fix(provider): gate Azure reasoning effort by endpoint

CONTRIBUTING.md

@@ -252,6 +252,33 @@ These are not strictly enforced, they are just general guidelines:
 
 For net-new functionality, start with a design conversation. Open an issue describing the problem, your proposed approach (optional), and why it belongs in OpenCode. The core team will help decide whether it should move forward; please wait for that approval instead of opening a feature PR directly.
 
+## Trust & Vouch System
+
+This project uses [vouch](https://github.com/mitchellh/vouch) to manage contributor trust. The vouch list is maintained in [`.github/VOUCHED.td`](.github/VOUCHED.td).
+
+### How it works
+
+- **Vouched users** are explicitly trusted contributors.
+- **Denounced users** are explicitly blocked. Issues and pull requests from denounced users are automatically closed. If you have been denounced, you can request to be unvouched by reaching out to a maintainer on [Discord](https://opencode.ai/discord)
+- **Everyone else** can participate normally — you don't need to be vouched to open issues or PRs.
+
+### For maintainers
+
+Collaborators with write access can manage the vouch list by commenting on any issue:
+
+- `vouch` — vouch for the issue author
+- `vouch @username` — vouch for a specific user
+- `denounce` — denounce the issue author
+- `denounce @username` — denounce a specific user
+- `denounce @username <reason>` — denounce with a reason
+- `unvouch` / `unvouch @username` — remove someone from the list
+
+Changes are committed automatically to `.github/VOUCHED.td`.
+
+### Denouncement policy
+
+Denouncement is reserved for users who repeatedly submit low-quality AI-generated contributions, spam, or otherwise act in bad faith. It is not used for disagreements or honest mistakes.
+
 ## Issue Requirements
 
 All issues **must** use one of our issue templates:

packages/opencode/src/provider/transform.ts

@@ -1270,11 +1270,6 @@ export function options(input: {
     result["gateway"] = { caching: "auto" }
   }
 
-  if (input.model.api.npm === "@ai-sdk/azure" && input.model.api.id.includes("gpt-5.5")) {
-    result["reasoningSummary"] = "auto"
-    return result
-  }
-
   if (input.model.api.id.includes("gpt-5") && !input.model.api.id.includes("gpt-5-chat")) {
     if (!input.model.api.id.includes("gpt-5-pro")) {
       result["reasoningEffort"] = "medium"

packages/opencode/src/session/llm/request.ts

@@ -93,6 +93,7 @@ export const prepare = Effect.fn("LLMRequestPrep.prepare")(function* (input: Pre
     input.model.api.npm === "@ai-sdk/azure" &&
     (input.provider.options.useCompletionUrls || input.model.options.useCompletionUrls || options.useCompletionUrls)
   ) {
+    delete options.reasoningEffort
     delete options.reasoningSummary
     delete options.include
   }

packages/opencode/test/provider/transform.test.ts

@@ -252,7 +252,7 @@ describe("ProviderTransform.options - setCacheKey", () => {
     expect(result.promptCacheKey).toBeUndefined()
   })
 
-  test("should keep the Azure cache key for gpt-5.5 early return", () => {
+  test("should keep the Azure cache key for gpt-5.5 Responses defaults", () => {
     const result = ProviderTransform.options({
       model: {
         ...mockModel,
@@ -525,7 +525,7 @@ describe("ProviderTransform.options - gpt-5 textVerbosity", () => {
     expect(result.include).toBeUndefined()
   })
 
-  test("azure chat completions omit Responses-only reasoning options after variants merge", async () => {
+  test("azure chat completions omit unsupported reasoning options after variants merge", async () => {
     const model = {
       ...createGpt5Model("gpt-5.4"),
       id: "azure/gpt-5.4",
@@ -580,7 +580,7 @@ describe("ProviderTransform.options - gpt-5 textVerbosity", () => {
         isWorkflow: false,
       }),
     )
-    expect(result.params.options.reasoningEffort).toBe("high")
+    expect(result.params.options.reasoningEffort).toBeUndefined()
     expect(result.params.options.reasoningSummary).toBeUndefined()
     expect(result.params.options.include).toBeUndefined()
     expect(result.tools.lookup.strict).toBe(false)
@@ -681,14 +681,15 @@ describe("ProviderTransform.options - gpt-5 reasoningEffort", () => {
     expect(result.reasoningEffort).toBeUndefined()
   })
 
-  test("gpt-5.5 should NOT set reasoningEffort", () => {
+  test("gpt-5.5 should set Responses reasoning options", () => {
     const result = ProviderTransform.options({
       model: createModel("gpt-5.5"),
       sessionID,
       providerOptions: {},
     })
 
-    expect(result.reasoningEffort).toBeUndefined()
+    expect(result.reasoningEffort).toBe("medium")
+    expect(result.reasoningSummary).toBe("auto")
   })
 })