feat:Add 200 response to prediction POST endpoints; fix 'endpoint' typos #124
Conversation
WalkthroughAdded HTTP 200 responses with schemas_prediction_response to two POST prediction creation endpoints to allow synchronous final results, alongside existing 201/202 asynchronous responses. Corrected “endpiont” to “endpoint” in several prediction-related descriptions. No other structural or signature changes. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
participant C as Client
participant A as API (POST /predictions)
participant W as Prediction Worker
rect rgb(235, 245, 255)
note over C,A: New synchronous path (200 OK)
C->>A: Create prediction (input)
A->>W: Dispatch job
W-->>A: Final output ready
A-->>C: 200 OK with schemas_prediction_response
end
opt Existing asynchronous paths (201/202)
C->>A: Create prediction (input)
A-->>C: 201/202 Accepted + status URL
loop Polling/Webhook
C->>A: GET status (poll) / A->>C: In-progress
A->>W: Check status
end
A-->>C: Final result when complete
end
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Poem
✨ Finishing Touches🧪 Generate unit tests
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. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR/Issue comments)Type Other keywords and placeholders
CodeRabbit Configuration File (
|
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
coderabbitai
bot
changed the title
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (3)
src/libs/Replicate/openapi.yaml (3)
850-872: Add 200 response for POST /predictions to match models endpoint and SDKs.Per the PR intent and for parity with /models/{owner}/{name}/predictions, POST /predictions should also document a 200 “Success” response carrying schemas_prediction_response for cases where the model completes within the Prefer: wait window. Currently only 201/202 are defined here.
Apply this diff to add the missing 200 response:
responses: + '200': + description: Success + content: + application/json: + schema: + $ref: '#/components/schemas/schemas_prediction_response' '201': description: 'Prediction has been created. If the `Prefer: wait` header is provided it will contain the final output.' content: application/json: schema: $ref: '#/components/schemas/schemas_prediction_response' '202': description: Prediction has been created but does not yet have all outputs content: application/json: schema: $ref: '#/components/schemas/schemas_prediction_response'
1278-1280: Doc bug: “url” should be “urls” (property name).The deprecation note says the stream link appears under the prediction’s url property; the schema defines urls (plural). Fix in both request schema descriptions to avoid confusion.
Apply this diff in both locations:
-This field is no longer needed as the returned prediction will always have a `stream` entry in its `url` property if the model supports streaming. +This field is no longer needed as the returned prediction will always have a `stream` entry in its `urls` property if the model supports streaming.Also applies to: 1505-1507
1549-1555: Regex allows wait=61..99; cap at 60.The current pattern permits 10–99 (including 61–99). Tighten it to 1–60 as documented.
Apply this diff:
- pattern: '^wait(=([1-9]|[1-9][0-9]|60))?$' + pattern: '^wait(=([1-9]|[1-5][0-9]|60))?$'
🧹 Nitpick comments (3)
src/libs/Replicate/openapi.yaml (3)
656-662: Good addition: 200 response enables synchronous success path.The new 200 response for models.predictions.create looks correct and uses the same schemas_prediction_response as 201/202. Consider keeping response-code ordering consistent (200, 201, 202) across operations for readability.
Apply this diff to reorder (optional):
responses: - '201': + '200': + description: Success + content: + application/json: + schema: + $ref: '#/components/schemas/schemas_prediction_response' + '201': description: 'Prediction has been created. If the `Prefer: wait` header is provided it will contain the final output.' content: application/json: schema: $ref: '#/components/schemas/schemas_prediction_response' '202': description: Prediction has been created but does not yet have all outputs content: application/json: schema: $ref: '#/components/schemas/schemas_prediction_response' - '200': - description: Successful - content: - application/json: - schema: - $ref: '#/components/schemas/schemas_prediction_response'
246-279: Optional: consider documenting a 200 success path here too for symmetry.If deployments-backed predictions can also complete within the Prefer: wait window, consider adding a 200 response like the models and predictions endpoints for consistency across SDKs and codegen.
Proposed diff (optional):
responses: + '200': + description: Success + content: + application/json: + schema: + $ref: '#/components/schemas/schemas_prediction_response' '201': description: 'Prediction has been created. If the `Prefer: wait` header is provided it will contain the final output.' content: application/json: schema: $ref: '#/components/schemas/schemas_prediction_response' '202': description: Prediction has been created but does not yet have all outputs content: application/json: schema: $ref: '#/components/schemas/schemas_prediction_response'
657-657: Unify response descriptions (“Success” vs “Successful”).You use both “Success” and “Successful”. Choose one (e.g., “Success”) for consistency across the spec. Not functionally critical, but it improves generated docs.
Example change:
- description: Successful + description: SuccessAlso applies to: 885-886, 191-191, 284-286, 462-464, 484-487, 709-713, 766-771, 916-921, 978-982
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
⛔ Files ignored due to path filters (6)
src/libs/Replicate/Generated/Replicate.IReplicateApi.DeploymentsPredictionsCreate.g.csis excluded by!**/generated/**src/libs/Replicate/Generated/Replicate.IReplicateApi.ModelsPredictionsCreate.g.csis excluded by!**/generated/**src/libs/Replicate/Generated/Replicate.IReplicateApi.PredictionsCreate.g.csis excluded by!**/generated/**src/libs/Replicate/Generated/Replicate.ReplicateApi.DeploymentsPredictionsCreate.g.csis excluded by!**/generated/**src/libs/Replicate/Generated/Replicate.ReplicateApi.ModelsPredictionsCreate.g.csis excluded by!**/generated/**src/libs/Replicate/Generated/Replicate.ReplicateApi.PredictionsCreate.g.csis excluded by!**/generated/**
📒 Files selected for processing (1)
src/libs/Replicate/openapi.yaml(3 hunks)
| post: | ||
| summary: Create a prediction using an official model | ||
| description: "Create a prediction using an [official model](https://replicate.com/changelog/2025-01-29-official-models).\n\nIf you're _not_ running an official model, use the [`predictions.create`](#predictions.create) operation instead.\n\nExample cURL request:\n\n```console\ncurl -s -X POST -H 'Prefer: wait' \\\n -d '{\"input\": {\"prompt\": \"Write a short poem about the weather.\"}}' \\\n -H \"Authorization: Bearer $REPLICATE_API_TOKEN\" \\\n -H 'Content-Type: application/json' \\\n https://api.replicate.com/v1/models/meta/meta-llama-3-70b-instruct/predictions\n```\n\nThe request will wait up to 60 seconds for the model to run. If this time is exceeded the prediction will be returned in a `\"starting\"` state and need to be retrieved using the `predictions.get` endpiont.\n\nFor a complete overview of the `deployments.predictions.create` API check out our documentation on [creating a prediction](https://replicate.com/docs/topics/predictions/create-a-prediction) which covers a variety of use cases.\n" | ||
| description: "Create a prediction using an [official model](https://replicate.com/changelog/2025-01-29-official-models).\n\nIf you're _not_ running an official model, use the [`predictions.create`](#predictions.create) operation instead.\n\nExample cURL request:\n\n```console\ncurl -s -X POST -H 'Prefer: wait' \\\n -d '{\"input\": {\"prompt\": \"Write a short poem about the weather.\"}}' \\\n -H \"Authorization: Bearer $REPLICATE_API_TOKEN\" \\\n -H 'Content-Type: application/json' \\\n https://api.replicate.com/v1/models/meta/meta-llama-3-70b-instruct/predictions\n```\n\nThe request will wait up to 60 seconds for the model to run. If this time is exceeded the prediction will be returned in a `\"starting\"` state and need to be retrieved using the `predictions.get` endpoint.\n\nFor a complete overview of the `deployments.predictions.create` API check out our documentation on [creating a prediction](https://replicate.com/docs/topics/predictions/create-a-prediction) which covers a variety of use cases.\n" |
There was a problem hiding this comment.
Fix incorrect cross-reference: should not point to deployments.predictions.create.
This is the models.predictions.create operation; the final sentence references deployments.predictions.create. Replace with models.predictions.create (or with predictions.create if you want a generic reference).
Apply this diff to the description text:
-For a complete overview of the `deployments.predictions.create` API check out our documentation on [creating a prediction](https://replicate.com/docs/topics/predictions/create-a-prediction) which covers a variety of use cases.
+For a complete overview of the `models.predictions.create` API, see our documentation on [creating a prediction](https://replicate.com/docs/topics/predictions/create-a-prediction), which covers a variety of use cases.📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| description: "Create a prediction using an [official model](https://replicate.com/changelog/2025-01-29-official-models).\n\nIf you're _not_ running an official model, use the [`predictions.create`](#predictions.create) operation instead.\n\nExample cURL request:\n\n```console\ncurl -s -X POST -H 'Prefer: wait' \\\n -d '{\"input\": {\"prompt\": \"Write a short poem about the weather.\"}}' \\\n -H \"Authorization: Bearer $REPLICATE_API_TOKEN\" \\\n -H 'Content-Type: application/json' \\\n https://api.replicate.com/v1/models/meta/meta-llama-3-70b-instruct/predictions\n```\n\nThe request will wait up to 60 seconds for the model to run. If this time is exceeded the prediction will be returned in a `\"starting\"` state and need to be retrieved using the `predictions.get` endpoint.\n\nFor a complete overview of the `deployments.predictions.create` API check out our documentation on [creating a prediction](https://replicate.com/docs/topics/predictions/create-a-prediction) which covers a variety of use cases.\n" | |
| description: "Create a prediction using an [official model](https://replicate.com/changelog/2025-01-29-official-models).\n\nIf you're _not_ running an official model, use the [`predictions.create`](#predictions.create) operation instead.\n\nExample cURL request:\n\n |
🤖 Prompt for AI Agents
In src/libs/Replicate/openapi.yaml around line 622, the description incorrectly
references deployments.predictions.create; update that final sentence to
reference models.predictions.create (or predictions.create for a generic link)
so it points to the correct operation for this models.predictions.create
endpoint, and ensure the wording matches the rest of the description.
Summary by CodeRabbit
New Features
Documentation