support opus 4.7 and adaptive thinking

Author: betaHi

README.md

@@ -210,13 +210,14 @@ New endpoints for monitoring your Copilot usage and quotas.
 | `GET /usage` | `GET`  | Get detailed Copilot usage statistics and quota information. |
 | `GET /token` | `GET`  | Get the current Copilot token being used by the API.         |
 
-## **GPT and Gemini Support**
+## **GPT, Claude Opus 4.7, and Gemini Support**
 
 | Model | Status | Notes |
 | ----- | ------ | ----- |
 | `gpt-5.4` | Supported | Uses the standard GPT-5 chat/completions path. |
 | `gpt-5.3-codex` | Supported | Uses the Responses API bridge internally. |
 | `gpt-5.4-mini` | Supported | Uses the Responses API bridge internally. |
+| `claude-opus-4.7` | Supported | Snapshot aliases such as `claude-opus-4-7-20260417` resolve to this model, with `low`, `medium`, `high`, `xhigh`, and `max` effort support. |
 | `gemini-3.1-pro` | Supported | Resolves to Copilot's current `gemini-3.1-pro-preview` model. |
 | `gemini-3-flash` | Supported | Resolves to Copilot's current `gemini-3-flash-preview` model. |
 
@@ -231,8 +232,9 @@ Reasoning effort is model-specific.
 | `gpt-5.4` | `low`, `medium`, `high`, `xhigh` | `medium` |
 | `gpt-5.3-codex` | `low`, `medium`, `high`, `xhigh` | `medium` |
 | `gpt-5.4-mini` | `none`, `low`, `medium` | `medium` |
+| `claude-opus-4.7` | `low`, `medium`, `high`, `xhigh`, `max` | `medium` |
 
-If an unsupported effort value is sent for one of these models, the proxy falls back to that model's default `medium` instead of forwarding an invalid upstream request.
+If an unsupported effort value is sent for one of these models, the proxy falls back to that model's default behavior instead of forwarding an invalid upstream request.
 
 ### `settings.json`
 

package.json

@@ -25,8 +25,8 @@
     "build": "tsdown",
     "dev": "bun run --watch ./src/main.ts",
     "knip": "knip-bun",
-    "lint": "eslint --cache",
-    "lint:all": "eslint --cache .",
+    "lint": "eslint --cache --no-warn-ignored",
+    "lint:all": "eslint --cache --no-warn-ignored .",
     "prepack": "bun run build",
     "prepare": "simple-git-hooks",
     "release": "bumpp && bun publish --access public",

src/lib/models.ts

@@ -13,6 +13,10 @@ const stripSnapshotSuffix = (modelId: string): string => {
     return "claude-sonnet-4"
   }
 
+  if (/^claude-opus-4-7-\d{8}$/.test(modelId)) {
+    return "claude-opus-4.7"
+  }
+
   if (modelId.startsWith("claude-opus-4-")) {
     return "claude-opus-4"
   }

src/routes/messages/anthropic-types.ts

@@ -19,7 +19,7 @@ export interface AnthropicMessagesPayload {
     name?: string
   }
   thinking?: {
-    type: "enabled"
+    type: "enabled" | "adaptive"
     budget_tokens?: number
   }
   reasoning_effort?: "none" | "low" | "medium" | "high" | "max" | "xhigh"

src/routes/messages/non-stream-translation.ts

@@ -42,18 +42,123 @@ export function translateToOpenAI(
     stream: payload.stream,
     temperature: payload.temperature,
     top_p: payload.top_p,
+    thinking: translateThinking(payload),
+    output_config: translateOutputConfig(payload),
     reasoning_effort: translateReasoningEffort(payload),
     user: payload.metadata?.user_id,
     tools: translateAnthropicToolsToOpenAI(payload.tools),
     tool_choice: translateAnthropicToolChoiceToOpenAI(payload.tool_choice),
   }
 }
 
+function isClaudeModel(modelId: string): boolean {
+  return modelId.startsWith("claude-")
+}
+
+function isClaudeOpus47Model(modelId: string): boolean {
+  return modelId === "claude-opus-4.7"
+}
+
+type ClaudeOpus47Effort = NonNullable<
+  NonNullable<ChatCompletionsPayload["output_config"]>["effort"]
+>
+
+function normalizeClaudeEffort(
+  value: string | undefined,
+): ClaudeOpus47Effort | undefined {
+  switch (value?.toLowerCase()) {
+    case "low": {
+      return "low"
+    }
+    case "medium": {
+      return "medium"
+    }
+    case "high": {
+      return "high"
+    }
+    case "xhigh": {
+      return "xhigh"
+    }
+    case "max": {
+      return "max"
+    }
+    default: {
+      return undefined
+    }
+  }
+}
+
+function getClaudeOpus47Effort(
+  payload: AnthropicMessagesPayload,
+): ClaudeOpus47Effort | undefined {
+  const explicitEffort = normalizeClaudeEffort(payload.reasoning_effort)
+  if (explicitEffort) {
+    return explicitEffort
+  }
+
+  if (payload.thinking?.type !== "enabled") {
+    return undefined
+  }
+
+  const budgetTokens = payload.thinking.budget_tokens
+  if (budgetTokens === undefined) {
+    return "medium"
+  }
+
+  if (budgetTokens <= 2_048) {
+    return "low"
+  }
+
+  if (budgetTokens <= 8_192) {
+    return "medium"
+  }
+
+  if (budgetTokens <= 24_576) {
+    return "high"
+  }
+
+  return "xhigh"
+}
+
+function translateThinking(
+  payload: AnthropicMessagesPayload,
+): ChatCompletionsPayload["thinking"] {
+  const modelId = translateModelName(payload.model)
+
+  if (!isClaudeOpus47Model(modelId)) {
+    return undefined
+  }
+
+  if (payload.thinking?.type === "adaptive") {
+    return { type: "adaptive" }
+  }
+
+  return payload.thinking?.type === "enabled" ? { type: "adaptive" } : undefined
+}
+
+function translateOutputConfig(
+  payload: AnthropicMessagesPayload,
+): ChatCompletionsPayload["output_config"] {
+  const modelId = translateModelName(payload.model)
+
+  if (!isClaudeOpus47Model(modelId)) {
+    return undefined
+  }
+
+  const effort = getClaudeOpus47Effort(payload)
+
+  return effort ? { effort } : undefined
+}
+
 function translateReasoningEffort(
   payload: AnthropicMessagesPayload,
 ): ChatCompletionsPayload["reasoning_effort"] {
   const modelId = translateModelName(payload.model)
 
+  if (isClaudeModel(modelId)) {
+    return undefined
+  }
+
   if (payload.reasoning_effort) {
     return sanitizeReasoningEffortForModel(
       modelId,

src/services/copilot/create-chat-completions.ts

@@ -18,6 +18,13 @@ import {
 const usesMaxCompletionTokens = (modelId: string): boolean =>
   modelId.startsWith("gpt-5")
 
+const isClaudeOpus47Model = (modelId: string): boolean =>
+  modelId === "claude-opus-4.7"
+
+type ClaudeOpus47Effort = NonNullable<
+  NonNullable<ChatCompletionsPayload["output_config"]>["effort"]
+>
+
 // Copilot rejects user identifiers longer than 64 characters.
 const MAX_USER_LENGTH = 64
 
@@ -102,6 +109,47 @@ const normalizeReasoningEffort = (
   }
 }
 
+const normalizeClaudeOpus47Effort = (
+  value: string | undefined | null,
+): ClaudeOpus47Effort | undefined => {
+  switch (value?.toLowerCase()) {
+    case "low": {
+      return "low"
+    }
+    case "medium": {
+      return "medium"
+    }
+    case "high": {
+      return "high"
+    }
+    case "xhigh": {
+      return "xhigh"
+    }
+    case "max": {
+      return "max"
+    }
+    default: {
+      return undefined
+    }
+  }
+}
+
+const getRequestedClaudeOpus47Effort = (
+  payload: ChatCompletionsPayload,
+  claudeSettingsEnv: Record<string, string>,
+): ClaudeOpus47Effort | undefined => {
+  if (!isClaudeOpus47Model(payload.model)) {
+    return undefined
+  }
+
+  return (
+    payload.output_config?.effort
+    ?? normalizeClaudeOpus47Effort(payload.reasoning_effort)
+    ?? normalizeClaudeOpus47Effort(process.env.COPILOT_REASONING_EFFORT)
+    ?? normalizeClaudeOpus47Effort(claudeSettingsEnv.COPILOT_REASONING_EFFORT)
+  )
+}
+
 export const sanitizeUserIdentifier = (
   user: string | null | undefined,
 ): string | undefined => {
@@ -120,6 +168,10 @@ const buildRequestPayload = (
     payload,
     claudeSettingsEnv,
   )
+  const requestedClaudeOpus47Effort = getRequestedClaudeOpus47Effort(
+    payload,
+    claudeSettingsEnv,
+  )
 
   const reasoningEffort =
     (
@@ -138,6 +190,17 @@ const buildRequestPayload = (
   ) {
     const sanitizedPayload = {
       ...payload,
+      output_config:
+        requestedClaudeOpus47Effort ?
+          {
+            ...payload.output_config,
+            effort: requestedClaudeOpus47Effort,
+          }
+        : payload.output_config,
+      reasoning_effort:
+        isClaudeOpus47Model(payload.model) ? undefined : (
+          payload.reasoning_effort
+        ),
       user: sanitizeUserIdentifier(payload.user),
     }
 
@@ -337,6 +400,13 @@ export interface ChatCompletionsPayload {
   temperature?: number | null
   top_p?: number | null
   max_tokens?: number | null
+  thinking?: {
+    type: "enabled" | "adaptive"
+    budget_tokens?: number
+  } | null
+  output_config?: {
+    effort?: "low" | "medium" | "high" | "xhigh" | "max"
+  } | null
   reasoning_effort?: "none" | "low" | "medium" | "high" | "max" | "xhigh" | null
   stop?: string | Array<string> | null
   n?: number | null