarkar056@users.noreply.github.com"},"sourceCommit":{"committedDate":"2025-12-17T00:27:12Z","message":"[Search Playground] Fix the issue related to token count (#246589)\n\n## Summary\n\nFixes token count display showing \"NaN / 200,000 tokens sent\" in the\nSearch Playground after the AI SDK v5 upgrade.\n\nThe issue was on the client-side in `parseDataStream` (`api.ts`), where\n`messageAnnotations` was being reset to `undefined` when a `text-start`\nchunk was received. In AI SDK v5, annotations (including token counts)\nare sent *before* the `text-start` chunk, so this reset was clearing the\nalready-collected token data. This PR removes that reset to preserve\nannotations across the stream, ensuring token counts are correctly\nattached to the final message and displayed in the UI.\n\n\n### Before\n<img width=\"865\" height=\"502\" alt=\"Screenshot 2025-12-16 at 10 39 42 AM\"\nsrc=\"https://github.com/user-attachments/assets/331d3c7c-1b3e-455e-b8d7-561e2832054c\"\n/>\n\n\n### After\n<img width=\"1008\" height=\"519\" alt=\"Screenshot 2025-12-16 at 9 56 13 AM\"\nsrc=\"https://github.com/user-attachments/assets/ec507093-e382-4320-b610-cc3d53a74c3b\"\n/>\n\n\n### Checklist\n\nCheck the PR satisfies following conditions. \n\nReviewers should verify this PR satisfies this list as well.\n\n- [ ] Any text added follows [EUI's writing\nguidelines](https://elastic.github.io/eui/#/guidelines/writing), uses\nsentence case text and includes [i18n\nsupport](https://github.com/elastic/kibana/blob/main/src/platform/packages/shared/kbn-i18n/README.md)\n- [ ]\n[Documentation](https://www.elastic.co/guide/en/kibana/master/development-documentation.html)\nwas added for features that require explanation or tutorials\n- [x] [Unit or functional\ntests](https://www.elastic.co/guide/en/kibana/master/development-tests.html)\nwere updated or added to match the most common scenarios\n- [ ] If a plugin configuration key changed, check if it needs to be\nallowlisted in the cloud and added to the [docker\nlist](https://github.com/elastic/kibana/blob/main/src/dev/build/tasks/os_packages/docker_generator/resources/base/bin/kibana-docker)\n- [ ] This was checked for breaking HTTP API changes, and any breaking\nchanges have been approved by the breaking-change committee. The\n`release_note:breaking` label should be applied in these situations.\n- [ ] [Flaky Test\nRunner](https://ci-stats.kibana.dev/trigger_flaky_test_runner/1) was\nused on any tests changed\n- [x] The PR description includes the appropriate Release Notes section,\nand the correct `release_note:*` label is applied per the\n[guidelines](https://www.elastic.co/guide/en/kibana/master/contributing.html#kibana-release-notes-process)\n- [x] Review the [backport\nguidelines](https://docs.google.com/document/d/1VyN5k91e5OVumlc0Gb9RPa3h1ewuPE705nRtioPiTvY/edit?usp=sharing)\nand apply applicable `backport:*` labels.\n\n### Identify risks\n\nDoes this PR introduce any risks? For example, consider risks like hard\nto test bugs, performance regression, potential of data loss.\n\nDescribe the risk, its severity, and mitigation for each identified\nrisk. Invite stakeholders and evaluate how to proceed before merging.\n\n- [ ] [See some risk\nexamples](https://github.com/elastic/kibana/blob/main/RISK_MATRIX.mdx)\n- [ ] ...\n\n\n## Release note\nFixes token count display showing \"NaN\" in Search Playground by\npreserving message annotations across the AI SDK v5 stream.","sha":"6eae531e0d82503feff37f1abebeb7d5b0e0907f","branchLabelMapping":{"^v9.3.0$":"main","^v(\\d+).(\\d+).\\d+$":"$1.$2"}},"sourcePullRequest":{"labels":["release_note:fix","Team:Search","backport:version","v9.3.0","v9.4.0"],"title":"[Search Playground] Fix the issue related to token count","number":246589,"url":"https://github.com/elastic/kibana/pull/246589","mergeCommit":{"message":"[Search Playground] Fix the issue related to token count (#246589)\n\n## Summary\n\nFixes token count display showing \"NaN / 200,000 tokens sent\" in the\nSearch Playground after the AI SDK v5 upgrade.\n\nThe issue was on the client-side in `parseDataStream` (`api.ts`), where\n`messageAnnotations` was being reset to `undefined` when a `text-start`\nchunk was received. In AI SDK v5, annotations (including token counts)\nare sent *before* the `text-start` chunk, so this reset was clearing the\nalready-collected token data. This PR removes that reset to preserve\nannotations across the stream, ensuring token counts are correctly\nattached to the final message and displayed in the UI.\n\n\n### Before\n<img width=\"865\" height=\"502\" alt=\"Screenshot 2025-12-16 at 10 39 42 AM\"\nsrc=\"https://github.com/user-attachments/assets/331d3c7c-1b3e-455e-b8d7-561e2832054c\"\n/>\n\n\n### After\n<img width=\"1008\" height=\"519\" alt=\"Screenshot 2025-12-16 at 9 56 13 AM\"\nsrc=\"https://github.com/user-attachments/assets/ec507093-e382-4320-b610-cc3d53a74c3b\"\n/>\n\n\n### Checklist\n\nCheck the PR satisfies following conditions. \n\nReviewers should verify this PR satisfies this list as well.\n\n- [ ] Any text added follows [EUI's writing\nguidelines](https://elastic.github.io/eui/#/guidelines/writing), uses\nsentence case text and includes [i18n\nsupport](https://github.com/elastic/kibana/blob/main/src/platform/packages/shared/kbn-i18n/README.md)\n- [ ]\n[Documentation](https://www.elastic.co/guide/en/kibana/master/development-documentation.html)\nwas added for features that require explanation or tutorials\n- [x] [Unit or functional\ntests](https://www.elastic.co/guide/en/kibana/master/development-tests.html)\nwere updated or added to match the most common scenarios\n- [ ] If a plugin configuration key changed, check if it needs to be\nallowlisted in the cloud and added to the [docker\nlist](https://github.com/elastic/kibana/blob/main/src/dev/build/tasks/os_packages/docker_generator/resources/base/bin/kibana-docker)\n- [ ] This was checked for breaking HTTP API changes, and any breaking\nchanges have been approved by the breaking-change committee. The\n`release_note:breaking` label should be applied in these situations.\n- [ ] [Flaky Test\nRunner](https://ci-stats.kibana.dev/trigger_flaky_test_runner/1) was\nused on any tests changed\n- [x] The PR description includes the appropriate Release Notes section,\nand the correct `release_note:*` label is applied per the\n[guidelines](https://www.elastic.co/guide/en/kibana/master/contributing.html#kibana-release-notes-process)\n- [x] Review the [backport\nguidelines](https://docs.google.com/document/d/1VyN5k91e5OVumlc0Gb9RPa3h1ewuPE705nRtioPiTvY/edit?usp=sharing)\nand apply applicable `backport:*` labels.\n\n### Identify risks\n\nDoes this PR introduce any risks? For example, consider risks like hard\nto test bugs, performance regression, potential of data loss.\n\nDescribe the risk, its severity, and mitigation for each identified\nrisk. Invite stakeholders and evaluate how to proceed before merging.\n\n- [ ] [See some risk\nexamples](https://github.com/elastic/kibana/blob/main/RISK_MATRIX.mdx)\n- [ ] ...\n\n\n## Release note\nFixes token count display showing \"NaN\" in Search Playground by\npreserving message annotations across the AI SDK v5 stream.","sha":"6eae531e0d82503feff37f1abebeb7d5b0e0907f"}},"sourceBranch":"main","suggestedTargetBranches":["9.4"],"targetPullRequestStates":[{"branch":"main","label":"v9.3.0","branchLabelMappingKey":"^v9.3.0$","isSourceBranch":true,"state":"MERGED","url":"https://github.com/elastic/kibana/pull/246589","number":246589,"mergeCommit":{"message":"[Search Playground] Fix the issue related to token count (#246589)\n\n## Summary\n\nFixes token count display showing \"NaN / 200,000 tokens sent\" in the\nSearch Playground after the AI SDK v5 upgrade.\n\nThe issue was on the client-side in `parseDataStream` (`api.ts`), where\n`messageAnnotations` was being reset to `undefined` when a `text-start`\nchunk was received. In AI SDK v5, annotations (including token counts)\nare sent *before* the `text-start` chunk, so this reset was clearing the\nalready-collected token data. This PR removes that reset to preserve\nannotations across the stream, ensuring token counts are correctly\nattached to the final message and displayed in the UI.\n\n\n### Before\n<img width=\"865\" height=\"502\" alt=\"Screenshot 2025-12-16 at 10 39 42 AM\"\nsrc=\"https://github.com/user-attachments/assets/331d3c7c-1b3e-455e-b8d7-561e2832054c\"\n/>\n\n\n### After\n<img width=\"1008\" height=\"519\" alt=\"Screenshot 2025-12-16 at 9 56 13 AM\"\nsrc=\"https://github.com/user-attachments/assets/ec507093-e382-4320-b610-cc3d53a74c3b\"\n/>\n\n\n### Checklist\n\nCheck the PR satisfies following conditions. \n\nReviewers should verify this PR satisfies this list as well.\n\n- [ ] Any text added follows [EUI's writing\nguidelines](https://elastic.github.io/eui/#/guidelines/writing), uses\nsentence case text and includes [i18n\nsupport](https://github.com/elastic/kibana/blob/main/src/platform/packages/shared/kbn-i18n/README.md)\n- [ ]\n[Documentation](https://www.elastic.co/guide/en/kibana/master/development-documentation.html)\nwas added for features that require explanation or tutorials\n- [x] [Unit or functional\ntests](https://www.elastic.co/guide/en/kibana/master/development-tests.html)\nwere updated or added to match the most common scenarios\n- [ ] If a plugin configuration key changed, check if it needs to be\nallowlisted in the cloud and added to the [docker\nlist](https://github.com/elastic/kibana/blob/main/src/dev/build/tasks/os_packages/docker_generator/resources/base/bin/kibana-docker)\n- [ ] This was checked for breaking HTTP API changes, and any breaking\nchanges have been approved by the breaking-change committee. The\n`release_note:breaking` label should be applied in these situations.\n- [ ] [Flaky Test\nRunner](https://ci-stats.kibana.dev/trigger_flaky_test_runner/1) was\nused on any tests changed\n- [x] The PR description includes the appropriate Release Notes section,\nand the correct `release_note:*` label is applied per the\n[guidelines](https://www.elastic.co/guide/en/kibana/master/contributing.html#kibana-release-notes-process)\n- [x] Review the [backport\nguidelines](https://docs.google.com/document/d/1VyN5k91e5OVumlc0Gb9RPa3h1ewuPE705nRtioPiTvY/edit?usp=sharing)\nand apply applicable `backport:*` labels.\n\n### Identify risks\n\nDoes this PR introduce any risks? For example, consider risks like hard\nto test bugs, performance regression, potential of data loss.\n\nDescribe the risk, its severity, and mitigation for each identified\nrisk. Invite stakeholders and evaluate how to proceed before merging.\n\n- [ ] [See some risk\nexamples](https://github.com/elastic/kibana/blob/main/RISK_MATRIX.mdx)\n- [ ] ...\n\n\n## Release note\nFixes token count display showing \"NaN\" in Search Playground by\npreserving message annotations across the AI SDK v5 stream.","sha":"6eae531e0d82503feff37f1abebeb7d5b0e0907f"}},{"branch":"9.4","label":"v9.4.0","branchLabelMappingKey":"^v(\\d+).(\\d+).\\d+$","isSourceBranch":false,"state":"NOT_CREATED"},{"url":"https://github.com/elastic/kibana/pull/246764","number":246764,"branch":"8.19","state":"OPEN"}]}] BACKPORT-->
saikatsarkar056
added a commit
that referenced
this pull request
Dec 19, 2025
) (#246764) # Backport This will backport the following commits from `main` to `8.19`: - [[Search Playground] Fix the issue related to token count (#246589)](#246589) <!--- Backport version: 10.2.0 --> ### Questions ? Please refer to the [Backport tool documentation](https://github.com/sorenlouv/backport) <!--BACKPORT [{"author":{"name":"Saikat Sarkar","email":"132922331+saikatsarkar056@users.noreply.github.com"},"sourceCommit":{"committedDate":"2025-12-17T00:27:12Z","message":"[Search Playground] Fix the issue related to token count (#246589)\n\n## Summary\n\nFixes token count display showing \"NaN / 200,000 tokens sent\" in the\nSearch Playground after the AI SDK v5 upgrade.\n\nThe issue was on the client-side in `parseDataStream` (`api.ts`), where\n`messageAnnotations` was being reset to `undefined` when a `text-start`\nchunk was received. In AI SDK v5, annotations (including token counts)\nare sent *before* the `text-start` chunk, so this reset was clearing the\nalready-collected token data. This PR removes that reset to preserve\nannotations across the stream, ensuring token counts are correctly\nattached to the final message and displayed in the UI.\n\n\n### Before\n<img width=\"865\" height=\"502\" alt=\"Screenshot 2025-12-16 at 10 39 42 AM\"\nsrc=\"https://github.com/user-attachments/assets/331d3c7c-1b3e-455e-b8d7-561e2832054c\"\n/>\n\n\n### After\n<img width=\"1008\" height=\"519\" alt=\"Screenshot 2025-12-16 at 9 56 13 AM\"\nsrc=\"https://github.com/user-attachments/assets/ec507093-e382-4320-b610-cc3d53a74c3b\"\n/>\n\n\n### Checklist\n\nCheck the PR satisfies following conditions. \n\nReviewers should verify this PR satisfies this list as well.\n\n- [ ] Any text added follows [EUI's writing\nguidelines](https://elastic.github.io/eui/#/guidelines/writing), uses\nsentence case text and includes [i18n\nsupport](https://github.com/elastic/kibana/blob/main/src/platform/packages/shared/kbn-i18n/README.md)\n- [ ]\n[Documentation](https://www.elastic.co/guide/en/kibana/master/development-documentation.html)\nwas added for features that require explanation or tutorials\n- [x] [Unit or functional\ntests](https://www.elastic.co/guide/en/kibana/master/development-tests.html)\nwere updated or added to match the most common scenarios\n- [ ] If a plugin configuration key changed, check if it needs to be\nallowlisted in the cloud and added to the [docker\nlist](https://github.com/elastic/kibana/blob/main/src/dev/build/tasks/os_packages/docker_generator/resources/base/bin/kibana-docker)\n- [ ] This was checked for breaking HTTP API changes, and any breaking\nchanges have been approved by the breaking-change committee. The\n`release_note:breaking` label should be applied in these situations.\n- [ ] [Flaky Test\nRunner](https://ci-stats.kibana.dev/trigger_flaky_test_runner/1) was\nused on any tests changed\n- [x] The PR description includes the appropriate Release Notes section,\nand the correct `release_note:*` label is applied per the\n[guidelines](https://www.elastic.co/guide/en/kibana/master/contributing.html#kibana-release-notes-process)\n- [x] Review the [backport\nguidelines](https://docs.google.com/document/d/1VyN5k91e5OVumlc0Gb9RPa3h1ewuPE705nRtioPiTvY/edit?usp=sharing)\nand apply applicable `backport:*` labels.\n\n### Identify risks\n\nDoes this PR introduce any risks? For example, consider risks like hard\nto test bugs, performance regression, potential of data loss.\n\nDescribe the risk, its severity, and mitigation for each identified\nrisk. Invite stakeholders and evaluate how to proceed before merging.\n\n- [ ] [See some risk\nexamples](https://github.com/elastic/kibana/blob/main/RISK_MATRIX.mdx)\n- [ ] ...\n\n\n## Release note\nFixes token count display showing \"NaN\" in Search Playground by\npreserving message annotations across the AI SDK v5 stream.","sha":"6eae531e0d82503feff37f1abebeb7d5b0e0907f","branchLabelMapping":{"^v9.3.0$":"main","^v(\\d+).(\\d+).\\d+$":"$1.$2"}},"sourcePullRequest":{"labels":["release_note:fix","Team:Search","backport:version","v9.3.0","v9.4.0"],"title":"[Search Playground] Fix the issue related to token count","number":246589,"url":"https://github.com/elastic/kibana/pull/246589","mergeCommit":{"message":"[Search Playground] Fix the issue related to token count (#246589)\n\n## Summary\n\nFixes token count display showing \"NaN / 200,000 tokens sent\" in the\nSearch Playground after the AI SDK v5 upgrade.\n\nThe issue was on the client-side in `parseDataStream` (`api.ts`), where\n`messageAnnotations` was being reset to `undefined` when a `text-start`\nchunk was received. In AI SDK v5, annotations (including token counts)\nare sent *before* the `text-start` chunk, so this reset was clearing the\nalready-collected token data. This PR removes that reset to preserve\nannotations across the stream, ensuring token counts are correctly\nattached to the final message and displayed in the UI.\n\n\n### Before\n<img width=\"865\" height=\"502\" alt=\"Screenshot 2025-12-16 at 10 39 42 AM\"\nsrc=\"https://github.com/user-attachments/assets/331d3c7c-1b3e-455e-b8d7-561e2832054c\"\n/>\n\n\n### After\n<img width=\"1008\" height=\"519\" alt=\"Screenshot 2025-12-16 at 9 56 13 AM\"\nsrc=\"https://github.com/user-attachments/assets/ec507093-e382-4320-b610-cc3d53a74c3b\"\n/>\n\n\n### Checklist\n\nCheck the PR satisfies following conditions. \n\nReviewers should verify this PR satisfies this list as well.\n\n- [ ] Any text added follows [EUI's writing\nguidelines](https://elastic.github.io/eui/#/guidelines/writing), uses\nsentence case text and includes [i18n\nsupport](https://github.com/elastic/kibana/blob/main/src/platform/packages/shared/kbn-i18n/README.md)\n- [ ]\n[Documentation](https://www.elastic.co/guide/en/kibana/master/development-documentation.html)\nwas added for features that require explanation or tutorials\n- [x] [Unit or functional\ntests](https://www.elastic.co/guide/en/kibana/master/development-tests.html)\nwere updated or added to match the most common scenarios\n- [ ] If a plugin configuration key changed, check if it needs to be\nallowlisted in the cloud and added to the [docker\nlist](https://github.com/elastic/kibana/blob/main/src/dev/build/tasks/os_packages/docker_generator/resources/base/bin/kibana-docker)\n- [ ] This was checked for breaking HTTP API changes, and any breaking\nchanges have been approved by the breaking-change committee. The\n`release_note:breaking` label should be applied in these situations.\n- [ ] [Flaky Test\nRunner](https://ci-stats.kibana.dev/trigger_flaky_test_runner/1) was\nused on any tests changed\n- [x] The PR description includes the appropriate Release Notes section,\nand the correct `release_note:*` label is applied per the\n[guidelines](https://www.elastic.co/guide/en/kibana/master/contributing.html#kibana-release-notes-process)\n- [x] Review the [backport\nguidelines](https://docs.google.com/document/d/1VyN5k91e5OVumlc0Gb9RPa3h1ewuPE705nRtioPiTvY/edit?usp=sharing)\nand apply applicable `backport:*` labels.\n\n### Identify risks\n\nDoes this PR introduce any risks? For example, consider risks like hard\nto test bugs, performance regression, potential of data loss.\n\nDescribe the risk, its severity, and mitigation for each identified\nrisk. Invite stakeholders and evaluate how to proceed before merging.\n\n- [ ] [See some risk\nexamples](https://github.com/elastic/kibana/blob/main/RISK_MATRIX.mdx)\n- [ ] ...\n\n\n## Release note\nFixes token count display showing \"NaN\" in Search Playground by\npreserving message annotations across the AI SDK v5 stream.","sha":"6eae531e0d82503feff37f1abebeb7d5b0e0907f"}},"sourceBranch":"main","suggestedTargetBranches":["9.4"],"targetPullRequestStates":[{"branch":"main","label":"v9.3.0","branchLabelMappingKey":"^v9.3.0$","isSourceBranch":true,"state":"MERGED","url":"https://github.com/elastic/kibana/pull/246589","number":246589,"mergeCommit":{"message":"[Search Playground] Fix the issue related to token count (#246589)\n\n## Summary\n\nFixes token count display showing \"NaN / 200,000 tokens sent\" in the\nSearch Playground after the AI SDK v5 upgrade.\n\nThe issue was on the client-side in `parseDataStream` (`api.ts`), where\n`messageAnnotations` was being reset to `undefined` when a `text-start`\nchunk was received. In AI SDK v5, annotations (including token counts)\nare sent *before* the `text-start` chunk, so this reset was clearing the\nalready-collected token data. This PR removes that reset to preserve\nannotations across the stream, ensuring token counts are correctly\nattached to the final message and displayed in the UI.\n\n\n### Before\n<img width=\"865\" height=\"502\" alt=\"Screenshot 2025-12-16 at 10 39 42 AM\"\nsrc=\"https://github.com/user-attachments/assets/331d3c7c-1b3e-455e-b8d7-561e2832054c\"\n/>\n\n\n### After\n<img width=\"1008\" height=\"519\" alt=\"Screenshot 2025-12-16 at 9 56 13 AM\"\nsrc=\"https://github.com/user-attachments/assets/ec507093-e382-4320-b610-cc3d53a74c3b\"\n/>\n\n\n### Checklist\n\nCheck the PR satisfies following conditions. \n\nReviewers should verify this PR satisfies this list as well.\n\n- [ ] Any text added follows [EUI's writing\nguidelines](https://elastic.github.io/eui/#/guidelines/writing), uses\nsentence case text and includes [i18n\nsupport](https://github.com/elastic/kibana/blob/main/src/platform/packages/shared/kbn-i18n/README.md)\n- [ ]\n[Documentation](https://www.elastic.co/guide/en/kibana/master/development-documentation.html)\nwas added for features that require explanation or tutorials\n- [x] [Unit or functional\ntests](https://www.elastic.co/guide/en/kibana/master/development-tests.html)\nwere updated or added to match the most common scenarios\n- [ ] If a plugin configuration key changed, check if it needs to be\nallowlisted in the cloud and added to the [docker\nlist](https://github.com/elastic/kibana/blob/main/src/dev/build/tasks/os_packages/docker_generator/resources/base/bin/kibana-docker)\n- [ ] This was checked for breaking HTTP API changes, and any breaking\nchanges have been approved by the breaking-change committee. The\n`release_note:breaking` label should be applied in these situations.\n- [ ] [Flaky Test\nRunner](https://ci-stats.kibana.dev/trigger_flaky_test_runner/1) was\nused on any tests changed\n- [x] The PR description includes the appropriate Release Notes section,\nand the correct `release_note:*` label is applied per the\n[guidelines](https://www.elastic.co/guide/en/kibana/master/contributing.html#kibana-release-notes-process)\n- [x] Review the [backport\nguidelines](https://docs.google.com/document/d/1VyN5k91e5OVumlc0Gb9RPa3h1ewuPE705nRtioPiTvY/edit?usp=sharing)\nand apply applicable `backport:*` labels.\n\n### Identify risks\n\nDoes this PR introduce any risks? For example, consider risks like hard\nto test bugs, performance regression, potential of data loss.\n\nDescribe the risk, its severity, and mitigation for each identified\nrisk. Invite stakeholders and evaluate how to proceed before merging.\n\n- [ ] [See some risk\nexamples](https://github.com/elastic/kibana/blob/main/RISK_MATRIX.mdx)\n- [ ] ...\n\n\n## Release note\nFixes token count display showing \"NaN\" in Search Playground by\npreserving message annotations across the AI SDK v5 stream.","sha":"6eae531e0d82503feff37f1abebeb7d5b0e0907f"}},{"branch":"9.4","label":"v9.4.0","branchLabelMappingKey":"^v(\\d+).(\\d+).\\d+$","isSourceBranch":false,"state":"NOT_CREATED"}]}] BACKPORT-->
kibanamachine
added
v9.1.9
v8.19.9
and removed
backport missing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Fixes token count display showing "NaN / 200,000 tokens sent" in the Search Playground after the AI SDK v5 upgrade.
The issue was on the client-side in
parseDataStream(api.ts), wheremessageAnnotationswas being reset toundefinedwhen atext-startchunk was received. In AI SDK v5, annotations (including token counts) are sent before thetext-startchunk, so this reset was clearing the already-collected token data. This PR removes that reset to preserve annotations across the stream, ensuring token counts are correctly attached to the final message and displayed in the UI.Before
After
Checklist
Check the PR satisfies following conditions.
Reviewers should verify this PR satisfies this list as well.
release_note:breakinglabel should be applied in these situations.release_note:*label is applied per the guidelinesbackport:*labels.Identify risks
Does this PR introduce any risks? For example, consider risks like hard to test bugs, performance regression, potential of data loss.
Describe the risk, its severity, and mitigation for each identified risk. Invite stakeholders and evaluate how to proceed before merging.
Release note
Fixes token count display showing "NaN" in Search Playground by preserving message annotations across the AI SDK v5 stream.