diff --git a/apps/server/package.json b/apps/server/package.json index d678f8b..eb70147 100644 --- a/apps/server/package.json +++ b/apps/server/package.json @@ -11,8 +11,10 @@ "test": "vitest run" }, "dependencies": { + "@ai-sdk/openai-compatible": "^2.0.47", "@fastify/static": "^7.0.4", "@fastify/websocket": "^10.0.1", + "ai": "^6.0.190", "fastify": "^4.28.1", "postgres": "^3.4.4", "ws": "^8.18.0", diff --git a/apps/server/src/services/inference/provider.ts b/apps/server/src/services/inference/provider.ts new file mode 100644 index 0000000..8edce34 --- /dev/null +++ b/apps/server/src/services/inference/provider.ts @@ -0,0 +1,26 @@ +import { createOpenAICompatible } from '@ai-sdk/openai-compatible'; +import type { LanguageModel } from 'ai'; + +// v1.13.1-A: AI SDK provider against llama-swap. baseURL is threaded from +// config.LLAMA_SWAP_URL at call time (not module-load) so tests can stub the +// upstream without touching env vars. No apiKey — llama-swap is unauth in our +// Tailscale topology and exposing it over the public internet is gated by +// Authelia at the Caddy layer, not by API keys. + +const cache = new Map>(); + +function getProvider(baseURL: string): ReturnType { + let provider = cache.get(baseURL); + if (!provider) { + provider = createOpenAICompatible({ + name: 'llama-swap', + baseURL: baseURL.endsWith('/v1') ? baseURL : `${baseURL}/v1`, + }); + cache.set(baseURL, provider); + } + return provider; +} + +export function upstreamModel(baseURL: string, modelId: string): LanguageModel { + return getProvider(baseURL).chatModel(modelId); +} diff --git a/apps/server/src/services/inference/stream-phase.ts b/apps/server/src/services/inference/stream-phase.ts index 2e5092f..7be694d 100644 --- a/apps/server/src/services/inference/stream-phase.ts +++ b/apps/server/src/services/inference/stream-phase.ts @@ -18,29 +18,8 @@ import type { StreamResult, TurnArgs, } from './turn.js'; - -interface ChatCompletionDelta { - role?: string; - content?: string | null; - tool_calls?: Array<{ - index: number; - id?: string; - type?: 'function'; - function?: { name?: string; arguments?: string }; - }>; -} - -interface ChatCompletionChunk { - choices?: Array<{ - delta: ChatCompletionDelta; - finish_reason: string | null; - }>; - usage?: { - prompt_tokens?: number; - completion_tokens?: number; - total_tokens?: number; - }; -} +import { upstreamModel } from './provider.js'; +import { jsonSchema, streamText, tool, type JSONValue, type ModelMessage } from 'ai'; interface StreamOptions { // null = omit tools entirely (compact phase); [] = caller stripped all tools @@ -49,44 +28,105 @@ interface StreamOptions { temperature?: number; } -async function* sseLines(stream: ReadableStream): AsyncGenerator { - const reader = stream.getReader(); - const decoder = new TextDecoder('utf-8'); - let buffer = ''; - try { - while (true) { - const { value, done } = await reader.read(); - if (done) break; - buffer += decoder.decode(value, { stream: true }); - let idx; - while ((idx = buffer.indexOf('\n')) >= 0) { - const line = buffer.slice(0, idx).replace(/\r$/, ''); - buffer = buffer.slice(idx + 1); - if (line.length === 0) continue; - yield line; +// v1.13.1-A: convert BooCode's OpenAI-shaped history into AI SDK +// ModelMessage[]. Tool result messages need a `toolName` field that the +// OpenAI shape doesn't carry; we look it up by scanning earlier assistant +// `tool_calls` entries for a matching id. +function toModelMessages(messages: OpenAiMessage[]): ModelMessage[] { + const toolNameById = new Map(); + for (const m of messages) { + if (m.role === 'assistant' && m.tool_calls) { + for (const tc of m.tool_calls) { + toolNameById.set(tc.id, tc.function.name); } } - if (buffer.length > 0) yield buffer; - } finally { - reader.releaseLock(); } + const out: ModelMessage[] = []; + for (const m of messages) { + if (m.role === 'system' || m.role === 'user') { + out.push({ role: m.role, content: m.content ?? '' }); + continue; + } + if (m.role === 'assistant') { + const hasTools = m.tool_calls && m.tool_calls.length > 0; + if (!hasTools) { + // Bare text assistant (string content). null content + no tool_calls + // is degenerate but harmless to forward. + out.push({ role: 'assistant', content: m.content ?? '' }); + continue; + } + const parts: Array< + | { type: 'text'; text: string } + | { type: 'tool-call'; toolCallId: string; toolName: string; input: unknown } + > = []; + if (m.content && m.content.length > 0) { + parts.push({ type: 'text', text: m.content }); + } + for (const tc of m.tool_calls!) { + let input: unknown = {}; + try { + input = tc.function.arguments.length > 0 ? JSON.parse(tc.function.arguments) : {}; + } catch { + // Malformed args from a prior turn: pass through as a raw blob so + // the model sees the same shape it emitted. Wraps the string under + // _raw to match the buildMessagesPayload upstream convention. + input = { _raw: tc.function.arguments }; + } + parts.push({ type: 'tool-call', toolCallId: tc.id, toolName: tc.function.name, input }); + } + out.push({ role: 'assistant', content: parts }); + continue; + } + if (m.role === 'tool') { + const toolCallId = m.tool_call_id ?? ''; + const toolName = toolNameById.get(toolCallId) ?? 'unknown'; + const raw = m.content ?? ''; + let output: { type: 'text'; value: string } | { type: 'json'; value: JSONValue }; + try { + // JSON.parse returns `any`; cast to JSONValue since the upstream + // tool_results column is already JSON-serializable by construction. + output = { type: 'json', value: JSON.parse(raw) as JSONValue }; + } catch { + output = { type: 'text', value: raw }; + } + out.push({ + role: 'tool', + content: [{ type: 'tool-result', toolCallId, toolName, output }], + }); + continue; + } + } + return out; +} + +// Build the AI SDK tools record from BooCode's JSON-schema tool definitions. +// No `execute` field: BooCode runs tools itself in tool-phase.ts; streamText +// surfaces the tool-call parts via fullStream and we capture them for the +// outer loop to dispatch. +function buildAiTools(schemas: ToolJsonSchema[]): Record> { + const out: Record> = {}; + for (const s of schemas) { + out[s.function.name] = tool({ + description: s.function.description, + inputSchema: jsonSchema(s.function.parameters), + }); + } + return out; } // v1.10.5 Qwen-coder XML fallback. Some local models (notably qwen3-coder via // llama-swap) emit tool calls as inline XML inside delta.content rather than -// the structured delta.tool_calls field. The XML shape is: +// the structured tool_calls field. We extract them out of the streamed text +// before flushing it to the client, mirroring the pre-AI-SDK behavior. +// +// XML shape: // // -// -// VALUE -// -// ...more parameters... +// VALUE +// ... // // // Multiple blocks may appear back-to-back; they never nest. -// streamCompletion buffers delta.content, extracts complete blocks, parses -// them via parseXmlToolCall, and pushes synthetic entries into the existing -// toolCallsBuffer alongside any native JSON-format tool calls. export async function streamCompletion( ctx: InferenceContext, model: string, @@ -96,149 +136,156 @@ export async function streamCompletion( onUsage: ((prompt: number | null, completion: number | null) => void) | undefined, signal?: AbortSignal ): Promise { - const body: Record = { - model, - messages, - stream: true, - stream_options: { include_usage: true }, - }; - if (opts.tools && opts.tools.length > 0) { - body['tools'] = opts.tools; - body['tool_choice'] = 'auto'; - } - if (typeof opts.temperature === 'number') { - body['temperature'] = opts.temperature; - } + const aiMessages = toModelMessages(messages); + const hasTools = opts.tools !== null && opts.tools.length > 0; + const aiTools = hasTools ? buildAiTools(opts.tools!) : undefined; - const res = await fetch(`${ctx.config.LLAMA_SWAP_URL}/v1/chat/completions`, { - method: 'POST', - headers: { 'Content-Type': 'application/json' }, - body: JSON.stringify(body), - signal, + const startedAt = Date.now(); + let reasoningDeltaCount = 0; + + const result = streamText({ + model: upstreamModel(ctx.config.LLAMA_SWAP_URL, model), + messages: aiMessages, + ...(aiTools ? { tools: aiTools, toolChoice: 'auto' as const } : {}), + ...(typeof opts.temperature === 'number' ? { temperature: opts.temperature } : {}), + abortSignal: signal, }); - if (!res.ok || !res.body) { - const text = await res.text().catch(() => ''); - throw new Error(`llama-swap returned ${res.status}: ${text.slice(0, 200)}`); - } let content = ''; - // v1.10.5: holds delta.content bytes that may contain a partial XML tool - // call. Anything not part of a (possibly forming) … - // pair is flushed to content + onDelta as soon as we know it's safe. let pendingBuffer = ''; let finishReason: string | null = null; - let promptTokens: number | null = null; - let completionTokens: number | null = null; - const toolCallsBuffer = new Map(); + // v1.13.1-A: AI SDK emits one `tool-call` part per fully-aggregated call, + // so we no longer need the OpenAI-index reassembly map the manual SSE + // parser used. XML tool calls extracted from text content go into the + // same flat list and keep the v1.10.5 synthetic id convention. + const toolCalls: ToolCall[] = []; - for await (const line of sseLines(res.body)) { - if (!line.startsWith('data:')) continue; - const payload = line.slice(5).trim(); - if (payload === '[DONE]') break; - let parsed: ChatCompletionChunk; - try { - parsed = JSON.parse(payload); - } catch { - continue; - } - - if (parsed.usage) { - if (typeof parsed.usage.prompt_tokens === 'number') { - promptTokens = parsed.usage.prompt_tokens; - } - if (typeof parsed.usage.completion_tokens === 'number') { - completionTokens = parsed.usage.completion_tokens; - } - onUsage?.(promptTokens, completionTokens); - } - // v1.11.3: removed dead `parsed.timings.n_ctx` read. llama-server's - // streaming completion does NOT emit n_ctx in timings (verified - // empirically); the authoritative source is llama-swap's - // /upstream//props endpoint, fetched per-turn via - // model-context.getModelContext() at the finalization sites below. - - const choice = parsed.choices?.[0]; - if (!choice) continue; - const delta = choice.delta ?? {}; - if (typeof delta.content === 'string' && delta.content.length > 0) { - // v1.10.5 XML fallback. Append, then extract any complete tool_call - // blocks before deciding what's safe to flush as visible content. - pendingBuffer += delta.content; - while (true) { - const startIdx = pendingBuffer.indexOf(XML_TOOL_OPEN); - if (startIdx === -1) break; - const closeIdx = pendingBuffer.indexOf(XML_TOOL_CLOSE, startIdx); - if (closeIdx === -1) break; - const blockEnd = closeIdx + XML_TOOL_CLOSE.length; - const block = pendingBuffer.slice(startIdx, blockEnd); - // Any text before the opener is plain content — flush it now. - if (startIdx > 0) { - const before = pendingBuffer.slice(0, startIdx); - content += before; - onDelta(before); + for await (const part of result.fullStream) { + switch (part.type) { + case 'text-delta': { + pendingBuffer += part.text; + // Extract any complete ... blocks before + // flushing visible text. + while (true) { + const startIdx = pendingBuffer.indexOf(XML_TOOL_OPEN); + if (startIdx === -1) break; + const closeIdx = pendingBuffer.indexOf(XML_TOOL_CLOSE, startIdx); + if (closeIdx === -1) break; + const blockEnd = closeIdx + XML_TOOL_CLOSE.length; + const block = pendingBuffer.slice(startIdx, blockEnd); + if (startIdx > 0) { + const before = pendingBuffer.slice(0, startIdx); + content += before; + onDelta(before); + } + const parsedCall = parseXmlToolCall(block); + if (parsedCall) { + const synthIdx = toolCalls.length; + toolCalls.push({ + id: `xml_call_${synthIdx}`, + name: parsedCall.name, + args: parsedCall.args, + }); + } + // Parse failures still drop the block — leaking XML to + // the chat would look worse than silently swallowing the bad block. + pendingBuffer = pendingBuffer.slice(blockEnd); } - const parsedCall = parseXmlToolCall(block); - if (parsedCall) { - const synthIdx = toolCallsBuffer.size; - toolCallsBuffer.set(synthIdx, { - id: `xml_call_${synthIdx}`, - name: parsedCall.name, - argsText: JSON.stringify(parsedCall.args), - }); + // Hold back any (partial or full) unclosed opener; flush the rest. + const partialIdx = partialXmlOpenerStart(pendingBuffer); + if (partialIdx >= 0) { + if (partialIdx > 0) { + const flush = pendingBuffer.slice(0, partialIdx); + content += flush; + onDelta(flush); + } + pendingBuffer = pendingBuffer.slice(partialIdx); + } else if (pendingBuffer.length > 0) { + content += pendingBuffer; + onDelta(pendingBuffer); + pendingBuffer = ''; } - // If parsing failed we still drop the block — emitting unparseable - // XML to the chat would look worse than silently swallowing it. - pendingBuffer = pendingBuffer.slice(blockEnd); + break; } - // After all complete blocks are out, hold back any (partial or full) - // unclosed opener; flush the rest. - const partialIdx = partialXmlOpenerStart(pendingBuffer); - if (partialIdx >= 0) { - if (partialIdx > 0) { - const flush = pendingBuffer.slice(0, partialIdx); - content += flush; - onDelta(flush); + case 'tool-call': { + // AI SDK has already parsed the input into an object. Match the + // ToolCall shape BooCode passes around in toolCallsBuffer downstream. + toolCalls.push({ + id: part.toolCallId, + name: part.toolName, + args: (part.input ?? {}) as Record, + }); + break; + } + case 'reasoning-delta': { + // v1.13.1-A: reasoning parts are dropped for now. v1.13.1-C will + // persist them as `kind='reasoning'` rows in message_parts. Counter + // is logged at finish so we know whether qwen3.6 actually emits any. + reasoningDeltaCount += 1; + break; + } + case 'finish': { + if (typeof part.finishReason === 'string') { + finishReason = part.finishReason; } - pendingBuffer = pendingBuffer.slice(partialIdx); - } else if (pendingBuffer.length > 0) { - content += pendingBuffer; - onDelta(pendingBuffer); - pendingBuffer = ''; + break; } - } - if (Array.isArray(delta.tool_calls)) { - for (const tc of delta.tool_calls) { - const idx = tc.index; - const existing = toolCallsBuffer.get(idx) ?? { id: '', name: '', argsText: '' }; - if (tc.id) existing.id = tc.id; - if (tc.function?.name) existing.name = tc.function.name; - if (typeof tc.function?.arguments === 'string') existing.argsText += tc.function.arguments; - toolCallsBuffer.set(idx, existing); + case 'error': { + const err = part.error; + throw err instanceof Error ? err : new Error(String(err)); } + // Intentional no-op: start, start-step, text-start, text-end, + // reasoning-start, reasoning-end, source, file, tool-input-start, + // tool-input-delta, tool-input-end, tool-result, tool-error, + // finish-step, raw. We only care about the aggregated tool-call and + // text-delta paths above; the rest are AI SDK lifecycle/streaming + // breadcrumbs that don't change BooCode's persistence or WS contract. + default: + break; } - if (choice.finish_reason) finishReason = choice.finish_reason; } - // v1.10.5: if the stream ended mid-XML (e.g. model truncated, no closer - // ever arrived), flush whatever was buffered as plain content so it isn't - // silently dropped. Better to show a stray `` than vanish text. + // v1.13.1-A: drain any buffered partial XML opener as plain text. The + // pre-AI-SDK path did this on stream end too — better to leak ` 0) { content += pendingBuffer; onDelta(pendingBuffer); pendingBuffer = ''; } - const toolCalls: ToolCall[] = []; - for (const [, t] of [...toolCallsBuffer.entries()].sort(([a], [b]) => a - b)) { - let args: Record = {}; - if (t.argsText.length > 0) { - try { - args = JSON.parse(t.argsText); - } catch { - args = { _raw: t.argsText }; - } - } - toolCalls.push({ id: t.id || `call_${toolCalls.length}`, name: t.name, args }); + // v1.13.1-A: AI SDK v6 swallows the abort signal — the fullStream iterator + // exits cleanly and we'd otherwise return a successful StreamResult, which + // makes executeStreamPhase call finalizeCompletion and write status='complete'. + // Detect post-iteration abort and throw an AbortError so handleAbortOrError + // owns the row instead, matching v1.12.x stop-button behavior. + if (signal?.aborted) { + const abortErr = new Error('aborted'); + abortErr.name = 'AbortError'; + throw abortErr; + } + + // Usage lands as a promise on the result; awaiting after fullStream is + // drained is safe. AI SDK v6 names: `inputTokens` / `outputTokens`. + let promptTokens: number | null = null; + let completionTokens: number | null = null; + try { + const usage = await result.usage; + if (typeof usage.inputTokens === 'number') promptTokens = usage.inputTokens; + if (typeof usage.outputTokens === 'number') completionTokens = usage.outputTokens; + } catch { + // Some providers omit usage on partial streams; leave both null. + } + + if (onUsage && (promptTokens !== null || completionTokens !== null)) { + onUsage(promptTokens, completionTokens); + } + + if (reasoningDeltaCount > 0) { + ctx.log.debug( + { reasoningDeltaCount, model, elapsed_ms: Date.now() - startedAt }, + 'streamCompletion: reasoning deltas dropped (captured in v1.13.1-C)', + ); } return { finishReason, content, toolCalls, promptTokens, completionTokens }; @@ -313,9 +360,12 @@ export async function executeStreamPhase( const mctxForStream = await modelContext.getModelContext(session.model); const nCtxForStream = mctxForStream?.n_ctx ?? null; - // v1.12.2: throttle live usage publishes to ~500ms. The model can land - // dozens of usage frames per second; without a throttle the WS turns into - // a firehose for a few KB savings on each render. + // v1.12.2 → v1.13.1-A: live usage publishes were throttled to ~500ms when + // the manual SSE parser saw `parsed.usage` per chunk. AI SDK v6 surfaces + // usage only at stream end (result.usage promise), so the throttle is + // effectively a single trailing publish. ChatThroughput will tick once at + // stream completion rather than mid-stream — known regression vs v1.12.2, + // recovered if a future dispatch interpolates from delta cadence. const USAGE_THROTTLE_MS = 500; let lastUsageAt = 0; let pendingUsage: { p: number | null; c: number | null } | null = null; diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 9b93b2a..b2d9c43 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -48,12 +48,18 @@ importers: apps/server: dependencies: + '@ai-sdk/openai-compatible': + specifier: ^2.0.47 + version: 2.0.47(zod@3.25.76) '@fastify/static': specifier: ^7.0.4 version: 7.0.4 '@fastify/websocket': specifier: ^10.0.1 version: 10.0.1 + ai: + specifier: ^6.0.190 + version: 6.0.190(zod@3.25.76) fastify: specifier: ^4.28.1 version: 4.29.1 @@ -179,6 +185,28 @@ importers: packages: + '@ai-sdk/gateway@3.0.119': + resolution: {integrity: sha512-VAhfRWC+JexZakkVfmjaJKaTj00x7/UHdE8kMWL3NhuQAlf8oXtg9r4dfvFZrByXxchGRBvYE3biEUyibkg0xg==} + engines: {node: '>=18'} + peerDependencies: + zod: ^3.25.76 || ^4.1.8 + + '@ai-sdk/openai-compatible@2.0.47': + resolution: {integrity: sha512-Enm5UlL0zUCrW3792opk5h7hRWxZOZzDe6eQYVFqX9LUOGGCe1h8MZWAGim765nwzgnjlpeYOsuzZmLtRsTPlg==} + engines: {node: '>=18'} + peerDependencies: + zod: ^3.25.76 || ^4.1.8 + + '@ai-sdk/provider-utils@4.0.27': + resolution: {integrity: sha512-ubkAJ+xODouwtmN1tYlvTPphH1hPOBfZaEQe8U7skGvFAnIRs9PPpsq57bC2+Ky/MB4yzhd6YOsxTAx9sGpazw==} + engines: {node: '>=18'} + peerDependencies: + zod: ^3.25.76 || ^4.1.8 + + '@ai-sdk/provider@3.0.10': + resolution: {integrity: sha512-Q3BZ27qfpYqnCYGvE3vt+Qi6LGOF9R5Nmzn+9JoM1lCRsD9mYaIhfJLkSunN48nfGXJ6n+XNV0J/XVpqGQl7Dw==} + engines: {node: '>=18'} + '@alloc/quick-lru@5.2.0': resolution: {integrity: sha512-UrcABB+4bUrFABwbluTIBErXwvbsU/V7TZWfmbgJfbkwiBuziS9gxdODUyuiecfdGQ85jglMW6juS3+z5TsKLw==} engines: {node: '>=10'} @@ -789,6 +817,10 @@ packages: '@open-draft/until@2.1.0': resolution: {integrity: sha512-U69T3ItWHvLwGg5eJ0n3I62nWuE6ilHlmz7zM0npLBRvPRd7e6NYmg54vvRtP5mZG7kZqZCFVdsTWo7BPtBujg==} + '@opentelemetry/api@1.9.1': + resolution: {integrity: sha512-gLyJlPHPZYdAk1JENA9LeHejZe1Ti77/pTeFm/nMXmQH/HFZlcS/O2XJB+L8fkbrNSqhdtlvjBVjxwUYanNH5Q==} + engines: {node: '>=8.0.0'} + '@pinojs/redact@0.4.0': resolution: {integrity: sha512-k2ENnmBugE/rzQfEcdWHcCY+/FM3VLzH9cYEsbdsoqrvzAKRhUZeRNhAZvB8OitQJ1TBed3yqWtdjzS6wJKBwg==} @@ -1646,6 +1678,9 @@ packages: resolution: {integrity: sha512-tlqY9xq5ukxTUZBmoOp+m61cqwQD5pHJtFY3Mn8CA8ps6yghLH/Hw8UPdqg4OLmFW3IFlcXnQNmo/dh8HzXYIQ==} engines: {node: '>=18'} + '@standard-schema/spec@1.1.0': + resolution: {integrity: sha512-l2aFy5jALhniG5HgqrD6jXLi/rUWrKvqN/qJx6yoJsgKhblVd+iqqU4RCXavm/jPityDo5TCvKMnpjKnOriy0w==} + '@tailwindcss/node@4.3.0': resolution: {integrity: sha512-aFb4gUhFOgdh9AXo4IzBEOzBkkAxm9VigwDJnMIYv3lcfXCJVesNfbEaBl4BNgVRyid92AmdviqwBUBRKSeY3g==} @@ -1811,6 +1846,10 @@ packages: '@ungap/structured-clone@1.3.1': resolution: {integrity: sha512-mUFwbeTqrVgDQxFveS+df2yfap6iuP20NAKAsBt5jDEoOTDew+zwLAOilHCeQJOVSvmgCX4ogqIrA0mnyr08yQ==} + '@vercel/oidc@3.2.0': + resolution: {integrity: sha512-UycprH3T6n3jH0k44NHMa7pnFHGu/N05MjojYr+Mc6I7obkoLIJujSWwin1pCvdy/eOxrI/l3uDLQsmcrOb4ug==} + engines: {node: '>= 20'} + '@vitejs/plugin-react@4.7.0': resolution: {integrity: sha512-gUu9hwfWvvEDBBmgtAowQCojwZmJ5mcLn3aufeCsitijs3+f2NsrPtlAWIR6OPiqljl96GVCUbLe0HyqIpVaoA==} engines: {node: ^14.18.0 || >=16.0.0} @@ -1878,6 +1917,12 @@ packages: resolution: {integrity: sha512-MnA+YT8fwfJPgBx3m60MNqakm30XOkyIoH1y6huTQvC0PwZG7ki8NacLBcrPbNoo8vEZy7Jpuk7+jMO+CUovTQ==} engines: {node: '>= 14'} + ai@6.0.190: + resolution: {integrity: sha512-T+ixHbWZ6jmHRREpVVJTkFyWJeCekCdzLPan7lp1F32jG5OUw4+odlVYjtMRXVzogU+pWzpMmXdRiHUmdL/q0w==} + engines: {node: '>=18'} + peerDependencies: + zod: ^3.25.76 || ^4.1.8 + ajv-formats@2.1.1: resolution: {integrity: sha512-Wx0Kx52hxE7C18hkMEggYlEifqWZtYaRgouJor+WMdPnQyEK13vgEWyVNup7SoeeoLMsr4kf5h6dOW11I15MUA==} peerDependencies: @@ -2694,6 +2739,9 @@ packages: json-schema-typed@8.0.2: resolution: {integrity: sha512-fQhoXdcvc3V28x7C7BMs4P5+kNlgUURe2jmUT1T//oBRMDrqy1QPelJimwZGo7Hg9VPV3EQV5Bnq4hbFy2vetA==} + json-schema@0.4.0: + resolution: {integrity: sha512-es94M3nTIfsEPisRafak+HDLfHXnKBhV3vU5eqPcS3flIWqcxJWgXHXiey3YrpaNsanY5ei1VoYEbOzijuq9BA==} + json5@2.2.3: resolution: {integrity: sha512-XmOWe7eyHYH14cLdVPoyg+GOH3rYX++KpzrylJwSW98t3Nk+U8XOl8FWKOgwtzdb8lXGf6zYwDUzeHMWfxasyg==} engines: {node: '>=6'} @@ -3966,6 +4014,30 @@ packages: snapshots: + '@ai-sdk/gateway@3.0.119(zod@3.25.76)': + dependencies: + '@ai-sdk/provider': 3.0.10 + '@ai-sdk/provider-utils': 4.0.27(zod@3.25.76) + '@vercel/oidc': 3.2.0 + zod: 3.25.76 + + '@ai-sdk/openai-compatible@2.0.47(zod@3.25.76)': + dependencies: + '@ai-sdk/provider': 3.0.10 + '@ai-sdk/provider-utils': 4.0.27(zod@3.25.76) + zod: 3.25.76 + + '@ai-sdk/provider-utils@4.0.27(zod@3.25.76)': + dependencies: + '@ai-sdk/provider': 3.0.10 + '@standard-schema/spec': 1.1.0 + eventsource-parser: 3.0.8 + zod: 3.25.76 + + '@ai-sdk/provider@3.0.10': + dependencies: + json-schema: 0.4.0 + '@alloc/quick-lru@5.2.0': {} '@babel/code-frame@7.29.0': @@ -4516,6 +4588,8 @@ snapshots: '@open-draft/until@2.1.0': {} + '@opentelemetry/api@1.9.1': {} + '@pinojs/redact@0.4.0': {} '@pkgjs/parseargs@0.11.0': @@ -5386,6 +5460,8 @@ snapshots: '@sindresorhus/merge-streams@4.0.0': {} + '@standard-schema/spec@1.1.0': {} + '@tailwindcss/node@4.3.0': dependencies: '@jridgewell/remapping': 2.3.5 @@ -5548,6 +5624,8 @@ snapshots: '@ungap/structured-clone@1.3.1': {} + '@vercel/oidc@3.2.0': {} + '@vitejs/plugin-react@4.7.0(vite@5.4.21(@types/node@20.19.41)(lightningcss@1.32.0))': dependencies: '@babel/core': 7.29.0 @@ -5628,6 +5706,14 @@ snapshots: agent-base@7.1.4: {} + ai@6.0.190(zod@3.25.76): + dependencies: + '@ai-sdk/gateway': 3.0.119(zod@3.25.76) + '@ai-sdk/provider': 3.0.10 + '@ai-sdk/provider-utils': 4.0.27(zod@3.25.76) + '@opentelemetry/api': 1.9.1 + zod: 3.25.76 + ajv-formats@2.1.1(ajv@8.20.0): optionalDependencies: ajv: 8.20.0 @@ -6453,6 +6539,8 @@ snapshots: json-schema-typed@8.0.2: {} + json-schema@0.4.0: {} + json5@2.2.3: {} jsonfile@6.2.1: