mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-01 21:02:12 +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>
1013 lines
34 KiB
TypeScript
1013 lines
34 KiB
TypeScript
/**
|
|
* PerplexityWebExecutor — Perplexity Web Session Provider
|
|
*
|
|
* Routes requests through Perplexity's internal SSE API using a Pro/Max
|
|
* subscription session cookie or JWT, translating between OpenAI chat
|
|
* completions format and Perplexity's internal protocol.
|
|
*/
|
|
|
|
import { BaseExecutor, type ExecuteInput } from "./base.ts";
|
|
import {
|
|
tlsFetchPerplexity,
|
|
isCloudflareChallenge,
|
|
TlsClientUnavailableError,
|
|
type TlsFetchResult,
|
|
} from "../services/perplexityTlsClient.ts";
|
|
import { prepareToolMessages, buildToolAwareResult } from "../translator/webTools.ts";
|
|
import { sanitizeErrorMessage } from "../utils/error.ts";
|
|
|
|
const PPLX_SSE_ENDPOINT = "https://www.perplexity.ai/rest/sse/perplexity_ask";
|
|
// Perplexity's current request schema version (sent in params.version). Perplexity rejects
|
|
// stale versions with HTTP 400 — keep this in lockstep with the website's payload.
|
|
const PPLX_API_VERSION = "2.18";
|
|
// Block use-cases the current web client advertises. The schematized API (use_schematized_api)
|
|
// validates the request shape, so this must be present (mirrors the browser request body).
|
|
const PPLX_SUPPORTED_BLOCK_USE_CASES = [
|
|
"answer_modes",
|
|
"media_items",
|
|
"knowledge_cards",
|
|
"inline_entity_cards",
|
|
"place_widgets",
|
|
"finance_widgets",
|
|
"sports_widgets",
|
|
"news_widgets",
|
|
"shopping_widgets",
|
|
"jobs_widgets",
|
|
"search_result_widgets",
|
|
"inline_images",
|
|
"inline_assets",
|
|
"placeholder_cards",
|
|
"diff_blocks",
|
|
"inline_knowledge_cards",
|
|
"entity_group_v2",
|
|
"refinement_filters",
|
|
"canvas_mode",
|
|
"maps_preview",
|
|
"answer_tabs",
|
|
"price_comparison_widgets",
|
|
"preserve_latex",
|
|
"generic_onboarding_widgets",
|
|
"in_context_suggestions",
|
|
"pending_followups",
|
|
"inline_claims",
|
|
"unified_assets",
|
|
"workflow_steps",
|
|
"background_agents",
|
|
];
|
|
// Firefox 148 — must match the `firefox_148` TLS profile used by perplexityTlsClient.
|
|
// A mismatched UA vs TLS fingerprint is itself a Cloudflare bot signal (issue #2459).
|
|
const PPLX_USER_AGENT =
|
|
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:148.0) Gecko/20100101 Firefox/148.0";
|
|
|
|
const MODEL_MAP: Record<string, [string, string]> = {
|
|
"pplx-auto": ["concise", "pplx_pro"],
|
|
"pplx-sonar": ["copilot", "experimental"],
|
|
"pplx-gpt": ["copilot", "gpt54"],
|
|
"pplx-gemini": ["copilot", "gemini31pro_high"],
|
|
"pplx-sonnet": ["copilot", "claude46sonnet"],
|
|
"pplx-opus": ["copilot", "claude46opus"],
|
|
"pplx-nemotron": ["copilot", "nv_nemotron_3_super"],
|
|
};
|
|
|
|
const THINKING_MAP: Record<string, string> = {
|
|
"pplx-gpt": "gpt54_thinking",
|
|
"pplx-sonnet": "claude46sonnetthinking",
|
|
"pplx-opus": "claude46opusthinking",
|
|
};
|
|
|
|
const CITATION_RE = /\[\d+\]/g;
|
|
const GROK_TAG_RE = /<grok:[^>]*>.*?<\/grok:[^>]*>/gs;
|
|
const GROK_SELF_RE = /<grok:[^>]*\/>/g;
|
|
const XML_DECL_RE = /<[?]xml[^?]*[?]>/g;
|
|
const RESPONSE_TAG_RE = /<\/?response\b[^>]*>/gi;
|
|
const MULTI_SPACE = / {2,}/g;
|
|
const MULTI_NL = /\n{3,}/g;
|
|
|
|
// ─── Session continuity ─────────────────────────────────────────────────────
|
|
|
|
const SESSION_MAX_AGE_MS = 3600_000;
|
|
const SESSION_MAX_ENTRIES = 200;
|
|
|
|
interface SessionEntry {
|
|
backendUuid: string;
|
|
ts: number;
|
|
}
|
|
|
|
const sessionCache = new Map<string, SessionEntry>();
|
|
|
|
function sessionKey(history: Array<{ role: string; content: string }>): string {
|
|
const parts = history.map((h) => `${h.role}:${h.content}`).join("\n");
|
|
let hash = 0x811c9dc5;
|
|
for (let i = 0; i < parts.length; i++) {
|
|
hash ^= parts.charCodeAt(i);
|
|
hash = (hash * 0x01000193) >>> 0;
|
|
}
|
|
return hash.toString(16).padStart(8, "0");
|
|
}
|
|
|
|
function sessionLookup(history: Array<{ role: string; content: string }>): string | null {
|
|
if (history.length === 0) return null;
|
|
const key = sessionKey(history);
|
|
const entry = sessionCache.get(key);
|
|
if (!entry) return null;
|
|
if (Date.now() - entry.ts > SESSION_MAX_AGE_MS) {
|
|
sessionCache.delete(key);
|
|
return null;
|
|
}
|
|
return entry.backendUuid;
|
|
}
|
|
|
|
function sessionStore(
|
|
history: Array<{ role: string; content: string }>,
|
|
currentMsg: string,
|
|
responseText: string,
|
|
backendUuid: string | null
|
|
): void {
|
|
if (!backendUuid) return;
|
|
const full = [
|
|
...history,
|
|
{ role: "user", content: currentMsg },
|
|
{ role: "assistant", content: responseText },
|
|
];
|
|
const key = sessionKey(full);
|
|
sessionCache.set(key, { backendUuid, ts: Date.now() });
|
|
if (sessionCache.size > SESSION_MAX_ENTRIES) {
|
|
let oldestKey: string | null = null;
|
|
let oldestTs = Infinity;
|
|
for (const [k, v] of sessionCache) {
|
|
if (v.ts < oldestTs) {
|
|
oldestTs = v.ts;
|
|
oldestKey = k;
|
|
}
|
|
}
|
|
if (oldestKey) sessionCache.delete(oldestKey);
|
|
}
|
|
}
|
|
|
|
// ─── Helpers ────────────────────────────────────────────────────────────────
|
|
|
|
function cleanResponse(text: string, strip = true): string {
|
|
let t = text;
|
|
t = t.replace(XML_DECL_RE, "");
|
|
t = t.replace(CITATION_RE, "");
|
|
t = t.replace(GROK_TAG_RE, "");
|
|
t = t.replace(GROK_SELF_RE, "");
|
|
t = t.replace(RESPONSE_TAG_RE, "");
|
|
if (strip) {
|
|
t = t.replace(MULTI_SPACE, " ");
|
|
t = t.replace(MULTI_NL, "\n\n");
|
|
t = t.trim();
|
|
}
|
|
return t;
|
|
}
|
|
|
|
// ─── SSE types ──────────────────────────────────────────────────────────────
|
|
|
|
interface PplxDiffPatch {
|
|
op?: string;
|
|
path?: string;
|
|
value?: unknown;
|
|
}
|
|
|
|
interface PplxBlock {
|
|
intended_usage?: string;
|
|
markdown_block?: {
|
|
answer?: string;
|
|
chunks?: string[];
|
|
progress?: string;
|
|
chunk_starting_offset?: number;
|
|
};
|
|
// Schematized API (use_schematized_api) streams block updates as RFC-6902
|
|
// JSON-patch diffs against a target field (e.g. markdown_block) instead of
|
|
// sending the whole block each frame. `field` names the block being patched.
|
|
diff_block?: {
|
|
field?: string;
|
|
patches?: PplxDiffPatch[];
|
|
};
|
|
web_result_block?: {
|
|
web_results?: Array<{ url?: string; name?: string; snippet?: string }>;
|
|
};
|
|
plan_block?: {
|
|
steps?: Array<{
|
|
step_type?: string;
|
|
search_web_content?: { queries?: Array<{ query?: string }> };
|
|
read_results_content?: { urls?: string[] };
|
|
}>;
|
|
goals?: Array<{ description?: string }>;
|
|
};
|
|
}
|
|
|
|
interface PplxStreamEvent {
|
|
status?: string;
|
|
final?: boolean;
|
|
text?: string;
|
|
blocks?: PplxBlock[];
|
|
backend_uuid?: string;
|
|
web_results?: Array<{ url?: string; name?: string }>;
|
|
error_code?: string;
|
|
error_message?: string;
|
|
display_model?: string;
|
|
}
|
|
|
|
// ─── SSE parsing ────────────────────────────────────────────────────────────
|
|
|
|
async function* readPplxSseEvents(
|
|
body: ReadableStream<Uint8Array>,
|
|
signal?: AbortSignal | null
|
|
): AsyncGenerator<PplxStreamEvent> {
|
|
const reader = body.getReader();
|
|
const decoder = new TextDecoder();
|
|
let buffer = "";
|
|
let dataLines: string[] = [];
|
|
|
|
function flush(): PplxStreamEvent | null | "done" {
|
|
if (dataLines.length === 0) return null;
|
|
const payload = dataLines.join("\n");
|
|
dataLines = [];
|
|
const trimmed = payload.trim();
|
|
if (!trimmed || trimmed === "[DONE]") return "done";
|
|
try {
|
|
return JSON.parse(trimmed) as PplxStreamEvent;
|
|
} catch {
|
|
return null;
|
|
}
|
|
}
|
|
|
|
try {
|
|
while (true) {
|
|
if (signal?.aborted) return;
|
|
const { value, done } = await reader.read();
|
|
if (done) break;
|
|
buffer += decoder.decode(value, { stream: true });
|
|
|
|
while (true) {
|
|
const idx = buffer.indexOf("\n");
|
|
if (idx < 0) break;
|
|
const rawLine = buffer.slice(0, idx);
|
|
buffer = buffer.slice(idx + 1);
|
|
const line = rawLine.endsWith("\r") ? rawLine.slice(0, -1) : rawLine;
|
|
|
|
if (line === "") {
|
|
const parsed = flush();
|
|
if (parsed === "done") return;
|
|
if (parsed) yield parsed;
|
|
continue;
|
|
}
|
|
if (line.startsWith("data:")) {
|
|
dataLines.push(line.slice(5).trimStart());
|
|
}
|
|
if (line === "event: end_of_stream") {
|
|
return;
|
|
}
|
|
}
|
|
}
|
|
|
|
buffer += decoder.decode();
|
|
if (buffer.trim().startsWith("data:")) {
|
|
dataLines.push(buffer.trim().slice(5).trimStart());
|
|
}
|
|
const tail = flush();
|
|
if (tail && tail !== "done") yield tail;
|
|
} finally {
|
|
reader.releaseLock();
|
|
}
|
|
}
|
|
|
|
// ─── OpenAI → Perplexity translation ────────────────────────────────────────
|
|
|
|
interface ParsedMessages {
|
|
systemMsg: string;
|
|
history: Array<{ role: string; content: string }>;
|
|
currentMsg: string;
|
|
}
|
|
|
|
function parseOpenAIMessages(messages: Array<Record<string, unknown>>): ParsedMessages {
|
|
let systemMsg = "";
|
|
const history: Array<{ role: string; content: string }> = [];
|
|
|
|
for (const msg of messages) {
|
|
let role = String(msg.role || "user");
|
|
if (role === "developer") role = "system";
|
|
|
|
let content = "";
|
|
if (typeof msg.content === "string") {
|
|
content = msg.content;
|
|
} else if (Array.isArray(msg.content)) {
|
|
content = (msg.content as Array<Record<string, unknown>>)
|
|
.filter((c) => c.type === "text")
|
|
.map((c) => String(c.text || ""))
|
|
.join(" ");
|
|
}
|
|
if (!content.trim()) continue;
|
|
|
|
if (role === "system") {
|
|
systemMsg += content + "\n";
|
|
} else if (role === "user" || role === "assistant") {
|
|
history.push({ role, content });
|
|
}
|
|
}
|
|
|
|
let currentMsg = "";
|
|
if (history.length > 0 && history[history.length - 1].role === "user") {
|
|
currentMsg = history.pop()!.content;
|
|
}
|
|
|
|
return { systemMsg, history, currentMsg };
|
|
}
|
|
|
|
function buildPplxRequestBody(
|
|
query: string,
|
|
dslQuery: string,
|
|
mode: string,
|
|
modelPref: string,
|
|
followUpUuid: string | null,
|
|
requestId: string
|
|
): Record<string, unknown> {
|
|
const tz = typeof Intl !== "undefined" ? Intl.DateTimeFormat().resolvedOptions().timeZone : "UTC";
|
|
|
|
// Mirrors the current www.perplexity.ai/rest/sse/perplexity_ask request body. Perplexity's
|
|
// schematized API validates this shape; an outdated version or missing required fields → HTTP 400.
|
|
const params: Record<string, unknown> = {
|
|
attachments: [],
|
|
language: "en-US",
|
|
timezone: tz,
|
|
search_focus: "internet",
|
|
sources: ["web"],
|
|
frontend_uuid: requestId,
|
|
mode,
|
|
model_preference: modelPref,
|
|
is_related_query: false,
|
|
is_sponsored: false,
|
|
frontend_context_uuid: crypto.randomUUID(),
|
|
prompt_source: "user",
|
|
query_source: "home",
|
|
is_incognito: true,
|
|
local_search_enabled: false,
|
|
use_schematized_api: true,
|
|
send_back_text_in_streaming_api: false,
|
|
supported_block_use_cases: PPLX_SUPPORTED_BLOCK_USE_CASES,
|
|
client_coordinates: null,
|
|
mentions: [],
|
|
dsl_query: dslQuery && dslQuery.trim() ? dslQuery : query,
|
|
skip_search_enabled: true,
|
|
is_nav_suggestions_disabled: false,
|
|
source: "default",
|
|
always_search_override: false,
|
|
override_no_search: false,
|
|
client_search_results_cache_key: requestId,
|
|
should_ask_for_mcp_tool_confirmation: true,
|
|
browser_agent_allow_once_from_toggle: false,
|
|
force_enable_browser_agent: false,
|
|
supported_features: ["browser_agent_permission_banner_v1.1"],
|
|
extended_context: false,
|
|
version: PPLX_API_VERSION,
|
|
rum_session_id: crypto.randomUUID(),
|
|
};
|
|
|
|
// Only present on follow-ups (matches the browser, which omits it for a fresh query).
|
|
if (followUpUuid) {
|
|
params.last_backend_uuid = followUpUuid;
|
|
}
|
|
|
|
return {
|
|
query_str: query,
|
|
params,
|
|
};
|
|
}
|
|
|
|
function buildQuery(parsed: ParsedMessages, followUpUuid: string | null): string {
|
|
if (followUpUuid) return parsed.currentMsg;
|
|
|
|
const obj: Record<string, unknown> = {};
|
|
if (parsed.systemMsg.trim()) {
|
|
obj.instructions = [
|
|
parsed.systemMsg.trim(),
|
|
"You have built-in web search. Answer questions directly using search results.",
|
|
];
|
|
}
|
|
if (parsed.history.length > 0) {
|
|
obj.history = parsed.history;
|
|
}
|
|
if (parsed.currentMsg) {
|
|
obj.query = parsed.currentMsg;
|
|
} else if (parsed.history.length === 0) {
|
|
obj.query = "";
|
|
}
|
|
const json = JSON.stringify(obj);
|
|
return json.length > 96000 ? json.slice(-96000) : json;
|
|
}
|
|
|
|
// ─── Content extraction ─────────────────────────────────────────────────────
|
|
|
|
interface ContentChunk {
|
|
delta?: string;
|
|
answer?: string;
|
|
backendUuid?: string;
|
|
thinking?: string;
|
|
error?: string;
|
|
done?: boolean;
|
|
}
|
|
|
|
// The schematized API delivers the answer text in blocks whose `intended_usage`
|
|
// is either the aggregate `ask_text` or per-segment `ask_text_<n>_markdown`
|
|
// (older builds used names merely containing "markdown"). All converge on the
|
|
// same answer, so we lock onto a single primary usage to avoid double-counting.
|
|
function isAnswerTextUsage(usage: string): boolean {
|
|
return usage === "ask_text" || /^ask_text_\d+_markdown$/.test(usage) || usage.includes("markdown");
|
|
}
|
|
|
|
// Reconstructed state for one answer-text block, built up from diff patches
|
|
// (streaming) or a materialized markdown_block (final COMPLETED frame).
|
|
interface MarkdownAccumulator {
|
|
chunks: string[];
|
|
}
|
|
|
|
// Apply a markdown_block diff_block patch set. Perplexity sends an initial
|
|
// `{op:"replace", path:"", value:{chunks:[...]}}` then incremental
|
|
// `{op:"add", path:"/chunks/<n>", value:"..."}` frames. We only need the
|
|
// chunks array; joining it yields the cumulative answer text.
|
|
function applyMarkdownDiff(acc: MarkdownAccumulator, patches: PplxDiffPatch[]): void {
|
|
for (const patch of patches) {
|
|
const path = patch.path ?? "";
|
|
if (path === "") {
|
|
const value = (patch.value ?? {}) as { chunks?: unknown };
|
|
acc.chunks = Array.isArray(value.chunks) ? value.chunks.map((c) => String(c)) : [];
|
|
continue;
|
|
}
|
|
const chunkMatch = /^\/chunks\/(\d+)$/.exec(path);
|
|
if (chunkMatch && typeof patch.value === "string") {
|
|
const idx = Number.parseInt(chunkMatch[1], 10);
|
|
acc.chunks[idx] = patch.value;
|
|
}
|
|
}
|
|
}
|
|
|
|
async function* extractContent(
|
|
eventStream: ReadableStream<Uint8Array>,
|
|
signal?: AbortSignal | null
|
|
): AsyncGenerator<ContentChunk> {
|
|
let fullAnswer = "";
|
|
let backendUuid: string | null = null;
|
|
let seenLen = 0;
|
|
const seenThinking = new Set<string>();
|
|
// Per-usage reconstructed answer-text blocks + the locked primary usage.
|
|
const mdState = new Map<string, MarkdownAccumulator>();
|
|
let primaryUsage: string | null = null;
|
|
|
|
for await (const event of readPplxSseEvents(eventStream, signal)) {
|
|
if (event.error_code || event.error_message) {
|
|
yield {
|
|
error: event.error_message || `Perplexity error: ${event.error_code}`,
|
|
done: true,
|
|
};
|
|
return;
|
|
}
|
|
|
|
if (event.backend_uuid) backendUuid = event.backend_uuid;
|
|
|
|
const blocks = event.blocks ?? [];
|
|
for (const block of blocks) {
|
|
const usage = block.intended_usage ?? "";
|
|
|
|
// Thinking: search steps
|
|
if (usage === "pro_search_steps" && block.plan_block?.steps) {
|
|
for (const step of block.plan_block.steps) {
|
|
if (step.step_type === "SEARCH_WEB") {
|
|
for (const q of step.search_web_content?.queries ?? []) {
|
|
const qr = q.query ?? "";
|
|
if (qr && !seenThinking.has(qr)) {
|
|
seenThinking.add(qr);
|
|
yield { thinking: `Searching: ${qr}`, backendUuid: backendUuid ?? undefined };
|
|
}
|
|
}
|
|
} else if (step.step_type === "READ_RESULTS") {
|
|
for (const u of (step.read_results_content?.urls ?? []).slice(0, 3)) {
|
|
if (u && !seenThinking.has(u)) {
|
|
seenThinking.add(u);
|
|
yield { thinking: `Reading: ${u}`, backendUuid: backendUuid ?? undefined };
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
// Thinking: plan goals
|
|
if (usage === "plan" && block.plan_block?.goals) {
|
|
for (const goal of block.plan_block.goals) {
|
|
const desc = goal.description ?? "";
|
|
if (desc && !seenThinking.has(desc)) {
|
|
seenThinking.add(desc);
|
|
yield { thinking: desc, backendUuid: backendUuid ?? undefined };
|
|
}
|
|
}
|
|
}
|
|
|
|
// Content: answer-text blocks (schematized diff frames OR materialized
|
|
// markdown_block on the final COMPLETED frame).
|
|
if (!isAnswerTextUsage(usage)) continue;
|
|
let acc = mdState.get(usage);
|
|
if (!acc) {
|
|
acc = { chunks: [] };
|
|
mdState.set(usage, acc);
|
|
}
|
|
|
|
if (block.diff_block && Array.isArray(block.diff_block.patches)) {
|
|
applyMarkdownDiff(acc, block.diff_block.patches);
|
|
} else if (block.markdown_block) {
|
|
const mb = block.markdown_block;
|
|
if (Array.isArray(mb.chunks) && mb.chunks.length > 0) {
|
|
acc.chunks = mb.chunks.map((c) => String(c));
|
|
} else if (typeof mb.answer === "string" && mb.answer.length > 0) {
|
|
acc.chunks = [mb.answer];
|
|
}
|
|
}
|
|
|
|
// Prefer the aggregate `ask_text` block; otherwise lock the first seen.
|
|
if (usage === "ask_text") {
|
|
primaryUsage = "ask_text";
|
|
} else if (!primaryUsage) {
|
|
primaryUsage = usage;
|
|
}
|
|
}
|
|
|
|
// Emit at most one content delta per event, from the locked primary usage.
|
|
if (primaryUsage) {
|
|
const currentAnswer = (mdState.get(primaryUsage)?.chunks ?? []).join("");
|
|
if (currentAnswer.length > seenLen) {
|
|
const delta = currentAnswer.slice(seenLen);
|
|
fullAnswer = currentAnswer;
|
|
seenLen = currentAnswer.length;
|
|
yield { delta, answer: fullAnswer, backendUuid: backendUuid ?? undefined };
|
|
}
|
|
}
|
|
|
|
// Legacy fallback: a plain non-JSON `text` field with no structured blocks.
|
|
// The schematized API's `text` field is a JSON step-blob (not user-facing),
|
|
// so only use it when there are no answer-text blocks at all.
|
|
if (!primaryUsage && blocks.length === 0 && event.text) {
|
|
const t = event.text.trim();
|
|
const looksLikeJson = t.startsWith("{") || t.startsWith("[");
|
|
if (!looksLikeJson && t.length > seenLen) {
|
|
const delta = t.slice(seenLen);
|
|
fullAnswer = t;
|
|
seenLen = t.length;
|
|
yield { delta, answer: fullAnswer, backendUuid: backendUuid ?? undefined };
|
|
}
|
|
}
|
|
|
|
// Only stop on the terminal COMPLETED frame. A `final:true` flag can appear
|
|
// on a still-PENDING frame BEFORE the COMPLETED frame that materializes the
|
|
// full markdown_block — breaking on `final` there drops the answer.
|
|
if (event.status === "COMPLETED") break;
|
|
}
|
|
|
|
yield { delta: "", answer: fullAnswer, backendUuid: backendUuid ?? undefined, done: true };
|
|
}
|
|
|
|
// ─── OpenAI SSE format ──────────────────────────────────────────────────────
|
|
|
|
function sseChunk(data: unknown): string {
|
|
return `data: ${JSON.stringify(data)}\n\n`;
|
|
}
|
|
|
|
function buildStreamingResponse(
|
|
eventStream: ReadableStream<Uint8Array>,
|
|
model: string,
|
|
cid: string,
|
|
created: number,
|
|
history: Array<{ role: string; content: string }>,
|
|
currentMsg: string,
|
|
signal?: AbortSignal | null
|
|
): ReadableStream<Uint8Array> {
|
|
const encoder = new TextEncoder();
|
|
|
|
return new ReadableStream(
|
|
{
|
|
async start(controller) {
|
|
try {
|
|
// Initial role chunk
|
|
controller.enqueue(
|
|
encoder.encode(
|
|
sseChunk({
|
|
id: cid,
|
|
object: "chat.completion.chunk",
|
|
created,
|
|
model,
|
|
system_fingerprint: null,
|
|
choices: [
|
|
{ index: 0, delta: { role: "assistant" }, finish_reason: null, logprobs: null },
|
|
],
|
|
})
|
|
)
|
|
);
|
|
|
|
let fullAnswer = "";
|
|
let respBackendUuid: string | null = null;
|
|
|
|
for await (const chunk of extractContent(eventStream, signal)) {
|
|
if (chunk.backendUuid) respBackendUuid = chunk.backendUuid;
|
|
|
|
if (chunk.error) {
|
|
controller.enqueue(
|
|
encoder.encode(
|
|
sseChunk({
|
|
id: cid,
|
|
object: "chat.completion.chunk",
|
|
created,
|
|
model,
|
|
system_fingerprint: null,
|
|
choices: [
|
|
{
|
|
index: 0,
|
|
delta: { content: `[Error: ${chunk.error}]` },
|
|
finish_reason: null,
|
|
logprobs: null,
|
|
},
|
|
],
|
|
})
|
|
)
|
|
);
|
|
break;
|
|
}
|
|
|
|
if (chunk.thinking) {
|
|
controller.enqueue(
|
|
encoder.encode(
|
|
sseChunk({
|
|
id: cid,
|
|
object: "chat.completion.chunk",
|
|
created,
|
|
model,
|
|
system_fingerprint: null,
|
|
choices: [
|
|
{
|
|
index: 0,
|
|
delta: { reasoning_content: chunk.thinking + "\n" },
|
|
finish_reason: null,
|
|
logprobs: null,
|
|
},
|
|
],
|
|
})
|
|
)
|
|
);
|
|
continue;
|
|
}
|
|
|
|
if (chunk.done) {
|
|
fullAnswer = chunk.answer || fullAnswer;
|
|
break;
|
|
}
|
|
|
|
let dt = chunk.delta || "";
|
|
if (dt) {
|
|
dt = cleanResponse(dt, false);
|
|
if (dt) {
|
|
controller.enqueue(
|
|
encoder.encode(
|
|
sseChunk({
|
|
id: cid,
|
|
object: "chat.completion.chunk",
|
|
created,
|
|
model,
|
|
system_fingerprint: null,
|
|
choices: [
|
|
{ index: 0, delta: { content: dt }, finish_reason: null, logprobs: null },
|
|
],
|
|
})
|
|
)
|
|
);
|
|
}
|
|
}
|
|
if (chunk.answer) fullAnswer = chunk.answer;
|
|
}
|
|
|
|
// Stop chunk
|
|
controller.enqueue(
|
|
encoder.encode(
|
|
sseChunk({
|
|
id: cid,
|
|
object: "chat.completion.chunk",
|
|
created,
|
|
model,
|
|
system_fingerprint: null,
|
|
choices: [{ index: 0, delta: {}, finish_reason: "stop", logprobs: null }],
|
|
})
|
|
)
|
|
);
|
|
controller.enqueue(encoder.encode("data: [DONE]\n\n"));
|
|
|
|
sessionStore(history, currentMsg, cleanResponse(fullAnswer), respBackendUuid);
|
|
} catch (err) {
|
|
controller.enqueue(
|
|
encoder.encode(
|
|
sseChunk({
|
|
id: cid,
|
|
object: "chat.completion.chunk",
|
|
created,
|
|
model,
|
|
system_fingerprint: null,
|
|
choices: [
|
|
{
|
|
index: 0,
|
|
delta: {
|
|
content: `[Stream error: ${err instanceof Error ? err.message : String(err)}]`,
|
|
},
|
|
finish_reason: "stop",
|
|
logprobs: null,
|
|
},
|
|
],
|
|
})
|
|
)
|
|
);
|
|
controller.enqueue(encoder.encode("data: [DONE]\n\n"));
|
|
} finally {
|
|
try { controller.close(); } catch {}
|
|
}
|
|
},
|
|
},
|
|
{ highWaterMark: 16384 }
|
|
);
|
|
}
|
|
|
|
async function buildNonStreamingResponse(
|
|
eventStream: ReadableStream<Uint8Array>,
|
|
model: string,
|
|
cid: string,
|
|
created: number,
|
|
history: Array<{ role: string; content: string }>,
|
|
currentMsg: string,
|
|
signal?: AbortSignal | null
|
|
): Promise<Response> {
|
|
let fullAnswer = "";
|
|
let respBackendUuid: string | null = null;
|
|
const thinkingParts: string[] = [];
|
|
|
|
for await (const chunk of extractContent(eventStream, signal)) {
|
|
if (chunk.backendUuid) respBackendUuid = chunk.backendUuid;
|
|
if (chunk.error) {
|
|
return new Response(
|
|
JSON.stringify({
|
|
error: { message: chunk.error, type: "upstream_error", code: "PPLX_ERROR" },
|
|
}),
|
|
{ status: 502, headers: { "Content-Type": "application/json" } }
|
|
);
|
|
}
|
|
if (chunk.thinking) {
|
|
thinkingParts.push(chunk.thinking);
|
|
continue;
|
|
}
|
|
if (chunk.done) {
|
|
fullAnswer = chunk.answer || fullAnswer;
|
|
break;
|
|
}
|
|
if (chunk.answer) fullAnswer = chunk.answer;
|
|
}
|
|
|
|
fullAnswer = cleanResponse(fullAnswer);
|
|
sessionStore(history, currentMsg, fullAnswer, respBackendUuid);
|
|
|
|
const reasoningContent = thinkingParts.length > 0 ? thinkingParts.join("\n") : undefined;
|
|
const msg: Record<string, unknown> = { role: "assistant", content: fullAnswer };
|
|
if (reasoningContent) msg.reasoning_content = reasoningContent;
|
|
|
|
const promptTokens = Math.ceil(currentMsg.length / 4);
|
|
const completionTokens = Math.ceil(fullAnswer.length / 4);
|
|
|
|
return new Response(
|
|
JSON.stringify({
|
|
id: cid,
|
|
object: "chat.completion",
|
|
created,
|
|
model,
|
|
system_fingerprint: null,
|
|
choices: [{ index: 0, message: msg, finish_reason: "stop", logprobs: null }],
|
|
usage: {
|
|
prompt_tokens: promptTokens,
|
|
completion_tokens: completionTokens,
|
|
total_tokens: promptTokens + completionTokens,
|
|
},
|
|
}),
|
|
{ status: 200, headers: { "Content-Type": "application/json" } }
|
|
);
|
|
}
|
|
|
|
// ─── Executor ───────────────────────────────────────────────────────────────
|
|
|
|
export class PerplexityWebExecutor extends BaseExecutor {
|
|
constructor() {
|
|
super("perplexity-web", { id: "perplexity-web", baseUrl: PPLX_SSE_ENDPOINT });
|
|
}
|
|
|
|
async execute({ model, body, stream, credentials, signal, log }: ExecuteInput) {
|
|
const bodyObj = (body || {}) as Record<string, unknown>;
|
|
const rawMessages = bodyObj.messages as
|
|
| Array<Record<string, unknown>>
|
|
| undefined;
|
|
if (!rawMessages || !Array.isArray(rawMessages) || rawMessages.length === 0) {
|
|
const errResp = new Response(
|
|
JSON.stringify({
|
|
error: { message: "Missing or empty messages array", type: "invalid_request" },
|
|
}),
|
|
{ status: 400, headers: { "Content-Type": "application/json" } }
|
|
);
|
|
return { response: errResp, url: PPLX_SSE_ENDPOINT, headers: {}, transformedBody: body };
|
|
}
|
|
|
|
const { hasTools, requestedTools, effectiveMessages } = prepareToolMessages(bodyObj, rawMessages as Array<{ role: string; content: unknown }>);
|
|
|
|
// Resolve thinking mode
|
|
const thinking =
|
|
bodyObj.thinking === true ||
|
|
(bodyObj.reasoning_effort != null && bodyObj.reasoning_effort !== "none");
|
|
|
|
let pplxMode: string;
|
|
let modelPref: string;
|
|
if (thinking && THINKING_MAP[model]) {
|
|
pplxMode = "copilot";
|
|
modelPref = THINKING_MAP[model];
|
|
log?.info?.("PPLX-WEB", `Thinking mode → ${model} using ${modelPref}`);
|
|
} else if (MODEL_MAP[model]) {
|
|
[pplxMode, modelPref] = MODEL_MAP[model];
|
|
} else {
|
|
pplxMode = "copilot";
|
|
modelPref = model;
|
|
log?.info?.("PPLX-WEB", `Unmapped model ${model}, using as raw preference`);
|
|
}
|
|
|
|
// Parse messages and check session continuity
|
|
const parsed = parseOpenAIMessages(effectiveMessages);
|
|
const followUpUuid = sessionLookup(parsed.history);
|
|
if (followUpUuid) {
|
|
log?.info?.("PPLX-WEB", `Session continue: ${followUpUuid.slice(0, 12)}...`);
|
|
}
|
|
|
|
const query = buildQuery(parsed, followUpUuid);
|
|
if (!query.trim()) {
|
|
const errResp = new Response(
|
|
JSON.stringify({
|
|
error: { message: "Empty query after processing", type: "invalid_request" },
|
|
}),
|
|
{ status: 400, headers: { "Content-Type": "application/json" } }
|
|
);
|
|
return { response: errResp, url: PPLX_SSE_ENDPOINT, headers: {}, transformedBody: body };
|
|
}
|
|
|
|
// Build Perplexity request
|
|
const requestId = crypto.randomUUID();
|
|
const pplxBody = buildPplxRequestBody(query, parsed.currentMsg, pplxMode, modelPref, followUpUuid, requestId);
|
|
|
|
const headers: Record<string, string> = {
|
|
"Content-Type": "application/json",
|
|
Accept: "text/event-stream",
|
|
Origin: "https://www.perplexity.ai",
|
|
Referer: "https://www.perplexity.ai/",
|
|
"User-Agent": PPLX_USER_AGENT,
|
|
// Current app request headers (replaced the stale X-App-ApiVersion/X-App-ApiClient pair,
|
|
// which the new endpoint no longer expects and which contributed to HTTP 400).
|
|
"x-perplexity-request-endpoint": PPLX_SSE_ENDPOINT,
|
|
"x-perplexity-request-reason": "ask-query-state-provider",
|
|
"x-perplexity-request-try-number": "1",
|
|
"x-request-id": requestId,
|
|
};
|
|
|
|
if (credentials.accessToken) {
|
|
headers["Authorization"] = `Bearer ${credentials.accessToken}`;
|
|
} else if (credentials.apiKey) {
|
|
headers["Cookie"] = `__Secure-next-auth.session-token=${credentials.apiKey}`;
|
|
}
|
|
|
|
log?.info?.(
|
|
"PPLX-WEB",
|
|
`Query to ${model} (pref=${modelPref}, mode=${pplxMode}), len=${query.length}`
|
|
);
|
|
|
|
// Fetch from Perplexity through the Firefox-fingerprinted TLS client.
|
|
// Perplexity sits behind Cloudflare Enterprise which pins JA3/JA4 to a real
|
|
// browser handshake; Node's fetch() is challenged with a 403 page from
|
|
// VPS/datacenter IPs even with a valid cookie (issue #2459).
|
|
let response: TlsFetchResult;
|
|
try {
|
|
response = await tlsFetchPerplexity(PPLX_SSE_ENDPOINT, {
|
|
method: "POST",
|
|
headers,
|
|
body: JSON.stringify(pplxBody),
|
|
signal: signal ?? null,
|
|
stream: true,
|
|
streamEofSymbol: "[DONE]",
|
|
});
|
|
} catch (err) {
|
|
const isTlsUnavail = err instanceof TlsClientUnavailableError;
|
|
log?.error?.("PPLX-WEB", `Fetch failed: ${err instanceof Error ? err.message : String(err)}`);
|
|
const errResp = new Response(
|
|
JSON.stringify({
|
|
error: {
|
|
message: isTlsUnavail
|
|
? `Perplexity TLS client unavailable: ${sanitizeErrorMessage((err as Error).message)}`
|
|
: `Perplexity connection failed: ${sanitizeErrorMessage(err instanceof Error ? err.message : String(err))}`,
|
|
type: "upstream_error",
|
|
},
|
|
}),
|
|
{ status: 502, headers: { "Content-Type": "application/json" } }
|
|
);
|
|
return { response: errResp, url: PPLX_SSE_ENDPOINT, headers, transformedBody: pplxBody };
|
|
}
|
|
|
|
if (response.status !== 200 || (!response.body && !response.text)) {
|
|
const status = response.status;
|
|
let errMsg = `Perplexity returned HTTP ${status}`;
|
|
if (status === 401 || status === 403) {
|
|
if (isCloudflareChallenge(response.text)) {
|
|
errMsg =
|
|
"Cloudflare blocked the request — Perplexity's edge rejected this server's TLS fingerprint " +
|
|
"(common on VPS/datacenter IPs). Ensure tls-client-node is installed with its native binary, " +
|
|
"or route perplexity-web through a residential proxy.";
|
|
log?.error?.("PPLX-WEB", "Cloudflare challenge detected — TLS bypass failed");
|
|
} else {
|
|
errMsg =
|
|
"Perplexity auth failed — session cookie may be expired. Re-paste your __Secure-next-auth.session-token.";
|
|
}
|
|
} else if (status === 429) {
|
|
errMsg = "Perplexity rate limited. Wait a moment and retry.";
|
|
}
|
|
log?.warn?.("PPLX-WEB", errMsg);
|
|
const errResp = new Response(
|
|
JSON.stringify({
|
|
error: { message: errMsg, type: "upstream_error", code: `HTTP_${status}` },
|
|
}),
|
|
{ status, headers: { "Content-Type": "application/json" } }
|
|
);
|
|
return { response: errResp, url: PPLX_SSE_ENDPOINT, headers, transformedBody: pplxBody };
|
|
}
|
|
|
|
if (!response.body) {
|
|
const errResp = new Response(
|
|
JSON.stringify({
|
|
error: { message: "Perplexity returned empty response body", type: "upstream_error" },
|
|
}),
|
|
{ status: 502, headers: { "Content-Type": "application/json" } }
|
|
);
|
|
return { response: errResp, url: PPLX_SSE_ENDPOINT, headers, transformedBody: pplxBody };
|
|
}
|
|
|
|
// Build OpenAI-compatible response
|
|
const cid = `chatcmpl-pplx-${crypto.randomUUID().slice(0, 12)}`;
|
|
const created = Math.floor(Date.now() / 1000);
|
|
|
|
let finalResponse: Response;
|
|
if (stream) {
|
|
const sseStream = buildStreamingResponse(
|
|
response.body,
|
|
model,
|
|
cid,
|
|
created,
|
|
parsed.history,
|
|
parsed.currentMsg,
|
|
signal
|
|
);
|
|
finalResponse = new Response(sseStream, {
|
|
status: 200,
|
|
headers: {
|
|
"Content-Type": "text/event-stream",
|
|
"Cache-Control": "no-cache",
|
|
"X-Accel-Buffering": "no",
|
|
},
|
|
});
|
|
} else {
|
|
finalResponse = await buildNonStreamingResponse(
|
|
response.body,
|
|
model,
|
|
cid,
|
|
created,
|
|
parsed.history,
|
|
parsed.currentMsg,
|
|
signal
|
|
);
|
|
}
|
|
|
|
if (hasTools && !stream) {
|
|
const bodyText = await (finalResponse as Response).text();
|
|
try {
|
|
const json = JSON.parse(bodyText);
|
|
const rawContent = json?.choices?.[0]?.message?.content || "";
|
|
const { content, toolCalls, finishReason } = buildToolAwareResult(rawContent, requestedTools, "pplx");
|
|
if (toolCalls) {
|
|
json.choices[0].message = { role: "assistant", content: null, tool_calls: toolCalls };
|
|
json.choices[0].finish_reason = finishReason;
|
|
} else {
|
|
json.choices[0].message.content = content;
|
|
}
|
|
finalResponse = new Response(JSON.stringify(json), {
|
|
status: 200, headers: { "Content-Type": "application/json" },
|
|
});
|
|
} catch { /* keep original response */ }
|
|
}
|
|
|
|
return {
|
|
response: finalResponse,
|
|
url: PPLX_SSE_ENDPOINT,
|
|
headers,
|
|
transformedBody: pplxBody,
|
|
};
|
|
}
|
|
}
|