shumengya/sproutclaw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add NVIDIA NIM provider

Browse Source
This commit is contained in:
Mario Zechner
2026-06-02 15:09:36 +02:00
parent 13898f048f
commit 6014801229
20 changed files with 700 additions and 66 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
packages/coding-agent/src/core/agent-session.ts
View File

@@ -2787,6 +2787,7 @@ export class AgentSession {
customInstructions,
replaceInstructions,
reserveTokens: branchSummarySettings.reserveTokens,
streamFn: this.agent.streamFn,
});
if (result.aborted) {
return { cancelled: true, aborted: true };

31
packages/coding-agent/src/core/compaction/branch-summarization.ts
View File

@@ -5,8 +5,8 @@
* a summary of the branch being left so context isn't lost.
*/
import type { AgentMessage } from "@earendil-works/pi-agent-core";
import type { Model } from "@earendil-works/pi-ai";
import type { AgentMessage, StreamFn } from "@earendil-works/pi-agent-core";
import type { Model, SimpleStreamOptions } from "@earendil-works/pi-ai";
import { completeSimple } from "@earendil-works/pi-ai";
import {
convertToLlm,
@@ -77,6 +77,8 @@ export interface GenerateBranchSummaryOptions {
replaceInstructions?: boolean;
/** Tokens reserved for prompt + LLM response (default 16384) */
reserveTokens?: number;
/** Optional session stream function. Used to preserve SDK request behavior without mutating agent state. */
streamFn?: StreamFn;
}
// ============================================================================
@@ -284,7 +286,16 @@ export async function generateBranchSummary(
entries: SessionEntry[],
options: GenerateBranchSummaryOptions,
): Promise<BranchSummaryResult> {
const { model, apiKey, headers, signal, customInstructions, replaceInstructions, reserveTokens = 16384 } = options;
const {
model,
apiKey,
headers,
signal,
customInstructions,
replaceInstructions,
reserveTokens = 16384,
streamFn,
} = options;
// Token budget = context window minus reserved space for prompt + response
const contextWindow = model.contextWindow || 128000;
@@ -320,12 +331,14 @@ export async function generateBranchSummary(
},
];
// Call LLM for summarization
const response = await completeSimple(
model,
{ systemPrompt: SUMMARIZATION_SYSTEM_PROMPT, messages: summarizationMessages },
{ apiKey, headers, signal, maxTokens: 2048 },
);
// Call LLM for summarization. Prefer the session stream function so SDK
// request behavior (timeouts, retries, attribution headers) stays consistent
// without running through agent state/events.
const context = { systemPrompt: SUMMARIZATION_SYSTEM_PROMPT, messages: summarizationMessages };
const requestOptions: SimpleStreamOptions = { apiKey, headers, signal, maxTokens: 2048 };
const response = streamFn
? await (await streamFn(model, context, requestOptions)).result()
: await completeSimple(model, context, requestOptions);
// Check if aborted or errored
if (response.stopReason === "aborted") {

1
packages/coding-agent/src/core/model-resolver.ts
View File

@@ -17,6 +17,7 @@ export const defaultModelPerProvider: Record<KnownProvider, string> = {
openai: "gpt-5.4",
"azure-openai-responses": "gpt-5.4",
"openai-codex": "gpt-5.5",
nvidia: "nvidia/nemotron-3-super-120b-a12b",
deepseek: "deepseek-v4-pro",
google: "gemini-3.1-pro-preview",
"google-vertex": "gemini-3.1-pro-preview",

97
packages/coding-agent/src/core/provider-attribution.ts Normal file
View File

@@ -0,0 +1,97 @@
import type { Api, Model } from "@earendil-works/pi-ai";
import type { SettingsManager } from "./settings-manager.ts";
import { isInstallTelemetryEnabled } from "./telemetry.ts";
const OPENROUTER_HOST = "openrouter.ai";
const NVIDIA_NIM_HOST = "integrate.api.nvidia.com";
const CLOUDFLARE_API_HOST = "api.cloudflare.com";
const CLOUDFLARE_AI_GATEWAY_HOST = "gateway.ai.cloudflare.com";
const OPENCODE_HOST = "opencode.ai";
function matchesHost(baseUrl: string, expectedHost: string): boolean {
try {
return new URL(baseUrl).hostname === expectedHost;
} catch {
return false;
}
}
function isOpenRouterModel(model: Model<Api>): boolean {
return model.provider === "openrouter" || model.baseUrl.includes(OPENROUTER_HOST);
}
function isNvidiaNimModel(model: Model<Api>): boolean {
return model.provider === "nvidia" || matchesHost(model.baseUrl, NVIDIA_NIM_HOST);
}
function isCloudflareModel(model: Model<Api>): boolean {
return (
model.provider === "cloudflare-workers-ai" ||
model.provider === "cloudflare-ai-gateway" ||
matchesHost(model.baseUrl, CLOUDFLARE_API_HOST) ||
matchesHost(model.baseUrl, CLOUDFLARE_AI_GATEWAY_HOST)
);
}
function getDefaultAttributionHeaders(
model: Model<Api>,
settingsManager: SettingsManager,
): Record<string, string> | undefined {
if (!isInstallTelemetryEnabled(settingsManager)) {
return undefined;
}
if (isOpenRouterModel(model)) {
return {
"HTTP-Referer": "https://pi.dev",
"X-OpenRouter-Title": "pi",
"X-OpenRouter-Categories": "cli-agent",
};
}
if (isNvidiaNimModel(model)) {
return {
"X-BILLING-INVOKE-ORIGIN": "Pi",
};
}
if (isCloudflareModel(model)) {
return {
"User-Agent": "pi-coding-agent",
};
}
return undefined;
}
function getSessionHeaders(model: Model<Api>, sessionId: string | undefined): Record<string, string> | undefined {
if (!sessionId) return undefined;
if (
model.provider !== "opencode" &&
model.provider !== "opencode-go" &&
!matchesHost(model.baseUrl, OPENCODE_HOST)
) {
return undefined;
}
return { "x-opencode-session": sessionId, "x-opencode-client": "pi" };
}
export function mergeProviderAttributionHeaders(
model: Model<Api>,
settingsManager: SettingsManager,
sessionId: string | undefined,
...headerSources: Array<Record<string, string> | undefined>
): Record<string, string> | undefined {
const merged = {
...getSessionHeaders(model, sessionId),
...getDefaultAttributionHeaders(model, settingsManager),
};
for (const headers of headerSources) {
if (headers) {
Object.assign(merged, headers);
}
}
return Object.keys(merged).length > 0 ? merged : undefined;
}

1
packages/coding-agent/src/core/provider-display-names.ts
View File

@@ -17,6 +17,7 @@ export const BUILT_IN_PROVIDER_DISPLAY_NAMES: Record<string, string> = {
"minimax-cn": "MiniMax (China)",
moonshotai: "Moonshot AI",
"moonshotai-cn": "Moonshot AI (China)",
nvidia: "NVIDIA NIM",
opencode: "OpenCode Zen",
"opencode-go": "OpenCode Go",
openai: "OpenAI",

52
packages/coding-agent/src/core/sdk.ts
View File

@@ -11,11 +11,11 @@ import type { ExtensionRunner, LoadExtensionsResult, SessionStartEvent, ToolDefi
import { convertToLlm } from "./messages.ts";
import { ModelRegistry } from "./model-registry.ts";
import { findInitialModel } from "./model-resolver.ts";
import { mergeProviderAttributionHeaders } from "./provider-attribution.ts";
import type { ResourceLoader } from "./resource-loader.ts";
import { DefaultResourceLoader } from "./resource-loader.ts";
import { getDefaultSessionDir, SessionManager } from "./session-manager.ts";
import { SettingsManager } from "./settings-manager.ts";
import { isInstallTelemetryEnabled } from "./telemetry.ts";
import { time } from "./timings.ts";
import {
createBashTool,
@@ -128,44 +128,6 @@ function getDefaultAgentDir(): string {
return getAgentDir();
}
function getAttributionHeaders(
model: Model<any>,
settingsManager: SettingsManager,
sessionId?: string,
): Record<string, string> | undefined {
if (
sessionId &&
(model.provider === "opencode" || model.provider === "opencode-go" || model.baseUrl.includes("opencode.ai"))
) {
return { "x-opencode-session": sessionId, "x-opencode-client": "pi" };
}
if (!isInstallTelemetryEnabled(settingsManager)) {
return undefined;
}
if (model.provider === "openrouter" || model.baseUrl.includes("openrouter.ai")) {
return {
"HTTP-Referer": "https://pi.dev",
"X-OpenRouter-Title": "pi",
"X-OpenRouter-Categories": "cli-agent",
};
}
if (
model.provider === "cloudflare-workers-ai" ||
model.provider === "cloudflare-ai-gateway" ||
model.baseUrl.includes("api.cloudflare.com") ||
model.baseUrl.includes("gateway.ai.cloudflare.com")
) {
return {
"User-Agent": "pi-coding-agent",
};
}
return undefined;
}
/**
* Create an AgentSession with the specified options.
*
@@ -349,7 +311,6 @@ export async function createAgentSession(options: CreateAgentSessionOptions = {}
const timeoutMs = options?.timeoutMs ?? providerRetrySettings.timeoutMs ?? effectiveTimeoutMs;
const websocketConnectTimeoutMs =
options?.websocketConnectTimeoutMs ?? settingsManager.getWebSocketConnectTimeoutMs();
const attributionHeaders = getAttributionHeaders(model, settingsManager, options?.sessionId);
return streamSimple(model, context, {
...options,
apiKey: auth.apiKey,
@@ -357,10 +318,13 @@ export async function createAgentSession(options: CreateAgentSessionOptions = {}
websocketConnectTimeoutMs,
maxRetries: options?.maxRetries ?? providerRetrySettings.maxRetries,
maxRetryDelayMs: options?.maxRetryDelayMs ?? providerRetrySettings.maxRetryDelayMs,
headers:
attributionHeaders || auth.headers || options?.headers
? { ...attributionHeaders, ...auth.headers, ...options?.headers }
: undefined,
headers: mergeProviderAttributionHeaders(
model,
settingsManager,
options?.sessionId,
auth.headers,
options?.headers,
),
});
},
onPayload: async (payload, _model) => {