From 9eedaf8cf3e0be975687dfa31752a0e195fd1e4d Mon Sep 17 00:00:00 2001
From: Mario Zechner <badlogicgames@gmail.com>
Date: Thu, 9 Jul 2026 10:39:27 +0200
Subject: [PATCH] fix(ai): update GitHub Copilot extended context windows to 1M

Updates GitHub Copilot built-in model metadata so models with GitHub's extended 1M capability use contextWindow 1000000 in Pi, preventing early compaction and under-budgeting for Claude Opus 4.7/4.8 and GPT-5.3 Codex/5.4/5.5.

Verified against raw docs markdown extended-capabilities table and live /models reports.

closes #6439
---
 packages/ai/CHANGELOG.md                      |  1 +
 packages/ai/scripts/generate-models.ts        | 21 +++++++++++++++++--
 .../ai/src/providers/github-copilot.models.ts | 10 ++++-----
 3 files changed, 25 insertions(+), 7 deletions(-)

diff --git a/packages/ai/CHANGELOG.md b/packages/ai/CHANGELOG.md
index e5eae4d0..6b2e62e6 100644
--- a/packages/ai/CHANGELOG.md
+++ b/packages/ai/CHANGELOG.md
@@ -15,6 +15,7 @@
 - Fixed OpenAI Completions and Responses providers to send `(no tool output)` instead of `(see attached image)` when a tool result has empty text and no image content, preventing the model from hallucinating image attachments.
 - Fixed OpenAI Responses and Azure OpenAI Responses requests to avoid sending `max_output_tokens` values below the provider minimum ([#6265](https://github.com/earendil-works/pi/issues/6265)).
 - Fixed retry classification for Cloudflare 524 timeout responses ([#6239](https://github.com/earendil-works/pi/issues/6239)).
+- Fixed GitHub Copilot extended context window models (Claude Opus 4.7/4.8, Claude Opus 4.6, Claude Sonnet 4.6/5, Claude Fable 5, GPT-5.3 Codex, GPT-5.4, GPT-5.5) to use `contextWindow: 1000000`, preventing premature compaction and under-budgeting ([#6439](https://github.com/earendil-works/pi/issues/6439)).
 
 ### Added
 
diff --git a/packages/ai/scripts/generate-models.ts b/packages/ai/scripts/generate-models.ts
index f262b7b5..08de7546 100644
--- a/packages/ai/scripts/generate-models.ts
+++ b/packages/ai/scripts/generate-models.ts
@@ -212,6 +212,20 @@ const OPENCODE_OPENAI_COMPLETIONS_LONG_CACHE_RETENTION_UNSUPPORTED_MODELS = new
 	"opencode-go:kimi-k2.6",
 ]);
 
+// GitHub's "Models with extended capabilities" table lists these Copilot models as supporting
+// the extended 1 million token context window.
+const GITHUB_COPILOT_EXTENDED_CONTEXT_MODELS = new Set([
+	"claude-fable-5",
+	"claude-opus-4.6",
+	"claude-opus-4.7",
+	"claude-opus-4.8",
+	"claude-sonnet-4.6",
+	"claude-sonnet-5",
+	"gpt-5.3-codex",
+	"gpt-5.4",
+	"gpt-5.5",
+]);
+
 // 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 = {
@@ -1606,11 +1620,14 @@ async function generateModels() {
 
 	// Temporary overrides until upstream model metadata is corrected.
 	for (const candidate of allModels) {
+		if (candidate.provider === "github-copilot" && GITHUB_COPILOT_EXTENDED_CONTEXT_MODELS.has(candidate.id)) {
+			candidate.contextWindow = 1000000;
+		}
+
 		if (
 			(candidate.provider === "anthropic" ||
 				candidate.provider === "opencode" ||
-				candidate.provider === "opencode-go" ||
-				candidate.provider === "github-copilot") &&
+				candidate.provider === "opencode-go") &&
 			(candidate.id === "claude-opus-4-6" ||
 				candidate.id === "claude-sonnet-4-6" ||
 				candidate.id === "claude-opus-4.6" ||
diff --git a/packages/ai/src/providers/github-copilot.models.ts b/packages/ai/src/providers/github-copilot.models.ts
index 21cb6411..12ebaf38 100644
--- a/packages/ai/src/providers/github-copilot.models.ts
+++ b/packages/ai/src/providers/github-copilot.models.ts
@@ -97,7 +97,7 @@ export const GITHUB_COPILOT_MODELS = {
 			cacheRead: 0.5,
 			cacheWrite: 6.25,
 		},
-		contextWindow: 200000,
+		contextWindow: 1000000,
 		maxTokens: 32000,
 	} satisfies Model<"anthropic-messages">,
 	"claude-opus-4.8": {
@@ -117,7 +117,7 @@ export const GITHUB_COPILOT_MODELS = {
 			cacheRead: 0.5,
 			cacheWrite: 6.25,
 		},
-		contextWindow: 200000,
+		contextWindow: 1000000,
 		maxTokens: 64000,
 	} satisfies Model<"anthropic-messages">,
 	"claude-sonnet-4": {
@@ -365,7 +365,7 @@ export const GITHUB_COPILOT_MODELS = {
 			cacheRead: 0.175,
 			cacheWrite: 0,
 		},
-		contextWindow: 400000,
+		contextWindow: 1000000,
 		maxTokens: 128000,
 	} satisfies Model<"openai-responses">,
 	"gpt-5.4": {
@@ -384,7 +384,7 @@ export const GITHUB_COPILOT_MODELS = {
 			cacheRead: 0.25,
 			cacheWrite: 0,
 		},
-		contextWindow: 400000,
+		contextWindow: 1000000,
 		maxTokens: 128000,
 	} satisfies Model<"openai-responses">,
 	"gpt-5.4-mini": {
@@ -441,7 +441,7 @@ export const GITHUB_COPILOT_MODELS = {
 			cacheRead: 0.5,
 			cacheWrite: 0,
 		},
-		contextWindow: 400000,
+		contextWindow: 1000000,
 		maxTokens: 128000,
 	} satisfies Model<"openai-responses">,
 	"kimi-k2.7-code": {