feat(semcov): Add Image Token Count and Cost Semantic Conventions #1787
Conversation
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
dosubot
bot
added
the
size:L
@arizeai/openinference-core
@arizeai/openinference-instrumentation-beeai
@arizeai/openinference-instrumentation-langchain
@arizeai/openinference-instrumentation-mcp
@arizeai/openinference-instrumentation-openai
@arizeai/openinference-mastra
@arizeai/openinference-semantic-conventions
@arizeai/openinference-vercel
commit: |
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
There was a problem hiding this comment.
Hey @sallyannarize - I've reviewed your changes - here's some feedback:
- Remove the duplicated prompt_details and completion_details constant definitions in the Python SpanAttributes class to avoid redefinition conflicts and keep the attribute grouping consistent.
- Consider splitting out the input/output cost prefix refactoring (LLM_COST_INPUT, LLM_COST_OUTPUT, etc.) into a separate PR so this one stays focused solely on adding the image token/count and cost conventions.
Prompt for AI Agents
Please address the comments from this code review:
## Overall Comments
- Remove the duplicated prompt_details and completion_details constant definitions in the Python SpanAttributes class to avoid redefinition conflicts and keep the attribute grouping consistent.
- Consider splitting out the input/output cost prefix refactoring (LLM_COST_INPUT, LLM_COST_OUTPUT, etc.) into a separate PR so this one stays focused solely on adding the image token/count and cost conventions.Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.
caroger
reviewed
Jun 17, 2025
| Total cost of all output tokens generated by the LLM in USD. This includes all tokens that were | ||
| generated in response to the prompt, including the main response and any additional output. | ||
| """ | ||
| LLM_COST_COMPLETION_DETAILS = "llm.cost.completion_details" |
There was a problem hiding this comment.
Is removing or renaming LLM_COST_COMPLETION_DETAILS intentional?
if so, tests in test_attributes.py should be updated to reflect this change otherwise CI wouldn't pass
There was a problem hiding this comment.
Must have accidentally deleted these, I have added them back
caroger
reviewed
Jun 17, 2025
| Total cost of all input tokens sent to the LLM in USD. This includes all tokens that were | ||
| processed as part of the prompt, including system messages, user messages, and any other input. | ||
| """ | ||
| LLM_COST_PROMPT_DETAILS = "llm.cost.prompt_details" |
There was a problem hiding this comment.
same comments here about LLM_COST_PROMPT_DETAILS
dosubot
bot
added
size:M
![graphite-app[bot]](https://avatars.githubusercontent.com/in/158384?s=60&v=4){kind=small}
js/packages/openinference-semantic-conventions/src/trace/SemanticConventions.ts
Outdated
Show resolved
Hide resolved
…ticConventions.ts Co-authored-by: graphite-app[bot] <96075541+graphite-app[bot]@users.noreply.github.com>
| AWS = "aws", | ||
| AZURE = "azure", | ||
| } | ||
| } |
There was a problem hiding this comment.
The file is missing a trailing newline character at the end. Adding a newline at the end of files is standard practice for POSIX compliance and helps prevent issues with certain tools and version control systems. Consider adding a newline character to maintain consistency with standard file formatting conventions.
Spotted by Diamond
Is this helpful? React 👍 or 👎 to let us know.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
This PR adds support for image token counting and cost tracking across OpenInference semantic conventions.
Changes Made
New Semantic Conventions:
llm.token_count.prompt_details.image- Number of image tokens in the promptllm.token_count.completion_details.image- Number of image tokens in the completionllm.cost.prompt_details.image- Cost of image tokens in the prompt (USD)llm.cost.completion_details.image- Cost of image tokens in the completion (USD)resolves #1780
Summary by Sourcery
Add image-specific token counting and cost tracking to OpenInference semantic conventions across Python and TypeScript implementations.
New Features:
Documentation: