feat(config): expose full pi-ai model compat fields in config schema (openclaw#11063) thanks @ikari-pl

Verified:
- pnpm build
- pnpm check
- pnpm test (full run; transient lobster timeout rerun passed)

Co-authored-by: ikari-pl <811702+ikari-pl@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>

CHANGELOG.md

@@ -145,6 +145,7 @@ Docs: https://docs.openclaw.ai
 - Onboarding/Providers: update MiniMax API default/recommended models from M2.1 to M2.5, add M2.5/M2.5-Lightning model entries, and include `minimax-m2.5` in modern model filtering. (#14865) Thanks @adao-max.
 - Ollama: use configured `models.providers.ollama.baseUrl` for model discovery and normalize `/v1` endpoints to the native Ollama API root. (#14131) Thanks @shtse8.
 - Voice Call: pass Twilio stream auth token via `<Parameter>` instead of query string. (#14029) Thanks @mcwigglesmcgee.
+- Config/Models: allow full `models.providers.*.models[*].compat` keys used by `openai-completions` (`thinkingFormat`, `supportsStrictMode`, and streaming/tool-result compatibility flags) so valid provider overrides no longer fail strict config validation. (#11063) Thanks @ikari-pl.
 - Feishu: pass `Buffer` directly to the Feishu SDK upload APIs instead of `Readable.from(...)` to avoid form-data upload failures. (#10345) Thanks @youngerstyle.
 - Feishu: trigger mention-gated group handling only when the bot itself is mentioned (not just any mention). (#11088) Thanks @openperf.
 - Feishu: probe status uses the resolved account context for multi-account credential checks. (#11233) Thanks @onevcat.

src/config/config.model-compat-schema.test.ts

@@ -0,0 +1,34 @@
+import { describe, expect, it } from "vitest";
+import { validateConfigObject } from "./validation.js";
+
+describe("model compat config schema", () => {
+  it("accepts full openai-completions compat fields", () => {
+    const res = validateConfigObject({
+      models: {
+        providers: {
+          local: {
+            baseUrl: "http://127.0.0.1:1234/v1",
+            api: "openai-completions",
+            models: [
+              {
+                id: "qwen3-32b",
+                name: "Qwen3 32B",
+                compat: {
+                  supportsUsageInStreaming: true,
+                  supportsStrictMode: false,
+                  thinkingFormat: "qwen",
+                  requiresToolResultName: true,
+                  requiresAssistantAfterToolResult: false,
+                  requiresThinkingAsText: false,
+                  requiresMistralToolIds: false,
+                },
+              },
+            ],
+          },
+        },
+      },
+    });
+
+    expect(res.ok).toBe(true);
+  });
+});

src/config/types.models.ts

@@ -11,7 +11,14 @@ export type ModelCompatConfig = {
   supportsStore?: boolean;
   supportsDeveloperRole?: boolean;
   supportsReasoningEffort?: boolean;
+  supportsUsageInStreaming?: boolean;
+  supportsStrictMode?: boolean;
   maxTokensField?: "max_completion_tokens" | "max_tokens";
+  thinkingFormat?: "openai" | "zai" | "qwen";
+  requiresToolResultName?: boolean;
+  requiresAssistantAfterToolResult?: boolean;
+  requiresThinkingAsText?: boolean;
+  requiresMistralToolIds?: boolean;
 };
 
 export type ModelProviderAuthMode = "api-key" | "aws-sdk" | "oauth" | "token";

src/config/zod-schema.core.ts

@@ -17,9 +17,16 @@ export const ModelCompatSchema = z
     supportsStore: z.boolean().optional(),
     supportsDeveloperRole: z.boolean().optional(),
     supportsReasoningEffort: z.boolean().optional(),
+    supportsUsageInStreaming: z.boolean().optional(),
+    supportsStrictMode: z.boolean().optional(),
     maxTokensField: z
       .union([z.literal("max_completion_tokens"), z.literal("max_tokens")])
       .optional(),
+    thinkingFormat: z.union([z.literal("openai"), z.literal("zai"), z.literal("qwen")]).optional(),
+    requiresToolResultName: z.boolean().optional(),
+    requiresAssistantAfterToolResult: z.boolean().optional(),
+    requiresThinkingAsText: z.boolean().optional(),
+    requiresMistralToolIds: z.boolean().optional(),
   })
   .strict()
   .optional();