Anthropic: wire explicit service tier params (#45453)

* Anthropic: add explicit service tier wrapper * Runner: wire explicit Anthropic service tiers * Tests: cover explicit Anthropic service tiers * Changelog: note Anthropic service tier follow-up * fix(agents): make Anthropic service tiers override fast mode * fix(config): drop duplicate healed sourceConfig * docs(anthropic): update fast mode service tier guidance * fix(agents): remove dead Anthropic Bedrock exports * fix(agents): avoid cross-provider Anthropic tier warnings * fix(agents): avoid cross-provider OpenAI tier warnings
2026-04-26 00:21:59 +00:00 · 2026-03-29 16:54:56 -07:00
parent feed2c42dd
commit 475defdf82
6 changed files with 299 additions and 10 deletions
--- a/src/agents/pi-embedded-runner-extraparams.test.ts
+++ b/src/agents/pi-embedded-runner-extraparams.test.ts
@@ -2122,6 +2122,179 @@ describe("applyExtraParamsToAgent", () => {
    expect(payload.service_tier).toBe("standard_only");
  });

+  it("injects configured Anthropic service_tier into direct Anthropic payloads", () => {
+    const payload = runResponsesPayloadMutationCase({
+      applyProvider: "anthropic",
+      applyModelId: "claude-sonnet-4-5",
+      cfg: {
+        agents: {
+          defaults: {
+            models: {
+              "anthropic/claude-sonnet-4-5": {
+                params: {
+                  serviceTier: "standard_only",
+                },
+              },
+            },
+          },
+        },
+      },
+      model: {
+        api: "anthropic-messages",
+        provider: "anthropic",
+        id: "claude-sonnet-4-5",
+        baseUrl: "https://api.anthropic.com",
+      } as unknown as Model<"anthropic-messages">,
+      payload: {},
+    });
+    expect(payload.service_tier).toBe("standard_only");
+  });
+
+  it("injects configured Anthropic service_tier into OAuth-authenticated Anthropic payloads", () => {
+    const payload = runResponsesPayloadMutationCase({
+      applyProvider: "anthropic",
+      applyModelId: "claude-sonnet-4-5",
+      cfg: {
+        agents: {
+          defaults: {
+            models: {
+              "anthropic/claude-sonnet-4-5": {
+                params: {
+                  serviceTier: "standard_only",
+                },
+              },
+            },
+          },
+        },
+      },
+      model: {
+        api: "anthropic-messages",
+        provider: "anthropic",
+        id: "claude-sonnet-4-5",
+        baseUrl: "https://api.anthropic.com",
+      } as unknown as Model<"anthropic-messages">,
+      options: {
+        apiKey: "sk-ant-oat-test-token",
+      },
+      payload: {},
+    });
+    expect(payload.service_tier).toBe("standard_only");
+  });
+
+  it("does not warn for valid Anthropic serviceTier values", () => {
+    const warnSpy = vi.spyOn(log, "warn").mockImplementation(() => undefined);
+    try {
+      const payload = runResponsesPayloadMutationCase({
+        applyProvider: "anthropic",
+        applyModelId: "claude-sonnet-4-5",
+        cfg: {
+          agents: {
+            defaults: {
+              models: {
+                "anthropic/claude-sonnet-4-5": {
+                  params: {
+                    serviceTier: "standard_only",
+                  },
+                },
+              },
+            },
+          },
+        },
+        model: {
+          api: "anthropic-messages",
+          provider: "anthropic",
+          id: "claude-sonnet-4-5",
+          baseUrl: "https://api.anthropic.com",
+        } as unknown as Model<"anthropic-messages">,
+        payload: {},
+      });
+
+      expect(payload.service_tier).toBe("standard_only");
+      expect(warnSpy).not.toHaveBeenCalled();
+    } finally {
+      warnSpy.mockRestore();
+    }
+  });
+
+  it("accepts snake_case Anthropic service_tier params", () => {
+    const payload = runResponsesPayloadMutationCase({
+      applyProvider: "anthropic",
+      applyModelId: "claude-sonnet-4-5",
+      extraParamsOverride: {
+        service_tier: "standard_only",
+      },
+      model: {
+        api: "anthropic-messages",
+        provider: "anthropic",
+        id: "claude-sonnet-4-5",
+        baseUrl: "https://api.anthropic.com",
+      } as unknown as Model<"anthropic-messages">,
+      payload: {},
+    });
+    expect(payload.service_tier).toBe("standard_only");
+  });
+
+  it("lets explicit Anthropic service_tier override fast mode defaults", () => {
+    const payload = runResponsesPayloadMutationCase({
+      applyProvider: "anthropic",
+      applyModelId: "claude-sonnet-4-5",
+      cfg: {
+        agents: {
+          defaults: {
+            models: {
+              "anthropic/claude-sonnet-4-5": {
+                params: {
+                  fastMode: true,
+                  serviceTier: "standard_only",
+                },
+              },
+            },
+          },
+        },
+      },
+      model: {
+        api: "anthropic-messages",
+        provider: "anthropic",
+        id: "claude-sonnet-4-5",
+        baseUrl: "https://api.anthropic.com",
+      } as unknown as Model<"anthropic-messages">,
+      payload: {},
+    });
+    expect(payload.service_tier).toBe("standard_only");
+  });
+
+  it("lets explicit Anthropic service_tier override OAuth fast mode defaults", () => {
+    const payload = runResponsesPayloadMutationCase({
+      applyProvider: "anthropic",
+      applyModelId: "claude-sonnet-4-5",
+      cfg: {
+        agents: {
+          defaults: {
+            models: {
+              "anthropic/claude-sonnet-4-5": {
+                params: {
+                  fastMode: true,
+                  serviceTier: "standard_only",
+                },
+              },
+            },
+          },
+        },
+      },
+      model: {
+        api: "anthropic-messages",
+        provider: "anthropic",
+        id: "claude-sonnet-4-5",
+        baseUrl: "https://api.anthropic.com",
+      } as unknown as Model<"anthropic-messages">,
+      options: {
+        apiKey: "sk-ant-oat-test-token",
+      },
+      payload: {},
+    });
+    expect(payload.service_tier).toBe("standard_only");
+  });
+
  it("injects Anthropic fast mode service_tier for OAuth auth", () => {
    const payload = runResponsesPayloadMutationCase({
      applyProvider: "anthropic",
@@ -2176,6 +2349,24 @@ describe("applyExtraParamsToAgent", () => {
    expect(payload).not.toHaveProperty("service_tier");
  });

+  it("does not inject explicit Anthropic service_tier for proxied base URLs", () => {
+    const payload = runResponsesPayloadMutationCase({
+      applyProvider: "anthropic",
+      applyModelId: "claude-sonnet-4-5",
+      extraParamsOverride: {
+        serviceTier: "standard_only",
+      },
+      model: {
+        api: "anthropic-messages",
+        provider: "anthropic",
+        id: "claude-sonnet-4-5",
+        baseUrl: "https://proxy.example.com/anthropic",
+      } as unknown as Model<"anthropic-messages">,
+      payload: {},
+    });
+    expect(payload).not.toHaveProperty("service_tier");
+  });
+
  it("maps fast mode to priority service_tier for openai-codex responses", () => {
    const payload = runResponsesPayloadMutationCase({
      applyProvider: "openai-codex",
@@ -2305,12 +2496,47 @@ describe("applyExtraParamsToAgent", () => {
      });

      expect(payload).not.toHaveProperty("service_tier");
+      expect(warnSpy).toHaveBeenCalledTimes(1);
      expect(warnSpy).toHaveBeenCalledWith("ignoring invalid OpenAI service tier param: invalid");
    } finally {
      warnSpy.mockRestore();
    }
  });

+  it("does not warn for valid OpenAI serviceTier values", () => {
+    const warnSpy = vi.spyOn(log, "warn").mockImplementation(() => undefined);
+    try {
+      const payload = runResponsesPayloadMutationCase({
+        applyProvider: "openai",
+        applyModelId: "gpt-5.4",
+        cfg: {
+          agents: {
+            defaults: {
+              models: {
+                "openai/gpt-5.4": {
+                  params: {
+                    serviceTier: "priority",
+                  },
+                },
+              },
+            },
+          },
+        },
+        model: {
+          api: "openai-responses",
+          provider: "openai",
+          id: "gpt-5.4",
+          baseUrl: "https://api.openai.com/v1",
+        } as unknown as Model<"openai-responses">,
+      });
+
+      expect(payload.service_tier).toBe("priority");
+      expect(warnSpy).not.toHaveBeenCalled();
+    } finally {
+      warnSpy.mockRestore();
+    }
+  });
+
  it("does not force store for OpenAI Responses routed through non-OpenAI base URLs", () => {
    const payload = runResponsesPayloadMutationCase({
      applyProvider: "openai",
--- a/src/agents/pi-embedded-runner/anthropic-stream-wrappers.ts
+++ b/src/agents/pi-embedded-runner/anthropic-stream-wrappers.ts
@@ -89,6 +89,17 @@ function hasOpenAiAnthropicToolPayloadCompatFlag(model: { compat?: unknown }): b
  );
 }

+function normalizeAnthropicServiceTier(value: unknown): AnthropicServiceTier | undefined {
+  if (typeof value !== "string") {
+    return undefined;
+  }
+  const normalized = value.trim().toLowerCase();
+  if (normalized === "auto" || normalized === "standard_only") {
+    return normalized;
+  }
+  return undefined;
+}
+
 function requiresAnthropicToolPayloadCompatibilityForModel(
  model: {
    api?: unknown;
@@ -374,8 +385,42 @@ export function createAnthropicFastModeWrapper(
  };
 }

+export function createAnthropicServiceTierWrapper(
+  baseStreamFn: StreamFn | undefined,
+  serviceTier: AnthropicServiceTier,
+): StreamFn {
+  const underlying = baseStreamFn ?? streamSimple;
+  return (model, context, options) => {
+    if (
+      model.api !== "anthropic-messages" ||
+      model.provider !== "anthropic" ||
+      !isAnthropicPublicApiBaseUrl(model.baseUrl)
+    ) {
+      return underlying(model, context, options);
+    }
+
+    return streamWithPayloadPatch(underlying, model, context, options, (payloadObj) => {
+      if (payloadObj.service_tier === undefined) {
+        payloadObj.service_tier = serviceTier;
+      }
+    });
+  };
+}
+
 export function resolveAnthropicFastMode(
  extraParams: Record<string, unknown> | undefined,
 ): boolean | undefined {
  return resolveFastModeParam(extraParams);
 }
+
+export function resolveAnthropicServiceTier(
+  extraParams: Record<string, unknown> | undefined,
+): AnthropicServiceTier | undefined {
+  const raw = extraParams?.serviceTier ?? extraParams?.service_tier;
+  const normalized = normalizeAnthropicServiceTier(raw);
+  if (raw !== undefined && normalized === undefined) {
+    const rawSummary = typeof raw === "string" ? raw : typeof raw;
+    log.warn(`ignoring invalid Anthropic service tier param: ${rawSummary}`);
+  }
+  return normalized;
+}
--- a/src/agents/pi-embedded-runner/extra-params.ts
+++ b/src/agents/pi-embedded-runner/extra-params.ts
@@ -12,8 +12,10 @@ import type { ProviderRuntimeModel } from "../../plugins/types.js";
 import {
  createAnthropicBetaHeadersWrapper,
  createAnthropicFastModeWrapper,
+  createAnthropicServiceTierWrapper,
  createAnthropicToolPayloadCompatibilityWrapper,
  resolveAnthropicFastMode,
+  resolveAnthropicServiceTier,
  resolveAnthropicBetas,
  resolveCacheRetention,
 } from "./anthropic-stream-wrappers.js";
@@ -364,6 +366,19 @@ function applyPostPluginStreamWrappers(
  // upstream model-ID heuristics for Gemini 3.1 variants.
  ctx.agent.streamFn = createGoogleThinkingPayloadWrapper(ctx.agent.streamFn, ctx.thinkingLevel);

+  if (ctx.provider === "anthropic") {
+    const anthropicServiceTier = resolveAnthropicServiceTier(ctx.effectiveExtraParams);
+    if (anthropicServiceTier) {
+      log.debug(
+        `applying Anthropic service_tier=${anthropicServiceTier} for ${ctx.provider}/${ctx.modelId}`,
+      );
+      ctx.agent.streamFn = createAnthropicServiceTierWrapper(
+        ctx.agent.streamFn,
+        anthropicServiceTier,
+      );
+    }
+  }
+
  const anthropicFastMode = resolveAnthropicFastMode(ctx.effectiveExtraParams);
  if (anthropicFastMode !== undefined) {
    log.debug(
@@ -388,12 +403,14 @@ function applyPostPluginStreamWrappers(
    ctx.agent.streamFn = createOpenAIFastModeWrapper(ctx.agent.streamFn);
  }

-  const openAIServiceTier = resolveOpenAIServiceTier(ctx.effectiveExtraParams);
-  if (openAIServiceTier) {
-    log.debug(
-      `applying OpenAI service_tier=${openAIServiceTier} for ${ctx.provider}/${ctx.modelId}`,
-    );
-    ctx.agent.streamFn = createOpenAIServiceTierWrapper(ctx.agent.streamFn, openAIServiceTier);
+  if (ctx.provider === "openai" || ctx.provider === "openai-codex") {
+    const openAIServiceTier = resolveOpenAIServiceTier(ctx.effectiveExtraParams);
+    if (openAIServiceTier) {
+      log.debug(
+        `applying OpenAI service_tier=${openAIServiceTier} for ${ctx.provider}/${ctx.modelId}`,
+      );
+      ctx.agent.streamFn = createOpenAIServiceTierWrapper(ctx.agent.streamFn, openAIServiceTier);
+    }
  }

  // Work around upstream pi-ai hardcoding `store: false` for Responses API.