vrr/openclaw
2
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-07-09 15:59:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 22

feat(stepfun): add step-3.7-flash model (#88082)

Browse source 
* feat(stepfun): add step-3.7-flash model and make it default

* fix(stepfun): set step-3.7-flash cacheRead cost to 0.04

* fix(stepfun): raise step-3.7-flash maxTokens to context limit

Output was artificially capped at 65536; StepFun docs set max_tokens
default to INF, bounded only by the 256K context window. Raise
step-3.7-flash maxTokens to 262144 on both stepfun and stepfun-plan,
matching contextWindow. Per models.dev anomalyco/models.dev#1903.
step-3.5-flash entries unchanged.

* fix(stepfun): zero step-plan step-3.7-flash cost for plan billing

Step Plan endpoint bills per subscription plan, not per token, matching
the sibling stepfun-plan/step-3.5-flash and step-3.5-flash-2603 entries
which already carry zero cost. Standard stepfun/step-3.7-flash keeps its
per-token rate. Per models.dev anomalyco/models.dev#1903, whose step-plan
providers omit cost entirely.

* docs(changelog): note StepFun 3.7 support

* style(stepfun): format provider table

* fix(stepfun): forward reasoning effort

* fix(stepfun): scope reasoning compat to 3.7

* test(stepfun): keep 3.5 reasoning compat unchanged

* fix(stepfun): carry off fallback through agent turns

* fix(stepfun): use documented token limit field

* fix(stepfun): match chat completions contract

* chore(stepfun): keep changelog release-owned

---------

Co-authored-by: Tianning Li <litianning@stepfun.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
This commit is contained in:
Tianning Li 2026-07-09 14:14:46 +08:00 • committed by GitHub
parent 240ca9dbd7
commit 583ca34bf8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 248 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

81
docs/providers/stepfun.md
View file

@ -35,16 +35,18 @@ Auth env var: `STEPFUN_API_KEY`
Standard (`stepfun`):
| Model ref | Context | Max output | Notes |
| ------------------------ | ------- | ---------- | ---------------------- |
| `stepfun/step-3.5-flash` | 262,144 | 65,536 | Default standard model |
| Model ref | Context | Max output | Notes |
| ------------------------ | ------- | ---------- | ------------------------------ |
| `stepfun/step-3.5-flash` | 262,144 | 65,536 | Default standard model |
| `stepfun/step-3.7-flash` | 262,144 | 262,144 | Multimodal image input support |
Step Plan (`stepfun-plan`):
| Model ref | Context | Max output | Notes |
| ---------------------------------- | ------- | ---------- | -------------------------- |
| `stepfun-plan/step-3.5-flash` | 262,144 | 65,536 | Default Step Plan model |
| `stepfun-plan/step-3.5-flash-2603` | 262,144 | 65,536 | Additional Step Plan model |
| Model ref | Context | Max output | Notes |
| ---------------------------------- | ------- | ---------- | ------------------------------ |
| `stepfun-plan/step-3.5-flash` | 262,144 | 65,536 | Default Step Plan model |
| `stepfun-plan/step-3.7-flash` | 262,144 | 262,144 | Multimodal image input support |
| `stepfun-plan/step-3.5-flash-2603` | 262,144 | 65,536 | Additional Step Plan model |
## Getting started
@ -84,6 +86,7 @@ Step Plan (`stepfun-plan`):
</Steps>
Default model: `stepfun/step-3.5-flash`
Alternate model: `stepfun/step-3.7-flash`
</Tab>
@ -122,7 +125,7 @@ Step Plan (`stepfun-plan`):
</Steps>
Default model: `stepfun-plan/step-3.5-flash`
Alternate model: `stepfun-plan/step-3.5-flash-2603`
Alternate models: `stepfun-plan/step-3.7-flash`, `stepfun-plan/step-3.5-flash-2603`
</Tab>
</Tabs>
@ -145,6 +148,36 @@ A single auth flow writes region-matched profiles for both `stepfun` and `stepfu
api: "openai-completions",
apiKey: "${STEPFUN_API_KEY}",
models: [
{
id: "step-3.7-flash",
name: "Step 3.7 Flash",
reasoning: true,
input: ["text", "image"],
thinkingLevelMap: { off: "low", minimal: "low", xhigh: "high", max: "high" },
cost: { input: 0.2, output: 1.15, cacheRead: 0.04, cacheWrite: 0 },
contextWindow: 262144,
maxTokens: 262144,
compat: {
supportsStore: false,
supportsDeveloperRole: false,
supportsUsageInStreaming: false,
supportsReasoningEffort: true,
supportsStrictMode: false,
supportedReasoningEfforts: ["low", "medium", "high"],
maxTokensField: "max_tokens",
reasoningEffortMap: {
off: "low",
none: "low",
minimal: "low",
low: "low",
medium: "medium",
high: "high",
xhigh: "high",
adaptive: "high",
max: "high",
},
},
},
{
id: "step-3.5-flash",
name: "Step 3.5 Flash",
@ -175,6 +208,36 @@ A single auth flow writes region-matched profiles for both `stepfun` and `stepfu
api: "openai-completions",
apiKey: "${STEPFUN_API_KEY}",
models: [
{
id: "step-3.7-flash",
name: "Step 3.7 Flash",
reasoning: true,
input: ["text", "image"],
thinkingLevelMap: { off: "low", minimal: "low", xhigh: "high", max: "high" },
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
contextWindow: 262144,
maxTokens: 262144,
compat: {
supportsStore: false,
supportsDeveloperRole: false,
supportsUsageInStreaming: false,
supportsReasoningEffort: true,
supportsStrictMode: false,
supportedReasoningEfforts: ["low", "medium", "high"],
maxTokensField: "max_tokens",
reasoningEffortMap: {
off: "low",
none: "low",
minimal: "low",
low: "low",
medium: "medium",
high: "high",
xhigh: "high",
adaptive: "high",
max: "high",
},
},
},
{
id: "step-3.5-flash",
name: "Step 3.5 Flash",
@ -202,6 +265,8 @@ A single auth flow writes region-matched profiles for both `stepfun` and `stepfu
</Accordion>
<Accordion title="Notes">
- `step-3.7-flash` accepts text and image input through OpenClaw. StepFun's API also supports video, which is not yet a model input modality in OpenClaw.
- Step 3.7 supports `low`, `medium`, and `high` reasoning effort. Because the model has no non-reasoning mode, `/think off` maps to `low`.
- `step-3.5-flash-2603` is currently exposed only on `stepfun-plan`.
- Use `openclaw models list` and `openclaw models set <provider/model>` to inspect or switch models.

93
extensions/stepfun/index.test.ts
View file

@ -1,12 +1,20 @@
// Stepfun tests cover index plugin behavior.
import { readFileSync } from "node:fs";
import { resolve } from "node:path";
import type { Context, Model } from "openclaw/plugin-sdk/llm";
import {
registerProviderPlugin,
requireRegisteredProvider,
} from "openclaw/plugin-sdk/plugin-test-runtime";
import { buildOpenAICompletionsParams } from "openclaw/plugin-sdk/provider-transport-runtime";
import { describe, expect, it } from "vitest";
import stepfunPlugin from "./index.js";
import {
STEPFUN_DEFAULT_MODEL_REF,
STEPFUN_PLAN_DEFAULT_MODEL_REF,
buildStepFunPlanProvider,
buildStepFunProvider,
} from "./provider-catalog.js";
type StepFunManifest = {
setup?: {
@ -28,6 +36,91 @@ function readManifest(): StepFunManifest {
}
describe("stepfun provider registration", () => {
it("adds Step 3.7 Flash without changing existing defaults", () => {
const standard = buildStepFunProvider();
const plan = buildStepFunPlanProvider();
const standardModel = standard.models?.find((model) => model.id === "step-3.7-flash");
const planModel = plan.models?.find((model) => model.id === "step-3.7-flash");
if (!standardModel) {
throw new Error("StepFun Standard catalog did not provide Step 3.7 Flash");
}
expect(STEPFUN_DEFAULT_MODEL_REF).toBe("stepfun/step-3.5-flash");
expect(STEPFUN_PLAN_DEFAULT_MODEL_REF).toBe("stepfun-plan/step-3.5-flash");
expect(
standard.models?.find((model) => model.id === "step-3.5-flash")?.compat
?.supportsReasoningEffort,
).not.toBe(true);
expect(standardModel).toMatchObject({
reasoning: true,
input: ["text", "image"],
thinkingLevelMap: { off: "low", minimal: "low", xhigh: "high", max: "high" },
contextWindow: 262144,
maxTokens: 262144,
cost: { input: 0.2, output: 1.15, cacheRead: 0.04, cacheWrite: 0 },
compat: {
supportsStore: false,
supportsDeveloperRole: false,
supportsUsageInStreaming: false,
supportsReasoningEffort: true,
supportsStrictMode: false,
supportedReasoningEfforts: ["low", "medium", "high"],
maxTokensField: "max_tokens",
reasoningEffortMap: expect.objectContaining({ off: "low", medium: "medium", max: "high" }),
},
});
expect(planModel).toMatchObject({
reasoning: true,
input: ["text", "image"],
thinkingLevelMap: { off: "low", minimal: "low", xhigh: "high", max: "high" },
contextWindow: 262144,
maxTokens: 262144,
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
compat: {
supportsStore: false,
supportsDeveloperRole: false,
supportsUsageInStreaming: false,
supportsReasoningEffort: true,
supportsStrictMode: false,
supportedReasoningEfforts: ["low", "medium", "high"],
maxTokensField: "max_tokens",
reasoningEffortMap: expect.objectContaining({ off: "low", medium: "medium", max: "high" }),
},
});
const transportModel = {
...standardModel,
provider: "stepfun",
api: "openai-completions",
baseUrl: standard.baseUrl,
} as Model<"openai-completions">;
const context = {
systemPrompt: "system",
messages: [{ role: "user", content: "hi", timestamp: 1 }],
} as Context;
const offReasoning = standardModel.thinkingLevelMap?.off;
expect(offReasoning).toBe("low");
const lowPayload = buildOpenAICompletionsParams(transportModel, context, {
reasoning: offReasoning,
maxTokens: 128,
} as never);
expect(lowPayload.reasoning_effort).toBe("low");
expect(lowPayload.max_tokens).toBe(128);
expect(lowPayload).not.toHaveProperty("max_completion_tokens");
expect(lowPayload).not.toHaveProperty("store");
expect(lowPayload).not.toHaveProperty("stream_options");
expect(lowPayload.messages).toEqual(
expect.arrayContaining([expect.objectContaining({ role: "system", content: "system" })]),
);
expect(lowPayload.messages).not.toEqual(
expect.arrayContaining([expect.objectContaining({ role: "developer" })]),
);
expect(
buildOpenAICompletionsParams(transportModel, context, { reasoning: "high" } as never)
.reasoning_effort,
).toBe("high");
});
it("keeps manifest auth choices aligned with runtime provider methods", async () => {
const { providers } = await registerProviderPlugin({
plugin: stepfunPlugin,

80
extensions/stepfun/openclaw.plugin.json
View file

@ -25,6 +25,46 @@
"baseUrl": "https://api.stepfun.ai/v1",
"api": "openai-completions",
"models": [
{
"id": "step-3.7-flash",
"name": "Step 3.7 Flash",
"reasoning": true,
"input": ["text", "image"],
"thinkingLevelMap": {
"off": "low",
"minimal": "low",
"xhigh": "high",
"max": "high"
},
"contextWindow": 262144,
"maxTokens": 262144,
"cost": {
"input": 0.2,
"output": 1.15,
"cacheRead": 0.04,
"cacheWrite": 0
},
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsUsageInStreaming": false,
"supportsReasoningEffort": true,
"supportsStrictMode": false,
"supportedReasoningEfforts": ["low", "medium", "high"],
"maxTokensField": "max_tokens",
"reasoningEffortMap": {
"off": "low",
"none": "low",
"minimal": "low",
"low": "low",
"medium": "medium",
"high": "high",
"xhigh": "high",
"adaptive": "high",
"max": "high"
}
}
},
{
"id": "step-3.5-flash",
"name": "Step 3.5 Flash",
@ -45,6 +85,46 @@
"baseUrl": "https://api.stepfun.ai/step_plan/v1",
"api": "openai-completions",
"models": [
{
"id": "step-3.7-flash",
"name": "Step 3.7 Flash",
"reasoning": true,
"input": ["text", "image"],
"thinkingLevelMap": {
"off": "low",
"minimal": "low",
"xhigh": "high",
"max": "high"
},
"contextWindow": 262144,
"maxTokens": 262144,
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsUsageInStreaming": false,
"supportsReasoningEffort": true,
"supportsStrictMode": false,
"supportedReasoningEfforts": ["low", "medium", "high"],
"maxTokensField": "max_tokens",
"reasoningEffortMap": {
"off": "low",
"none": "low",
"minimal": "low",
"low": "low",
"medium": "medium",
"high": "high",
"xhigh": "high",
"adaptive": "high",
"max": "high"
}
}
},
{
"id": "step-3.5-flash",
"name": "Step 3.5 Flash",

4
src/agents/models-config.providers.stepfun.test.ts
View file

@ -7,8 +7,8 @@ import type { ModelDefinitionConfig, ModelProviderConfig } from "../config/types
import { upsertAuthProfile } from "./auth-profiles.js";
import { installModelsConfigTestHooks } from "./models-config.e2e-harness.js";
const EXPECTED_STANDARD_MODELS = ["step-3.5-flash"];
const EXPECTED_PLAN_MODELS = ["step-3.5-flash", "step-3.5-flash-2603"];
const EXPECTED_STANDARD_MODELS = ["step-3.7-flash", "step-3.5-flash"];
const EXPECTED_PLAN_MODELS = ["step-3.7-flash", "step-3.5-flash", "step-3.5-flash-2603"];
const STEPFUN_STANDARD_CN_BASE_URL = "https://api.stepfun.com/v1";
const STEPFUN_STANDARD_INTL_BASE_URL = "https://api.stepfun.ai/v1";
const STEPFUN_PLAN_CN_BASE_URL = "https://api.stepfun.com/step_plan/v1";