UNPKG

@bitkyc08/opencodex

Version:

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM with Codex CLI/App/SDK and Claude Code

176 lines (166 loc) • 8.27 kB
import { protectGlmSummaryBudget } from "./summary-budget"; import { openAIChatTransport, stripBracketedModelSuffix } from "./wire"; import type { AdapterRequest } from "../base"; import { frameAgentRouterMessages } from "../agentrouter"; import { applyExplicitChatDeveloperRole } from "./developer-role"; import { openRouterProviderPayload, resolveOpenRouterRouting } from "../../providers/openrouter-routing"; import { resolveVercelGatewayRouting, vercelGatewayProviderPayload } from "../../providers/vercel-gateway-routing"; import { fastPolicyForModel } from "../../providers/service-tier"; import { applyGithubCopilotContextTier } from "../../providers/github-copilot-context"; import { canonicalFastTierMarker, decideTier, type ResolvedFastPolicy } from "../../providers/fastwire"; import { debugProviderDiagnostic } from "../../lib/debug"; import { isDebugEnabled } from "../../lib/debug-settings"; import { modelRecordValue } from "../../reasoning-effort"; import { modelInList, type OcxProviderConfig } from "../../types"; import { chatParallelToolCallsWireValue } from "./parallel-tool-calls"; import { applyExplicitChatReasoningWirePolicy } from "./reasoning-wire"; const CHAT_PASSTHROUGH_FIELDS = [ "audio", "frequency_penalty", "logit_bias", "logprobs", "max_completion_tokens", "max_tokens", "metadata", "modalities", "n", "prediction", "presence_penalty", "reasoning_effort", "response_format", "seed", "stop", "store", "temperature", "tool_choice", "tools", "top_logprobs", "top_p", "user", "web_search_options", ] as const; /** * Build a provider request from an inbound Chat Completions body without translating it * through the Responses contract. This is deliberately a whitelist: Chat-only caller * fields retain their exact wire representation, while provider capability gates remain * centralized beside the ordinary openai-chat adapter. */ export function buildOpenAIChatPassthroughRequest( provider: OcxProviderConfig, rawBody: Record<string, unknown>, modelId: string, stream: boolean, fastPolicy: ResolvedFastPolicy = fastPolicyForModel(provider, modelId, undefined, "chat"), fastMode?: boolean, providerName?: string, ): AdapterRequest { const { url, headers, hasCredential } = openAIChatTransport(provider); const body: Record<string, unknown> = { model: provider.modelSuffixBracketStrip ? stripBracketedModelSuffix(modelId) : modelId, // The caller's messages are forwarded as they arrived, with one exception: an operator who // recorded that this destination rejects the `developer` role gets that role converted in // place. Verbatim was not neutral there — it sent the role anyway and the turn failed // upstream with a 400 before the model saw it. An unrecorded destination is still verbatim, // and the conversion changes the role of those messages and nothing else, so the position // of every message and every other field survive unchanged. messages: applyExplicitChatDeveloperRole( frameAgentRouterMessages(provider.baseUrl, rawBody.messages), provider, ), stream, }; for (const field of CHAT_PASSTHROUGH_FIELDS) { if (rawBody[field] !== undefined) body[field] = rawBody[field]; } if (protectGlmSummaryBudget(body, provider.baseUrl, body.reasoning_effort)) body.reasoning_effort = "low"; const rawEfforts = modelRecordValue(provider.modelReasoningEfforts, modelId) ?? provider.reasoningEfforts; const reasoningDisabled = modelInList(provider.noReasoningModels, modelId) || rawEfforts?.length === 0; if (reasoningDisabled) { delete body.reasoning_effort; } const hasTools = Array.isArray(rawBody.tools) && rawBody.tools.length > 0; const requestedEffort = typeof body.reasoning_effort === "string" ? body.reasoning_effort : undefined; applyExplicitChatReasoningWirePolicy({ provider, modelId, hasTools, requestedEffort, wireEffort: requestedEffort, reasoningDisabled, body, }); const openRouterRouting = resolveOpenRouterRouting(provider, modelId); if (openRouterRouting) body.provider = openRouterProviderPayload(openRouterRouting); const vercelRouting = resolveVercelGatewayRouting(provider, modelId); if (vercelRouting) body.provider = vercelGatewayProviderPayload(vercelRouting); if (modelInList(provider.noTemperatureModels, modelId)) delete body.temperature; if (modelInList(provider.noTopPModels, modelId)) delete body.top_p; if (modelInList(provider.noStopModels, modelId)) delete body.stop; if (modelInList(provider.noPenaltyModels, modelId)) { delete body.presence_penalty; delete body.frequency_penalty; } // Exact match, unlike the gates above: `noStructuredOutputModels` is documented as // "only an exact requested-model match omits the field" (#1424), and the Responses // ingress enforces exactly that. A prefix match here would strip response_format from // `<listed>:<tag>` siblings the operator never opted out, silently returning prose. if (provider.noStructuredOutputModels?.includes(modelId)) delete body.response_format; // Narrower neighbour: the model takes `json_object` but rejects `json_schema`. Downgrade // rather than drop, so a caller that asked for JSON still gets JSON. The type check also // makes the kill switch above win without an else — after its `delete` there is no type // left to match. const passthroughFormat = body.response_format; if (provider.noJsonSchemaModels?.includes(modelId) && typeof passthroughFormat === "object" && passthroughFormat !== null && (passthroughFormat as { type?: unknown }).type === "json_schema") { body.response_format = { type: "json_object" }; } // Run the same complete Fast policy as the translated Chat path, including explicit // fastMode and foreign-tier handling. On inherited canonical Fast, the passthrough still // retains the caller's exact spelling; forced Fast uses the policy-owned wire value. const callerTier = typeof rawBody.service_tier === "string" ? rawBody.service_tier : undefined; const tierDecision = decideTier(fastPolicy, fastMode, callerTier); if (tierDecision.kind === "set") { body.service_tier = fastMode === undefined && canonicalFastTierMarker(callerTier) !== undefined ? callerTier : tierDecision.value; } else if (tierDecision.kind === "forward-caller" && rawBody.service_tier !== undefined) { body.service_tier = rawBody.service_tier; } if (provider.promptCacheKey && rawBody.prompt_cache_key !== undefined) { body.prompt_cache_key = rawBody.prompt_cache_key; } if (hasTools) { // Same three provider states as the translated path, and the same defect in the unset one: // a caller's explicit false was dropped here too (#5211). The native route reads the bit off // the raw request rather than the parsed options, since nothing projects this body. const requested = typeof rawBody.parallel_tool_calls === "boolean" ? rawBody.parallel_tool_calls : undefined; const parallelToolCalls = chatParallelToolCallsWireValue(provider, requested); if (parallelToolCalls !== undefined) body.parallel_tool_calls = parallelToolCalls; } if (stream) { const callerOptions = rawBody.stream_options !== null && typeof rawBody.stream_options === "object" && !Array.isArray(rawBody.stream_options) ? rawBody.stream_options as Record<string, unknown> : {}; body.stream_options = { ...callerOptions, include_usage: true }; } else if (rawBody.stream_options !== undefined) { body.stream_options = rawBody.stream_options; } const bodyJson = JSON.stringify(applyGithubCopilotContextTier(body, provider, modelId, providerName)); if (isDebugEnabled()) { let host = "upstream"; try { host = new URL(url).host; } catch { /* keep fallback */ } debugProviderDiagnostic("openai-chat", "passthrough-request", { host, model: body.model, stream, messageCount: Array.isArray(body.messages) ? body.messages.length : 0, toolCount: Array.isArray(body.tools) ? body.tools.length : 0, hasCredential, bodyBytes: Buffer.byteLength(bodyJson, "utf8"), }); } return { url, method: "POST", headers, body: bodyJson }; }