Repository navigation
Add a Model tab to the task-instance page for common.ai - #74334
Merged
Merged
Conversation
Member
Author
1 task done
kaxil
reviewed
Oct 7, 2026
Member
Author
pierrejeambrun
marked this pull request as ready for review
October 7, 2026 13:11
pierrejeambrun
requested review from
Lee-W,
amoghrajesh,
ashb,
bugraoz93,
gopidesupavan,
jason810496,
jscheffl and
potiuk
as code owners
October 7, 2026 13:11
kaxil
reviewed
Oct 7, 2026
kaxil
approved these changes
Oct 7, 2026
pierrejeambrun
force-pushed
the
common-ai-model-name-ui
branch
2 times, most recently
from
October 8, 2026 15:21
0629768 to
9ac59d0
Compare
Reading which model answered and what the run cost currently means pulling raw XComs; the tab shows the model name and usage XComs as a readable table for LLMOperator and AgentOperator runs.
pierrejeambrun
force-pushed
the
common-ai-model-name-ui
branch
from
October 13, 2026 09:00
9ac59d0 to
f879581
Compare
The project-structure check expects the tests for _plugin_urls.py in test__plugin_urls.py.
common.ai now registers a second entry-point plugin, so the plugins manager loads eight provider plugins.
1 task done
1 task done
This was referenced Oct 29, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.



Follow-up to #74272 (merged): this PR surfaces the model name (
__AIRFLOW__COMMON_AI_MODEL_NAME__) andusageXComs as a first-class "AI Model" tab on the task-instance page, instead of leaving them only reachable through the raw XCom tab.The tab reads the XComs directly from the core REST API (same-origin, cookie auth) rather than adding a new backend endpoint, and is scoped via
applies_toto the operators that actually publish this data (LLMOperator,AgentOperator, and their@task.llm/@task.agentTaskFlow forms) so it doesn't show up as a dead end on unrelated tasks.LLMBranchOperator,LLMSQLQueryOperator,LLMSchemaCompareOperator, andLLMFileAnalysisOperatordon't publish the model name yet and aren't in scope here either -- that's upcoming work.Screenshots below are from a real
AgentOperatorrun (an AIP-tracking agent with tool calls against Confluence/GitHub) rather than a synthetic example, to show real token/cost numbers.Model + full token usage, cost (33 tool calls, ~195k tokens):
Cost tooltip (best-effort pricing explanation):
Empty state on a plain
@taskin the same Dag run -- note the tab isn't even in the nav list (applies_to scoping), this is a direct link:Also fixes a latent bug in
update_providers_dependencies.py: it sorted each provider's plugin list by comparing the raw dicts directly, which only worked because no provider had more than one plugin before this one.Was generative AI tooling used to co-author this PR?
Generated-by: Claude Code (Opus 4.7) following the guidelines