[NA] [BE][FE] chore: sync provider model definitions - #7941
Open
CometActions wants to merge 1 commit into
Open
Conversation
github-actions
Bot
added
java
Contributor
⏱️ pre-commit per-hook timing
⏭️ 40 skipped (no matching files changed)
|
![baz-reviewer[bot]](https://avatars.githubusercontent.com/in/933528?s=60&v=4){kind=small}
Comment on lines
+1536
to
1540
| - id: "stealth/ox-alpha" | ||
| label: "stealth/ox-alpha" | ||
| - id: "stepfun-ai/step3" | ||
| label: "stepfun-ai/step3" | ||
| - id: "stepfun/step-3.5-flash" |
Contributor
There was a problem hiding this comment.
Structured-capable judges use wrong strategy
The newly selectable records omit structuredOutput and reasoning, so LlmModelDefinition defaults both to false, causing LlmProviderFactoryImpl.getStructuredOutputStrategy to select InstructionStrategy for supported models and isReasoningModel to misclassify Ox Alpha. Should we emit the source capability flags or exclude unsupported combinations instead?
Want Baz to fix this for you? Activate Fixer
Other fix methods
Prompt for AI Agents
Before applying, verify this suggestion against the current code. In
`apps/opik-backend/src/main/resources/llm-models-default.yaml` around lines 1536-1540,
update the newly added model definitions and adjacent Tencent entries so their
`structuredOutput` and `reasoning` flags reflect the authoritative OpenRouter
capabilities instead of relying on false-by-omission defaults. Ensure `stealth/ox-alpha`
is marked as reasoning-capable and supports the applicable structured/tool output
strategy, and mark `tencent/hy-mt2-30b-a3b` as structured-output capable; verify the
remaining new model’s capabilities as well. If a model’s supported capability
combination cannot be represented accurately, remove it rather than publishing incorrect
metadata that affects `LlmProviderFactoryImpl.getStructuredOutputStrategy` and the
frontend’s `isReasoningModel` logic.
Comment on lines
+1550
to
+1553
| - id: "tencent/hy-mt2-1.8b" | ||
| label: "tencent/hy-mt2-1.8b" | ||
| - id: "tencent/hy-mt2-30b-a3b" | ||
| label: "tencent/hy-mt2-30b-a3b" |
Contributor
There was a problem hiding this comment.
Tencent usage is silently free
The sync exposes both paid Tencent models as selectable OpenRouter records even though tencent/hy-mt2-1.8b and tencent/hy-mt2-30b-a3b lack entries in model_prices_and_context_window.json or model_prices_overrides.json, so CostService returns ModelPrice.empty() when its openrouter lookup and tencent prefix fallback fail, leaving spans and BudgetGuard with zero cost — should we add authoritative price rows/aliases before exposing them or reject/flag them as unpriced during sync?
Want Baz to fix this for you? Activate Fixer
Other fix methods
Prompt for AI Agents
Before applying, verify this suggestion against the current code. In
apps/opik-backend/src/main/resources/llm-models-default.yaml around lines 1550-1553,
update the model-sync configuration for `tencent/hy-mt2-1.8b` and
`tencent/hy-mt2-30b-a3b`. Ensure each model has authoritative entries or aliases in the
pricing data consumed by `CostService` before exposing it; otherwise, change the sync
validation to reject or flag these unpriced models so zero-cost usage cannot bypass
spans and `BudgetGuard` limits.
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.
Details
Automated sync of LLM provider model definitions from source APIs and prices JSON.
Sync summary:
Change checklist
Issues
AI-WATERMARK
AI-WATERMARK: yes
sync_provider_models.yml)Testing
Documentation
N/A