xiaohei/azure-gpt-cursor
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Allow disabling reasoning summaries

Browse Source
This commit is contained in:
gabrii
2025-09-15 10:49:29 +02:00
parent dab0265142
commit af9a30f9bc
2 changed files with 19 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+14 -14
View File
@@ -37,27 +37,27 @@ If you prefer to deploy the service (for example, to allow multiple members of y
### 1. Service configuration
Make a copy of the file `.env.example` as `.env` and update the following flags:
Make a copy of the file `.env.example` as `.env` and update the following flags as needed:
| Flag | Description | Default |
| ------------------ | ---------------------------------------------------------------------------------------------------- | ----------- |
| `AZURE_BASE_URL` | Your Azure OpenAI endpoint base URL (no trailing slash), e.g. `https://<resource>.openai.azure.com`. | required |
| `AZURE_API_KEY` | Azure OpenAI API key. | required |
| `AZURE_DEPLOYMENT` | Name of the Azure model deployment to use. | `gpt-5` |
| `SERVICE_API_KEY` | Arbitrary API key to protect your service. Set it to a random string. | `change-me` |
| Flag | Description | Default |
| --------------------- | ------------------------------------------------------------------------------------------------------------------------------ | ----------- |
| `AZURE_BASE_URL` | Your Azure OpenAI endpoint base URL (no trailing slash), e.g. `https://<resource>.openai.azure.com`. | required |
| `AZURE_API_KEY` | Azure OpenAI API key. | required |
| `AZURE_DEPLOYMENT` | Name of the Azure model deployment to use. | `gpt-5` |
| `SERVICE_API_KEY` | Arbitrary API key to protect your service. Set it to a random string. | `change-me` |
| `AZURE_SUMMARY_LEVEL` | Set to `none` to disable summaries. You might have to disable them if your organization hasn't been approved for this feature. | `detailed` |
Alternatively, you can pass them through the environment where you run the application.
<details>
<summary>Optional Configuration</summary>
| Flag | Description | Default |
| --------------------- | ---------------------------------------------------------------------- | -------------------- |
| `AZURE_API_VERSION` | Azure OpenAI Responses API version to call. | `2025-04-01-preview` |
| `AZURE_SUMMARY_LEVEL` | Reasoning summary level for responses. | `detailed` |
| `AZURE_TRUNCATION` | Truncation strategy for long inputs. | `auto` |
| `FLASK_ENV` | Flask environment. Use `development` for dev or `production` for prod. | `production` |
| `RECORD_TRAFFIC` | Toggle writing request/response traffic to `recordings/` | `off` |
| Flag | Description | Default |
| ------------------- | ---------------------------------------------------------------------- | -------------------- |
| `AZURE_API_VERSION` | Azure OpenAI Responses API version to call. | `2025-04-01-preview` |
| `AZURE_TRUNCATION` | Truncation strategy for long inputs. | `auto` |
| `FLASK_ENV` | Flask environment. Use `development` for dev or `production` for prod. | `production` |
| `RECORD_TRAFFIC` | Toggle writing request/response traffic to `recordings/` | `off` |
</details>
app/azure/request_adapter.py
+5 -1
View File
@@ -241,9 +241,13 @@ class RequestAdapter:
responses_body["reasoning"] = {
"effort": reasoning_effort,
"summary": settings["AZURE_SUMMARY_LEVEL"],
}
# Concise is not supported by GPT-5,
# but allowing it for now to be able to test it on other models
if settings["AZURE_SUMMARY_LEVEL"] in {"auto", "detailed", "concise"}:
responses_body["reasoning"]["summary"] = settings["AZURE_SUMMARY_LEVEL"]
responses_body["store"] = False
responses_body["stream_options"] = {"include_obfuscation": False}
responses_body["truncation"] = settings["AZURE_TRUNCATION"]