feat(ai): move API implementations to src/api with lazy wrappers (phase 2)

Stream implementations move from src/providers/ to src/api/, renamed by API id (anthropic.ts -> anthropic-messages.ts, google.ts -> google-generative-ai.ts, mistral.ts -> mistral-conversations.ts, amazon-bedrock.ts -> bedrock-converse-stream.ts). Every module now exports exactly stream/streamSimple; shared helpers move alongside. New ProviderStreams dispatch contract in types.ts, lazyApi() wrapper in api/lazy.ts, and one .lazy.ts wrapper per API. Bedrock's wrapper keeps the node-only variable-specifier import and setBedrockProviderModule() (now taking ProviderStreams). providers/register-builtins.ts deleted; interim until the compat entrypoint lands, builtin api-registry registration lives in stream.ts and lazy wrappers are exported from the root barrel. Old per-API lazy exports (streamAnthropic, ...) are gone; package.json subpaths retarget to dist/api/.
2026-06-10 20:08:59 +02:00
parent ee276e4db5
commit ba93da9a93
66 changed files with 283 additions and 560 deletions
@@ -0,0 +1,53 @@
+import type { Api, Model, SimpleStreamOptions, StreamOptions, ThinkingBudgets, ThinkingLevel } from "../types.ts";
+
+export function buildBaseOptions(_model: Model<Api>, options?: SimpleStreamOptions, apiKey?: string): StreamOptions {
+	return {
+		temperature: options?.temperature,
+		maxTokens: options?.maxTokens,
+		signal: options?.signal,
+		apiKey: apiKey || options?.apiKey,
+		transport: options?.transport,
+		cacheRetention: options?.cacheRetention,
+		sessionId: options?.sessionId,
+		headers: options?.headers,
+		onPayload: options?.onPayload,
+		onResponse: options?.onResponse,
+		timeoutMs: options?.timeoutMs,
+		websocketConnectTimeoutMs: options?.websocketConnectTimeoutMs,
+		maxRetries: options?.maxRetries,
+		maxRetryDelayMs: options?.maxRetryDelayMs,
+		metadata: options?.metadata,
+	};
+}
+
+export function clampReasoning(effort: ThinkingLevel | undefined): Exclude<ThinkingLevel, "xhigh"> | undefined {
+	return effort === "xhigh" ? "high" : effort;
+}
+
+export function adjustMaxTokensForThinking(
+	// Undefined means no explicit caller cap. Use the model cap and fit thinking inside it.
+	baseMaxTokens: number | undefined,
+	modelMaxTokens: number,
+	reasoningLevel: ThinkingLevel,
+	customBudgets?: ThinkingBudgets,
+): { maxTokens: number; thinkingBudget: number } {
+	const defaultBudgets: ThinkingBudgets = {
+		minimal: 1024,
+		low: 2048,
+		medium: 8192,
+		high: 16384,
+	};
+	const budgets = { ...defaultBudgets, ...customBudgets };
+
+	const minOutputTokens = 1024;
+	const level = clampReasoning(reasoningLevel)!;
+	let thinkingBudget = budgets[level]!;
+	const maxTokens =
+		baseMaxTokens === undefined ? modelMaxTokens : Math.min(baseMaxTokens + thinkingBudget, modelMaxTokens);
+
+	if (maxTokens <= thinkingBudget) {
+		thinkingBudget = Math.max(0, maxTokens - minOutputTokens);
+	}
+
+	return { maxTokens, thinkingBudget };
+}