fix(ai): update Copilot Claude thinking metadata

closes #4637

packages/ai/CHANGELOG.md

@@ -4,6 +4,7 @@
 
 ### Fixed
 
+- Fixed GitHub Copilot Claude adaptive-thinking effort metadata to match manually checked Copilot model capabilities ([#4637](https://github.com/earendil-works/pi/issues/4637)).
 - Fixed OpenCode/OpenCode Go completion models that reject `prompt_cache_retention` to omit long-retention cache fields when `cacheRetention` is `long` ([#5702](https://github.com/earendil-works/pi/issues/5702)).
 
 ## [0.79.3] - 2026-06-13

packages/ai/scripts/generate-models.ts

@@ -196,6 +196,14 @@ const OPENCODE_OPENAI_COMPLETIONS_LONG_CACHE_RETENTION_UNSUPPORTED_MODELS = new
 	"opencode-go:kimi-k2.6",
 ]);
 
+// Checked manually against the authenticated GitHub Copilot /models endpoint on 2026-06-15.
+// Keep this to narrow corrections over models.dev metadata instead of snapshotting Copilot's catalog.
+const GITHUB_COPILOT_THINKING_LEVEL_OVERRIDES = {
+	"claude-opus-4.7": { minimal: "low" },
+	"claude-opus-4.8": { minimal: "low" },
+	"claude-sonnet-4.6": { minimal: "low", xhigh: "max" },
+} satisfies Record<string, NonNullable<Model<Api>["thinkingLevelMap"]>>;
+
 function mergeThinkingLevelMap(model: Model<any>, map: NonNullable<Model<any>["thinkingLevelMap"]>): void {
 	model.thinkingLevelMap = { ...model.thinkingLevelMap, ...map };
 }
@@ -358,6 +366,12 @@ function applyThinkingLevelMetadata(model: Model<any>): void {
 		// Ring reasons by default. Only high/xhigh have documented explicit effort controls.
 		mergeThinkingLevelMap(model, ANT_LING_RING_THINKING_LEVEL_MAP);
 	}
+	if (model.provider === "github-copilot") {
+		const override = GITHUB_COPILOT_THINKING_LEVEL_OVERRIDES[model.id];
+		if (override) {
+			mergeThinkingLevelMap(model, override);
+		}
+	}
 }
 
 function getAnthropicMessagesCompat(provider: string, modelId: string): AnthropicMessagesCompat | undefined {

packages/ai/src/models.generated.ts

@@ -4194,7 +4194,7 @@ export const MODELS = {
 			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
 			compat: {"forceAdaptiveThinking":true,"supportsTemperature":false},
 			reasoning: true,
-			thinkingLevelMap: {"xhigh":"xhigh"},
+			thinkingLevelMap: {"xhigh":"xhigh","minimal":"low"},
 			input: ["text", "image"],
 			cost: {
 				input: 5,
@@ -4214,7 +4214,7 @@ export const MODELS = {
 			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
 			compat: {"forceAdaptiveThinking":true,"supportsTemperature":false},
 			reasoning: true,
-			thinkingLevelMap: {"xhigh":"xhigh"},
+			thinkingLevelMap: {"xhigh":"xhigh","minimal":"low"},
 			input: ["text", "image"],
 			cost: {
 				input: 5,
@@ -4272,6 +4272,7 @@ export const MODELS = {
 			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
 			compat: {"forceAdaptiveThinking":true},
 			reasoning: true,
+			thinkingLevelMap: {"minimal":"low","xhigh":"max"},
 			input: ["text", "image"],
 			cost: {
 				input: 3,
@@ -4831,6 +4832,42 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 32768,
 		} satisfies Model<"google-generative-ai">,
+		"gemma-4-E2B-it": {
+			id: "gemma-4-E2B-it",
+			name: "Gemma 4 E2B IT",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: true,
+			thinkingLevelMap: {"off":null,"minimal":"MINIMAL","low":null,"medium":null,"high":"HIGH"},
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 8192,
+		} satisfies Model<"google-generative-ai">,
+		"gemma-4-E4B-it": {
+			id: "gemma-4-E4B-it",
+			name: "Gemma 4 E4B IT",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: true,
+			thinkingLevelMap: {"off":null,"minimal":"MINIMAL","low":null,"medium":null,"high":"HIGH"},
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 8192,
+		} satisfies Model<"google-generative-ai">,
 	},
 	"google-vertex": {
 		"gemini-1.5-flash": {
@@ -9432,13 +9469,13 @@ export const MODELS = {
 			thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"xhigh"},
 			input: ["text"],
 			cost: {
-				input: 0.098,
-				output: 0.196,
+				input: 0.09,
+				output: 0.18,
 				cacheRead: 0.02,
 				cacheWrite: 0,
 			},
 			contextWindow: 1048576,
-			maxTokens: 4096,
+			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
 		"deepseek/deepseek-v4-pro": {
 			id: "deepseek/deepseek-v4-pro",
@@ -13304,6 +13341,25 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 131000,
 		} satisfies Model<"openai-completions">,
+		"moonshotai/Kimi-K2.7-Code": {
+			id: "moonshotai/Kimi-K2.7-Code",
+			name: "Kimi K2.7 Code",
+			api: "openai-completions",
+			provider: "together",
+			baseUrl: "https://api.together.ai/v1",
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
+			reasoning: true,
+			thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
+			input: ["text"],
+			cost: {
+				input: 0.95,
+				output: 4,
+				cacheRead: 0.19,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
 		"nvidia/nemotron-3-ultra-550b-a55b": {
 			id: "nvidia/nemotron-3-ultra-550b-a55b",
 			name: "Nemotron 3 Ultra 550B A55B",

packages/ai/test/github-copilot-anthropic.test.ts

@@ -1,5 +1,5 @@
 import { describe, expect, it, vi } from "vitest";
-import { getModel } from "../src/models.ts";
+import { getModel, getSupportedThinkingLevels } from "../src/models.ts";
 import { streamAnthropic } from "../src/providers/anthropic.ts";
 import type { Context } from "../src/types.ts";
 
@@ -54,6 +54,16 @@ describe("Copilot Claude via Anthropic Messages", () => {
 		messages: [{ role: "user", content: "Hello", timestamp: Date.now() }],
 	};
 
+	it("applies Copilot-specific adaptive thinking effort overrides", () => {
+		const opus47 = getModel("github-copilot", "claude-opus-4.7");
+		expect(opus47.thinkingLevelMap).toMatchObject({ minimal: "low", xhigh: "xhigh" });
+		expect(getSupportedThinkingLevels(opus47)).toContain("xhigh");
+
+		const sonnet46 = getModel("github-copilot", "claude-sonnet-4.6");
+		expect(sonnet46.thinkingLevelMap).toMatchObject({ minimal: "low", xhigh: "max" });
+		expect(getSupportedThinkingLevels(sonnet46)).toContain("xhigh");
+	});
+
 	it("uses Bearer auth, Copilot headers, and valid Anthropic Messages payload", async () => {
 		const model = getModel("github-copilot", "claude-sonnet-4.6");
 		expect(model.api).toBe("anthropic-messages");