refactor: migrate token metrics to hooks/plugins system#653
Open
ajbozarth wants to merge 4 commits intogenerative-computing:mainfrom
Open
refactor: migrate token metrics to hooks/plugins system#653ajbozarth wants to merge 4 commits intogenerative-computing:mainfrom
ajbozarth wants to merge 4 commits intogenerative-computing:mainfrom
Conversation
- Add usage field to ModelOutputThunk with OpenAI-compatible format - Update all 5 backends to populate usage field during post_processing Signed-off-by: Alex Bozarth <ajbozart@us.ibm.com>
Completes migration from direct backend metrics calls to hook-based plugin system. TokenMetricsPlugin now handles all token metrics recording via generation_post_call hook. - Remove record_token_usage_metrics() calls from OpenAI, Ollama, LiteLLM, WatsonX, HuggingFace backends - Update metrics output format for OTel compliance Signed-off-by: Alex Bozarth <ajbozart@us.ibm.com>
Add assertions to verify usage, model, and provider fields are populated in test_async_avalue tests for all 5 supported backends. Signed-off-by: Alex Bozarth <ajbozart@us.ibm.com>
Signed-off-by: Alex Bozarth <ajbozart@us.ibm.com>
ajbozarth
requested review from
a team,
jakelorocco and
nrfulton
as code owners
Contributor
|
The PR description has been updated. Please fill out the template for your PR to be reviewed. |
Merge ProtectionsYour pull request matches the following merge protections and will not be merged until they are valid. 🟢 Enforce conventional commitWonderful, this rule succeeded.Make sure that we follow https://www.conventionalcommits.org/en/v1.0.0/
|
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Misc PR
Type of PR
Description
Refactors token metrics implementation to use the hooks/plugins system.
Token Usage Standardization (#607)
usagefield toModelOutputThunk(uses the OpenAI-compatible format)ModelOutputThunk:result.usage['prompt_tokens'],result.usage['completion_tokens'],result.usage['total_tokens']Hooks/Plugins Migration (#608)
TokenMetricsPluginthat hooks into thegeneration_post_callMELLEA_METRICS_ENABLED=trueFIRE_AND_FORGETmode (async, non-blocking)Testing