mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-14 19:22:32 +03:00
Compare commits
1 Commits
feat/image
...
fix/codeql
| Author | SHA1 | Date | |
|---|---|---|---|
|
ab36b35035 |
@@ -442,7 +442,7 @@
|
||||
"src/app/(dashboard)/dashboard/providers/[id]/components/modals/AddApiKeyModal.tsx": 1062,
|
||||
"src/app/(dashboard)/dashboard/providers/[id]/hooks/useProviderConnections.ts": 1051,
|
||||
"src/shared/components/ModelSelectModal.tsx": 1138,
|
||||
"src/shared/constants/providers/apikey/gateways.ts": 1255,
|
||||
"src/shared/constants/providers/apikey/gateways.ts": 1250,
|
||||
"open-sse/vendor/codex-chatgpt-web/bridge.ts": 1387,
|
||||
"_rebaseline_2026_08_11_v3850_merge_storm_provider_registry": "DRIFT do merge-storm 2026-08-11 (99 PRs mergeados no release/v3.8.50). AddApiKeyModal.tsx (PR #8949 ChatGPT Web provider) e useProviderConnections.ts/ModelSelectModal.tsx (PRs #9011 combo test-all, #9499 image combos) = UI nova legitima acima do cap; gateways.ts = god-file de catalogo de providers que cresceu com PRs #9009/#9421/#9468/#9594 (qualquer split arriscaria corromper o merge de novo — o proprio PR #9421 quebrou o arquivo); bridge.ts (PR #8949) = ponte Chromium vendored; proxyFetch.ts 1207->1220 = drift herdado de merges. Owner autorizou rebaseline com anotacao (2026-08-11).",
|
||||
"src/lib/modelCapabilities.ts": 1006,
|
||||
@@ -609,6 +609,5 @@
|
||||
"_rebaseline_2026_08_06_9006_reconcile_onto_tip_2": "PR #9006 (fix/vertex-claude-catalog-dispatch) second rebase-onto-tip reconciliation. Same two files as _rebaseline_2026_08_04_9006_reconcile_onto_tip below, further inherited drift, still not this PR's own growth (verified via git diff against the fresh upstream/release/v3.8.50 merge-base — this PR's own commits still touch neither file): open-sse/executors/base.ts 1623->1640 (+17) and src/sse/handlers/chat.ts 1847->1881 (+34), both measured post-merge via split(\"\\n\").length. More already-merged release/v3.8.50 PRs grew these files without updating their baseline entries (same root cause as every other entry in this chain: fast-gates PR->release does not run check:file-size). No offending branch left to fix.",
|
||||
"_rebaseline_2026_08_12_v3850_basereds_round3": "Base-reds round 3 (#9985, 2026-08-12): ModelSelectModal.tsx 1135->1138 = base drift from the #10198 SWR/build repair (flagged as non-blocking drift by Release-Green run 31634993212, rebaselined here so the PR queue's Fast Quality Gates stop failing on inherited drift); gateways.ts 1215->1250 = base drift from the 08-12 merges (#10131 regolo/naga-ac repair, #9210 void-ai+helixmind) plus this PR restoring the chatanywhere metadata entry that round 2 dropped along with its duplicate (wave3 audited entry, +16 lines; same god-file no-split rationale as the 2026-08-11 annotation). Owner-authorized sweep (/sweep-reds).",
|
||||
"_rebaseline_2026_08_12_proxyfetch_redaction": "Base-reds round 3 (#9985): proxyFetch.ts 1220->1239 (+19) = redactProxyDetailsInMessage() helper closing the credential leak #10032 reintroduced (raw proxy URL with user:password appended to the propagated error, Hard Rule #12); irreducible security fix at the existing error-surface chokepoint. Covered by tests/unit/tls-proxy-context.test.ts (strengthened leak guards).",
|
||||
"_rebaseline_2026_08_12_modelcapabilities_snapshot_routing": "Base-reds round 3 (#9985): modelCapabilities.ts crossed the new-file cap at 1006 (+~10) when the context/max-input-token override lookups were routed through the #9199 bulk snapshot (fixing 323 per-model SQLite reads per catalog prepare — auto-combo-context-advertising guard); cohesive change at the existing resolution chokepoints, not extractable. Covered by tests/unit/auto-combo-context-advertising.test.ts + model-capability-resolution-snapshot-9199.test.ts.",
|
||||
"_rebaseline_2026_08_14_imagetotext_servicekinds": "Image-to-Text category (#10275/#10291): gateways.ts grew 1250→1255 by data lines only — the serviceKinds: [\"llm\", \"imageToText\"] declarations on the openrouter and chutes catalog entries, plus the 3-line comment recording why chutes needs no static dots.ocr entry (passthroughModels discovery). No new logic or branching; the file is a provider catalog of declarative metadata. Splitting a catalog for five lines would be worse than the growth (semantic-families rule)."
|
||||
"_rebaseline_2026_08_12_modelcapabilities_snapshot_routing": "Base-reds round 3 (#9985): modelCapabilities.ts crossed the new-file cap at 1006 (+~10) when the context/max-input-token override lookups were routed through the #9199 bulk snapshot (fixing 323 per-model SQLite reads per catalog prepare — auto-combo-context-advertising guard); cohesive change at the existing resolution chokepoints, not extractable. Covered by tests/unit/auto-combo-context-advertising.test.ts + model-capability-resolution-snapshot-9199.test.ts."
|
||||
}
|
||||
|
||||
@@ -102,7 +102,7 @@
|
||||
"_rebaseline_2026_07_28_v3849_release": "75.5 -> 99 (+23.5). Aperto EXIGIDO pelo modo --require-tighten do ratchet: a métrica melhorou de verdade no ciclo v3.8.49. A causa é o workflow assíncrono de tradução, que finalmente alcançou o denominador em EN — as rebaselines anteriores (v3.8.39/.44/.47) foram todas afrouxamentos registrando o atraso das traduções, e agora ele foi pago. O coletor SUBTRAI os placeholders (present - placeholder em scripts/quality/collect-metrics.mjs), então os 317 marcadores __MISSING__ que esta release introduziu para o drift de valor já estão descontados dos 99 — o número é honesto, não inflado por placeholder. Medido pelo collect-metrics do CI no run 30404226939."
|
||||
},
|
||||
"deadExports": {
|
||||
"value": 415,
|
||||
"value": 409,
|
||||
"direction": "down",
|
||||
"_rebaseline_2026_08_09_v3850_post_sweep": "227 -> 230. Measured by npm run check:dead-code on the unmodified release/v3.8.50 tip 382449d593 during the mandatory --full-ci pre-flight. The +3 is inherited cycle drift from the authorized merge sweep; this repair adds no production exports. Rebaseline records the actual tip so ci.yml quality-gate can run, while structural cleanup remains separate debt.",
|
||||
"_rebaseline_2026_07_01_v3843_release": "225->227 (+2). v3.8.43 cycle drift, surfaced in the Quality Ratchet job after eslintWarnings was rebaselined (check:dead-code runs there). 227 = measured by check:dead-code (knip) on the release tip 4635076eb. The 5 CI fixes add 0 dead exports: safeHttpHref in linkify.ts is module-local AND used (called by linkifyText); no new exports; test files are not scanned. Tighten via --update next cycle.",
|
||||
@@ -111,8 +111,7 @@
|
||||
"_rebaseline_2026_06_27_v3838_release": "345->346 (+1). v3.8.38 cycle drift surfaced by the release-green pre-flight (Quality Ratchet does NOT run on PR->release fast-gates). Net +1 inherited from this cycle's feature/fix merges (new executors/providers, compression fidelity-gate module) minus #5138's removal of dead legacy store modules. Release-finalize working tree touches ONLY CHANGELOG.md + i18n mirrors + README + baselines — 0 production-code change. Structural cleanup tracked as debt.",
|
||||
"_rebaseline_2026_06_26_v3837_release": "343->345. v3.8.37 cycle drift surfaced by the release-green pre-flight (the Quality Ratchet does NOT run on PR->release fast-gates, so warnings/complexity accrued unmeasured across this cycle's 76 commits — provider adds DGrid/Pioneer/xAI, headroom proxy lifecycle #4649, ~50 SSE/translator fixes, Engine Combos #5062). Trust-but-verify: this release-finalize working tree touches ONLY CHANGELOG.md, docs/i18n/*/CHANGELOG.md mirrors, and these baselines — 0 production-code change, so all drift is inherited cycle drift (`any` warn-allowed in open-sse/ + tests/). Tighten via --require-tighten next cycle.",
|
||||
"_rebaseline_2026_08_11_v3850_merge_storm": "230 -> 248. Own drift from the 2026-08-11 merge storm (99 PRs into release/v3.8.50 via authorized sweep): new providers/executors/handlers added dead exports that knip cannot see as used. Measured on the base-fix tip (7ca73697b0 + this repair PR). Owner authorized rebaseline (2026-08-11) — structural cleanup remains separate debt.",
|
||||
"_rebaseline_2026_08_13_v3850_knip_bump": "248 -> 409. NOT code-added dead exports: dependabot bump #10043 (2026-08-13) upgraded knip 6.27.0 -> 6.32.x, and the new knip detects 162 MORE genuinely-unused exports (331 vs 169 deadExports) that 6.27 missed. DEAD_FILES unchanged (78). Reproduced identically on the clean release/v3.8.50 tip 266e39d3 with a fresh knip 6.32 node_modules — so every PR is born red on this gate until the tool change is absorbed. Owner authorized rebaseline (2026-08-13, via base-reds PR #10260). Structural cleanup of the 162 newly-surfaced dead exports remains separate debt.",
|
||||
"_rebaseline_2026_08_14_ocr_imagetotext_series": "OCR/image-to-text series (#10275/#10283/#10287/#10289/#10291): deadExports 409 -> 415. Each PR in the series adds public util/registry exports that are exercised by their unit tests but not yet by a second production caller — normalizeImageBuffer (imageNormalize), MISTRAL_PASSTHROUGH / AZURE_DI_TRANSFORMATION / getOcrTransformation (ocrRegistry), resolveOcrCredentials (v1/ocr route). They are the documented public surface of the new modules and are covered by tests; structural cleanup stays tracked in #3501."
|
||||
"_rebaseline_2026_08_13_v3850_knip_bump": "248 -> 409. NOT code-added dead exports: dependabot bump #10043 (2026-08-13) upgraded knip 6.27.0 -> 6.32.x, and the new knip detects 162 MORE genuinely-unused exports (331 vs 169 deadExports) that 6.27 missed. DEAD_FILES unchanged (78). Reproduced identically on the clean release/v3.8.50 tip 266e39d3 with a fresh knip 6.32 node_modules — so every PR is born red on this gate until the tool change is absorbed. Owner authorized rebaseline (2026-08-13, via base-reds PR #10260). Structural cleanup of the 162 newly-surfaced dead exports remains separate debt."
|
||||
},
|
||||
"cognitiveComplexity": {
|
||||
"value": 1223,
|
||||
|
||||
@@ -6840,17 +6840,9 @@ paths:
|
||||
- Images
|
||||
summary: Document OCR
|
||||
description: >-
|
||||
Multi-provider document OCR endpoint (Mistral OCR–compatible request
|
||||
and response shape). Accepts a JSON body referencing a document/image
|
||||
and returns extracted text. `model` selects the provider via a
|
||||
`provider/model` prefix (e.g. `mistral/mistral-ocr-latest`,
|
||||
`azure-document-intelligence/prebuilt-read`); a bare model id (e.g.
|
||||
`mistral-ocr-latest`) resolves to its registered provider, and an
|
||||
omitted `model` defaults to Mistral. Azure Document Intelligence is
|
||||
asynchronous upstream — the handler polls the returned operation
|
||||
until it succeeds or fails before responding, so this endpoint can
|
||||
take longer to return for that provider. Success responses carry the
|
||||
`X-OmniRoute-*` cost-telemetry headers.
|
||||
Mistral OCR–compatible document OCR endpoint. Accepts a JSON body
|
||||
referencing a document/image and returns extracted text. Success
|
||||
responses carry the `X-OmniRoute-*` cost-telemetry headers.
|
||||
security:
|
||||
- BearerAuth: []
|
||||
requestBody:
|
||||
@@ -6862,11 +6854,6 @@ paths:
|
||||
properties:
|
||||
model:
|
||||
type: string
|
||||
description: >-
|
||||
`provider/model` id or bare model id. Registered ids:
|
||||
`mistral/mistral-ocr-latest`,
|
||||
`azure-document-intelligence/prebuilt-read`. Defaults to
|
||||
`mistral-ocr-latest` when omitted.
|
||||
document:
|
||||
type: object
|
||||
responses:
|
||||
|
||||
@@ -17,7 +17,6 @@ Complete reference for all OmniRoute API endpoints.
|
||||
- [Chat Completions](#chat-completions)
|
||||
- [Embeddings](#embeddings)
|
||||
- [Image Generation](#image-generation)
|
||||
- [Document OCR](#document-ocr)
|
||||
- [List Models](#list-models)
|
||||
- [Provider Plugin Manifest](#provider-plugin-manifest)
|
||||
- [Compatibility Endpoints](#compatibility-endpoints)
|
||||
@@ -200,53 +199,6 @@ GET /v1/images/generations
|
||||
|
||||
---
|
||||
|
||||
## Document OCR
|
||||
|
||||
```bash
|
||||
POST /v1/ocr
|
||||
Authorization: Bearer your-api-key
|
||||
Content-Type: application/json
|
||||
|
||||
{
|
||||
"model": "mistral/mistral-ocr-latest",
|
||||
"document": {
|
||||
"type": "document_url",
|
||||
"document_url": "https://example.com/invoice.pdf"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
`model` selects the OCR provider via a `provider/model` prefix; a bare model id (e.g.
|
||||
`mistral-ocr-latest`) resolves to its registered provider, and an omitted `model` defaults to
|
||||
Mistral (`mistral-ocr-latest`). Registered providers (`open-sse/config/ocrRegistry.ts`):
|
||||
|
||||
| Provider id | Model id | `model` value | Notes |
|
||||
| ----------------------------- | -------------------- | ----------------------------------------------------------- | ------------------------------------------------------------------------------ |
|
||||
| `mistral` | `mistral-ocr-latest` | `mistral/mistral-ocr-latest` (or bare `mistral-ocr-latest`) | Synchronous — the response is returned directly from the single upstream call. |
|
||||
| `azure-document-intelligence` | `prebuilt-read` | `azure-document-intelligence/prebuilt-read` | Asynchronous upstream (`analyze` + poll) — see below. |
|
||||
|
||||
Both providers respond in the same Mistral-shaped body:
|
||||
|
||||
```json
|
||||
{
|
||||
"pages": [{ "index": 0, "markdown": "# Extracted text..." }],
|
||||
"model": "mistral-ocr-latest",
|
||||
"usage_info": { "pages_processed": 1 }
|
||||
}
|
||||
```
|
||||
|
||||
### Azure Document Intelligence poll flow
|
||||
|
||||
Azure Document Intelligence's `analyze` API is asynchronous: the initial request returns an
|
||||
`Operation-Location` header instead of a body, and the result must be polled for. The handler
|
||||
(`open-sse/handlers/ocr.ts`) polls that URL every second for up to 30 attempts, fails fast (does
|
||||
not keep polling) on a non-`ok` poll response or a `"failed"` status, and returns `504` if the
|
||||
operation is still running after the attempt budget is exhausted. The final Azure response is
|
||||
normalized into the same `pages`/`markdown` shape used by Mistral before being returned to the
|
||||
caller, so client code does not need to special-case the provider.
|
||||
|
||||
---
|
||||
|
||||
## List Models
|
||||
|
||||
```bash
|
||||
@@ -537,18 +489,18 @@ call**, so the reported `X-OmniRoute-Response-Latency` is near-zero
|
||||
(benchmarking, p50/p99 monitoring) should check the
|
||||
`X-OmniRoute-Cache-Latency` response header:
|
||||
|
||||
| Value | Meaning |
|
||||
| ----------- | ------------------------------------------------------------- |
|
||||
| Value | Meaning |
|
||||
|-------|---------|
|
||||
| `synthetic` | Response served from cache; latency is not real upstream time |
|
||||
| _(absent)_ | Response from real upstream call |
|
||||
| *(absent)* | Response from real upstream call |
|
||||
|
||||
### Per-key cache bypass
|
||||
|
||||
API keys can opt out of semantic cache reads via `cacheDefaultMode`:
|
||||
|
||||
| Value | Behavior |
|
||||
| -------- | ----------------------------------------------- |
|
||||
| `legacy` | Normal cache behavior (default) |
|
||||
| Value | Behavior |
|
||||
|-------|----------|
|
||||
| `legacy` | Normal cache behavior (default) |
|
||||
| `bypass` | Skip cache lookup entirely; always hit upstream |
|
||||
|
||||
Set at key creation (`POST /api/keys`) or update (`PATCH /api/keys/[id]`):
|
||||
@@ -651,13 +603,13 @@ X-OmniRoute-No-Cache: true
|
||||
|
||||
### Monitoring
|
||||
|
||||
| Endpoint | Method | Description |
|
||||
| ---------------------------- | ---------- | --------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `/api/sessions` | GET | Active session tracking |
|
||||
| `/api/rate-limits` | GET | Per-account rate limits |
|
||||
| `/api/monitoring/health` | GET | Health check + provider summary (`catalogCount`, `configuredCount`, `activeCount`, `monitoredCount`) |
|
||||
| `/api/cache/stats` | GET/DELETE | Cache stats / clear |
|
||||
| `/api/modality-bridge/stats` | GET | In-memory Modality Bridge telemetry — per-modality `bridged`/`cacheHits`/`failures`/`lastUsedAt` counters (reset on restart; management auth) |
|
||||
| Endpoint | Method | Description |
|
||||
| ------------------------ | ---------- | ---------------------------------------------------------------------------------------------------- |
|
||||
| `/api/sessions` | GET | Active session tracking |
|
||||
| `/api/rate-limits` | GET | Per-account rate limits |
|
||||
| `/api/monitoring/health` | GET | Health check + provider summary (`catalogCount`, `configuredCount`, `activeCount`, `monitoredCount`) |
|
||||
| `/api/cache/stats` | GET/DELETE | Cache stats / clear |
|
||||
| `/api/modality-bridge/stats` | GET | In-memory Modality Bridge telemetry — per-modality `bridged`/`cacheHits`/`failures`/`lastUsedAt` counters (reset on restart; management auth) |
|
||||
|
||||
### Backup & Export/Import
|
||||
|
||||
|
||||
@@ -37,15 +37,26 @@ function nonEmptyString(value: unknown): string | null {
|
||||
return normalized || null;
|
||||
}
|
||||
|
||||
/** Keep the historical installation-id layout so existing accounts stay stable. */
|
||||
/**
|
||||
* Keep the historical installation-id layout so existing accounts stay stable.
|
||||
* CodeQL: not password hashing — this derives a deterministic installation UUID
|
||||
* from an account seed, never verified against a stored credential. Same
|
||||
* false-positive class as src/lib/db/apiKeys.ts::hashKey.
|
||||
* lgtm[js/insufficient-password-hash]
|
||||
*/
|
||||
function uuidFromLegacyInstallationValue(value: string): string {
|
||||
const hash = createHash("sha256").update(value).digest("hex");
|
||||
const hash = createHash("sha256").update(value).digest("hex"); // nosemgrep: insufficient-password-hash
|
||||
return `${hash.slice(0, 8)}-${hash.slice(8, 12)}-4${hash.slice(13, 16)}-a${hash.slice(17, 20)}-${hash.slice(20, 32)}`;
|
||||
}
|
||||
|
||||
/** RFC4122 v4 from SHA-256. Same seed → same UUID. */
|
||||
/**
|
||||
* RFC4122 v4 from SHA-256. Same seed → same UUID.
|
||||
* CodeQL: not password hashing — deterministic ID derivation from an account
|
||||
* seed, never verified against a stored credential.
|
||||
* lgtm[js/insufficient-password-hash]
|
||||
*/
|
||||
export function deriveStableUUIDv4(seed: string): string {
|
||||
const digest = createHash("sha256").update(seed).digest();
|
||||
const digest = createHash("sha256").update(seed).digest(); // nosemgrep: insufficient-password-hash
|
||||
const bytes = Buffer.from(digest.subarray(0, 16));
|
||||
bytes[6] = (bytes[6] & 0x0f) | 0x40;
|
||||
bytes[8] = (bytes[8] & 0x3f) | 0x80;
|
||||
|
||||
@@ -179,24 +179,6 @@ export const HTTP_STATUS = {
|
||||
SERVICE_UNAVAILABLE: 503,
|
||||
GATEWAY_TIMEOUT: 504,
|
||||
};
|
||||
|
||||
/**
|
||||
* #10360 — stable error code for an INTERNAL violation of the executor
|
||||
* `execute()` result contract (`normalizeExecutorResult` received something
|
||||
* that is neither a Response nor `{ response: Response }`).
|
||||
*
|
||||
* This is our own bug, never a provider/account health signal, so every
|
||||
* resilience layer must treat it as request-scoped and terminal: no connection
|
||||
* cooldown, no provider circuit-breaker trip, no retry. It rides on the error's
|
||||
* `.code` (read by `getUpstreamErrorIdentifier`) and therefore reaches
|
||||
* `checkFallbackError` as `structuredError.code` and the chat/combo predicates
|
||||
* as `result.errorCode`.
|
||||
*
|
||||
* Lives here (leaf config module) so both `open-sse/handlers/` and
|
||||
* `open-sse/services/` can import it without creating a cycle.
|
||||
*/
|
||||
export const EXECUTOR_CONTRACT_VIOLATION_CODE = "executor_contract_violation";
|
||||
|
||||
export {
|
||||
BACKOFF_CONFIG,
|
||||
COOLDOWN_MS,
|
||||
|
||||
@@ -13,11 +13,9 @@
|
||||
* derives membership from here instead of duplicating it by hand, so adding a
|
||||
* provider to a registry automatically surfaces it — no second edit, no drift.
|
||||
*
|
||||
* `imageToText` is additionally derived from `OCR_PROVIDERS` (see
|
||||
* `resolveProviderServiceKinds`): a provider registered in the OCR registry gets
|
||||
* `imageToText` for free, no manual `serviceKinds` edit needed. Kinds without any
|
||||
* backing registry (webSearch, webFetch, llm) are still declared explicitly via
|
||||
* `serviceKinds` on the provider entry; callers union declared + derived sources.
|
||||
* Kinds without a backing registry (imageToText, webSearch, webFetch, llm) are
|
||||
* still declared explicitly via `serviceKinds` on the provider entry; callers
|
||||
* union the two sources.
|
||||
*/
|
||||
import { AUDIO_TRANSCRIPTION_PROVIDERS, AUDIO_SPEECH_PROVIDERS } from "./audioRegistry.ts";
|
||||
import { VIDEO_PROVIDERS } from "./videoRegistry.ts";
|
||||
@@ -60,8 +58,7 @@ export function getRegistryMediaKinds(providerId: string): RegistryMediaKind[] {
|
||||
|
||||
/**
|
||||
* Full set of serviceKinds for a provider: the explicitly declared ones (llm,
|
||||
* web*, imageToText) unioned with the media kinds derived from the registries,
|
||||
* plus `imageToText` derived from the OCR registry when not already declared.
|
||||
* web*, imageToText) unioned with the media kinds derived from the registries.
|
||||
*/
|
||||
export function resolveProviderServiceKinds(
|
||||
providerId: string,
|
||||
@@ -69,8 +66,5 @@ export function resolveProviderServiceKinds(
|
||||
): string[] {
|
||||
const set = new Set<string>(declared ?? []);
|
||||
for (const kind of getRegistryMediaKinds(providerId)) set.add(kind);
|
||||
if (Object.prototype.hasOwnProperty.call(OCR_PROVIDERS, providerId)) {
|
||||
set.add("imageToText");
|
||||
}
|
||||
return [...set];
|
||||
}
|
||||
|
||||
@@ -16,7 +16,6 @@ export interface OcrProvider {
|
||||
authType: string;
|
||||
authHeader: string;
|
||||
models: OcrModel[];
|
||||
transformation?: OcrTransformation;
|
||||
}
|
||||
|
||||
export interface ParsedOcrModel {
|
||||
@@ -24,86 +23,6 @@ export interface ParsedOcrModel {
|
||||
model: string | null;
|
||||
}
|
||||
|
||||
export interface OcrResponseShape {
|
||||
pages: Array<{ index: number; markdown: string }>;
|
||||
model: string;
|
||||
usage_info?: Record<string, unknown>;
|
||||
}
|
||||
|
||||
export interface OcrTransformation {
|
||||
buildRequest(args: {
|
||||
baseUrl: string;
|
||||
token: string;
|
||||
body: Record<string, unknown>;
|
||||
modelId: string;
|
||||
}): { url: string; init: RequestInit };
|
||||
parseResponse(raw: unknown): OcrResponseShape;
|
||||
/** Async providers (Azure DI): return the poll URL from the first response, else null. */
|
||||
pollUrl?(res: Response): string | null;
|
||||
}
|
||||
|
||||
export const MISTRAL_PASSTHROUGH: OcrTransformation = {
|
||||
buildRequest({ baseUrl, token, body, modelId }) {
|
||||
return {
|
||||
url: baseUrl,
|
||||
init: {
|
||||
method: "POST",
|
||||
headers: { "Content-Type": "application/json", Authorization: `Bearer ${token}` },
|
||||
body: JSON.stringify({ ...body, model: modelId }),
|
||||
},
|
||||
};
|
||||
},
|
||||
parseResponse(raw) {
|
||||
return raw as OcrResponseShape;
|
||||
},
|
||||
};
|
||||
|
||||
export function getOcrTransformation(providerId: string): OcrTransformation {
|
||||
return OCR_PROVIDERS[providerId]?.transformation ?? MISTRAL_PASSTHROUGH;
|
||||
}
|
||||
|
||||
const AZURE_DI_API_VERSION = "2024-11-30";
|
||||
|
||||
function azureDiSource(document: Record<string, unknown> | undefined): Record<string, string> {
|
||||
if (!document) return {};
|
||||
const url = String(document.document_url ?? document.image_url ?? "");
|
||||
if (url.startsWith("data:")) {
|
||||
const comma = url.indexOf(",");
|
||||
return { base64Source: comma >= 0 ? url.slice(comma + 1) : "" };
|
||||
}
|
||||
return url ? { urlSource: url } : {};
|
||||
}
|
||||
|
||||
export const AZURE_DI_TRANSFORMATION: OcrTransformation = {
|
||||
buildRequest({ baseUrl, token, body, modelId }) {
|
||||
const root = baseUrl.replace(/\/+$/, "");
|
||||
return {
|
||||
url: `${root}/documentintelligence/documentModels/${modelId}:analyze?api-version=${AZURE_DI_API_VERSION}&outputContentFormat=markdown`,
|
||||
init: {
|
||||
method: "POST",
|
||||
headers: { "Content-Type": "application/json", "Ocp-Apim-Subscription-Key": token },
|
||||
body: JSON.stringify(azureDiSource(body.document as Record<string, unknown>)),
|
||||
},
|
||||
};
|
||||
},
|
||||
pollUrl(res) {
|
||||
return res.headers.get("Operation-Location");
|
||||
},
|
||||
parseResponse(raw) {
|
||||
const r = raw as {
|
||||
analyzeResult?: { content?: string; pages?: unknown[] };
|
||||
};
|
||||
const pageCount = r.analyzeResult?.pages?.length ?? 1;
|
||||
// Azure returns the whole-document markdown in `content`; we mirror it into the
|
||||
// Mistral shape as a single aggregated "page" (index 0), preserving pageCount.
|
||||
return {
|
||||
pages: [{ index: 0, markdown: r.analyzeResult?.content ?? "" }],
|
||||
model: "prebuilt-read",
|
||||
usage_info: { pages_processed: pageCount },
|
||||
};
|
||||
},
|
||||
};
|
||||
|
||||
export const OCR_PROVIDERS: Record<string, OcrProvider> = {
|
||||
mistral: {
|
||||
id: "mistral",
|
||||
@@ -112,14 +31,6 @@ export const OCR_PROVIDERS: Record<string, OcrProvider> = {
|
||||
authHeader: "bearer",
|
||||
models: [{ id: "mistral-ocr-latest", name: "Mistral OCR" }],
|
||||
},
|
||||
"azure-document-intelligence": {
|
||||
id: "azure-document-intelligence",
|
||||
baseUrl: "",
|
||||
authType: "apikey",
|
||||
authHeader: "Ocp-Apim-Subscription-Key",
|
||||
models: [{ id: "prebuilt-read", name: "Azure Document Intelligence (Read)" }],
|
||||
transformation: AZURE_DI_TRANSFORMATION,
|
||||
},
|
||||
};
|
||||
|
||||
/**
|
||||
|
||||
@@ -1,8 +1,4 @@
|
||||
import {
|
||||
EXECUTOR_CONTRACT_VIOLATION_CODE,
|
||||
FETCH_TIMEOUT_MS,
|
||||
HTTP_STATUS,
|
||||
} from "../../config/constants.ts";
|
||||
import { FETCH_TIMEOUT_MS } from "../../config/constants.ts";
|
||||
import { getModelTimeoutMs } from "../../config/providerModels.ts";
|
||||
import {
|
||||
getLoggedInputTokens,
|
||||
@@ -102,62 +98,6 @@ export function getExecutorTimeoutMs(executor: unknown, provider?: string, model
|
||||
return resolveProviderTimeoutMs(executor);
|
||||
}
|
||||
|
||||
/**
|
||||
* Cross-realm Response detection (#10360).
|
||||
*
|
||||
* `instanceof Response` is a NOMINAL check against `globalThis.Response`, and
|
||||
* OmniRoute's default egress does not use the global one: `proxyFetch.ts`
|
||||
* dispatches through the npm `undici` package's `fetch`, whose `Response` is a
|
||||
* different class from the Node built-in. A bare `instanceof` therefore
|
||||
* rejected virtually every real upstream response as a "contract violation".
|
||||
*
|
||||
* Accept the built-in fast path first, then fall back to a structural probe:
|
||||
* the `Symbol.toStringTag` brand plus the members the pipeline actually reads
|
||||
* (`status`/`ok`/`headers.get`/`text`/`clone`). A plain `{ status, ok }` bag
|
||||
* still fails, so the guard keeps its value.
|
||||
*/
|
||||
export function isResponseLike(value: unknown): value is Response {
|
||||
if (value instanceof Response) return true;
|
||||
if (!value || typeof value !== "object") return false;
|
||||
const candidate = value as {
|
||||
status?: unknown;
|
||||
ok?: unknown;
|
||||
headers?: { get?: unknown } | null;
|
||||
text?: unknown;
|
||||
clone?: unknown;
|
||||
};
|
||||
return (
|
||||
Object.prototype.toString.call(value) === "[object Response]" &&
|
||||
typeof candidate.status === "number" &&
|
||||
typeof candidate.ok === "boolean" &&
|
||||
!!candidate.headers &&
|
||||
typeof candidate.headers.get === "function" &&
|
||||
typeof candidate.text === "function" &&
|
||||
typeof candidate.clone === "function"
|
||||
);
|
||||
}
|
||||
|
||||
/**
|
||||
* Builds the terminal error thrown on a genuine contract violation (#10360).
|
||||
*
|
||||
* Carries `status = 500` and `code = EXECUTOR_CONTRACT_VIOLATION_CODE` so the
|
||||
* failure is classified as an INTERNAL, non-retryable defect instead of falling
|
||||
* through chatCore's `BAD_GATEWAY` default. A 502 made every layer treat our own
|
||||
* bug as a flaky provider: the connection was cooled down as "rate limited", the
|
||||
* provider breaker counted it, and the batch runner (which retries 429/502/504)
|
||||
* span for its full 24h window on an error that can never resolve itself.
|
||||
*/
|
||||
export function createExecutorContractError(): Error & { status: number; code: string } {
|
||||
const err = new TypeError("Executor result must contain a Response") as TypeError & {
|
||||
status: number;
|
||||
code: string;
|
||||
};
|
||||
err.name = "ExecutorContractError";
|
||||
err.status = HTTP_STATUS.SERVER_ERROR;
|
||||
err.code = EXECUTOR_CONTRACT_VIOLATION_CODE;
|
||||
return err;
|
||||
}
|
||||
|
||||
export function normalizeExecutorResult(result: unknown): {
|
||||
response: Response;
|
||||
url: string;
|
||||
@@ -165,16 +105,16 @@ export function normalizeExecutorResult(result: unknown): {
|
||||
transformedBody: unknown;
|
||||
transport?: string;
|
||||
} {
|
||||
if (isResponseLike(result)) {
|
||||
if (result instanceof Response) {
|
||||
return { response: result, url: "", headers: {}, transformedBody: null };
|
||||
}
|
||||
if (
|
||||
!result ||
|
||||
typeof result !== "object" ||
|
||||
!("response" in result) ||
|
||||
!isResponseLike(result.response)
|
||||
!(result.response instanceof Response)
|
||||
) {
|
||||
throw createExecutorContractError();
|
||||
throw new TypeError("Executor result must contain a Response");
|
||||
}
|
||||
const normalized = result as {
|
||||
response: Response;
|
||||
|
||||
@@ -5,43 +5,21 @@ import { CORS_HEADERS } from "../utils/cors.ts";
|
||||
* Handles POST /v1/ocr (Mistral OCR API format).
|
||||
*/
|
||||
|
||||
import {
|
||||
getOcrProvider,
|
||||
getOcrTransformation,
|
||||
parseOcrModel,
|
||||
OCR_PROVIDERS,
|
||||
} from "../config/ocrRegistry.ts";
|
||||
import { getOcrProvider, parseOcrModel } from "../config/ocrRegistry.ts";
|
||||
import { errorResponse } from "../utils/error.ts";
|
||||
import { attachOmniRouteMetaHeaders } from "@/domain/omnirouteResponseMeta";
|
||||
import { generateRequestId } from "@/shared/utils/requestId";
|
||||
|
||||
const OCR_POLL_MAX_ATTEMPTS = 30;
|
||||
const OCR_POLL_INTERVAL_MS = 1000;
|
||||
|
||||
const defaultSleep = (ms: number) => new Promise((resolve) => setTimeout(resolve, ms));
|
||||
|
||||
/**
|
||||
* Handle OCR request
|
||||
*
|
||||
* Dispatches to the per-provider transformation (see `open-sse/config/ocrRegistry.ts`)
|
||||
* to build the upstream request, then (for async providers like Azure Document
|
||||
* Intelligence) polls the returned operation URL until it succeeds or fails,
|
||||
* before normalizing the response into the Mistral OCR shape.
|
||||
*
|
||||
* @param {Object} options
|
||||
* @param {Object} options.body - JSON body { model, document }
|
||||
* @param {Object} options.credentials - Provider credentials { apiKey, accessToken, baseUrl }
|
||||
* @param {Function} [options.fetchImpl] - DI hook for tests; defaults to global fetch
|
||||
* @param {Function} [options.sleepImpl] - DI hook for tests; defaults to a real setTimeout-based sleep
|
||||
* @param {Object} options.credentials - Provider credentials { apiKey }
|
||||
* @returns {Response}
|
||||
*/
|
||||
/** @returns {Promise<unknown>} */
|
||||
export async function handleOcr({
|
||||
body,
|
||||
credentials,
|
||||
fetchImpl = fetch,
|
||||
sleepImpl = defaultSleep,
|
||||
}) {
|
||||
export async function handleOcr({ body, credentials }) {
|
||||
const startTime = Date.now();
|
||||
if (!body.document) {
|
||||
return errorResponse(400, "document is required");
|
||||
@@ -53,10 +31,7 @@ export async function handleOcr({
|
||||
const providerConfig = providerId ? getOcrProvider(providerId) : null;
|
||||
|
||||
if (!providerConfig) {
|
||||
return errorResponse(
|
||||
400,
|
||||
`No OCR provider found for model "${model}". Available: ${Object.keys(OCR_PROVIDERS).join(", ")}`
|
||||
);
|
||||
return errorResponse(400, `No OCR provider found for model "${model}". Available: mistral`);
|
||||
}
|
||||
|
||||
const token = credentials?.apiKey || credentials?.accessToken;
|
||||
@@ -64,15 +39,18 @@ export async function handleOcr({
|
||||
return errorResponse(401, `No credentials for OCR provider: ${providerId}`);
|
||||
}
|
||||
|
||||
const baseUrl = credentials?.baseUrl || providerConfig.baseUrl;
|
||||
if (!baseUrl) {
|
||||
return errorResponse(400, `No base URL configured for OCR provider: ${providerId}`);
|
||||
}
|
||||
|
||||
try {
|
||||
const transformation = getOcrTransformation(providerId);
|
||||
const { url, init } = transformation.buildRequest({ baseUrl, token, body, modelId });
|
||||
const res = await fetchImpl(url, init);
|
||||
const res = await fetch(providerConfig.baseUrl, {
|
||||
method: "POST",
|
||||
headers: {
|
||||
"Content-Type": "application/json",
|
||||
Authorization: `Bearer ${token}`,
|
||||
},
|
||||
body: JSON.stringify({
|
||||
...body,
|
||||
model: modelId,
|
||||
}),
|
||||
});
|
||||
|
||||
if (!res.ok) {
|
||||
const errText = await res.text();
|
||||
@@ -85,17 +63,7 @@ export async function handleOcr({
|
||||
});
|
||||
}
|
||||
|
||||
const pollUrl = transformation.pollUrl?.(res) ?? null;
|
||||
let data: unknown;
|
||||
if (pollUrl) {
|
||||
const authHeader = buildAuthHeader(providerConfig.authHeader, token);
|
||||
data = await pollOcrOperation({ pollUrl, authHeader, fetchImpl, sleepImpl });
|
||||
if (data instanceof Response) return data;
|
||||
} else {
|
||||
data = await res.json();
|
||||
}
|
||||
|
||||
const parsed = transformation.parseResponse(data);
|
||||
const data = await res.json();
|
||||
const headers = new Headers({ ...CORS_HEADERS, "Content-Type": "application/json" });
|
||||
attachOmniRouteMetaHeaders(headers, {
|
||||
provider: providerId,
|
||||
@@ -104,48 +72,8 @@ export async function handleOcr({
|
||||
latencyMs: Date.now() - startTime,
|
||||
requestId: generateRequestId(),
|
||||
});
|
||||
return new Response(JSON.stringify(parsed), { status: 200, headers });
|
||||
return new Response(JSON.stringify(data), { status: 200, headers });
|
||||
} catch (err) {
|
||||
console.error("[OCR]", err);
|
||||
return errorResponse(500, "OCR request failed");
|
||||
return errorResponse(500, `OCR request failed: ${err.message}`);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Build the same auth header used for the initial upstream request, so the
|
||||
* poll GET (e.g. Azure Document Intelligence's Operation-Location) authenticates
|
||||
* identically.
|
||||
*/
|
||||
function buildAuthHeader(authHeader: string, token: string): Record<string, string> {
|
||||
if (authHeader === "bearer") {
|
||||
return { Authorization: `Bearer ${token}` };
|
||||
}
|
||||
return { [authHeader]: token };
|
||||
}
|
||||
|
||||
/**
|
||||
* Poll an async OCR operation (Azure Document Intelligence) until it succeeds or fails.
|
||||
*
|
||||
* @returns {Promise<unknown|Response>} the parsed JSON body on success, or an error Response
|
||||
*/
|
||||
async function pollOcrOperation({ pollUrl, authHeader, fetchImpl, sleepImpl }) {
|
||||
for (let attempt = 0; attempt < OCR_POLL_MAX_ATTEMPTS; attempt++) {
|
||||
await sleepImpl(OCR_POLL_INTERVAL_MS);
|
||||
const pollRes = await fetchImpl(pollUrl, {
|
||||
method: "GET",
|
||||
headers: authHeader,
|
||||
});
|
||||
if (!pollRes.ok) {
|
||||
console.error("[OCR] poll error", pollRes.status);
|
||||
return errorResponse(502, "OCR analysis failed");
|
||||
}
|
||||
const json = await pollRes.json();
|
||||
if (json.status === "succeeded") {
|
||||
return json;
|
||||
}
|
||||
if (json.status === "failed") {
|
||||
return errorResponse(502, "OCR analysis failed");
|
||||
}
|
||||
}
|
||||
return errorResponse(504, "OCR analysis timed out");
|
||||
}
|
||||
|
||||
@@ -1,6 +1,5 @@
|
||||
import {
|
||||
BACKOFF_STEPS_MS,
|
||||
EXECUTOR_CONTRACT_VIOLATION_CODE,
|
||||
PROVIDER_PROFILES,
|
||||
RateLimitReason,
|
||||
HTTP_STATUS,
|
||||
@@ -1459,21 +1458,6 @@ export function checkFallbackError(
|
||||
* caller can persist an explicit reset window instead of the engine's scaled cooldown. */
|
||||
configuredCooldownMs?: number;
|
||||
} {
|
||||
// #10360: an executor-result contract violation is OUR bug, not the provider's.
|
||||
// Retrying reproduces it verbatim, and cooling the connection down (or tripping
|
||||
// the provider breaker) punishes a healthy account for an internal defect. Must
|
||||
// run before every other classification — the surfaced status is a plain 500,
|
||||
// which the retryable set below would otherwise treat as a transient upstream
|
||||
// failure and hand a backoff cooldown.
|
||||
if (structuredError?.code === EXECUTOR_CONTRACT_VIOLATION_CODE) {
|
||||
return {
|
||||
shouldFallback: false,
|
||||
cooldownMs: 0,
|
||||
reason: EXECUTOR_CONTRACT_VIOLATION_CODE,
|
||||
skipProviderBreaker: true,
|
||||
};
|
||||
}
|
||||
|
||||
const svc = serviceSupervisorCooldown(status, headers);
|
||||
if (svc) return svc;
|
||||
const rg = rot.gateFor(status, rotation?.account);
|
||||
|
||||
@@ -6,7 +6,6 @@
|
||||
* predicates are re-exported from combo.ts for backward compatibility.
|
||||
*/
|
||||
|
||||
import { EXECUTOR_CONTRACT_VIOLATION_CODE } from "../../config/constants.ts";
|
||||
import { errorResponse } from "../../utils/error.ts";
|
||||
import { parseModel } from "../model.ts";
|
||||
import { isSelfInflictedUpstreamTimeout } from "../../handlers/chatCore/cooldownClassification.ts";
|
||||
@@ -202,9 +201,6 @@ const REQUEST_SCOPED_UPSTREAM_ERROR_CODES: Record<string, true> = {
|
||||
rate_limit_queue_timeout: true,
|
||||
rate_limit_queue_full: true,
|
||||
rate_limit_queue_wedged: true,
|
||||
// #10360: our own executor-result contract violation. An internal defect, not
|
||||
// a provider/account fault — it must never cool a connection or trip a breaker.
|
||||
[EXECUTOR_CONTRACT_VIOLATION_CODE]: true,
|
||||
};
|
||||
|
||||
/** Request/model-specific failures must not poison provider-wide resilience state. */
|
||||
|
||||
@@ -302,7 +302,11 @@ export function buildAssistantMessageCacheKey(
|
||||
if (!message || message.role !== "assistant") return "";
|
||||
|
||||
const transcript = messages.slice(0, messageIndex + 1).map(canonicalizeHistoryMessage);
|
||||
const digest = createHash("sha256")
|
||||
// CodeQL: not password hashing — this derives a cache-lookup key from the
|
||||
// conversation transcript, never verified against a stored credential.
|
||||
// Same false-positive class as src/lib/db/apiKeys.ts::hashKey.
|
||||
// lgtm[js/insufficient-password-hash]
|
||||
const digest = createHash("sha256") // nosemgrep: insufficient-password-hash
|
||||
.update(normalizedScope)
|
||||
.update("\x1f")
|
||||
.update(JSON.stringify(transcript))
|
||||
|
||||
@@ -16,7 +16,6 @@ export interface CustomModelEntry {
|
||||
apiFormat?: string;
|
||||
supportedEndpoints?: string[];
|
||||
inputTokenLimit?: number;
|
||||
outputTokenLimit?: number;
|
||||
isHidden?: boolean;
|
||||
// User-set "vision-capable" flag (persisted by addCustomModel / replaceCustomModels
|
||||
// in src/lib/db/models.ts). Surfaced into `/v1/models` via
|
||||
|
||||
@@ -15,25 +15,6 @@ import {
|
||||
rateLimitedProviderResponse,
|
||||
} from "@/app/api/v1/_shared/rateLimit";
|
||||
|
||||
/**
|
||||
* Custom-endpoint providers (e.g. azure-document-intelligence) store the
|
||||
* connection's resource endpoint under providerSpecificData.baseUrl, not as
|
||||
* a top-level credentials field — mirror the convention used across
|
||||
* src/lib/providers/validation/* (see e.g. urlHelpers.ts). handleOcr reads
|
||||
* credentials.baseUrl, so surface it here. An existing top-level baseUrl
|
||||
* always wins (kept for tests/callers that pass it directly).
|
||||
*/
|
||||
export function resolveOcrCredentials<
|
||||
T extends { baseUrl?: string; providerSpecificData?: Record<string, unknown> },
|
||||
>(credentials: T): T {
|
||||
if (credentials?.baseUrl) return credentials;
|
||||
const providerSpecificBaseUrl = credentials?.providerSpecificData?.baseUrl;
|
||||
if (typeof providerSpecificBaseUrl === "string" && providerSpecificBaseUrl.trim()) {
|
||||
return { ...credentials, baseUrl: providerSpecificBaseUrl };
|
||||
}
|
||||
return credentials;
|
||||
}
|
||||
|
||||
/**
|
||||
* Handle CORS preflight
|
||||
*/
|
||||
@@ -85,9 +66,7 @@ async function postHandler(request, context) {
|
||||
return rateLimitedProviderResponse(resolvedProvider, credentials);
|
||||
}
|
||||
|
||||
const ocrCredentials = resolveOcrCredentials(credentials);
|
||||
|
||||
const response = await handleOcr({ body: { ...body, model }, credentials: ocrCredentials });
|
||||
const response = await handleOcr({ body: { ...body, model }, credentials });
|
||||
if (response?.ok) {
|
||||
await clearRecoveredProviderState(credentials);
|
||||
}
|
||||
|
||||
@@ -932,10 +932,6 @@ export const APIKEY_PROVIDERS_GATEWAYS = {
|
||||
"No free tier as of 2026 — Chutes moved to pay-as-you-go (free Early Access ended 2026-03).",
|
||||
authHint: "Bearer API key for the Chutes OpenAI-compatible gateway.",
|
||||
passthroughModels: true,
|
||||
// dots.ocr (rednote-hilab/dots.ocr) is served via Chutes discovery — no static
|
||||
// model entry needed (passthroughModels). Declare imageToText alongside llm
|
||||
// (declaring serviceKinds means "llm" must be explicit too, see #10275).
|
||||
serviceKinds: ["llm", "imageToText"],
|
||||
},
|
||||
// Factory AI ("Factory Droids") subscription gateway — the same backend the
|
||||
// local `droid` CLI shells into, exposed here as an OpenAI-compatible HTTP
|
||||
|
||||
@@ -219,7 +219,6 @@
|
||||
"tests/unit/edgetts-provider.test.ts",
|
||||
"tests/unit/embeddings-auth.test.ts",
|
||||
"tests/unit/error-classification.test.ts",
|
||||
"tests/unit/executor-contract-violation-terminal.test.ts",
|
||||
"tests/unit/error-message-sanitization.test.ts",
|
||||
"tests/unit/error-sensitive-redaction.test.ts",
|
||||
"tests/unit/execute-chat-resource-pressure-breaker.test.ts",
|
||||
|
||||
@@ -22,7 +22,7 @@ const ROUTES = [
|
||||
|
||||
for (const route of ROUTES) {
|
||||
test(`${route.name} early-heartbeat gate uses the real stream resolver`, () => {
|
||||
const escapedBodyExpression = route.bodyExpression.replace(/[?.]/g, "\\$&");
|
||||
const escapedBodyExpression = route.bodyExpression.replace(/[.?\\]/g, "\\$&");
|
||||
assert.match(
|
||||
route.source,
|
||||
new RegExp(
|
||||
|
||||
@@ -1,173 +0,0 @@
|
||||
/**
|
||||
* #10360 — the executor-result contract guard must not hot-loop the router.
|
||||
*
|
||||
* Two defects, one symptom (`tests/unit/batch_api.test.ts` hanging forever):
|
||||
*
|
||||
* 1. CROSS-REALM FALSE POSITIVE. The guard added in #10256 used a bare
|
||||
* `result.response instanceof Response`. OmniRoute's default egress
|
||||
* (`open-sse/utils/proxyFetch.ts`) is the npm `undici` package's `fetch`,
|
||||
* whose `Response` class is NOT `globalThis.Response` — so every ordinary
|
||||
* upstream response arrived as a "contract violation". The guard must
|
||||
* recognize a structurally valid Response from any realm.
|
||||
*
|
||||
* 2. TRANSIENT MISCLASSIFICATION. A genuine contract violation is an INTERNAL
|
||||
* bug, not a flaky upstream. It carried no `.status`, so chatCore's default
|
||||
* mapped it to 502 → the connection got cooled down as "rate limited", the
|
||||
* provider breaker counted it, and `processSingleItemWithRetry` (which
|
||||
* retries 429/502/504 up to 200×/24h) span forever. It must surface as a
|
||||
* terminal internal 500 carrying a stable error code, and every resilience
|
||||
* layer must treat that code as request-scoped: no cooldown, no breaker.
|
||||
*/
|
||||
import test from "node:test";
|
||||
import assert from "node:assert/strict";
|
||||
import { Response as UndiciResponse } from "undici";
|
||||
|
||||
import { normalizeExecutorResult } from "../../open-sse/handlers/chatCore/upstreamTimeouts.ts";
|
||||
import { EXECUTOR_CONTRACT_VIOLATION_CODE } from "../../open-sse/config/constants.ts";
|
||||
import {
|
||||
isRequestScopedUpstreamFailure,
|
||||
shouldSkipConnDisable,
|
||||
} from "../../open-sse/services/combo/comboPredicates.ts";
|
||||
import { shouldTripProviderBreakerForResult } from "../../src/sse/handlers/chatPredicates.ts";
|
||||
import { checkFallbackError } from "../../open-sse/services/accountFallback.ts";
|
||||
|
||||
// ─── 1. Cross-realm Response acceptance ──────────────────────────────────────
|
||||
|
||||
test("undici's Response is a different class than the global one (premise)", () => {
|
||||
assert.notEqual(
|
||||
UndiciResponse as unknown,
|
||||
globalThis.Response as unknown,
|
||||
"if these ever become the same class the cross-realm guard below is moot"
|
||||
);
|
||||
assert.equal(
|
||||
new UndiciResponse("x", { status: 200 }) instanceof globalThis.Response,
|
||||
false,
|
||||
"premise: an undici Response fails a bare `instanceof Response`"
|
||||
);
|
||||
});
|
||||
|
||||
test("normalizeExecutorResult accepts a cross-realm Response in the capture-object arm", () => {
|
||||
const response = new UndiciResponse(JSON.stringify({ ok: true }), { status: 401 });
|
||||
|
||||
const normalized = normalizeExecutorResult({
|
||||
response,
|
||||
url: "https://api.openai.com/v1/chat/completions",
|
||||
headers: { "x-req": "1" },
|
||||
transformedBody: { a: 1 },
|
||||
});
|
||||
|
||||
assert.equal(normalized.response, response as unknown);
|
||||
assert.equal(normalized.response.status, 401);
|
||||
assert.equal(normalized.url, "https://api.openai.com/v1/chat/completions");
|
||||
assert.deepEqual(normalized.headers, { "x-req": "1" });
|
||||
assert.deepEqual(normalized.transformedBody, { a: 1 });
|
||||
});
|
||||
|
||||
test("normalizeExecutorResult accepts a bare cross-realm Response", () => {
|
||||
const response = new UndiciResponse("body", { status: 503 });
|
||||
|
||||
const normalized = normalizeExecutorResult(response);
|
||||
|
||||
assert.equal(normalized.response, response as unknown);
|
||||
assert.equal(normalized.response.status, 503);
|
||||
assert.equal(normalized.url, "");
|
||||
assert.deepEqual(normalized.headers, {});
|
||||
assert.equal(normalized.transformedBody, null);
|
||||
});
|
||||
|
||||
// ─── 2. A genuine violation is terminal, not a transient provider failure ────
|
||||
|
||||
function captureThrow(run: () => unknown): Error & { status?: unknown; code?: unknown } {
|
||||
try {
|
||||
run();
|
||||
} catch (err) {
|
||||
return err as Error & { status?: unknown; code?: unknown };
|
||||
}
|
||||
throw new assert.AssertionError({ message: "expected normalizeExecutorResult to throw" });
|
||||
}
|
||||
|
||||
test("a genuinely malformed executor result still throws", () => {
|
||||
assert.throws(() => normalizeExecutorResult({}), /must contain a Response/);
|
||||
assert.throws(() => normalizeExecutorResult(undefined), /must contain a Response/);
|
||||
assert.throws(() => normalizeExecutorResult({ response: "not-a-response" }), /must contain a/);
|
||||
// A partial look-alike (no body readers) must NOT slip past the duck-type.
|
||||
assert.throws(
|
||||
() => normalizeExecutorResult({ response: { status: 200, ok: true } }),
|
||||
/must contain a Response/
|
||||
);
|
||||
});
|
||||
|
||||
test("the contract-violation error carries an internal-terminal status + stable code", () => {
|
||||
const err = captureThrow(() => normalizeExecutorResult({ response: "not-a-response" }));
|
||||
|
||||
assert.equal(err.status, 500, "an internal contract violation is a 500, never a provider 502");
|
||||
assert.equal(
|
||||
err.code,
|
||||
EXECUTOR_CONTRACT_VIOLATION_CODE,
|
||||
"chatCore reads `.code` (getUpstreamErrorIdentifier) to tag the surfaced error"
|
||||
);
|
||||
assert.equal(EXECUTOR_CONTRACT_VIOLATION_CODE, "executor_contract_violation");
|
||||
});
|
||||
|
||||
test("the contract-violation code is classified as a request-scoped failure", () => {
|
||||
assert.equal(isRequestScopedUpstreamFailure({ code: EXECUTOR_CONTRACT_VIOLATION_CODE }), true);
|
||||
});
|
||||
|
||||
test("a contract violation must not cool the connection down", () => {
|
||||
assert.equal(
|
||||
shouldSkipConnDisable(
|
||||
{
|
||||
status: 500,
|
||||
errorCode: EXECUTOR_CONTRACT_VIOLATION_CODE,
|
||||
errorType: null,
|
||||
error: "Executor result must contain a Response",
|
||||
},
|
||||
false,
|
||||
false,
|
||||
"openai"
|
||||
),
|
||||
true,
|
||||
"our own bug must never mark the operator's account as rate-limited/unavailable"
|
||||
);
|
||||
});
|
||||
|
||||
test("a contract violation must not trip the provider circuit breaker", () => {
|
||||
assert.equal(
|
||||
shouldTripProviderBreakerForResult(
|
||||
{
|
||||
status: 500,
|
||||
errorCode: EXECUTOR_CONTRACT_VIOLATION_CODE,
|
||||
errorType: null,
|
||||
error: "Executor result must contain a Response",
|
||||
},
|
||||
false,
|
||||
false
|
||||
),
|
||||
false,
|
||||
"500 is a breaker-failure status, but this one never reached the provider"
|
||||
);
|
||||
});
|
||||
|
||||
test("checkFallbackError treats the contract violation as terminal — no retry, no cooldown", () => {
|
||||
const decision = checkFallbackError(
|
||||
500,
|
||||
"[500]: Executor result must contain a Response",
|
||||
0,
|
||||
"gpt-4o-mini",
|
||||
"openai",
|
||||
null,
|
||||
null,
|
||||
{ code: EXECUTOR_CONTRACT_VIOLATION_CODE }
|
||||
);
|
||||
|
||||
assert.equal(decision.shouldFallback, false, "retrying our own bug just reproduces it");
|
||||
assert.equal(decision.cooldownMs, 0, "no connection cooldown for an internal defect");
|
||||
assert.equal(decision.skipProviderBreaker, true);
|
||||
});
|
||||
|
||||
test("a real provider 500 is still retryable (the terminal branch is not over-broad)", () => {
|
||||
const decision = checkFallbackError(500, "Internal server error", 0, null, "openai");
|
||||
|
||||
assert.equal(decision.shouldFallback, true);
|
||||
assert.ok(decision.cooldownMs > 0, "a genuine upstream 500 keeps its backoff cooldown");
|
||||
});
|
||||
@@ -1,21 +0,0 @@
|
||||
import { test } from "node:test";
|
||||
import assert from "node:assert/strict";
|
||||
import { resolveProviderServiceKinds } from "../../open-sse/config/mediaServiceKinds.ts";
|
||||
import { AI_PROVIDERS } from "../../src/shared/constants/providers.ts";
|
||||
|
||||
test("OCR-registry providers derive imageToText without manual declaration", () => {
|
||||
assert.ok(resolveProviderServiceKinds("mistral", undefined).includes("imageToText"));
|
||||
assert.ok(
|
||||
resolveProviderServiceKinds("azure-document-intelligence", undefined).includes("imageToText")
|
||||
);
|
||||
});
|
||||
|
||||
test("non-OCR providers do not gain imageToText implicitly", () => {
|
||||
assert.ok(!resolveProviderServiceKinds("groq", undefined).includes("imageToText"));
|
||||
});
|
||||
|
||||
test("chutes declares llm + imageToText (dots.ocr seed, served via passthrough discovery)", () => {
|
||||
const kinds = resolveProviderServiceKinds("chutes", AI_PROVIDERS.chutes.serviceKinds);
|
||||
assert.ok(kinds.includes("imageToText"));
|
||||
assert.ok(kinds.includes("llm"));
|
||||
});
|
||||
@@ -251,11 +251,6 @@ test("v1 model catalog overlays same-id custom metadata before final overrides",
|
||||
{ outputTokenLimit: 32000 },
|
||||
false
|
||||
);
|
||||
|
||||
const customProjected = await getModel(`${prefix}/${modelId}`);
|
||||
assert.ok(customProjected);
|
||||
assert.equal(customProjected.max_output_tokens, 32000);
|
||||
|
||||
assert.equal(
|
||||
capabilityOverrides.setModelCapabilityOverride(
|
||||
`${prefix}/${modelId}`,
|
||||
|
||||
@@ -1398,15 +1398,8 @@ test("v1 models catalog skips duplicate built-ins and custom models from inactiv
|
||||
const duplicateBuiltins = body.data.filter((item) => item.id === "openai/gpt-4o-2024-11-20");
|
||||
|
||||
assert.equal(response.status, 200);
|
||||
// Still exactly one entry: the custom row overlays the built-in, it does not duplicate it.
|
||||
assert.equal(duplicateBuiltins.length, 1);
|
||||
// #10248 changed the contract: a custom row for an id that already exists is the
|
||||
// operator-owned overlay for that model (catalog.ts:1330) — its explicitly stored
|
||||
// fields win over the discovered metadata, and the merged entry is flagged `custom`.
|
||||
// Before #10248 the duplicate was skipped outright, so this asserted `false`.
|
||||
assert.equal(duplicateBuiltins[0].custom, true);
|
||||
// The overlay must keep the catalog identity rather than becoming a detached entry.
|
||||
assert.equal(duplicateBuiltins[0].id, "openai/gpt-4o-2024-11-20");
|
||||
assert.equal(duplicateBuiltins[0].custom === true, false);
|
||||
assert.equal(
|
||||
body.data.some((item) => item.id === "cl/inactive-only" || item.id === "cline/inactive-only"),
|
||||
false
|
||||
|
||||
@@ -1,133 +0,0 @@
|
||||
import { test } from "node:test";
|
||||
import assert from "node:assert/strict";
|
||||
import { handleOcr } from "../../open-sse/handlers/ocr.ts";
|
||||
|
||||
function fetchStub(
|
||||
script: Array<{ status: number; headers?: Record<string, string>; json?: unknown }>
|
||||
) {
|
||||
const calls: Array<{ url: string; init: RequestInit }> = [];
|
||||
const impl = async (url: string, init: RequestInit) => {
|
||||
calls.push({ url, init });
|
||||
const step = script.shift()!;
|
||||
return new Response(step.json !== undefined ? JSON.stringify(step.json) : null, {
|
||||
status: step.status,
|
||||
headers: { "Content-Type": "application/json", ...(step.headers ?? {}) },
|
||||
});
|
||||
};
|
||||
return { impl, calls };
|
||||
}
|
||||
|
||||
const noSleep = async () => {};
|
||||
|
||||
test("mistral path posts once and returns the upstream body", async () => {
|
||||
const { impl, calls } = fetchStub([
|
||||
{ status: 200, json: { pages: [{ index: 0, markdown: "ok" }], model: "mistral-ocr-latest" } },
|
||||
]);
|
||||
const res = await handleOcr({
|
||||
body: {
|
||||
model: "mistral/mistral-ocr-latest",
|
||||
document: { type: "image_url", image_url: "https://x/y.png" },
|
||||
},
|
||||
credentials: { apiKey: "sk" },
|
||||
fetchImpl: impl,
|
||||
sleepImpl: noSleep,
|
||||
});
|
||||
assert.equal(res.status, 200);
|
||||
assert.equal(calls.length, 1);
|
||||
const data = await res.json();
|
||||
assert.equal(data.pages[0].markdown, "ok");
|
||||
});
|
||||
|
||||
test("azure DI path polls Operation-Location until succeeded", async () => {
|
||||
const { impl, calls } = fetchStub([
|
||||
{ status: 202, headers: { "Operation-Location": "https://poll/op/1" } },
|
||||
{ status: 200, json: { status: "running" } },
|
||||
{ status: 200, json: { status: "succeeded", analyzeResult: { content: "# md", pages: [{}] } } },
|
||||
]);
|
||||
const res = await handleOcr({
|
||||
body: {
|
||||
model: "azure-document-intelligence/prebuilt-read",
|
||||
document: { type: "document_url", document_url: "https://x/d.pdf" },
|
||||
},
|
||||
credentials: { apiKey: "azkey", baseUrl: "https://r.cognitiveservices.azure.com" },
|
||||
fetchImpl: impl,
|
||||
sleepImpl: noSleep,
|
||||
});
|
||||
assert.equal(res.status, 200);
|
||||
assert.ok(calls.length >= 3);
|
||||
const data = await res.json();
|
||||
assert.equal(data.pages[0].markdown, "# md");
|
||||
});
|
||||
|
||||
test("unknown model lists available providers dynamically and errors do not leak internals", async () => {
|
||||
const res = await handleOcr({
|
||||
body: { model: "nope/none", document: { type: "image_url", image_url: "https://x" } },
|
||||
credentials: { apiKey: "k" },
|
||||
fetchImpl: async () => new Response("{}", { status: 200 }),
|
||||
sleepImpl: noSleep,
|
||||
});
|
||||
assert.equal(res.status, 400);
|
||||
const body = await res.json();
|
||||
assert.ok(body.error.message.includes("azure-document-intelligence"));
|
||||
assert.ok(!body.error.message.includes("at /"));
|
||||
});
|
||||
|
||||
test("azure DI poll returns failed status maps to 502", async () => {
|
||||
const { impl } = fetchStub([
|
||||
{ status: 202, headers: { "Operation-Location": "https://poll/op/1" } },
|
||||
{ status: 200, json: { status: "failed" } },
|
||||
]);
|
||||
const res = await handleOcr({
|
||||
body: {
|
||||
model: "azure-document-intelligence/prebuilt-read",
|
||||
document: { type: "document_url", document_url: "https://x/d.pdf" },
|
||||
},
|
||||
credentials: { apiKey: "azkey", baseUrl: "https://r.cognitiveservices.azure.com" },
|
||||
fetchImpl: impl,
|
||||
sleepImpl: noSleep,
|
||||
});
|
||||
assert.equal(res.status, 502);
|
||||
const body = await res.json();
|
||||
assert.ok(!body.error.message.includes("at /"));
|
||||
});
|
||||
|
||||
test("azure DI poll returns a non-ok response (401) and fails fast without exhausting the loop", async () => {
|
||||
const { impl, calls } = fetchStub([
|
||||
{ status: 202, headers: { "Operation-Location": "https://poll/op/1" } },
|
||||
{ status: 401, json: { error: "unauthorized" } },
|
||||
]);
|
||||
const res = await handleOcr({
|
||||
body: {
|
||||
model: "azure-document-intelligence/prebuilt-read",
|
||||
document: { type: "document_url", document_url: "https://x/d.pdf" },
|
||||
},
|
||||
credentials: { apiKey: "azkey", baseUrl: "https://r.cognitiveservices.azure.com" },
|
||||
fetchImpl: impl,
|
||||
sleepImpl: noSleep,
|
||||
});
|
||||
assert.equal(res.status, 502);
|
||||
// 1 initial POST + 1 poll: the loop stopped immediately, it did not run all 30 attempts.
|
||||
assert.equal(calls.length, 2);
|
||||
const body = await res.json();
|
||||
assert.ok(!body.error.message.includes("at /"));
|
||||
});
|
||||
|
||||
test("azure DI poll never resolves and times out after 30 attempts with a 504", async () => {
|
||||
const script = [{ status: 202, headers: { "Operation-Location": "https://poll/op/1" } }];
|
||||
for (let i = 0; i < 30; i++) {
|
||||
script.push({ status: 200, json: { status: "running" } });
|
||||
}
|
||||
const { impl, calls } = fetchStub(script);
|
||||
const res = await handleOcr({
|
||||
body: {
|
||||
model: "azure-document-intelligence/prebuilt-read",
|
||||
document: { type: "document_url", document_url: "https://x/d.pdf" },
|
||||
},
|
||||
credentials: { apiKey: "azkey", baseUrl: "https://r.cognitiveservices.azure.com" },
|
||||
fetchImpl: impl,
|
||||
sleepImpl: noSleep,
|
||||
});
|
||||
assert.equal(res.status, 504);
|
||||
// 1 initial POST + 30 poll attempts (the max cap), no more.
|
||||
assert.equal(calls.length, 31);
|
||||
});
|
||||
@@ -1,74 +0,0 @@
|
||||
import { test } from "node:test";
|
||||
import assert from "node:assert/strict";
|
||||
import {
|
||||
OCR_PROVIDERS,
|
||||
getOcrTransformation,
|
||||
MISTRAL_PASSTHROUGH,
|
||||
} from "../../open-sse/config/ocrRegistry.ts";
|
||||
|
||||
test("mistral resolves the passthrough transformation by default", () => {
|
||||
const t = getOcrTransformation("mistral");
|
||||
assert.equal(t, MISTRAL_PASSTHROUGH);
|
||||
const { url, init } = t.buildRequest({
|
||||
baseUrl: OCR_PROVIDERS.mistral.baseUrl,
|
||||
token: "sk-test",
|
||||
body: { document: { type: "image_url", image_url: "https://x/y.png" } },
|
||||
modelId: "mistral-ocr-latest",
|
||||
});
|
||||
assert.equal(url, "https://api.mistral.ai/v1/ocr");
|
||||
assert.equal(init.method, "POST");
|
||||
assert.equal((init.headers as Record<string, string>).Authorization, "Bearer sk-test");
|
||||
const sent = JSON.parse(String(init.body));
|
||||
assert.equal(sent.model, "mistral-ocr-latest");
|
||||
});
|
||||
|
||||
test("passthrough parseResponse returns the body unchanged (Mistral is the canonical shape)", () => {
|
||||
const raw = { pages: [{ index: 0, markdown: "hello" }], model: "mistral-ocr-latest" };
|
||||
assert.deepEqual(MISTRAL_PASSTHROUGH.parseResponse(raw), raw);
|
||||
});
|
||||
|
||||
test("azure-document-intelligence builds the prebuilt-read:analyze request", () => {
|
||||
const t = getOcrTransformation("azure-document-intelligence");
|
||||
const { url, init } = t.buildRequest({
|
||||
baseUrl: "https://myres.cognitiveservices.azure.com",
|
||||
token: "azkey",
|
||||
body: { document: { type: "document_url", document_url: "https://x/d.pdf" } },
|
||||
modelId: "prebuilt-read",
|
||||
});
|
||||
assert.equal(
|
||||
url,
|
||||
"https://myres.cognitiveservices.azure.com/documentintelligence/documentModels/prebuilt-read:analyze?api-version=2024-11-30&outputContentFormat=markdown"
|
||||
);
|
||||
assert.equal((init.headers as Record<string, string>)["Ocp-Apim-Subscription-Key"], "azkey");
|
||||
const sent = JSON.parse(String(init.body));
|
||||
assert.equal(sent.urlSource, "https://x/d.pdf");
|
||||
});
|
||||
|
||||
test("azure-document-intelligence extracts poll URL and parses analyzeResult into Mistral shape", () => {
|
||||
const t = getOcrTransformation("azure-document-intelligence");
|
||||
const res = new Response(null, {
|
||||
status: 202,
|
||||
headers: { "Operation-Location": "https://poll/op/1" },
|
||||
});
|
||||
assert.equal(t.pollUrl?.(res), "https://poll/op/1");
|
||||
const parsed = t.parseResponse({
|
||||
status: "succeeded",
|
||||
analyzeResult: { content: "# doc text", pages: [{ pageNumber: 1 }] },
|
||||
});
|
||||
assert.equal(parsed.pages.length, 1);
|
||||
assert.equal(parsed.pages[0].index, 0);
|
||||
assert.equal(parsed.pages[0].markdown, "# doc text");
|
||||
assert.equal(parsed.model, "prebuilt-read");
|
||||
});
|
||||
|
||||
test("azure DI maps base64/image_url documents to base64Source/urlSource", () => {
|
||||
const t = getOcrTransformation("azure-document-intelligence");
|
||||
const { init } = t.buildRequest({
|
||||
baseUrl: "https://r.example.com",
|
||||
token: "k",
|
||||
body: { document: { type: "image_url", image_url: "data:image/png;base64,AAAA" } },
|
||||
modelId: "prebuilt-read",
|
||||
});
|
||||
const sent = JSON.parse(String(init.body));
|
||||
assert.equal(sent.base64Source, "AAAA");
|
||||
});
|
||||
@@ -1,48 +0,0 @@
|
||||
import { test } from "node:test";
|
||||
import assert from "node:assert/strict";
|
||||
import { getAllOcrModels, parseOcrModel } from "../../open-sse/config/ocrRegistry.ts";
|
||||
import { resolveOcrCredentials } from "../../src/app/api/v1/ocr/route.ts";
|
||||
|
||||
test("getAllOcrModels exposes both the mistral and azure-document-intelligence OCR models", () => {
|
||||
const ids = getAllOcrModels().map((m) => m.id);
|
||||
assert.ok(ids.includes("mistral/mistral-ocr-latest"));
|
||||
assert.ok(ids.includes("azure-document-intelligence/prebuilt-read"));
|
||||
});
|
||||
|
||||
test("parseOcrModel resolves the azure-document-intelligence provider prefix", () => {
|
||||
assert.deepEqual(parseOcrModel("azure-document-intelligence/prebuilt-read"), {
|
||||
provider: "azure-document-intelligence",
|
||||
model: "prebuilt-read",
|
||||
});
|
||||
});
|
||||
|
||||
// ── resolveOcrCredentials — maps the connection's custom endpoint (stored
|
||||
// under providerSpecificData.baseUrl per the src/lib/providers/validation/*
|
||||
// convention) onto the top-level credentials.baseUrl field that handleOcr
|
||||
// reads, so azure-document-intelligence connections resolve their endpoint. ──
|
||||
|
||||
test("resolveOcrCredentials surfaces providerSpecificData.baseUrl to the top level", () => {
|
||||
const credentials = {
|
||||
apiKey: "azkey",
|
||||
providerSpecificData: { baseUrl: "https://r.cognitiveservices.azure.com" },
|
||||
};
|
||||
assert.deepEqual(resolveOcrCredentials(credentials), {
|
||||
apiKey: "azkey",
|
||||
providerSpecificData: { baseUrl: "https://r.cognitiveservices.azure.com" },
|
||||
baseUrl: "https://r.cognitiveservices.azure.com",
|
||||
});
|
||||
});
|
||||
|
||||
test("resolveOcrCredentials keeps an existing top-level baseUrl untouched", () => {
|
||||
const credentials = {
|
||||
apiKey: "azkey",
|
||||
baseUrl: "https://explicit.example.com",
|
||||
providerSpecificData: { baseUrl: "https://ignored.example.com" },
|
||||
};
|
||||
assert.equal(resolveOcrCredentials(credentials).baseUrl, "https://explicit.example.com");
|
||||
});
|
||||
|
||||
test("resolveOcrCredentials is a no-op when there is no providerSpecificData.baseUrl (mistral)", () => {
|
||||
const credentials = { apiKey: "sk-mistral" };
|
||||
assert.deepEqual(resolveOcrCredentials(credentials), credentials);
|
||||
});
|
||||
@@ -183,7 +183,6 @@ test("handleOcr returns a sanitized 500 when the upstream request throws", async
|
||||
const payload = (await response.json()) as any;
|
||||
|
||||
assert.equal(response.status, 500);
|
||||
assert.ok(payload.error.message.includes("OCR request failed"));
|
||||
assert.ok(!payload.error.message.includes("socket closed"));
|
||||
assert.match(payload.error.message, /OCR request failed: socket closed/);
|
||||
assert.ok(!payload.error.message.includes("at /"));
|
||||
});
|
||||
|
||||
Reference in New Issue
Block a user