feat(providers): add Azure OpenAI provider#219
Open
nagarjunr wants to merge 1 commit intorohitg00:mainfrom
Open
feat(providers): add Azure OpenAI provider#219nagarjunr wants to merge 1 commit intorohitg00:mainfrom
nagarjunr wants to merge 1 commit intorohitg00:mainfrom
Conversation
|
Someone is attempting to deploy a commit to the rohitg00's projects Team on Vercel. A member of the Team first needs to authorize it. |
📝 WalkthroughWalkthroughAdds Azure OpenAI provider support to the system. Updates configuration detection to recognize Azure OpenAI environment variables, implements a new Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
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. Review rate limit: 6/8 reviews remaining, refill in 11 minutes and 27 seconds.Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@src/config.ts`:
- Around line 90-101: The fallback provider list is filtering out "azure-openai"
because VALID_PROVIDERS doesn't include it; update VALID_PROVIDERS to include
"azure-openai" so loadFallbackConfig will honor
FALLBACK_PROVIDERS="azure-openai". Locate the VALID_PROVIDERS constant and add
the string "azure-openai" (and ensure any related enum/array used by
loadFallbackConfig and detectProvider is updated consistently) so that
loadFallbackConfig and detectProvider treat Azure as a valid fallback provider.
In `@src/providers/azure-openai.ts`:
- Around line 38-52: The fetch call that sets response (the POST to url with
headers using this.apiKey and body containing model: this.deploymentName and
max_tokens: this.maxTokens) needs a request timeout to avoid hanging; wrap the
fetch in an AbortController, start a timer (configurable or a new
this.requestTimeout) that calls controller.abort() after the timeout, pass
signal: controller.signal into fetch, and clear the timer after fetch completes;
also ensure the calling method handles the abort/timeout error (AbortError)
appropriately.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: c8f28d4a-c694-410d-9771-0ac2dc18e39b
📒 Files selected for processing (5)
src/config.tssrc/providers/azure-openai.tssrc/providers/index.tssrc/types.tssrc/viewer/index.html
Comment on lines
+90
to
+101
| if ( | ||
| hasRealValue(env["AZURE_OPENAI_API_KEY"]) && | ||
| hasRealValue(env["AZURE_OPENAI_ENDPOINT"]) && | ||
| hasRealValue(env["AZURE_OPENAI_DEPLOYMENT"]) | ||
| ) { | ||
| return { | ||
| provider: "azure-openai", | ||
| model: env["AZURE_OPENAI_DEPLOYMENT"], | ||
| maxTokens, | ||
| baseURL: env["AZURE_OPENAI_ENDPOINT"], | ||
| }; | ||
| } |
There was a problem hiding this comment.
Add azure-openai to fallback allowlist.
detectProvider now supports Azure, but loadFallbackConfig() still filters fallback providers through VALID_PROVIDERS without "azure-openai", so FALLBACK_PROVIDERS=azure-openai is silently dropped.
Suggested fix
const VALID_PROVIDERS = new Set([
"anthropic",
+ "azure-openai",
"gemini",
"openrouter",
"agent-sdk",
"minimax",
]);🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@src/config.ts` around lines 90 - 101, The fallback provider list is filtering
out "azure-openai" because VALID_PROVIDERS doesn't include it; update
VALID_PROVIDERS to include "azure-openai" so loadFallbackConfig will honor
FALLBACK_PROVIDERS="azure-openai". Locate the VALID_PROVIDERS constant and add
the string "azure-openai" (and ensure any related enum/array used by
loadFallbackConfig and detectProvider is updated consistently) so that
loadFallbackConfig and detectProvider treat Azure as a valid fallback provider.
Comment on lines
+38
to
+52
| const response = await fetch(url, { | ||
| method: "POST", | ||
| headers: { | ||
| "Content-Type": "application/json", | ||
| "api-key": this.apiKey, | ||
| }, | ||
| body: JSON.stringify({ | ||
| model: this.deploymentName, | ||
| max_tokens: this.maxTokens, | ||
| messages: [ | ||
| { role: "system", content: systemPrompt }, | ||
| { role: "user", content: userPrompt }, | ||
| ], | ||
| }), | ||
| }); |
There was a problem hiding this comment.
Add a request timeout for Azure API calls.
External calls here can hang indefinitely; this can block compression/summarization paths when Azure stalls.
Suggested fix
export class AzureOpenAIProvider implements MemoryProvider {
name = "azure-openai";
+ private readonly requestTimeoutMs = 30_000;
private apiKey: string;
private endpoint: string;
private deploymentName: string;
private apiVersion: string;
private maxTokens: number;
@@
- const response = await fetch(url, {
- method: "POST",
- headers: {
- "Content-Type": "application/json",
- "api-key": this.apiKey,
- },
- body: JSON.stringify({
- model: this.deploymentName,
- max_tokens: this.maxTokens,
- messages: [
- { role: "system", content: systemPrompt },
- { role: "user", content: userPrompt },
- ],
- }),
- });
+ const controller = new AbortController();
+ const timeout = setTimeout(() => controller.abort(), this.requestTimeoutMs);
+ let response: Response;
+ try {
+ response = await fetch(url, {
+ method: "POST",
+ headers: {
+ "Content-Type": "application/json",
+ "api-key": this.apiKey,
+ },
+ signal: controller.signal,
+ body: JSON.stringify({
+ model: this.deploymentName,
+ max_tokens: this.maxTokens,
+ messages: [
+ { role: "system", content: systemPrompt },
+ { role: "user", content: userPrompt },
+ ],
+ }),
+ });
+ } catch (error) {
+ if (error instanceof Error && error.name === "AbortError") {
+ throw new Error(`azure-openai request timed out after ${this.requestTimeoutMs}ms`);
+ }
+ throw error;
+ } finally {
+ clearTimeout(timeout);
+ }🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@src/providers/azure-openai.ts` around lines 38 - 52, The fetch call that sets
response (the POST to url with headers using this.apiKey and body containing
model: this.deploymentName and max_tokens: this.maxTokens) needs a request
timeout to avoid hanging; wrap the fetch in an AbortController, start a timer
(configurable or a new this.requestTimeout) that calls controller.abort() after
the timeout, pass signal: controller.signal into fetch, and clear the timer
after fetch completes; also ensure the calling method handles the abort/timeout
error (AbortError) appropriately.
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.
Summary
Adds support for Azure OpenAI Service as an LLM provider for compression, summarization, and graph extraction.
Changes
src/providers/azure-openai.ts(new) —AzureOpenAIProviderclass. Constructs the Azure-style URL (/openai/deployments/{name}/chat/completions?api-version=...), usesapi-keyheader instead ofAuthorization: Bearer, otherwise follows the same OpenAI-compatible request/response shape as the existingOpenRouterProvider.src/types.ts— adds"azure-openai"to theProviderTypeunion.src/config.ts— detects all three required Azure env vars and returnsprovider: "azure-openai"config; updatesdetectLlmProviderKind()to return"llm"when Azure vars are set; updates the "no key found" error message.src/providers/index.ts— wires thecase "azure-openai"branch intocreateBaseProvider.src/viewer/index.html— updates the "No LLM provider key set" flag banner to show both Anthropic and Azure setup instructions.Usage
Add to
~/.agentmemory/.env:Then restart:
npx @agentmemory/agentmemoryTest plan
providershows asazure-openaiin health endpoint responseAZURE_OPENAI_ENDPOINTorAZURE_OPENAI_DEPLOYMENTfalls through to noop (no partial config accepted)Summary by CodeRabbit
New Features
Documentation