fix(ollama): unify context window handling across discovery, merge, and OpenAI-compat transport (#29205)

* fix(ollama): inject num_ctx for OpenAI-compatible transport * fix(ollama): discover per-model context and preserve higher limits * fix(agents): prefer matching provider model for fallback limits * fix(types): require numeric token limits in provider model merge * fix(types): accept unknown payload in ollama num_ctx wrapper * fix(types): simplify ollama settled-result extraction * config(models): add provider flag for Ollama OpenAI num_ctx injection * config(schema): allow provider num_ctx injection flag * config(labels): label provider num_ctx injection flag * config(help): document provider num_ctx injection flag * agents(ollama): gate OpenAI num_ctx injection with provider config * tests(ollama): cover provider num_ctx injection flag behavior * docs(config): list provider num_ctx injection option * docs(ollama): document OpenAI num_ctx injection toggle * docs(config): clarify merge token-limit precedence * config(help): note merge uses higher model token limits * fix(ollama): cap /api/show discovery concurrency * fix(ollama): restrict num_ctx injection to OpenAI compat * tests(ollama): cover ipv6 and compat num_ctx gating * fix(ollama): detect remote compat endpoints for ollama-labeled providers * fix(ollama): cap per-model /api/show lookups to bound discovery load
2026-05-11 16:53:49 +00:00 · 2026-02-27 17:20:47 -08:00
parent 70a4f25ab1
commit f16ecd1dac
14 changed files with 582 additions and 21 deletions
--- a/src/agents/models-config.fills-missing-provider-apikey-from-env-var.test.ts
+++ b/src/agents/models-config.fills-missing-provider-apikey-from-env-var.test.ts
@@ -307,4 +307,57 @@ describe("models-config", () => {
      }
    });
  });
+
+  it("preserves explicit larger token limits when they exceed implicit catalog defaults", async () => {
+    await withTempHome(async () => {
+      const prevKey = process.env.MOONSHOT_API_KEY;
+      process.env.MOONSHOT_API_KEY = "sk-moonshot-test";
+      try {
+        const cfg: OpenClawConfig = {
+          models: {
+            providers: {
+              moonshot: {
+                baseUrl: "https://api.moonshot.ai/v1",
+                api: "openai-completions",
+                models: [
+                  {
+                    id: "kimi-k2.5",
+                    name: "Kimi K2.5",
+                    reasoning: false,
+                    input: ["text"],
+                    cost: { input: 123, output: 456, cacheRead: 0, cacheWrite: 0 },
+                    contextWindow: 350000,
+                    maxTokens: 16384,
+                  },
+                ],
+              },
+            },
+          },
+        };
+
+        await ensureOpenClawModelsJson(cfg);
+        const parsed = await readGeneratedModelsJson<{
+          providers: Record<
+            string,
+            {
+              models?: Array<{
+                id: string;
+                contextWindow?: number;
+                maxTokens?: number;
+              }>;
+            }
+          >;
+        }>();
+        const kimi = parsed.providers.moonshot?.models?.find((model) => model.id === "kimi-k2.5");
+        expect(kimi?.contextWindow).toBe(350000);
+        expect(kimi?.maxTokens).toBe(16384);
+      } finally {
+        if (prevKey === undefined) {
+          delete process.env.MOONSHOT_API_KEY;
+        } else {
+          process.env.MOONSHOT_API_KEY = prevKey;
+        }
+      }
+    });
+  });
 });