Files
OmniRoute/open-sse/executors/perplexity-web.ts
Diego Rodrigues de Sa e Souza fa367dd99e Release v3.8.27 (#3968)
* 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 commit c9b5b1a892)

* 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 into 05213ac6a. 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>
2026-06-17 02:43:21 -03:00

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,
};
}
}