Skip to content

feat:Add descriptions to /finetuning endpoints and support "thinking" chat type #231

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jul 18, 2025

Conversation

HavenDV
Copy link
Contributor

@HavenDV HavenDV commented Jul 18, 2025

Summary by CodeRabbit

  • New Features

    • Chat messages now support a new "thinking" content type in addition to "text".
  • Documentation

    • Added detailed descriptions to several fine-tuning API endpoints to improve clarity and understanding of their behavior and usage.

Copy link

coderabbitai bot commented Jul 18, 2025

Walkthrough

This update enhances the OpenAPI specification by adding detailed descriptions to several /finetuning endpoints and extends the chat content schema to support a new "thinking" content type. These changes improve API documentation clarity and expand the range of valid chat message content types.

Changes

File Change Summary
src/libs/Cohere/openapi.yaml Added description fields to multiple /finetuning endpoints; extended chat content schemas to support a new "thinking" content type.

Poem

🐇
In the land of endpoints, clarity blooms,
With descriptions added, confusion resumes!
Now chat can be "thinking"—what a neat trick,
The API grows smarter, and rabbits hop quick.
With specs now refined, let’s hop to deploy,
For thoughtful exchanges, and documentation joy!

✨ Finishing Touches
🧪 Generate unit tests
  • Create PR with unit tests
  • Post copyable unit tests in a comment
  • Commit unit tests in branch bot/update-openapi_202507182122

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Explain this complex logic.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai explain this code block.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and explain its main purpose.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate docstrings to generate docstrings for this PR.
  • @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
  • @coderabbitai auto-generate unit tests to generate unit tests for this PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

@HavenDV HavenDV enabled auto-merge (squash) July 18, 2025 21:23
@HavenDV HavenDV merged commit 905a2fd into main Jul 18, 2025
3 of 4 checks passed
@HavenDV HavenDV deleted the bot/update-openapi_202507182122 branch July 18, 2025 21:24
@coderabbitai coderabbitai bot changed the title feat:@coderabbitai feat:Add descriptions to /finetuning endpoints and support "thinking" chat type Jul 18, 2025
Copy link

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 1

♻️ Duplicate comments (1)
src/libs/Cohere/openapi.yaml (1)

12597-12601: Enum value without schema definition
This enum now references thinking, but until the missing schema above is added clients will fail to generate types. Fixing the previous comment will resolve this too.

🧹 Nitpick comments (6)
src/libs/Cohere/openapi.yaml (6)

5684-5688: Consider mentioning pagination & response token details
The new description is helpful, but users will likely look for details on how to paginate ( page_size, next_page_token, max limits ). A single sentence clarifying that the response contains next_page_token (or whatever the spec actually returns) would remove ambiguity.


5816-5818: Describe async behaviour & expected response code
The endpoint kicks off a long-running training job, so most providers return 202 Accepted with a polling location / event stream. If that is the case here, call it out explicitly in the description (and in the responses section).


5905-5907: Use YAML block scalars for multi-line text
The embedded \n escapes are valid, but they hurt readability and make diffs noisy. A folded or literal block is clearer:

-      description: "Returns a list of events that occurred during the life-cycle of the fine-tuned model.\nThe events are ordered by creation time, with the most recent event first.\nThe list can be paginated using `page_size` and `page_token` parameters."
+      description: |
+        Returns a list of events that occurred during the life-cycle of the fine-tuned model.
+        The events are ordered by creation time, with the most recent event first.
+        The list can be paginated using `page_size` and `page_token` parameters.

Apply the same style to the other multiline descriptions for consistency.


6018-6020: Same block-scalar readability comment as above
The triple-escaped string would be clearer using | or > style.


6129-6131: Minor wording tweak
“will be removed from the system” could be interpreted as immediate physical deletion. If a grace period or soft-delete exists, spell it out to avoid surprises.


6315-6317: Clarify what can be updated
If only the name and a subset of settings are mutable, enumerate them here to prevent over-expectation.

📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between bee2d5f and b4d7e8b.

⛔ Files ignored due to path filters (16)
  • src/libs/Cohere/Generated/Cohere.FinetuningClient.CreateFinetunedModel.g.cs is excluded by !**/generated/**
  • src/libs/Cohere/Generated/Cohere.FinetuningClient.DeleteFinetunedModel.g.cs is excluded by !**/generated/**
  • src/libs/Cohere/Generated/Cohere.FinetuningClient.GetFinetunedModel.g.cs is excluded by !**/generated/**
  • src/libs/Cohere/Generated/Cohere.FinetuningClient.ListEvents.g.cs is excluded by !**/generated/**
  • src/libs/Cohere/Generated/Cohere.FinetuningClient.ListFinetunedModels.g.cs is excluded by !**/generated/**
  • src/libs/Cohere/Generated/Cohere.FinetuningClient.ListTrainingStepMetrics.g.cs is excluded by !**/generated/**
  • src/libs/Cohere/Generated/Cohere.FinetuningClient.UpdateFinetunedModel.g.cs is excluded by !**/generated/**
  • src/libs/Cohere/Generated/Cohere.IFinetuningClient.CreateFinetunedModel.g.cs is excluded by !**/generated/**
  • src/libs/Cohere/Generated/Cohere.IFinetuningClient.DeleteFinetunedModel.g.cs is excluded by !**/generated/**
  • src/libs/Cohere/Generated/Cohere.IFinetuningClient.GetFinetunedModel.g.cs is excluded by !**/generated/**
  • src/libs/Cohere/Generated/Cohere.IFinetuningClient.ListEvents.g.cs is excluded by !**/generated/**
  • src/libs/Cohere/Generated/Cohere.IFinetuningClient.ListFinetunedModels.g.cs is excluded by !**/generated/**
  • src/libs/Cohere/Generated/Cohere.IFinetuningClient.ListTrainingStepMetrics.g.cs is excluded by !**/generated/**
  • src/libs/Cohere/Generated/Cohere.IFinetuningClient.UpdateFinetunedModel.g.cs is excluded by !**/generated/**
  • src/libs/Cohere/Generated/Cohere.Models.AssistantMessageResponseContentItemDiscriminatorType.g.cs is excluded by !**/generated/**
  • src/libs/Cohere/Generated/Cohere.Models.ChatContentStartEventVariant2DeltaMessageContentType.g.cs is excluded by !**/generated/**
📒 Files selected for processing (1)
  • src/libs/Cohere/openapi.yaml (9 hunks)
🔇 Additional comments (1)
src/libs/Cohere/openapi.yaml (1)

6210-6212: LGTM – concise and clear
No issues spotted.

Comment on lines 12364 to +12367
propertyName: type
mapping:
text: '#/components/schemas/ChatTextContent'
thinking: '#/components/schemas/ChatThinkingContent'
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue

ChatThinkingContent schema is missing – spec will break
The discriminator now maps thinking to #/components/schemas/ChatThinkingContent, but that schema isn’t defined anywhere in the file. This makes the OpenAPI document invalid.

+    ChatThinkingContent:
+      type: object
+      description: Content representing the assistant’s chain-of-thought. **Not returned to the end user** unless explicitly requested.
+      properties:
+        type:
+          type: string
+          enum: [thinking]
+        text:
+          type: string
+      required: [type, text]

Add a proper schema (and possibly mark it readOnly: true or behind a feature flag) before merging.

Committable suggestion skipped: line range outside the PR's diff.

🤖 Prompt for AI Agents
In src/libs/Cohere/openapi.yaml around lines 12364 to 12367, the discriminator
mapping references a ChatThinkingContent schema that is not defined, causing the
OpenAPI spec to be invalid. Define the ChatThinkingContent schema in the
components/schemas section with appropriate properties, and consider marking it
as readOnly or gating it behind a feature flag as suggested. This will ensure
the spec is valid and the discriminator mapping works correctly.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant