fix(ai): use OpenAI endpoint for Fireworks GLM-5.2

closes #5923

packages/ai/CHANGELOG.md

@@ -8,6 +8,7 @@
 
 ### Fixed
 
+- Fixed Fireworks GLM-5.2 metadata to use the OpenAI-compatible Chat Completions endpoint with `reasoning_effort` support ([#5923](https://github.com/earendil-works/pi/issues/5923)).
 - Fixed OpenRouter GLM-5.2 metadata to expose `xhigh` reasoning and send OpenRouter's native `xhigh` effort ([#5770](https://github.com/earendil-works/pi/issues/5770)).
 - Fixed GitHub Copilot OAuth model availability to use the authenticated account's model picker catalog ([#5897](https://github.com/earendil-works/pi/issues/5897)).
 

packages/ai/scripts/generate-models.ts

@@ -377,6 +377,9 @@ function applyThinkingLevelMetadata(model: Model<any>): void {
 	if (model.provider === "openrouter" && model.id === "z-ai/glm-5.2") {
 		mergeThinkingLevelMap(model, { xhigh: "xhigh" });
 	}
+	if (model.provider === "fireworks" && model.id === "accounts/fireworks/models/glm-5p2") {
+		mergeThinkingLevelMap(model, { off: "none", minimal: null, low: "high", medium: "high", xhigh: "max" });
+	}
 	if (model.provider === "opencode-go" && model.id === "kimi-k2.6") {
 		// OpenCode Go exposes Kimi K2.6 thinking as on/off, not distinct effort tiers.
 		mergeThinkingLevelMap(model, { minimal: null, low: null, medium: null });
@@ -1514,7 +1517,11 @@ async function generateModels() {
 			candidate.cost.output = 1.9;
 			candidate.cost.cacheRead = 0.119;
 		}
-
+		if (candidate.provider === "fireworks" && candidate.id === "accounts/fireworks/models/glm-5p2") {
+			candidate.api = "openai-completions";
+			candidate.baseUrl = "https://api.fireworks.ai/inference/v1";
+			candidate.compat = { supportsStore: false, supportsDeveloperRole: false };
+		}
 	}
 
 

packages/ai/src/models.generated.ts

@@ -3930,11 +3930,12 @@ export const MODELS = {
 		"accounts/fireworks/models/glm-5p2": {
 			id: "accounts/fireworks/models/glm-5p2",
 			name: "GLM 5.2",
-			api: "anthropic-messages",
+			api: "openai-completions",
 			provider: "fireworks",
-			baseUrl: "https://api.fireworks.ai/inference",
+			baseUrl: "https://api.fireworks.ai/inference/v1",
-			compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false},
 			reasoning: true,
+			thinkingLevelMap: {"off":"none","minimal":null,"low":"high","medium":"high","xhigh":"max"},
 			input: ["text"],
 			cost: {
 				input: 1.4,
@@ -3944,7 +3945,7 @@ export const MODELS = {
 			},
 			contextWindow: 1048576,
 			maxTokens: 131072,
-		} satisfies Model<"anthropic-messages">,
+		} satisfies Model<"openai-completions">,
 		"accounts/fireworks/models/gpt-oss-120b": {
 			id: "accounts/fireworks/models/gpt-oss-120b",
 			name: "GPT OSS 120B",