mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-07-26 09:52:11 +03:00
* chore(release): open v3.8.27 development cycle * fix(security): polynomial ReDoS in comboAgentMiddleware regex (#3982) * fix(security): eliminate polynomial ReDoS in comboAgentMiddleware <omniModel> regex (CodeQL js/polynomial-redos) CACHE_TAG_PATTERN wrapped the tag in an unbounded `(?:\\n|\n|\r)*` prefix/suffix. On an unanchored `.test()`/`.exec()` that is O(n²) on inputs with many newlines (CodeQL js/polynomial-redos, alerts #612/#613). The surrounding runs are irrelevant to detecting/capturing the tag, so the detection pattern now matches only the core `<omniModel>([^<]+)</omniModel>`; the global strip pattern still consumes the wrapping newlines (combo.ts streaming, #531) but BOUNDED ({0,16}) so it stays linear. Behavior preserved: detection, model extraction, multi-tag stripping (#454) and blank-line cleanup all unchanged (107 related tests green). Adds ReDoS-safety regression tests (50k-newline inputs complete in <1ms). * docs(changelog): add #3982 ReDoS fix to [3.8.27] * ci(security): harden workflows — artipacked persist-credentials + cache-poisoning + SC2086 (#3965) * Refine provider quota card display (#3969) Integrated into release/v3.8.27 * feat: add sidebar group separator toggles (#3971) Integrated into release/v3.8.27 * Gate control-plane proxy direct fallback (#3963) Integrated into release/v3.8.27 * Capture actual upstream provider requests (#3941) Integrated into release/v3.8.27 * ci(quality): flip require-tighten + osv + Trivy to blocking (v3.8.27 cycle-end) (#3984) * fix(resilience): respect connection cooldown stored as numeric epoch (#3954) (#3995) rate_limited_until is a TEXT column, but setConnectionRateLimitUntil (Antigravity full-quota path) persists a raw epoch number that SQLite coerces to a numeric string ("1781696905131.0"). The selection predicate isAccountUnavailable then did new Date("1781696905131.0") -> NaN, so the cooling connection was never skipped and the router kept dispatching to rate-limited accounts. Normalize numeric-epoch strings (and number/Date/ISO) via a shared cooldownUntilMs() helper in isAccountUnavailable / getEarliestRateLimitedUntil / filterAvailableAccounts / parseFutureDateMs. ISO behavior preserved. * fix(providers): fetch live /models for LLM7 and BytePlus (#3976) (#3996) llm7 and byteplus carry a real modelsUrl but were not classified by any live-fetch branch of the model-import route, so their hardcoded 4-entry registry catalog was served (source local_catalog) instead of the upstream catalog. Add both to NAMED_OPENAI_STYLE_PROVIDERS so the route probes <baseUrl>/models and serves the live list, falling back to the local catalog only on fetch failure. * fix(dashboard): logs auto-refresh reads live visibility, not a stale mount ref (#3972) (#3997) The auto-refresh interval gated each tick on visibleRef, seeded once at mount and updated only by a visibilitychange event. A tab mounted while document.visibilityState is 'hidden' (background load, bfcache, embedded/proxied webviews) with no later visibilitychange left the ref false forever, so the interval ticked but never fetched — only the manual button worked. Read the live document.visibilityState in the tick instead. * feat(compression): add Indonesian caveman rules and language pack (#3975) Integrated into release/v3.8.27 (cherry picked from commitc9b5b1a892) * fix(combo): shuffle strict-random fallback remainder to spread load (#3959) (#3998) strict-random shuffled only the deck-selected slot 0 and left the fallback remainder in fixed priority order, so after a failing deck pick the chain always fell through to the same top-priority model — a persistently-failing model was retried on essentially every request and fallback load never spread across peers. Shuffle the remainder too (like the random strategy). * Add provider auth visibility controls (#3953) Integrated into release/v3.8.27 * fix(claude): forward client tool-search-tool anthropic-beta on the Claude OAuth path (#3974) (#3999) The client-negotiated anthropic-beta: tool-search-tool-2025-10-19 was dropped on both Claude code paths (default executor rebuilt from static ANTHROPIC_BETA_CLAUDE_OAUTH; selectBetaFlags only read the client beta to gate thinking/effort), so claude.ai rejected deferred-tool requests with 400 'Tool reference not found'. Add an allowlist-merge (mergeClientAnthropicBeta) that unions the client's allowlisted betas into the outbound set on both paths, preserving #3415 (no forced thinking/effort). * feat(providers): add model search filter to provider dashboard (#3950) Integrated into release/v3.8.27 * fix(vision-bridge): force bridge for tokenrouter deepseek models (#3946) Integrated into release/v3.8.27 * fix(executor): strip stream_options on non-streaming requests (#3884) (#4000) Clients that send stream_options:{include_usage:true} regardless of stream (e.g. the OpenAI Python SDK) had it passed through on non-streaming calls; NVIDIA NIM rejected it with 400 'Stream options can only be defined when stream=True'. DefaultExecutor.transformRequest only injected/cleared stream_options on the streaming branch and never stripped a client-sent value when stream=false. Add a !stream strip branch; the streaming injection path is unchanged. Global to openai-compat providers. * fix(qwen-web): cookie validation false-positive - check response body for user object (#3958) Integrated into release/v3.8.27 * fix(db): persist backup retention days (#3970) Integrated into release/v3.8.27 * 大量UI显示和i18n优化 (#3973) Integrated into release/v3.8.27 * deps: bump the npm_and_yarn group across 1 directory with 2 updates (#3943) Integrated into release/v3.8.27 * deps: bump form-data from 4.0.5 to 4.0.6 (#3944) Integrated into release/v3.8.27 * deps: bump vite from 8.0.5 to 8.0.16 (#3942) Integrated into release/v3.8.27 * chore(quality): re-baseline validation.ts 4407->4428 (#3958 qwen body-check) The qwen-web validation body-check merged in #3958 pushed validation.ts past its frozen size on the integrated release tip. Bump the baseline with justification; no logic is separately extractable from the existing qwen-web validation branch. * deps: bump the production group with 13 updates (#3915) Integrated into release/v3.8.27 — low-risk group (playwright 1.60→1.61 minor + transitive patches; fumadocs-core 16.9→16.10 minor). * chore(deps): ignore jscpd major bumps (v5 Rust rewrite breaks the duplication gate) Our duplication ratchet (scripts/check/check-duplication.mjs) is pinned to jscpd@4 and parses jscpd-report.json against a frozen baseline. jscpd v5 is a native Rust binary with no Node.js API and a different report/bin, so a major bump would break the gate. Migrate deliberately, not via dependabot. Closes the noise from #3916. * fix(perplexity-web): parse schematized diff_block stream so answers aren't empty (#4001) Integrated into release/v3.8.27 — schematized diff_block parsing follow-up to #3938. * refactor: modularize providerRegistry.ts into 159 individual provider plugins (#3993) Modularize provider registry (#3594). Integrated into release/v3.8.27 after rebase + behavior-preservation verification (provider-consistency gate 159/232/0, typecheck, registry tests, build 556/556). Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * fix(registry): restore byteplus + mimocode dropped by #3993 modularization The provider-registry modularization (#3993) was cut from a base predating the byteplus (#3877) and mimocode (#3837) registry entries, so merging it silently dropped both providers (getRegistryEntry returned undefined → validation reported 'not supported'). Re-add them as registry modules in the new structure; registered count 159→161, provider-consistency 161/232/0. Also align the pre-existing qwen-web validator test to #3958: since the validator now requires a real `user` object in the 200 body, the mock must carry one. * refactor: modularize schemas (non-stacked) (#3988) Modularize validation schemas (#3594). Integrated into release/v3.8.27 after rebase (reconciled the merged hiddenSidebarGroupLabels #3971 + intelligenceSyncRequestSchema into the new modules) + behavior verification (typecheck, 195 schema/settings/validation tests, build 556/556). Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * fix(default-executor): honor custom providerSpecificData.baseUrl for OpenAI-format providers (#4002) Integrated into release/v3.8.27 — honor custom providerSpecificData.baseUrl in DefaultExecutor (openai-format), tested. * feat(openai): honor custom base URL in model discovery + complete openai/codex pricing (#4005) Integrated into release/v3.8.27 — openai model-discovery honors custom base URL (SSRF-guarded) + pricing rows for new openai/codex models. Tested + baselines bumped. * fix(live-ws): bridge sidecar events to dashboard (#4004) Integrated into release/v3.8.27 — repair LiveWS sidecar (startup, same-origin /live-ws, main→sidecar compression.completed bridge, early-msg queue). Fixed the cookie-parse regex (\s) + added a focused unit test; baseline bumped for the non-blocking chatCore bridge. * docs(troubleshooting): note MITM proxy cannot intercept Windows-host apps under WSL (#4003) Integrated into release/v3.8.27 — MITM/WSL troubleshooting note. * fix(repo): untrack accidentally-committed root node_modules symlink + gitignore it A worktree node_modules symlink (-> the main checkout's node_modules) was staged by a `git add -A` during the #3988 merge and committed into05213ac6a. The symlink points at the repo's own node_modules path, so checking it out turns the main checkout's node_modules into a self-referential symlink (breaking tsx/all node ops). Untrack it and add a root-anchored /node_modules ignore so the symlink form can't be re-committed (the existing 'node_modules/' only matches directories). * fix(quality): allowlist socks dep (declared by #4004, never allowlisted) socks@^2.8.7 was added to package.json in #4004 (LiveWS sidecar,02302131f) as a phantom-dep cleanup but never added to dependency-allowlist.json, so check:deps has been red on the release tip ever since. socks is the standard SOCKS proxy client (dep of fetch-socks), legitimate and years old. * feat(sse): real LLMLingua-2 ONNX compression engine (stable) (#4014) Integrated into release/v3.8.27. Adjustments before merge: - Synced with the current release tip (was 11 commits behind). - Added the 3 LLMLingua-2 ONNX optional-runtime deps to dependency-allowlist.json (@atjsh/llmlingua-2, @tensorflow/tfjs, js-tiktoken) — the only gate that was red. - socks was allowlisted directly on release (separate fix d7db5c73d; it was declared by #4004 but never allowlisted, leaving check:deps red release-wide). Verified locally: check:deps OK, file-size OK, public-creds OK, provider-consistency 161/232/0, typecheck:core clean, 24/24 LLMLingua tests pass. The only remaining Fast-QG red is the pre-existing #3972 orphan test (request-logger-autorefresh-visibility-3972.test.tsx), which is release-wide and unrelated to this PR. * test(dashboard): rehome #3972 logs auto-refresh test so a runner collects it tests/unit/request-logger-autorefresh-visibility-3972.test.tsx (added by #3972 via #3997) sat at the top level of tests/unit/ as a .tsx vitest test, which NO runner collects: the node runner only globs *.test.ts, and test:vitest:ui only runs tests/unit/ui. So the #3972 regression guard never executed in CI and check:test-discovery was red release-wide. Move it under tests/unit/ui/ (the collected vitest:ui path) and fix the relative import depth. Verified: the test now runs and passes (2/2), and check:test-discovery is green. * feat(compression): capture per-engine analytics (#3960) + Lite schema fix (#3952) (#4018) Captures the net-new value from #3960 (per-engine breakdown analytics) and #3952 (Lite engine schema fix) onto release/v3.8.27. Fast QG green; 622/622 compression+analytics tests pass. * fix(sse): guard model-less registry entries in getUnsupportedParams (mimocode) (#4015) Real bugfix: guard model-less registry entries (mimocode) in getUnsupportedParams so handleChatCore no longer throws 'entry.models is not iterable' / reports 'All models failed' for unrelated requests. Includes a regression test. Fast QG green. * feat(ci): Quality Gate v2 — Onda 0 + Onda 1 (gate flips, TIA, SAST, DAST-smoke, mutation infra) (#4016) * docs(ops): add quality-gate assessment + replication playbook (Fase 9 foundation) * feat(ci): flip oasdiff breaking-change gate to blocking (ratchet) * docs(ops): deliver main branch-protection ruleset for owner to apply * fix(ci): run typecheck:core in PR->release fast-gates (close fast-gates hole, part 1) * perf(mutation): enable Stryker incremental mode + cache (scales the 60/80 rollout) * feat(ci): commit CodeQL advanced config (security-extended), replacing default-setup * feat(ci): version semgrep SAST workflow (owasp/secrets), advisory * feat(quality): TIA test-impact map builder (import-graph; map built at runtime, gitignored) * feat(quality): TIA impacted-test selector with run-all fail-safe * fix(ci): run TIA-impacted unit tests in PR->release fast-gates (build map at runtime, fail-safe full) * feat(ci): DAST-smoke per-PR (schemathesis subset + promptfoo injection-guard, blocking) * fix(ci): unbreak Fase 9 PR CI (MDX frontmatter, CodeQL conflict, dast-smoke advisory) - Add MDX frontmatter to docs/ops/{BRANCH_PROTECTION_MAIN,QUALITY_GATE_PLAYBOOK}.md. fumadocs rejects frontmatter-less docs -> 'npm run build' failed -> broke dast-smoke's build step (the release fast-gates never runs build, so this only surfaced on the PR). - codeql.yml: workflow_dispatch-only until the owner switches repo CodeQL Default->Advanced (advanced configs cannot be processed while default setup is enabled; documented inline). - dast-smoke.yml: job-level continue-on-error (advisory) so this brand-new gate matures before it blocks (repo convention: advisory -> blocking). * ci(quality): make TIA unit-test step advisory until release test-debt is cleared release/v3.8.27 carries ~17 pre-existing failing unit tests (budget #3537, apiKey #3552, several Zod schemas, Puter/Qwen executors, mimocode entry, etc.) unrelated to this PR — the new 'run tests on PR->release' gate surfaced them. Per the repo's advisory->blocking convention, this step enters advisory (it still runs + reports) so pre-existing debt doesn't block the gate program. typecheck:core stays blocking. Flip to blocking (remove continue-on-error) once the release suite is green. * fix(sse): preserve Kiro streaming finish_reason tool_calls (#3980) (#4025) * fix(guardrails): preserve original image when vision-bridge describe fails (#4012) (#4026) * feat(api): advertise combo capabilities on import surfaces (#3979) (#4027) * feat(sse): delegated Anthropic Context Editing for Claude (clear_tool_uses) (#4021) Opt-in Claude-only delegated compression: injects context_management.clear_tool_uses_20250919 at the Claude pre-serialization chokepoint (composes with clear_thinking, thinking first), threaded via ExecuteInput from handleChatCore. Pure edit-builder + 11 tests (7 unit + 4 e2e fetch-capture). Beta context-management-2025-06-27 already advertised; allowlist done. Telemetry/400-fallback/claude-web coverage deferred. * fix(opencode): map x-session-affinity to x-opencode-session for custom providers (#4022) (#4028) * fix(dashboard): Playground Compare tab loading + HTTP method guard (#4024) randomUUID non-HTTPS fallback + static CompareTab import; raw HTTP TRACE->405 method guard wired into dev + standalone servers. Integrated into release/v3.8.27. * refactor(dashboard): settings UI layout + API Keys naming (#4020) Presentation/relabel refactor of the Settings dashboard (API Manager -> API Keys), card relocations, Toggle adoption, present-but-disabled engine steps. Auth-file changes are string/comment-only (no behavior change). Integrated into release/v3.8.27. * fix: restore unit regressions dropped by lossy schema/registry modularizations (#4030) Restores schema fields (combo reasoningTokenBuffer, budget-0 #3537, openrouter preset, proxy family #3777, resilience degradation/providerCooldown), qwen-web v2 endpoint+catalog, mimocode models key — all dropped by #3988/#3993 — and aligns 3 tests to #3941/#3993. Verified: 8 failing regression tests on release tip -> 131/131 green on this branch. Integrated into release/v3.8.27. * fix(api): return 400 (not 500) for malformed JSON on /api/auth/login (#4031) Wrap request.json() so a malformed/non-JSON login body returns a structured 400 instead of falling through to the 500 catch. Fixes the schemathesis high-risk-endpoint DAST finding (verified: schemathesis step now passes). +TDD test. Integrated into release/v3.8.27. * feat(dashboard): real circuit-breaker state in the Combo Live cascade (U1b) (#4029) Overlays real provider circuit-breaker state (GET /api/monitoring/health) onto the Combo Live cascade as a 'CB: OPEN · 41s' badge. Pure enrichRunWithBreakers + fail-soft useProviderBreakerHealth poll; graceful when health is absent. +13 tests. Integrated into release/v3.8.27. * Fix promptfoo security assertion parsing (#4032) * chore(deps): dependabot security bumps + drop unused gray-matter (#4036) Integrated into release/v3.8.27 — dependabot security bumps (form-data/js-yaml/protobufjs/dompurify/hono) + drop unused gray-matter. Unblocks the npm audit:deps gate (Lint) branch-wide. * fix(ci): scope TIA to node:test unit files only (mirror test:unit glob) (#4035) Integrated into release/v3.8.27 — scopes the advisory TIA step to the test:unit node:test glob, fixing the 99 false failures. +4 TDD. * Refine compression settings, storage labels, and sidebar grouping (#4033) Integrated into release/v3.8.27 — relocate Token Saver into Compression Settings (controlled component), reorder Security/Authz tabs, storage labels + i18n relabel. Thanks @rdself! * [codex] add per-key local usage command (#4034) Integrated into release/v3.8.27 — per-key local @@om-usage command (cached quota, no upstream routing). Rebased onto modularized schemas/keys.ts + file-size rebaseline. Thanks @Witroch4! * chore(release): reconcile v3.8.27 CHANGELOG + i18n mirrors * ci(quality): unblock v3.8.27 release gates (zizmor pin + test-masking allowlist) - zizmor ratchet (151→139, no regression): SHA-pin every action ref ADDED this cycle — codeql/dast-smoke/semgrep (3 new workflows) + trivy-action (docker-publish) + actions/cache (nightly-mutation). Pre-existing tag refs keep the repo convention. - test-masking: add config/quality/test-masking-allowlist.json + allowlist support in check-test-masking.mjs (exempts ONLY the net-assert-reduction signal; tautology/skip/ deletion still fire). Allowlists 2 verified-legitimate reductions: appearance-widget-settings-schema (#4033 removed showTokenSaverOnEndpoint field) and dashboard-shell-tabs (#3973 tabs→redirect refactor, asserts replaced). +4 gate tests. * test(quality): reword test-masking self-test comments to avoid literal masking patterns The added allowlist-test comments contained the literal strings 'assert.ok(true)' and '.skip' which the masking detector's own regexes match as text — making the gate flag its own test file (net +1 tautology/skip/extended-tautology vs main). Reworded to plain prose ('a new tautology', 'a new skip marker'); test logic unchanged (24/24 pass). * fix(quality): unblock v3.8.27 release — align 3 stale tests + restore modularized settings-schema parity Release-PR full CI surfaced 3 deterministic test failures (no live product regression), all stale vs legitimate cycle changes: - settings-schema parity (#3988): the modularized updateSettingsSchema barrel (schemas/settings.ts) had diverged from the canonical settingsSchemas.ts (45 vs 85 fields — 40 dropped + 6 extra), a lossy-modularization dead-code copy. Re-export from the canonical source so the barrel can never diverge again (runtime already uses canonical). Parity test now passes. - api-manager permissions modal: #4034 added a 4th self-service switch (per-key usage allowance); a11y invariant (every switch type="button") still holds. Updated the static count 3 -> 4. - pack-artifact policy: dist/http-method-guard.cjs became a required runtime path; added it to the test's expected missing-paths list. Also documents the gate gap for Fase 9 (QUALITY_GATE_PLAYBOOK Parte 6): G1 run the deterministic unit layer + test-masking on PR->release (not just PR->main), G2 a modularization-parity gate (would have caught the #3988 drop at its PR), G3 flake quarantine. Env flakes (LiveWS startup timeout, integration server-startup cascade) are pre-existing/CI-env, triaged separately. --------- Co-authored-by: Randi <55005611+rdself@users.noreply.github.com> Co-authored-by: Veier04 <118300867+Veier04@users.noreply.github.com> Co-authored-by: Felipe Sartori <felipesartori.ti@gmail.com> Co-authored-by: WormAlien <164898390+WormAlien@users.noreply.github.com> Co-authored-by: thezukiru <121331256+thezukiru@users.noreply.github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: NOXX - Commiter <artur1992123@mail.ru> Co-authored-by: Paijo <14921983+oyi77@users.noreply.github.com> Co-authored-by: Demiurge The Single <megamen932@gmail.com> Co-authored-by: Witroch4 <witalo_rocha@hotmail.com>
715 lines
22 KiB
TypeScript
715 lines
22 KiB
TypeScript
// @ts-nocheck
|
|
import {
|
|
BedrockRuntimeClient,
|
|
ConverseCommand,
|
|
ConverseStreamCommand,
|
|
} from "@aws-sdk/client-bedrock-runtime";
|
|
import { randomUUID } from "node:crypto";
|
|
|
|
import { BaseExecutor } from "./base.ts";
|
|
import { PROVIDERS } from "../config/constants.ts";
|
|
import { buildBedrockNativeConverseUrl, resolveBedrockRegion } from "../config/bedrock.ts";
|
|
import * as prl from "../utils/providerRequestLogging.ts";
|
|
|
|
const encoder = new TextEncoder();
|
|
|
|
function asRecord(value) {
|
|
return value && typeof value === "object" && !Array.isArray(value) ? value : {};
|
|
}
|
|
|
|
function getCustomUserAgent(providerSpecificData) {
|
|
const value = asRecord(providerSpecificData).customUserAgent;
|
|
return typeof value === "string" && value.trim() ? value.trim() : null;
|
|
}
|
|
|
|
function toText(value) {
|
|
if (typeof value === "string") return value;
|
|
if (value === null || value === undefined) return "";
|
|
try {
|
|
return JSON.stringify(value);
|
|
} catch {
|
|
return String(value);
|
|
}
|
|
}
|
|
|
|
function stripDataUrlPrefix(value) {
|
|
if (typeof value !== "string") return null;
|
|
const match = value.match(/^data:image\/(png|jpeg|jpg|gif|webp);base64,(.+)$/i);
|
|
if (!match) return null;
|
|
const format = match[1].toLowerCase() === "jpg" ? "jpeg" : match[1].toLowerCase();
|
|
return { format, data: match[2] };
|
|
}
|
|
|
|
function decodeBase64(value) {
|
|
return Uint8Array.from(Buffer.from(value, "base64"));
|
|
}
|
|
|
|
function normalizeRole(role) {
|
|
if (role === "assistant") return "assistant";
|
|
return "user";
|
|
}
|
|
|
|
function normalizeToolUseId(value) {
|
|
return typeof value === "string" && value.trim() ? value.trim() : null;
|
|
}
|
|
|
|
function textBlocksFromContent(content, options = {}) {
|
|
if (typeof content === "string") return content.trim() ? [{ text: content }] : [];
|
|
if (!Array.isArray(content)) return [];
|
|
|
|
const blocks = [];
|
|
for (const part of content) {
|
|
if (typeof part === "string") {
|
|
if (part.trim()) blocks.push({ text: part });
|
|
continue;
|
|
}
|
|
const p = asRecord(part);
|
|
const type = typeof p.type === "string" ? p.type : "";
|
|
if ((type === "text" || type === "input_text") && typeof p.text === "string") {
|
|
if (p.text.trim()) blocks.push({ text: p.text });
|
|
continue;
|
|
}
|
|
if (type === "image_url" || type === "input_image") {
|
|
const url = typeof p.image_url === "string" ? p.image_url : p.image_url?.url || p.image_url;
|
|
const image = stripDataUrlPrefix(url);
|
|
if (image) {
|
|
blocks.push({
|
|
image: { format: image.format, source: { bytes: decodeBase64(image.data) } },
|
|
});
|
|
}
|
|
continue;
|
|
}
|
|
if (type === "tool_use" && typeof p.id === "string" && typeof p.name === "string") {
|
|
const rawId = normalizeToolUseId(p.id);
|
|
if (rawId && options.skipToolUseIds?.has(rawId)) continue;
|
|
if (rawId && !options.answeredToolUseIds?.has(rawId)) continue;
|
|
blocks.push({
|
|
toolUse: {
|
|
toolUseId: rawId || `toolu_${randomUUID()}`,
|
|
name: p.name,
|
|
input: asRecord(p.input),
|
|
},
|
|
});
|
|
continue;
|
|
}
|
|
if (type === "tool_result" && typeof p.tool_use_id === "string") {
|
|
blocks.push({
|
|
toolResult: {
|
|
toolUseId: p.tool_use_id,
|
|
content: [{ text: toText(p.content) }],
|
|
status: p.is_error ? "error" : "success",
|
|
},
|
|
});
|
|
}
|
|
}
|
|
|
|
return blocks;
|
|
}
|
|
|
|
function systemBlocksFromOpenAI(messages) {
|
|
const blocks = [];
|
|
for (const message of messages) {
|
|
const role = message?.role;
|
|
if (role !== "system" && role !== "developer") continue;
|
|
const text = textBlocksFromContent(message.content)
|
|
.map((block) => (typeof block.text === "string" ? block.text : ""))
|
|
.filter(Boolean)
|
|
.join("\n");
|
|
if (text.trim()) blocks.push({ text });
|
|
}
|
|
return blocks;
|
|
}
|
|
|
|
function toolResultContentFromMessage(message) {
|
|
const content = message.content;
|
|
if (typeof content === "string") return [{ text: content || " " }];
|
|
if (Array.isArray(content)) {
|
|
const result = [];
|
|
for (const part of content) {
|
|
if (typeof part === "string") {
|
|
result.push({ text: part || " " });
|
|
continue;
|
|
}
|
|
const p = asRecord(part);
|
|
if (typeof p.text === "string") result.push({ text: p.text || " " });
|
|
else if (p.type === "json" && p.json !== undefined) result.push({ json: p.json });
|
|
else if (p.content !== undefined) result.push({ text: toText(p.content) });
|
|
}
|
|
return result.length > 0 ? result : [{ text: " " }];
|
|
}
|
|
return [{ text: toText(content) || " " }];
|
|
}
|
|
|
|
function collectAnsweredToolUseIds(messages) {
|
|
const answered = new Set();
|
|
for (const message of messages) {
|
|
if (!message || typeof message !== "object") continue;
|
|
if (message.role === "tool") {
|
|
const id = normalizeToolUseId(message.tool_call_id);
|
|
if (id) answered.add(id);
|
|
}
|
|
if (!Array.isArray(message.content)) continue;
|
|
for (const part of message.content) {
|
|
const p = asRecord(part);
|
|
if (p.type !== "tool_result") continue;
|
|
const id = normalizeToolUseId(p.tool_use_id);
|
|
if (id) answered.add(id);
|
|
}
|
|
}
|
|
return answered;
|
|
}
|
|
|
|
function getToolUseIdFromBlock(block) {
|
|
return normalizeToolUseId(block?.toolUse?.toolUseId);
|
|
}
|
|
|
|
function getToolResultIdFromBlock(block) {
|
|
return normalizeToolUseId(block?.toolResult?.toolUseId);
|
|
}
|
|
|
|
function isToolResultOnlyMessage(message) {
|
|
return (
|
|
message?.role === "user" &&
|
|
Array.isArray(message.content) &&
|
|
message.content.length > 0 &&
|
|
message.content.every((block) => Boolean(getToolResultIdFromBlock(block)))
|
|
);
|
|
}
|
|
|
|
function mergeConsecutiveToolResultMessages(messages) {
|
|
const merged = [];
|
|
for (const message of messages) {
|
|
const previous = merged[merged.length - 1];
|
|
if (isToolResultOnlyMessage(previous) && isToolResultOnlyMessage(message)) {
|
|
previous.content.push(...message.content);
|
|
continue;
|
|
}
|
|
merged.push(message);
|
|
}
|
|
return merged;
|
|
}
|
|
|
|
function ensureNonEmptyContent(message) {
|
|
if (!Array.isArray(message.content) || message.content.length === 0) {
|
|
message.content = [{ text: " " }];
|
|
}
|
|
}
|
|
|
|
function sanitizeBedrockToolPairs(messages) {
|
|
const normalized = mergeConsecutiveToolResultMessages(messages);
|
|
const validResultCounts = new Map();
|
|
|
|
for (let i = 0; i < normalized.length; i++) {
|
|
const message = normalized[i];
|
|
if (message?.role !== "assistant" || !Array.isArray(message.content)) continue;
|
|
|
|
const nextMessage = normalized[i + 1];
|
|
const nextResultIds = new Set(
|
|
nextMessage?.role === "user" && Array.isArray(nextMessage.content)
|
|
? nextMessage.content.map(getToolResultIdFromBlock).filter(Boolean)
|
|
: []
|
|
);
|
|
|
|
const toolUseIds = message.content.map(getToolUseIdFromBlock).filter(Boolean);
|
|
if (toolUseIds.length === 0) continue;
|
|
|
|
const allowedIds = new Set(toolUseIds.filter((id) => nextResultIds.has(id)));
|
|
message.content = message.content.filter((block) => {
|
|
const toolUseId = getToolUseIdFromBlock(block);
|
|
return !toolUseId || allowedIds.has(toolUseId);
|
|
});
|
|
ensureNonEmptyContent(message);
|
|
for (const id of allowedIds) {
|
|
validResultCounts.set(id, (validResultCounts.get(id) || 0) + 1);
|
|
}
|
|
}
|
|
|
|
for (const message of normalized) {
|
|
if (message?.role !== "user" || !Array.isArray(message.content)) continue;
|
|
message.content = message.content.filter((block) => {
|
|
const resultId = getToolResultIdFromBlock(block);
|
|
if (!resultId) return true;
|
|
const remaining = validResultCounts.get(resultId) || 0;
|
|
if (remaining <= 0) return false;
|
|
validResultCounts.set(resultId, remaining - 1);
|
|
return true;
|
|
});
|
|
ensureNonEmptyContent(message);
|
|
}
|
|
|
|
return normalized;
|
|
}
|
|
|
|
function messagesFromOpenAI(messages) {
|
|
const converted = [];
|
|
const pendingToolUseIds = new Set();
|
|
const answeredToolUseIds = collectAnsweredToolUseIds(messages);
|
|
|
|
for (const message of messages) {
|
|
if (!message || typeof message !== "object") continue;
|
|
if (message.role === "system" || message.role === "developer") continue;
|
|
|
|
if (message.role === "tool") {
|
|
const toolUseId = normalizeToolUseId(message.tool_call_id) || `toolu_${randomUUID()}`;
|
|
pendingToolUseIds.delete(toolUseId);
|
|
answeredToolUseIds.add(toolUseId);
|
|
converted.push({
|
|
role: "user",
|
|
content: [
|
|
{
|
|
toolResult: {
|
|
toolUseId,
|
|
content: toolResultContentFromMessage(message),
|
|
status: "success",
|
|
},
|
|
},
|
|
],
|
|
});
|
|
continue;
|
|
}
|
|
|
|
const toolCalls = Array.isArray(message.tool_calls) ? message.tool_calls : [];
|
|
const toolCallIds = new Set(
|
|
toolCalls.map((call) => normalizeToolUseId(call?.id)).filter(Boolean)
|
|
);
|
|
const content = textBlocksFromContent(message.content, {
|
|
skipToolUseIds: toolCallIds,
|
|
answeredToolUseIds,
|
|
});
|
|
for (const call of toolCalls) {
|
|
const fn = asRecord(call.function);
|
|
const rawArgs = typeof fn.arguments === "string" ? fn.arguments : "{}";
|
|
let input = {};
|
|
try {
|
|
input = rawArgs.trim() ? JSON.parse(rawArgs) : {};
|
|
} catch {
|
|
input = { arguments: rawArgs };
|
|
}
|
|
const toolUseId = normalizeToolUseId(call.id) || `toolu_${randomUUID()}`;
|
|
if (pendingToolUseIds.has(toolUseId)) continue;
|
|
if (!answeredToolUseIds.has(toolUseId)) continue;
|
|
pendingToolUseIds.add(toolUseId);
|
|
content.push({
|
|
toolUse: {
|
|
toolUseId,
|
|
name: typeof fn.name === "string" && fn.name ? fn.name : "unknown_tool",
|
|
input,
|
|
},
|
|
});
|
|
}
|
|
|
|
if (content.length === 0) {
|
|
content.push({ text: " " });
|
|
}
|
|
|
|
converted.push({ role: normalizeRole(message.role), content });
|
|
}
|
|
|
|
if (converted.length === 0) {
|
|
converted.push({ role: "user", content: [{ text: " " }] });
|
|
}
|
|
|
|
return sanitizeBedrockToolPairs(converted);
|
|
}
|
|
|
|
function toolConfigFromOpenAI(tools, toolChoice) {
|
|
if (!Array.isArray(tools) || tools.length === 0) return undefined;
|
|
const bedrockTools = [];
|
|
for (const tool of tools) {
|
|
const t = asRecord(tool);
|
|
const fn = t.type === "function" ? asRecord(t.function) : t;
|
|
const name = typeof fn.name === "string" ? fn.name.trim() : "";
|
|
if (!name) continue;
|
|
bedrockTools.push({
|
|
toolSpec: {
|
|
name,
|
|
description: typeof fn.description === "string" ? fn.description : undefined,
|
|
inputSchema: { json: asRecord(fn.parameters) },
|
|
},
|
|
});
|
|
}
|
|
if (bedrockTools.length === 0) return undefined;
|
|
|
|
const config = { tools: bedrockTools };
|
|
if (toolChoice === "required") config.toolChoice = { any: {} };
|
|
else if (toolChoice === "auto") config.toolChoice = { auto: {} };
|
|
else if (toolChoice && typeof toolChoice === "object") {
|
|
const fn = asRecord(toolChoice.function);
|
|
const name = typeof fn.name === "string" ? fn.name : "";
|
|
if (name) config.toolChoice = { tool: { name } };
|
|
}
|
|
return config;
|
|
}
|
|
|
|
export function openAIToBedrockConverse(model, body) {
|
|
const request = asRecord(body);
|
|
const messages = Array.isArray(request.messages) ? request.messages : [];
|
|
const inferenceConfig = {};
|
|
|
|
const maxTokens = request.max_tokens ?? request.max_completion_tokens;
|
|
if (typeof maxTokens === "number") inferenceConfig.maxTokens = Math.max(1, Math.floor(maxTokens));
|
|
if (typeof request.temperature === "number") inferenceConfig.temperature = request.temperature;
|
|
if (typeof request.top_p === "number") inferenceConfig.topP = request.top_p;
|
|
if (Array.isArray(request.stop)) inferenceConfig.stopSequences = request.stop.filter(Boolean);
|
|
else if (typeof request.stop === "string" && request.stop)
|
|
inferenceConfig.stopSequences = [request.stop];
|
|
|
|
const payload = {
|
|
modelId: model,
|
|
messages: messagesFromOpenAI(messages),
|
|
};
|
|
|
|
const system = systemBlocksFromOpenAI(messages);
|
|
if (system.length > 0) payload.system = system;
|
|
if (Object.keys(inferenceConfig).length > 0) payload.inferenceConfig = inferenceConfig;
|
|
|
|
const toolConfig = toolConfigFromOpenAI(request.tools, request.tool_choice);
|
|
if (toolConfig) payload.toolConfig = toolConfig;
|
|
|
|
return payload;
|
|
}
|
|
|
|
function convertStopReason(reason) {
|
|
switch (reason) {
|
|
case "tool_use":
|
|
return "tool_calls";
|
|
case "max_tokens":
|
|
return "length";
|
|
case "stop_sequence":
|
|
case "end_turn":
|
|
default:
|
|
return "stop";
|
|
}
|
|
}
|
|
|
|
function usageFromBedrock(usage) {
|
|
const input = Number(usage?.inputTokens || 0);
|
|
const output = Number(usage?.outputTokens || 0);
|
|
return {
|
|
prompt_tokens: input,
|
|
completion_tokens: output,
|
|
total_tokens: Number(usage?.totalTokens || input + output),
|
|
};
|
|
}
|
|
|
|
function contentBlocksToOpenAIMessage(blocks) {
|
|
const text = [];
|
|
const reasoning = [];
|
|
const toolCalls = [];
|
|
for (const block of Array.isArray(blocks) ? blocks : []) {
|
|
if (typeof block?.text === "string") text.push(block.text);
|
|
if (typeof block?.reasoningContent?.reasoningText?.text === "string") {
|
|
reasoning.push(block.reasoningContent.reasoningText.text);
|
|
}
|
|
if (block?.toolUse) {
|
|
toolCalls.push({
|
|
id: block.toolUse.toolUseId,
|
|
type: "function",
|
|
function: {
|
|
name: block.toolUse.name,
|
|
arguments: JSON.stringify(block.toolUse.input || {}),
|
|
},
|
|
});
|
|
}
|
|
}
|
|
|
|
const message = { role: "assistant", content: text.join("") };
|
|
if (reasoning.length > 0) message.reasoning_content = reasoning.join("");
|
|
if (toolCalls.length > 0) {
|
|
message.content = message.content || null;
|
|
message.tool_calls = toolCalls;
|
|
}
|
|
return message;
|
|
}
|
|
|
|
function openAICompletionFromConverse(output, model) {
|
|
const message = contentBlocksToOpenAIMessage(output?.output?.message?.content || []);
|
|
return {
|
|
id: `chatcmpl-bedrock-${randomUUID()}`,
|
|
object: "chat.completion",
|
|
created: Math.floor(Date.now() / 1000),
|
|
model,
|
|
choices: [
|
|
{
|
|
index: 0,
|
|
message,
|
|
finish_reason: convertStopReason(output?.stopReason),
|
|
},
|
|
],
|
|
usage: usageFromBedrock(output?.usage),
|
|
};
|
|
}
|
|
|
|
function sse(data) {
|
|
return encoder.encode(`data: ${JSON.stringify(data)}\n\n`);
|
|
}
|
|
|
|
function done() {
|
|
return encoder.encode("data: [DONE]\n\n");
|
|
}
|
|
|
|
function openAIChunk(model, delta, finishReason = null, usage = undefined) {
|
|
const chunk = {
|
|
id: `chatcmpl-bedrock-${model}`,
|
|
object: "chat.completion.chunk",
|
|
created: Math.floor(Date.now() / 1000),
|
|
model,
|
|
choices: [{ index: 0, delta, finish_reason: finishReason }],
|
|
};
|
|
if (usage) chunk.usage = usage;
|
|
return chunk;
|
|
}
|
|
|
|
function statusFromError(error) {
|
|
const status = Number(error?.$metadata?.httpStatusCode || error?.statusCode || error?.status);
|
|
return Number.isInteger(status) && status >= 400 && status <= 599 ? status : 502;
|
|
}
|
|
|
|
function errorBody(error, fallback = "Bedrock request failed") {
|
|
const status = statusFromError(error);
|
|
const code = typeof error?.name === "string" ? error.name : `HTTP_${status}`;
|
|
const message = typeof error?.message === "string" && error.message ? error.message : fallback;
|
|
return {
|
|
error: {
|
|
message,
|
|
type:
|
|
status === 429
|
|
? "rate_limit_error"
|
|
: status === 401 || status === 403
|
|
? "auth_error"
|
|
: "upstream_error",
|
|
code,
|
|
status,
|
|
},
|
|
};
|
|
}
|
|
|
|
function streamExceptionPayload(event) {
|
|
const candidates = [
|
|
event?.throttlingException,
|
|
event?.validationException,
|
|
event?.modelStreamErrorException,
|
|
event?.serviceUnavailableException,
|
|
event?.internalServerException,
|
|
].filter(Boolean);
|
|
return candidates[0] || null;
|
|
}
|
|
|
|
function statusFromStreamException(exception) {
|
|
const name = String(exception?.name || exception?.code || "");
|
|
if (name.includes("Throttling")) return 429;
|
|
if (name.includes("Validation")) return 400;
|
|
if (name.includes("ServiceUnavailable")) return 503;
|
|
if (name.includes("InternalServer")) return 500;
|
|
return 502;
|
|
}
|
|
|
|
function createOpenAIStreamFromBedrock(stream, model) {
|
|
const blockToolIndexes = new Map();
|
|
let nextToolIndex = 0;
|
|
let finishReason = "stop";
|
|
let finalUsage = null;
|
|
|
|
return new ReadableStream({
|
|
async start(controller) {
|
|
try {
|
|
controller.enqueue(sse(openAIChunk(model, { role: "assistant" })));
|
|
for await (const event of stream || []) {
|
|
const exception = streamExceptionPayload(event);
|
|
if (exception) {
|
|
const status = statusFromStreamException(exception);
|
|
controller.enqueue(
|
|
sse({
|
|
error: {
|
|
message: exception.message || "Bedrock stream failed",
|
|
type: status === 429 ? "rate_limit_error" : "upstream_error",
|
|
code: exception.name || "bedrock_stream_error",
|
|
status,
|
|
},
|
|
})
|
|
);
|
|
break;
|
|
}
|
|
|
|
if (event.contentBlockStart?.start?.toolUse) {
|
|
const tool = event.contentBlockStart.start.toolUse;
|
|
const index = nextToolIndex++;
|
|
blockToolIndexes.set(event.contentBlockStart.contentBlockIndex, index);
|
|
controller.enqueue(
|
|
sse(
|
|
openAIChunk(model, {
|
|
tool_calls: [
|
|
{
|
|
index,
|
|
id: tool.toolUseId,
|
|
type: "function",
|
|
function: { name: tool.name, arguments: "" },
|
|
},
|
|
],
|
|
})
|
|
)
|
|
);
|
|
continue;
|
|
}
|
|
|
|
if (event.contentBlockDelta?.delta) {
|
|
const delta = event.contentBlockDelta.delta;
|
|
if (typeof delta.text === "string" && delta.text.length > 0) {
|
|
controller.enqueue(sse(openAIChunk(model, { content: delta.text })));
|
|
}
|
|
if (typeof delta.reasoningContent?.text === "string" && delta.reasoningContent.text) {
|
|
controller.enqueue(
|
|
sse(openAIChunk(model, { reasoning_content: delta.reasoningContent.text }))
|
|
);
|
|
}
|
|
if (typeof delta.toolUse?.input === "string") {
|
|
const index = blockToolIndexes.get(event.contentBlockDelta.contentBlockIndex) ?? 0;
|
|
controller.enqueue(
|
|
sse(
|
|
openAIChunk(model, {
|
|
tool_calls: [{ index, function: { arguments: delta.toolUse.input } }],
|
|
})
|
|
)
|
|
);
|
|
}
|
|
continue;
|
|
}
|
|
|
|
if (event.messageStop?.stopReason) {
|
|
finishReason = convertStopReason(event.messageStop.stopReason);
|
|
continue;
|
|
}
|
|
|
|
if (event.metadata?.usage) {
|
|
finalUsage = usageFromBedrock(event.metadata.usage);
|
|
}
|
|
}
|
|
|
|
controller.enqueue(sse(openAIChunk(model, {}, finishReason, finalUsage || undefined)));
|
|
controller.enqueue(done());
|
|
controller.close();
|
|
} catch (error) {
|
|
const body = errorBody(error);
|
|
controller.enqueue(sse(body));
|
|
controller.enqueue(done());
|
|
controller.close();
|
|
}
|
|
},
|
|
});
|
|
}
|
|
|
|
export class BedrockExecutor extends BaseExecutor {
|
|
constructor(clientFactory = null) {
|
|
super("bedrock", PROVIDERS.bedrock || { format: "openai" });
|
|
this.clientFactory = clientFactory;
|
|
}
|
|
|
|
buildUrl(model, stream, _urlIndex = 0, credentials = null) {
|
|
return buildBedrockNativeConverseUrl(
|
|
resolveBedrockRegion(credentials?.providerSpecificData),
|
|
model,
|
|
stream
|
|
);
|
|
}
|
|
|
|
buildHeaders(credentials) {
|
|
return {
|
|
"Content-Type": "application/json",
|
|
Authorization: credentials?.apiKey ? "Bearer ***" : "",
|
|
};
|
|
}
|
|
|
|
createClient(credentials) {
|
|
if (this.clientFactory) return this.clientFactory(credentials);
|
|
const region = resolveBedrockRegion(credentials?.providerSpecificData);
|
|
const customUserAgent = getCustomUserAgent(credentials?.providerSpecificData);
|
|
return new BedrockRuntimeClient({
|
|
region,
|
|
token: { token: credentials.apiKey },
|
|
authSchemePreference: ["httpBearerAuth"],
|
|
maxAttempts: 1,
|
|
...(customUserAgent ? { customUserAgent } : {}),
|
|
});
|
|
}
|
|
|
|
async execute({ model, body, stream, credentials, signal, log }) {
|
|
const url = this.buildUrl(model, stream, 0, credentials);
|
|
const headers = this.buildHeaders(credentials);
|
|
|
|
if (!credentials?.apiKey) {
|
|
return {
|
|
response: new Response(
|
|
JSON.stringify(
|
|
errorBody({
|
|
name: "MissingCredentials",
|
|
message: "Missing Bedrock API key",
|
|
$metadata: { httpStatusCode: 401 },
|
|
})
|
|
),
|
|
{
|
|
status: 401,
|
|
headers: { "Content-Type": "application/json" },
|
|
}
|
|
),
|
|
url,
|
|
headers,
|
|
transformedBody: null,
|
|
};
|
|
}
|
|
|
|
const cleanedBody = this.transformRequest(model, body, stream, credentials);
|
|
const transformedBody = openAIToBedrockConverse(model, cleanedBody);
|
|
|
|
try {
|
|
const client = this.createClient(credentials);
|
|
await prl.captureCurrentProviderRequest(
|
|
url,
|
|
headers,
|
|
transformedBody,
|
|
JSON.stringify(transformedBody),
|
|
log
|
|
);
|
|
if (stream) {
|
|
const output = await client.send(new ConverseStreamCommand(transformedBody), {
|
|
abortSignal: signal || undefined,
|
|
});
|
|
return {
|
|
response: new Response(createOpenAIStreamFromBedrock(output.stream, model), {
|
|
status: 200,
|
|
headers: { "Content-Type": "text/event-stream" },
|
|
}),
|
|
url,
|
|
headers,
|
|
transformedBody,
|
|
};
|
|
}
|
|
|
|
const output = await client.send(new ConverseCommand(transformedBody), {
|
|
abortSignal: signal || undefined,
|
|
});
|
|
return {
|
|
response: new Response(JSON.stringify(openAICompletionFromConverse(output, model)), {
|
|
status: 200,
|
|
headers: { "Content-Type": "application/json" },
|
|
}),
|
|
url,
|
|
headers,
|
|
transformedBody,
|
|
};
|
|
} catch (error) {
|
|
const status = statusFromError(error);
|
|
return {
|
|
response: new Response(JSON.stringify(errorBody(error)), {
|
|
status,
|
|
headers: { "Content-Type": "application/json" },
|
|
}),
|
|
url,
|
|
headers,
|
|
transformedBody,
|
|
};
|
|
}
|
|
}
|
|
}
|
|
|
|
export default BedrockExecutor;
|