c7a75d069d
* feat(ai): job-shaped AI service with OpenAI-compatible backend, extraction-first; stop extracting every inbox document twice Sovereign plan WS1 PR1 (#1406 Tier 2, extraction-first, aligned with the AI surface audit). lib/ai grows a job-shaped service (generateText / generateStructured / extractFromDocument; no streaming members yet, see plan rule R3): - services/anthropic-family delegates to the existing createAiClient() and sends the exact request literals the inbox extractor sent before (request-shape tests deep-equal them), so hosted Bedrock stays byte-identical. - services/openai-compatible talks to any chat-completions endpoint (BYO Swedish provider) via Vercel AI SDK 6.x, exact-pinned and guarded: images as parts, PDFs rasterized with poppler (AI_PDF_MODE) or sent natively, AI_VISION / AI_STRICT_JSON declared, honest skips (ai_no_vision, pdf_rasterizer_missing) instead of fake failures. - config.ts: AI_PROVIDER/AI_BASE_URL/AI_API_KEY/AI_MODEL and per-tier AI_*_MODEL with the legacy BEDROCK_* names kept as the same overrides; getAiStatus() is the single source of truth for "is AI wired up". - provider.ts: openai-compatible in the auto-detect chain (after Bedrock and the direct API); createAiClient() refuses it loudly. Document extraction moves onto the service and gets the audit's fixes: - Inbox documents were extracted TWICE (pipeline A ran inside uploadDocument() before the inbox row existed, so its dedupe branch never fired; 3 707 + 1 666 calls / 30 d). The inbox now declares extractionOwner on the upload, the extension yields, and the inbox mirrors its single outcome onto document_attachments from every writer (sync, deferred, attach, retry, MCP). - Every "no extraction will ever happen" outcome is stamped (skipped:no_ai_entitlement / ai_unconfigured / system_generated / ...); the status route maps the quiet ones to 'disabled' on the first poll instead of a 30 s client timeout. Prod showed 309 of the 327 never-extracted uploads were the paywall working silently. - Self-generated documents (our own invoice PDFs, payout files) are no longer OCR'd. - Agent invoke answers 503 ai_unconfigured when the deployment has no assistant backend, distinct from the paywall. Guard: new direct-ai-client antipattern check (shrink-only allowlist of the pre-abstraction SDK callers) plus exact pins for @anthropic-ai/sdk, ai and @ai-sdk/openai-compatible. Verified: 15 958 unit tests green, guards, lint ratchet, typecheck, and a live smoke against hosted Bedrock through the new service (ping, streamed tool turn, thinking+cache, PDF extraction). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(ai): make AI_API_KEY optional for OpenAI-compatible endpoints (keyless local model servers) A local model server (llama.cpp's server, Ollama /v1, LM Studio, vLLM) usually has no auth. Before, the OpenAI-compatible backend required both AI_BASE_URL and AI_API_KEY to count as configured, so running Accounted on a local model meant setting a meaningless placeholder key. - resolveAiProvider / hasAiCredentials: a base URL alone is now enough. - services/openai-compatible: only send Authorization: Bearer when AI_API_KEY is set, so a keyless server is never handed an empty bearer; a hosted provider that needs a key still sets it. - Docs (SELF-HOSTING Option 3: local-model example, key marked optional), DECISIONS. Verified: with no AI_API_KEY, just AI_BASE_URL + AI_MODEL, getAiStatus() reports configured=true / provider=openai-compatible (live). lib/ai suite 71 green; tsc, guards, lint clean. Bedrock/Anthropic logic unchanged. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Jakob Wennberg <311770904+jakobwennberg-oss@users.noreply.github.com> Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
181 lines
6.7 KiB
TypeScript
181 lines
6.7 KiB
TypeScript
import {
|
|
hasAiCredentials,
|
|
resolveAiProvider,
|
|
toProviderModelId,
|
|
type AiProvider,
|
|
} from './provider'
|
|
import type { AiCapabilities, AiPdfMode, AiStatus, AiTier } from './types'
|
|
|
|
/**
|
|
* Environment parsing for the AI layer. Read on every call (cheap string
|
|
* reads) so tests and the smoke script see env changes; the service cache in
|
|
* lib/ai/index.ts keys on the resolved config, not on this module's state.
|
|
*
|
|
* Variables (all optional; legacy BEDROCK_* names keep working):
|
|
*
|
|
* AI_PROVIDER bedrock | anthropic | openai-compatible (else auto-detect)
|
|
* AI_BASE_URL OpenAI-compatible endpoint (Swedish provider or a local model)
|
|
* AI_API_KEY optional: only when that endpoint requires auth
|
|
* AI_MODEL default model id for every tier
|
|
* AI_ASSISTANT_MODEL per-tier overrides (fallbacks: BEDROCK_SONNET_MODEL_ID,
|
|
* AI_HEAVY_MODEL BEDROCK_OPUS_MODEL_ID, BEDROCK_MODEL_ID respectively)
|
|
* AI_EXTRACTION_MODEL
|
|
* AI_EXTRACTION_MAX_TOKENS output cap for document extraction (fallback BEDROCK_MAX_TOKENS, then 8192)
|
|
* AI_VISION OpenAI-compatible only: the configured models accept images (default true)
|
|
* AI_STRICT_JSON OpenAI-compatible only: use response_format json_schema (default false)
|
|
* AI_PDF_MODE auto | native | rasterize (auto = native on Claude, rasterize elsewhere)
|
|
* AI_PDF_MAX_PAGES pages rasterized per PDF (default 4)
|
|
*/
|
|
|
|
export interface ResolvedAiConfig {
|
|
provider: AiProvider
|
|
/** Credentials present (and, for OpenAI-compatible, a model id). */
|
|
configured: boolean
|
|
reason: AiStatus['reason']
|
|
baseUrl: string | null
|
|
apiKey: string | null
|
|
/** Bare model ids per tier (null only when OpenAI-compatible has none configured). */
|
|
models: Record<AiTier, string | null>
|
|
extractionMaxTokens: number
|
|
vision: boolean
|
|
strictJson: boolean
|
|
pdfMode: AiPdfMode
|
|
pdfMaxPages: number
|
|
}
|
|
|
|
const DEFAULT_CLAUDE_MODEL = 'claude-sonnet-5'
|
|
const DEFAULT_EXTRACTION_MAX_TOKENS = 8192
|
|
const DEFAULT_PDF_MAX_PAGES = 4
|
|
|
|
function env(name: string): string | null {
|
|
const v = process.env[name]
|
|
if (v === undefined) return null
|
|
const trimmed = v.trim()
|
|
return trimmed.length > 0 ? trimmed : null
|
|
}
|
|
|
|
function envBool(name: string, fallback: boolean): boolean {
|
|
const v = env(name)?.toLowerCase()
|
|
if (v === null || v === undefined) return fallback
|
|
if (v === 'true' || v === '1' || v === 'yes' || v === 'on') return true
|
|
if (v === 'false' || v === '0' || v === 'no' || v === 'off') return false
|
|
return fallback
|
|
}
|
|
|
|
// Use the env value only if it's a positive number: `||` would also fall back
|
|
// on a deliberate `0`, masking what is really an invalid configuration rather
|
|
// than the intent to disable.
|
|
function envPositiveInt(name: string): number | null {
|
|
const raw = env(name)
|
|
if (raw === null) return null
|
|
const parsed = Number(raw)
|
|
return Number.isFinite(parsed) && parsed > 0 ? Math.floor(parsed) : null
|
|
}
|
|
|
|
const LEGACY_TIER_VARS: Record<AiTier, string> = {
|
|
assistant: 'BEDROCK_SONNET_MODEL_ID',
|
|
heavy: 'BEDROCK_OPUS_MODEL_ID',
|
|
extraction: 'BEDROCK_MODEL_ID',
|
|
}
|
|
|
|
const TIER_VARS: Record<AiTier, string> = {
|
|
assistant: 'AI_ASSISTANT_MODEL',
|
|
heavy: 'AI_HEAVY_MODEL',
|
|
extraction: 'AI_EXTRACTION_MODEL',
|
|
}
|
|
|
|
/**
|
|
* Model id for a tier, most specific wins: AI_<TIER>_MODEL, then the legacy
|
|
* Bedrock-era tier variable, then AI_MODEL, then the Claude default on the
|
|
* Anthropic family. An OpenAI-compatible endpoint has no sane default model,
|
|
* so the result is null there and the status reports `no_model`.
|
|
*/
|
|
export function resolveTierModel(tier: AiTier, provider: AiProvider = resolveAiProvider()): string | null {
|
|
const specific = env(TIER_VARS[tier]) ?? env(LEGACY_TIER_VARS[tier]) ?? env('AI_MODEL')
|
|
if (specific) return specific
|
|
return provider === 'openai-compatible' ? null : DEFAULT_CLAUDE_MODEL
|
|
}
|
|
|
|
export function readAiConfig(): ResolvedAiConfig {
|
|
const provider = resolveAiProvider()
|
|
const models: Record<AiTier, string | null> = {
|
|
assistant: resolveTierModel('assistant', provider),
|
|
heavy: resolveTierModel('heavy', provider),
|
|
extraction: resolveTierModel('extraction', provider),
|
|
}
|
|
const credentials = hasAiCredentials()
|
|
const isOpenAiCompatible = provider === 'openai-compatible'
|
|
const hasModels = !isOpenAiCompatible || Object.values(models).every((m) => m !== null)
|
|
|
|
const pdfModeRaw = env('AI_PDF_MODE')?.toLowerCase()
|
|
const pdfMode: AiPdfMode =
|
|
pdfModeRaw === 'native' || pdfModeRaw === 'rasterize'
|
|
? pdfModeRaw
|
|
: isOpenAiCompatible
|
|
? 'rasterize'
|
|
: 'native'
|
|
|
|
return {
|
|
provider,
|
|
configured: credentials && hasModels,
|
|
reason: !credentials ? 'no_credentials' : !hasModels ? 'no_model' : 'ok',
|
|
baseUrl: isOpenAiCompatible ? env('AI_BASE_URL') : null,
|
|
apiKey: isOpenAiCompatible ? env('AI_API_KEY') : null,
|
|
models,
|
|
extractionMaxTokens:
|
|
envPositiveInt('AI_EXTRACTION_MAX_TOKENS') ??
|
|
envPositiveInt('BEDROCK_MAX_TOKENS') ??
|
|
DEFAULT_EXTRACTION_MAX_TOKENS,
|
|
vision: envBool('AI_VISION', true),
|
|
strictJson: envBool('AI_STRICT_JSON', false),
|
|
pdfMode,
|
|
pdfMaxPages: envPositiveInt('AI_PDF_MAX_PAGES') ?? DEFAULT_PDF_MAX_PAGES,
|
|
}
|
|
}
|
|
|
|
export function capabilitiesFor(cfg: ResolvedAiConfig): AiCapabilities {
|
|
if (cfg.provider === 'openai-compatible') {
|
|
return {
|
|
pdfNative: cfg.pdfMode === 'native',
|
|
imageInput: cfg.vision,
|
|
toolUse: true,
|
|
forcedToolChoice: false,
|
|
strictJsonSchema: cfg.strictJson,
|
|
}
|
|
}
|
|
return {
|
|
pdfNative: true,
|
|
imageInput: true,
|
|
toolUse: true,
|
|
forcedToolChoice: true,
|
|
strictJsonSchema: false,
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Single source of truth for "is AI wired up here, and for what". Cheap: env
|
|
* reads only, no network. Drives the extraction fail-fast path (a document is
|
|
* stamped `skipped:ai_unconfigured` instead of waiting 30 s for nothing), the
|
|
* status route, agent routes (503 instead of a stream that dies), and the
|
|
* smoke script.
|
|
*/
|
|
export function getAiStatus(): AiStatus {
|
|
const cfg = readAiConfig()
|
|
const capabilities = capabilitiesFor(cfg)
|
|
const models: Record<AiTier, string | null> = {
|
|
assistant: cfg.models.assistant ? toProviderModelId(cfg.models.assistant, cfg.provider) : null,
|
|
heavy: cfg.models.heavy ? toProviderModelId(cfg.models.heavy, cfg.provider) : null,
|
|
extraction: cfg.models.extraction ? toProviderModelId(cfg.models.extraction, cfg.provider) : null,
|
|
}
|
|
return {
|
|
provider: cfg.provider,
|
|
configured: cfg.configured,
|
|
reason: cfg.reason,
|
|
capabilities,
|
|
models,
|
|
pdfMode: cfg.pdfMode,
|
|
// The chat loop still speaks the Anthropic messages surface directly.
|
|
assistantAvailable: cfg.configured && cfg.provider !== 'openai-compatible',
|
|
}
|
|
}
|