paragraph counts. restore unwrapped and other fixes #10
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -68,3 +68,6 @@ fastlane/test_output | |
|
|
||
| claude-agent-sdk-demos | ||
| xcuserdata | ||
|
|
||
| apps/pipeline/app.log | ||
| .tmp | ||
| Original file line number | Diff line number | Diff line change | ||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| @@ -0,0 +1,50 @@ | ||||||||||||||||||||||
| import OpenAI from "openai"; | ||||||||||||||||||||||
| import { type z } from "zod"; | ||||||||||||||||||||||
|
|
||||||||||||||||||||||
| const endpoint = "https://bookgenius.services.ai.azure.com/openai/v1/"; | ||||||||||||||||||||||
| const model = "grok-4-fast-reasoning"; | ||||||||||||||||||||||
| const api_key = process.env.AZURE_GROK_KEY; | ||||||||||||||||||||||
|
|
||||||||||||||||||||||
| const client = new OpenAI({ baseURL: endpoint, apiKey: api_key }); | ||||||||||||||||||||||
|
Comment on lines
+6
to
+8
Contributor
There was a problem hiding this comment. The const api_key = process.env.AZURE_GROK_KEY;
if (!api_key) {
throw new Error("Missing environment variable: AZURE_GROK_KEY");
}
const client = new OpenAI({ baseURL: endpoint, apiKey: api_key });
Comment on lines
+6
to
+8
Contributor
There was a problem hiding this comment. Missing API key validation before client initialization. If 🛡️ Proposed fix const api_key = process.env.AZURE_GROK_KEY;
+
+if (!api_key) {
+ throw new Error("Missing AZURE_GROK_KEY environment variable");
+}
const client = new OpenAI({ baseURL: endpoint, apiKey: api_key });📝 Committable suggestion
Suggested change
🤖 Prompt for AI Agents |
||||||||||||||||||||||
|
|
||||||||||||||||||||||
| export const callGrokAzure = async (prompt: string) => { | ||||||||||||||||||||||
| const completion = await client.chat.completions.create({ | ||||||||||||||||||||||
| messages: [{ role: "user", content: prompt }], | ||||||||||||||||||||||
| model, | ||||||||||||||||||||||
| }); | ||||||||||||||||||||||
|
|
||||||||||||||||||||||
| return completion.choices[0].message.content; | ||||||||||||||||||||||
| }; | ||||||||||||||||||||||
|
Comment on lines
+10
to
+17
Contributor
There was a problem hiding this comment. Return type may be null; consider handling.
🛡️ Proposed fix to handle null content-export const callGrokAzure = async (prompt: string) => {
+export const callGrokAzure = async (prompt: string): Promise<string> => {
const completion = await client.chat.completions.create({
messages: [{ role: "user", content: prompt }],
model,
});
- return completion.choices[0].message.content;
+ const content = completion.choices[0].message.content;
+ if (content === null) {
+ throw new Error("Model returned null content");
+ }
+ return content;
};🤖 Prompt for AI Agents |
||||||||||||||||||||||
|
|
||||||||||||||||||||||
| export const callGrokAzureWithSchema = async <T>(prompt: string, zodSchema: z.ZodSchema<T>) => { | ||||||||||||||||||||||
| const completion = await client.chat.completions.create({ | ||||||||||||||||||||||
| messages: [{ role: "user", content: prompt }], | ||||||||||||||||||||||
| model, | ||||||||||||||||||||||
| response_format: { | ||||||||||||||||||||||
| type: "json_schema", | ||||||||||||||||||||||
| json_schema: { | ||||||||||||||||||||||
| name: "response", | ||||||||||||||||||||||
| strict: true, | ||||||||||||||||||||||
| // @ts-expect-error(zod typing) | ||||||||||||||||||||||
| schema: zodSchema.shape, | ||||||||||||||||||||||
|
Comment on lines
+28
to
+29
Contributor
There was a problem hiding this comment. Using Consider using a library like import { zodToJsonSchema } from 'zod-to-json-schema';
// ... inside callGrokAzureWithSchema
const jsonSchema = zodToJsonSchema(zodSchema);
const completion = await client.chat.completions.create({
// ...
response_format: {
type: "json_schema",
json_schema: {
name: "response",
strict: true,
schema: jsonSchema,
},
},
});This will require adding |
||||||||||||||||||||||
| }, | ||||||||||||||||||||||
| }, | ||||||||||||||||||||||
| }); | ||||||||||||||||||||||
| let result: T; | ||||||||||||||||||||||
| try { | ||||||||||||||||||||||
| result = JSON.parse(completion.choices[0].message.content as string) as T; | ||||||||||||||||||||||
|
Contributor
There was a problem hiding this comment. The API response const content = completion.choices[0].message.content;
if (content === null) {
throw new Error("Received null content from the model.");
}
result = JSON.parse(content) as T; |
||||||||||||||||||||||
| } catch (e) { | ||||||||||||||||||||||
| console.error("Error parsing JSON", e); | ||||||||||||||||||||||
| throw e; | ||||||||||||||||||||||
| } | ||||||||||||||||||||||
| return result; | ||||||||||||||||||||||
| }; | ||||||||||||||||||||||
|
|
||||||||||||||||||||||
| // if (require.main === module) { | ||||||||||||||||||||||
| // const schema = z.object({ name: z.string(), age: z.number() }); | ||||||||||||||||||||||
| // const prompt = "What is my name? My name is John Doe and I'm 30"; | ||||||||||||||||||||||
| // const result = await callGrokAzureWithSchema(prompt, schema); | ||||||||||||||||||||||
| // console.log(result); | ||||||||||||||||||||||
| // console.log(result.name); | ||||||||||||||||||||||
| // console.log(result.age); | ||||||||||||||||||||||
| // } | ||||||||||||||||||||||
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -22,7 +22,6 @@ export const callO3WithSchema = async <T>( | |
| model: openai(model), | ||
| schema: zodSchema, | ||
| prompt, | ||
| experimental_telemetry: { isEnabled: true, recordInputs: true, recordOutputs: true }, | ||
| }); | ||
|
|
||
|
|
@@ -36,7 +35,7 @@ export const callGpt5 = async <T = string>( | |
| ) => { | ||
| const chatCompletion = await client.chat.completions.create({ | ||
| messages: [{ role: "user", content: prompt }], | ||
| model: "gpt-5.2", | ||
| reasoning_effort: "medium", | ||
|
Comment on lines
36
to
39
Contributor
There was a problem hiding this comment. 🧩 Analysis chain🌐 Web query:
💡 Result: As of February 5, 2026, GPT‑5.2 is available to all developers in the OpenAI API, including the Chat Completions API.
Citations:
🏁 Script executed: cat -n apps/pipeline/src/callO3.tsRepository: TheBrainFamily/BookgeniusPlayer Length of output: 1671 Remove the review concern: The model is officially supported for all developers as of February 2026, including the direct OpenAI SDK path used here. However, the 🤖 Prompt for AI Agents |
||
| }); | ||
| return chatCompletion.choices[0].message.content as string; | ||
|
|
||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🧩 Analysis chain
🏁 Script executed:
Repository: TheBrainFamily/BookgeniusPlayer
Length of output: 6042
🌐 Web query:
@ai-sdk v3 and ai v6 migration guide compatibility peer dependencies💡 Result:
Compatibility (AI SDK v6 +
@ai-sdk/*v3)For AI SDK 6, Vercel’s migration guide says to align package majors like this:
ai@^6+@ai-sdk/*@^3, plus@ai-sdk/provider@^3and@ai-sdk/provider-utils@^4. [1]That effectively means
@ai-sdk/*v3 is the “provider/UI generation” set that matchesaiv6 (don’t mix with older major lines unless a package explicitly supports multiple majors). [1]Peer dependencies (the ones that commonly cause install conflicts)
aiv6ai@6.xdeclares a peer dependency onzod:zod: ^3.25.76 || ^4.1.8[2]and requires Node >= 18. [2]
@ai-sdk/reactv3 (example@ai-sdk/*v3 package)@ai-sdk/react@3.xdeclares a peer dependency onreact:react: ^18 || ~19.0.1 || ~19.1.2 || ^19.2.1[3](It brings
ai@6.xas a regular dependency in its package metadata.) [3]Providers (
@ai-sdk/openai, etc.)The AI SDK 6 migration guide indicates providers should be on the
@ai-sdk/*@^3line as well when upgrading to v6. [1]If you need “compatibility across majors” (peer dep ranges)
Some third-party integrations explicitly broaden their peer dependency ranges to support multiple
aimajors (example: Trigger.dev acceptingai@^4 || ^5 || ^6). [4]Sources:
[1] AI SDK “Migrate AI SDK 5.x to 6.0” (package version alignment) (ai-sdk.dev)
[2]
ai@6.xpackage.json (peerDependencies, Node engine) (app.unpkg.com)[3]
@ai-sdk/react@3.xpackage.json (peerDependencies) (app.unpkg.com)[4] Example of broadened peer dependency compatibility across
aimajors (trigger.dev)Citations:
🌐 Web query:
@ai-sdk/anthropic@ai-sdk/openaiv3.0 ai v6.0 breaking changes requirements💡 Result:
Version alignment / requirements (AI SDK v6 + provider v3)
When upgrading to AI SDK
aiv6.x, you should upgrade the provider packages to the matching major versions:@ai-sdk/*→^3.0.0, plus the shared internals@ai-sdk/provider→^3.0.0and@ai-sdk/provider-utils→^4.0.0. The core package becomesai→^6.0.0. [1]The repo’s install requirements call out Node.js 18+. [2]
AI SDK (
ai) v6.0 breaking changes (high impact)Experimental_Agentreplaced byToolLoopAgent;systemrenamed toinstructions; defaultstopWhenchanged (from 1 step to 20). [1]CoreMessageremoved;convertToCoreMessagesreplaced byconvertToModelMessages, which is now async (requiresawait). [1]generateObject/streamObjectare deprecated in v6 (planned for removal later); prefergenerateText/streamTextwith the newoutputsetting. [1]@ai-sdk/openaiv3.0 breaking changes (notable behavior change)strictJsonSchemadefaults totruefor JSON outputs and tool calls (stricter schema validation; you may need to adjust schemas like usingnullinstead ofundefined, or explicitly disable strict mode). [1]@ai-sdk/anthropicv3.0 breaking changes (notable new option)structuredOutputModeto control how structured outputs are produced ('outputFormat' | 'jsonTool' | 'auto'), reflecting Anthropic’s native structured outputs support on newer models. [1]Sources:
[1] AI SDK “Migrate AI SDK 5.x to 6.0” (package versions + breaking changes, incl. OpenAI/Anthropic sections) https://ai-sdk.dev/docs/migration-guides/migration-guide-6-0
[2] vercel/ai GitHub README (Node.js requirement) https://github.com/vercel/ai
Update
@ai-sdk/cerebrasto v3.x and audit migration impact.The peer dependencies are aligned (zod@^4.1.8, react@^19.2.0), but
@ai-sdk/cerebras@^2.0.30should be@ai-sdk/cerebras@^3.xto match theai@^6ecosystem per Vercel's migration guide.Also review code for ai v6 breaking changes:
generateObjectandstreamObjectare deprecated; migrate togenerateText/streamTextwith theoutputsettingconvertToCoreMessagesreplaced byconvertToModelMessages(now async, requiresawait)Experimental_Agentreplaced byToolLoopAgent;systemrenamed toinstructions@ai-sdk/openai@3.0:strictJsonSchemadefaults totrue(may require schema adjustments)🤖 Prompt for AI Agents