Files
OmniRoute/docs/research/UNLIMITED_LLM_ACCESS.md
Diego Rodrigues de Sa e Souza f59f8daa94 Release v3.8.6 (#2804)
* fix(gemini): preserve structured tool calls for antigravity

* fix(gemini): parse prefixed textual tool calls

* fix(antigravity): preserve textual SSE tool calls

* fix(stream): normalize textual passthrough tool calls

* fix(stream): normalize split textual tool calls

* fix(stream): suppress malformed textual tool calls

* fix(stream): suppress compact malformed tool calls

* fix(stream): emit structured textual tool calls

* fix(stream): suppress unknown textual tool calls

* fix(stream): normalize responses textual tool calls

* chore: ignore .claude/settings.local.json (per-user Claude Code permissions)

* fix(opencode-go): route qwen3.x via claude messages + repair fixMissingToolResponses for Claude-shape upstreams (#2791)

Integrated into release/v3.8.6

* fix: resolve npm install warnings — remove dead deps, relax engine constraint (#2792)

Integrated into release/v3.8.6

* fix: register missing web-cookie validators (claude-web, gemini-web, copilot-web, t3-web) (#2793)

Integrated into release/v3.8.6

* fix: Error: Unable to inspect existing database #2771 (#2795)

Integrated into release/v3.8.6

* fix(oauth): repair Google loopback callback flow (#2796)

Integrated into release/v3.8.6

* feat(logs): add clean history button (#2799)

Integrated into release/v3.8.6

* [codex] home: restore settings-driven home layout and quota auto-refresh (#2800)

Integrated into release/v3.8.6

* fix(gemini): emit signaturelessToolCallMode:text for GEMINI format models (#2801)

Integrated into release/v3.8.6

* feat(modelSpecs): align opencode-go family with upstream provider limits (#2802)

Integrated into release/v3.8.6

* chore: apply unit test fixes, polyfills, and environment precedence fixes

* docs(agents): atualiza fluxos de release e triagem

Expande os workflows de release para incluir auditoria de segurança,
CHANGELOG completo por commits, quality gate obrigatório, homologação em
VPS local, publicação oficial, deploy em Akamai e validação de artefatos.

Reorganiza a triagem de features com arquivos permanentes por bucket,
suporte a itens em andamento, regra de reclaim após 15 dias e novo
tratamento para ideias viáveis catalogadas.

Corrige a orientação de revisão de discussões para usar a ordem
cronológica real dos comentários e respostas ao identificar a última
atividade.

* fix(lockout): classify Gemini Antigravity resource exhaustion as quota_exhausted

* fix(reasoning): gate replay by interleaved field

* docs(rule-16): permit human Co-authored-by, restrict only AI/bot trailers

Rule #16 previously banned all `Co-Authored-By` trailers absolutely.
That blocked the upstream-port workflows (`/port-upstream-features` and
`/port-upstream-issues`), which must credit human upstream PR authors
and issue reporters in OmniRoute commits.

Refine the rule to ban only AI/bot-attributed trailers (Claude, GPT,
Copilot, Bot; anthropic.com / openai.com / bot-owned noreply.github.com
emails) while allowing standard human `Co-authored-by: Name <email>`
attribution.

Sync the rule across the source CLAUDE.md, the E2E shakedown doc note,
and 41 i18n translations.

* fix(gitlawb): add specialty validators for connection test — bypass /models probe

GitLawB OpenGateway API (xiaomi-mimo compatible) does not expose a /models
endpoint, causing validateOpenAILikeProvider to 404 on the initial probe
and report 'Provider validation endpoint not supported'.

Add specialty validators for both gitlawb and gitlawb-gmi that follow the
same pattern as the existing xiaomi-mimo validator: skip GET /models,
validate directly via POST /chat/completions with a minimal test message.
Any 401/403 response means an invalid key; all other responses mean auth
is OK.

Fixes test-connection returning 404 for GitLawB providers.

* test(gitlawb): add 12 unit tests for gitlawb and gitlawb-gmi specialty validators

Covers success, auth failure (401/403), non-auth acceptance (400/422/429),
network errors, and custom baseUrl overrides for both providers.

* feat(gitlawb): serve models from static registry without API-unavailable warning

GitLawB's OpenGateway API does not expose a /models endpoint per
provider-path. Previously the models route fell through to the generic
fallback which returned static catalog models with the misleading
'API unavailable — using local catalog' warning.

Now gitlawb and gitlawb-gmi are handled as static model providers
(same pattern as reka and qwen OAuth) — models are served from the
provider registry without any warning, since all registered models
are functional via POST /chat/completions.

* refactor(gitlawb): extract shared opengateway validator factory, fix docs path in test

- Extract gitlawb/gitlawb-gmi validators into buildOpengatewayValidator factory
- Fix dockerignore-docs-coverage test: update stale docs/AUTO-COMBO.md -> docs/routing/AUTO-COMBO.md

* fix(reasoning): guard interleaved capability lookup

* feat(gitlawb): dynamic model fetch with gmi-cloud fallback

Hybrid approach:
- gitlawb (xiaomi-mimo): dynamic /models endpoint → 356 models
- gitlawb-gmi (gmi-cloud): 404 fallback → local catalog gracefully
Mimics Gitlawb/openclaude's model-routing pattern

* i18n(pt-BR): complete missing translations and sync with en.json

* feat(build): nix multi-OS package manager install (#2806)

Integrated into release/v3.8.6

* fix(i18n): translate 144 new __MISSING__ pt-BR strings (#2816)

Integrated into release/v3.8.6

* chore(docs): set coverage gate to 40/40/40/40 in CLAUDE.md

Aligns the documented coverage gate with the v3.8.6 release decision
(lowered from 75/75/75/70). Matches the threshold already set in
package.json by the large feature PRs (planos 11-22).

* fix(cli): respect PORT env var in serve command (#2845)

Integrated into release/v3.8.6.

* fix(deepseek-web): return 400 when client sends tools[] - chat.deepseek.com has no tool support (#2854)

Integrated into release/v3.8.6.

* fix(qoder): reject invalid/expired PATs returning Cosy 500 error (#2860)

Integrated into release/v3.8.6.

* fix(cli): register openclaw in tool-detector (#2833) (#2850)

Integrated into release/v3.8.6.

* fix(api): include noAuth providers in /v1/models catalog (#2798) (#2814)

Integrated into release/v3.8.6.

* fix(combo): resolve custom provider targets via combo name (#2778) (#2812)

Integrated into release/v3.8.6.

* fix(translator): strip safety_identifier in openai-responses cleanup (#2770) (#2809)

Integrated into release/v3.8.6.

* fix(quota): honor explicit per-connection preflight opt-out (#2831) (#2844)

Integrated into release/v3.8.6.

* fix(usage): un-invert GitHub Copilot Free/limited quota — limited_user_quotas is remaining (#2876) (#2881)

Integrated into release/v3.8.6.

* fix(nous-research): correct baseUrl to include /chat/completions (#2826) (#2835)

Integrated into release/v3.8.6.

* fix(opencode): qwen3.x max/plus models lack vision support (#2822) (#2836)

Integrated into release/v3.8.6.

* fix(translator): pass-through tool_search built-in tool type (#2766) (#2811)

Integrated into release/v3.8.6.

* fix(github): route claude-opus-4.6 via chat completions (#2821)

Integrated into release/v3.8.6.

* docs(oauth): add Windsurf login fix design (Phase 1 hotfix + Phase 2 Firebase OAuth)

Two-phase plan to fix the broken Windsurf OAuth flow:
- Phase 1: drop the dead app.devin.ai/editor/signin PKCE path, promote
  import-token from windsurf.com/show-auth-token as the primary path
- Phase 2: port Firebase OAuth + RegisterUser flow from
  fendoushaonian/WindSurf-gRPC-API for full browser-based automation

Spec only - no code changes yet.

* docs(plan): Phase 1 windsurf login hotfix implementation plan

10 tasks covering:
- TDD assertions for flowType + 410 Gone responses
- Provider switch to import_token
- Route handler retiring authorize/start-callback-server/poll-callback
- OAuthModal UI override
- i18n sync
- Verification + PR steps

* fix(cli): replace cli-table3 with hand-rolled formatter (#2752) (#2813)

Integrated into release/v3.8.6.

* fix(skills): skip interception for unregistered client-native tools (#2815) (#2817)

Integrated into release/v3.8.6.

* feat(sse): add RTK filters for kubectl, docker-build, composer, gh (#2824)

Integrated into release/v3.8.6.

* fix(geminiHelper): support rec.image content shape + warn on dropped remote URLs (refs #2807) (#2855)

Integrated into release/v3.8.6.

* fix(cli): allow nullable/optional apiKey in cliMitmStartSchema (#2857)

Integrated into release/v3.8.6.

* fix(combo): preserve system messages during context handoff summary generation (#2865)

Integrated into release/v3.8.6.

* fix: wire CLIProxyAPI fallback settings into chatCore routing engine (#2866)

Integrated into release/v3.8.6.

* fix(usage): add opencode quota fetcher (#2852) (#2867)

Integrated into release/v3.8.6.

* feat(claude): default xhigh support for newer Opus models (#2874)

Integrated into release/v3.8.6.

* fix(cli): restore omniroute logs command stream (#2756) (#2810)

Integrated into release/v3.8.6.

* fix(combo): normalize upstream Headers for Node 24 undici interop (#2751) (#2823)

Integrated into release/v3.8.6.

* Rename proxy log Public IP to Client IP (#2880)

Integrated into release/v3.8.6.

* fix(claude): preserve max effort for supported models (#2875)

Integrated into release/v3.8.6.

* fix(oauth): switch windsurf provider to import_token flow

The PKCE auth URL targeting app.devin.ai/editor/signin returns 404
post-rebrand. Until Phase 2 ports Firebase OAuth + RegisterUser, the
only supported path is import-token via windsurf.com/show-auth-token.

- windsurf.ts: drop buildAuthUrl, set flowType=import_token
- generateAuthData returns supported:false + helpful error for windsurf/devin-cli
- tests: assert flowType + disabled stub

* fix(oauth): return 410 Gone for retired windsurf/devin-cli PKCE actions

start-callback-server, authorize, and poll-callback (GET + POST) now
return 410 Gone with a pointer to /import-token. The 410 short-circuit
runs before auth so the response is honest about the action being
permanently gone, not gated. Codex PKCE flow unchanged.

Tests: 5 new assertions cover GET + POST 410 paths and a Codex
regression check.

* refactor(oauth): annotate retired PKCE fields in WINDSURF_CONFIG

No behaviour change - comment-only update documenting that authorizeUrl,
codeChallengeMethod, callbackPort, callbackPath, apiServerUrl, and
exchangePath are no longer consumed. Active fields (inferenceUrl,
showAuthTokenUrl, firebaseApiKey, ideName) called out separately.

* fix(cli,docs): use requireCliToolsAuth in logs route + document OPENCODE quota env

Post-merge contract fixes for v3.8.6:
- src/app/api/cli-tools/logs/route.ts (#2810) now uses the shared
  requireCliToolsAuth guard (param renamed req->request) to satisfy the
  cli-tools-auth-hardening contract test.
- Document OMNIROUTE_OPENCODE_QUOTA_URL (#2867) in docs/reference/ENVIRONMENT.md
  to satisfy the env/docs sync contract.

* fix(dashboard): force import-token panel for windsurf/devin-cli

Phase 1 hotfix: hide the 'Browser Login' tab and start in Paste API Key
mode. Removes windsurf/devin-cli from PKCE_CALLBACK_SERVER_PROVIDERS so
no callback server is started for them. Codex still uses the PKCE flow.

The 'Get token' link continues to point at windsurf.com/show-auth-token
via the existing supportsTokenPaste form copy.

* fix(oauth): windsurf import-token mapTokens signature mismatch

The route at `src/app/api/oauth/[provider]/[action]/route.ts` invokes
`providerData.mapTokens({ accessToken: token })` (object), matching the
cursor/kiro signature. The windsurf provider was declared with
`mapTokens(token: string)` instead, so the entire object was stored as
`accessToken`. When the connection record reached the SQLite layer it
crashed with:

  SQLite3 can only bind numbers, strings, bigints, buffers, and null

Fix by aligning windsurf's `mapTokens` signature with the route caller
and the cursor/kiro convention. Also dedupe a copy-pasted second
`if (action === "import-token")` block in the route handler — the
second block was unreachable but identical to the first.

Adds two regression tests asserting that
`provider.mapTokens({ accessToken })` returns a string `accessToken` for
both windsurf and devin-cli, so a future signature drift trips the gate
instead of the SQLite bind error in production.

* feat(compression): expand pt-BR pack with troglodita rules (15 → 49) (#2818)

Integrated into release/v3.8.6

* fix(sse): repair RTK engine defaults so dedup and direct calls work (#2825)

Integrated into release/v3.8.6

* fix(mcp): redirect console.log/warn to stderr in --mcp stdio mode (#2840)

Integrated into release/v3.8.6

* fix(gemini-cli): prefer real project IDs over default-project (#2841)

Integrated into release/v3.8.6

* fix(opencode-go): add provider limits quota fetcher (#2861)

Integrated into release/v3.8.6

* Audit & add web cookie providers: fix 4 missing registry entries + DuckDuckGo (#2862)

Integrated into release/v3.8.6

* fix(antigravity): harden signatureless tool history (#2878)

Integrated into release/v3.8.6

* fix: provider model sync pruning and dynamic antigravity MITM proxy mappings (#2886)

Integrated into release/v3.8.6

* feat(usage): per-API-key token limits scoped to model/provider/global (#2888)

Integrated into release/v3.8.6

* fix(audio): build multipart body manually to preserve Content-Type (#2842)

Integrated into release/v3.8.6

* refactor: remove agent skill documentation files and streamline maintenance workflows

* test(stabilization): resolve unit test failures in blackbox-web, schema-coercion, translator-helper-branches, usage-service-hardening, and audio-transcription

* fix(security): mitigate Socket.dev supply-chain findings + secrets opt-in + minimal build profile (#2863) (#2871)

Two real security gaps closed and four cosmetic Socket.dev fingerprints removed.
See docs/security/SOCKET_DEV_FINDINGS.md for the per-finding maintainer
attestation.

Real bugs fixed:
- cloudSync: HMAC verification of `X-Cloud-Sig` + opt-in
  `OMNIROUTE_CLOUD_SYNC_SECRETS=true` before overwriting `accessToken` /
  `refreshToken` / `providerSpecificData` from a remote response. Closes the
  silent-credential-swap surface (a misconfigured or hostile CLOUD_URL could
  previously replace local tokens unverified).
- Zed import: split into 2-step `/discover` + `/import` flow. `/import` now
  requires `confirmedAccounts: [{ service, account, fingerprint }]` and
  re-reads the keychain server-side to filter by fingerprint, so a tampered
  discover response cannot trick the endpoint into saving an unrelated token.

Cosmetic Socket.dev mitigations:
- runElevatedPowerShell writes the elevated payload to a per-call temp `.ps1`
  file (mode 0o600) and references it via `-File`. Removes the textbook
  `-EncodedCommand <base64utf16le>` pattern flagged as malware by Socket's AI
  classifier.
- Maintainer attestation `SECURITY-AUDITOR-NOTE:` blocks added at every
  flagged call site pointing to `docs/security/SOCKET_DEV_FINDINGS.md`.

Build-time hardening:
- `OMNIROUTE_BUILD_PROFILE=minimal` (`npm run build:secure`) physically
  removes the four sensitive modules from the standalone bundle via webpack
  `NormalModuleReplacementPlugin`. Stubs throw `FeatureDisabledError` at
  runtime. Intended for the `omniroute-secure` artifact.

Tests:
- 24 new unit tests in `tests/unit/security/` covering the wrapper builder,
  HMAC verification (4 cases), credential fingerprint determinism (5 cases),
  confirmedAccounts validation + fingerprint filtering (6 cases), and the
  minimal-build stubs (5 cases).

Docs:
- New `docs/security/SOCKET_DEV_FINDINGS.md` — per-finding attestation.
- New `socket.yml` — Socket.dev v2 config pointing at the attestation.
- Updated `SECURITY.md` — supply-chain scanner section.
- Updated `.env.example` — three new env vars documented.

Backwards compatibility:
- Cloud sync token overwrite is OFF by default. Users who relied on
  it must set `OMNIROUTE_CLOUD_SYNC_SECRETS=true`. Breaking change documented
  in CHANGELOG.
- Zed import 2-step is the new default; legacy 1-step preserved behind
  `OMNIROUTE_ZED_IMPORT_LEGACY_ONE_STEP=true` and will be removed in v3.9.

Closes #2863

* fix(security): redact public Firebase Web key from windsurf spec; doc SHA-256 cache-key rationale (#2894)

Two security-scanning findings on release/v3.8.6:

- Secret-scanning alert 7 (google_api_key): the windsurf login-fix design spec
  embedded the literal public Firebase Web API key on two lines. Firebase Web
  API keys are non-sensitive by design (they identify the project; access is
  gated by Firebase Security Rules + key restrictions), but the literal trips
  secret scanning. Redacted to a placeholder; the embedded default still goes
  through resolvePublicCred per rule #11.

- Code-scanning alert 261 (js/insufficient-password-hash): tokenCacheKey() uses
  SHA-256 to derive an in-memory cache key from the session token, not for
  password-at-rest storage. Added a comment documenting why CWE-916 KDFs do not
  apply (false positive).

* fix(ci): resolve release/v3.8.6 gate failures (docs-sync, any-budget, pack-artifact) (#2895)

* fix(ci): resolve release/v3.8.6 gate failures (docs-sync, any-budget, pack-artifact)

Three CI gates failed on release/v3.8.6 (run 26630300877):

- docs-sync: CHANGELOG had a spurious "## [3.8.6-patch]" section above
  "## [3.8.6]", so the latest release no longer matched package.json (3.8.6)
  and the 41 i18n CHANGELOG mirrors were flagged as missing that section.
  Fold the lone #2752 entry into [3.8.6] and drop the patch heading.
- any-budget:t11: open-sse/handlers/chatCore.ts regressed to 1 explicit `any`
  (budget 0). Type the persist callback arg as Record<string, unknown>, which
  matches runWithOnPersist's RefreshPersistFn contract exactly.
- pack-artifact: open-sse/utils/setupPolyfill.ts ships via package.json "files"
  (bin/omniroute.mjs imports it at startup) but was missing from the pack
  policy allowlist. Allow it and add a regression test.

* fix(security): redact public Firebase Web key from windsurf spec

Redact the literal public Firebase Web API key (secret-scanning #7) to a
placeholder, mirroring the redaction on release/v3.8.6 (PR #2894) and the
windsurf fix branch. Non-sensitive public Web key; trips secret scanning.

* feat(combo): Zero-Latency Combos (Hedging, Proactive Compression, Predictive TTFT) (#2868)

* feat(combo): implement zero-latency combo optimizations (hedging, proactive compression, predictive TTFT)

* fix(combo): fix predictive TTFT skip logic and unhandled promise rejections

---------

Co-authored-by: Automation <automation@omniroute>

* feat: implement automated skill workflows and update system configuration and validation schemas

* test: eliminate dynamic cast warnings in cloud-sync unit test

* test: isolate services-branch-hardening database directory to avoid concurrency issues

* feat(providers): add 7 new web-cookie providers + research catalog + discovery tool

New providers:
- huggingchat: free LLM chat via huggingface.co/chat (no subscription)
- phind: free dev-focused AI chat via phind.com/api/agent
- poe-web: multi-model chat via poe.com GraphQL (p-b cookie)
- venice-web: privacy-focused AI chat via venice.ai (session cookie)
- v0-vercel-web: Vercel v0 code gen via v0.dev (session cookie)
- kimi-web: Moonshot Kimi chat via kimi.moonshot.cn (session cookie)
- doubao-web: ByteDance Doubao chat via doubao.com (session cookie)

Additional:
- Research catalog: docs/research/UNLIMITED_LLM_ACCESS.md
- Discovery tool design + stub: src/lib/discovery/ + migration 073
- Unit tests: 33 tests for all 7 providers
- Shared helpers consolidated in error.ts (slop cleanup)
- All registered in WEB_COOKIE_PROVIDERS + providerRegistry + webSessionCredentials

Closes #2885

* fix(typecheck): resolve typecheck errors in combo spec and compression modules

* feat(api,oauth): add `agy` (Antigravity CLI) standalone provider with CLI token import (#2899)

Add a standalone OAuth provider `agy` (Antigravity CLI) next to gemini-cli/antigravity.
It reuses the antigravity inference backend (identical Google client_id +
daily-cloudcode-pa.googleapis.com endpoint, executor and token-refresh) but ships its own
model catalog — including the Claude models the backend exposes (claude-opus-4-6-thinking,
claude-sonnet-4-6) — its own account pool, and four ways to connect:

- token-file import (paste/upload the agy oauth token JSON)
- auto-detect a local CLI login (~/.gemini/antigravity-cli/antigravity-oauth-token)
- browser OAuth (via the shared OAuthModal Google loopback flow)
- bulk / ZIP import

New routes: POST /api/providers/agy-auth/{import,import-bulk,zip-extract,apply-local}.
Catalog pinned from the live :fetchAvailableModels endpoint. Docs (openapi.yaml,
ENVIRONMENT.md, .env.example, CHANGELOG) updated; new unit tests for registration,
the token parser, and route auth-hardening.

* fix(security): redact public Firebase Web key from windsurf spec (#2896)

Redact the literal public Firebase Web API key (secret-scanning #7) to a
placeholder. Firebase Web API keys are non-sensitive by design but the literal
trips GitHub secret scanning. Mirrors the redaction landed on release/v3.8.6
(PR #2894). Embedded default still flows through resolvePublicCred (rule #11).

* Pr 2871 (#2897)

* fix(security): mitigate Socket.dev supply-chain findings + secrets opt-in + minimal build profile (#2863)

Two real security gaps closed and four cosmetic Socket.dev fingerprints removed.
See docs/security/SOCKET_DEV_FINDINGS.md for the per-finding maintainer
attestation.

Real bugs fixed:
- cloudSync: HMAC verification of `X-Cloud-Sig` + opt-in
  `OMNIROUTE_CLOUD_SYNC_SECRETS=true` before overwriting `accessToken` /
  `refreshToken` / `providerSpecificData` from a remote response. Closes the
  silent-credential-swap surface (a misconfigured or hostile CLOUD_URL could
  previously replace local tokens unverified).
- Zed import: split into 2-step `/discover` + `/import` flow. `/import` now
  requires `confirmedAccounts: [{ service, account, fingerprint }]` and
  re-reads the keychain server-side to filter by fingerprint, so a tampered
  discover response cannot trick the endpoint into saving an unrelated token.

Cosmetic Socket.dev mitigations:
- runElevatedPowerShell writes the elevated payload to a per-call temp `.ps1`
  file (mode 0o600) and references it via `-File`. Removes the textbook
  `-EncodedCommand <base64utf16le>` pattern flagged as malware by Socket's AI
  classifier.
- Maintainer attestation `SECURITY-AUDITOR-NOTE:` blocks added at every
  flagged call site pointing to `docs/security/SOCKET_DEV_FINDINGS.md`.

Build-time hardening:
- `OMNIROUTE_BUILD_PROFILE=minimal` (`npm run build:secure`) physically
  removes the four sensitive modules from the standalone bundle via webpack
  `NormalModuleReplacementPlugin`. Stubs throw `FeatureDisabledError` at
  runtime. Intended for the `omniroute-secure` artifact.

Tests:
- 24 new unit tests in `tests/unit/security/` covering the wrapper builder,
  HMAC verification (4 cases), credential fingerprint determinism (5 cases),
  confirmedAccounts validation + fingerprint filtering (6 cases), and the
  minimal-build stubs (5 cases).

Docs:
- New `docs/security/SOCKET_DEV_FINDINGS.md` — per-finding attestation.
- New `socket.yml` — Socket.dev v2 config pointing at the attestation.
- Updated `SECURITY.md` — supply-chain scanner section.
- Updated `.env.example` — three new env vars documented.

Backwards compatibility:
- Cloud sync token overwrite is OFF by default. Users who relied on
  it must set `OMNIROUTE_CLOUD_SYNC_SECRETS=true`. Breaking change documented
  in CHANGELOG.
- Zed import 2-step is the new default; legacy 1-step preserved behind
  `OMNIROUTE_ZED_IMPORT_LEGACY_ONE_STEP=true` and will be removed in v3.9.

Closes #2863

* feat: implement automated skill workflows and update system configuration and validation schemas

* test: eliminate dynamic cast warnings in cloud-sync unit test

* test: isolate services-branch-hardening database directory to avoid concurrency issues

* chore(docs): refresh generated docs collection index

Update the generated Fumadocs browser collection mapping to keep
documentation imports in sync with the current docs structure.

* docs: update generated browser docs collection manifest

Refresh the generated Fumadocs browser collection mapping so the docs site can resolve the current documentation files correctly.

---------

Co-authored-by: OpenClaw <openclaw@kuzhomesrv.local>
Co-authored-by: Dmitry Kuznetsov <139351986+dmitry@users.noreply.local>
Co-authored-by: KuzyaBot <kuzya@local>
Co-authored-by: JeferssonLemes <jeferssondev@gmail.com>
Co-authored-by: Paijo <14921983+oyi77@users.noreply.github.com>
Co-authored-by: Markus Hartung <mail@hartmark.se>
Co-authored-by: akarray <akarray@users.noreply.github.com>
Co-authored-by: Apostol Apostolov <theapoapostolov@gmail.com>
Co-authored-by: Hernan Javier Ardila Sanchez <hjasgr@gmail.com>
Co-authored-by: Dmitry Kuznetsov <dmitry@kuznetsov.me>
Co-authored-by: Nikolay Alafuzov <alafuzov_nn@rusklimat.ru>
Co-authored-by: oyi77 <oyi77@users.noreply.github.com>
Co-authored-by: Ronaldo Davi <alltomatos@users.noreply.github.com>
Co-authored-by: levonk <277861+levonk@users.noreply.github.com>
Co-authored-by: Lenine Júnior <lenine@engrene.com.br>
Co-authored-by: Annas Alghoffar <aag.annas@gmail.com>
Co-authored-by: Tushar Agarwal <76201310+Tushar49@users.noreply.github.com>
Co-authored-by: GreatLiu <eurasiaxz@qq.com>
Co-authored-by: yuna amelia <230527278+yunaamelia@users.noreply.github.com>
Co-authored-by: Randi <55005611+rdself@users.noreply.github.com>
Co-authored-by: Container <78986709+disonjer@users.noreply.github.com>
Co-authored-by: nickwizard <35692452+nickwizard@users.noreply.github.com>
Co-authored-by: Rajvardhan Patil <rajvardhanpatil7890@gmail.com>
Co-authored-by: Raxxoor <manker_lol@hotmail.com>
Co-authored-by: Muhammad Mugni Hadi <mugnimaestra3@gmail.com>
Co-authored-by: mi <123757457+soyelmismo@users.noreply.github.com>
Co-authored-by: Automation <automation@omniroute>
2026-05-29 12:44:29 -03:00

323 lines
16 KiB
Markdown

# Unlimited LLM Access — Research Catalog
> **Last updated:** 2026-05-29
> **Status:** Active research
> **Related:** [Issue #2885](https://github.com/diegosouzapw/OmniRoute/issues/2885)
## Overview
This document catalogs every known method for accessing LLMs without paying — through reverse engineering, web cookies, auto-registration, trial exploitation, session pooling, and free-tier maximization. Each method includes feasibility rating, risk assessment, and implementation guidance.
**Feasibility Scale:** 1 (theoretical) → 5 (proven in production)
---
## Method Categories
### 1. Web-Cookie Subscription Bypass
**How it works:** Extract session cookies/tokens from a logged-in browser session and use them to call the provider's internal API directly, bypassing the official API and its billing.
**OmniRoute pattern:** Already implemented for 16 providers. Uses `webCookieAuth.ts` helpers for cookie normalization, TLS fingerprint bypass for Cloudflare, and OpenAI format translation.
| Provider | Cookie/Token | API Endpoint | Feasibility | Risk | Complexity | Status |
|----------|-------------|--------------|-------------|------|------------|--------|
| ChatGPT Web | `__Secure-next-auth.session-token` | `chatgpt.com/backend-api/f/conversation` | 5 | Medium | High (PoW + TLS) | ✅ Implemented |
| Claude Web | `sessionKey` | `claude.ai/api/organizations/{org}/chat_conversations/{conv}/completion` | 5 | Medium | High (Turnstile) | ✅ Implemented |
| Gemini Web | `__Secure-1PSID` | `gemini.google.com` (Playwright) | 5 | Low | Medium | ✅ Implemented |
| Copilot Web | `access_token` | `wss://copilot.microsoft.com/c/api/chat` | 5 | Medium | Medium (WebSocket) | ✅ Implemented |
| DeepSeek Web | `userToken` (localStorage) | `chat.deepseek.com/api/v0/chat/completion` | 5 | Medium | High (PoW) | ✅ Implemented |
| Perplexity Web | `__Secure-next-auth.session-token` | `perplexity.ai/rest/sse/perplexity_ask` | 5 | Medium | Medium (TLS) | ✅ Implemented |
| Blackbox Web | `__Secure-authjs.session-token` | `app.blackbox.ai/api/chat` | 5 | Medium | Low | ✅ Implemented |
| Grok Web | `sso` cookie | `grok.com/rest/app-chat/conversations/new` | 5 | Medium | High (NDJSON) | ✅ Implemented |
| Meta AI Web | `ecto_1_sess` | `meta.ai/api/graphql` | 5 | Medium | Medium | ✅ Implemented |
| t3.chat Web | cookies + `convex-session-id` | `t3.chat/api/chat` | 4 | Low | Medium | ✅ Skeleton |
| Inner.ai | `token` cookie | `chatapi.innerai.com/chat` | 5 | Low | Low | ✅ Implemented |
| Adapta Web | Clerk JWT | `agent.adapta.one/api/chat/stream/v1` | 5 | Low | Medium | ✅ Implemented |
**New candidates (not yet implemented):**
| Provider | Cookie/Token | API Endpoint | Feasibility | Risk | Complexity | Notes |
|----------|-------------|--------------|-------------|------|------------|-------|
| Poe Web | `p-b` cookie | `poe.com/api/gql_POST` (GraphQL) | 4 | Medium | High (GraphQL) | Many models via single subscription |
| Venice Web | session cookie | `venice.ai/api/...` | 4 | Low | Low | Privacy-focused, less bot detection |
| v0 Vercel Web | session cookie | `v0.dev/api/...` | 3 | Low | Medium | Code gen focused |
| Kimi Web | session cookie | `kimi.moonshot.cn/api/...` | 4 | Medium | Medium | Chinese market, may need captcha |
| Doubao Web | session cookie | `doubao.com/api/...` | 4 | Medium | Medium | ByteDance, large model catalog |
| you.com | session cookie | `you.com/api/...` | 4 | Low | Medium | Issue #2690 |
| HuggingChat | CSRF token | `huggingface.co/chat/conversation` | 5 | Low | Low | Free, no auth for basic use |
| Phind | session cookie | `phind.com/api/...` | 4 | Low | Low | Free tier, dev-focused |
**Key techniques:**
- Cookie normalization via `extractCookieValue()` / `normalizeSessionCookieHeader()`
- TLS fingerprint bypass (JA3/JA4 matching) for Cloudflare-protected sites
- Proof-of-work solvers (SHA3-512, DeepSeekHashV1, hashcash)
- Browser fingerprint spoofing (User-Agent, Sec-Ch-Ua, Origin, Referer)
- Auto-refresh wrappers for session expiry handling
---
### 2. Free-Tier / No-Auth Providers
**How it works:** Use providers that offer free access without authentication, or with generous free tiers that don't require payment.
| Provider | Auth Required | Rate Limit | Models | Feasibility | Risk | Status |
|----------|--------------|------------|--------|-------------|------|--------|
| OpenCode Free | No | Yes | Kimi, GLM, Qwen, MiMo, MiniMax | 5 | None | ✅ Implemented |
| Qoder AI | No | Yes | Multiple | 5 | None | ✅ Implemented |
| Pollinations | No | Yes | Image/gen models | 5 | None | ✅ Implemented |
| HuggingChat | No | Yes | Multiple open-source | 5 | None | 🔲 Candidate |
| Phind | Free tier | Yes | Code-focused | 5 | None | 🔲 Candidate |
| DuckDuckGo AI | No | Yes | GPT-4o-mini, Claude, etc. | 5 | None | 🔲 PR #2862 |
---
### 3. Auto-Registration (Programmatic Account Creation)
**How it works:** Automate the signup flow to create throwaway accounts, extract session tokens, and use them until they expire or get banned. Then repeat.
**Risk level:** HIGH — violates ToS of most providers. Research only unless user approves.
#### 3a. Disposable Email + Verification
**How it works:** Use disposable email services (Guerrilla Mail, TempMail, Mailinator) to create accounts. Most providers send a verification link — click it programmatically to complete signup.
| Provider | Signup Method | Verification | Feasibility | Risk | Notes |
|----------|--------------|--------------|-------------|------|-------|
| ChatGPT | Email + password | Email link | 4 | High | Rate limits on signup, phone verification may be required |
| Claude | Email + password | Email link | 3 | High | Anthropic may require phone |
| Gemini | Google account | OAuth | 3 | Medium | Need Google account automation |
| Perplexity | Email + password | Email link | 4 | Medium | Less aggressive bot detection |
| Poe | Email + password | Email link | 4 | Medium | Quora account system |
**Implementation complexity:** Medium
- Need: disposable email API, HTTP client for signup flow, email link extractor, session token storage
- Challenge: CAPTCHAs (most providers use reCAPTCHA/hCaptcha), IP rate limiting, phone verification
#### 3b. OAuth Automation
**How it works:** Create throwaway Google/GitHub/Apple accounts, then use OAuth to sign up for LLM providers. More reliable than email-based signup because OAuth tokens are harder to invalidate.
| OAuth Provider | Target LLM Providers | Feasibility | Risk | Notes |
|---------------|---------------------|-------------|------|-------|
| Google | Gemini, ChatGPT, Claude | 3 | High | Google account creation requires phone |
| GitHub | Copilot, various | 4 | Medium | GitHub free tier is generous |
| Apple | Claude, others | 2 | High | Apple ID creation is heavily gated |
**Implementation complexity:** High
- Need: Playwright-based browser automation, CAPTCHA solving service, phone verification service
- Challenge: Google/Apple account creation requires phone number, increasingly aggressive bot detection
#### 3c. SMS Verification
**How it works:** Use virtual phone number services (SMS-Activate, 5sim, SMSpva) to receive verification codes during signup.
| Service | Cost per SMS | Countries | Reliability | Notes |
|---------|-------------|-----------|-------------|-------|
| SMS-Activate | $0.10-0.50 | 180+ | High | Most popular |
| 5sim | $0.05-0.30 | 100+ | Medium | Cheaper but less reliable |
| SMSpva | $0.10-0.50 | 50+ | Medium | Limited country selection |
**Implementation complexity:** High
- Need: virtual number API integration, SMS parsing, retry logic for failed verifications
- Challenge: cost per attempt, number recycling (may get already-used numbers), provider blacklisting
---
### 4. Token Harvesting / Session Pooling
**How it works:** Extract tokens from existing authenticated sessions (browser extensions, CLI tools, other apps) and pool them for high-throughput access.
#### 4a. CLI Tool Token Extraction
| Tool | Token Location | Token Type | Feasibility | Notes |
|------|---------------|------------|-------------|-------|
| `gemini-cli` | `~/.gemini/oauth_creds.json` | OAuth refresh token | 5 | Already used by gemini-cli provider |
| `claude-code` | `~/.claude/credentials` | OAuth token | 5 | Already used by claude-code provider |
| `copilot-cli` | `~/.config/github-copilot/` | OAuth token | 4 | Used by copilot provider |
| `codex-cli` | `~/.codex/` | OAuth token | 4 | Used by codex provider |
#### 4b. Session Pool Architecture
```
┌─────────────────┐
│ Session Pool │
│ ┌───┐ ┌───┐ │
│ │ S1│ │ S2│... │ ← Multiple authenticated sessions
│ └───┘ └───┘ │
│ ┌──────────┐ │
│ │ Rotator │ │ ← Round-robin or health-based rotation
│ └──────────┘ │
│ ┌──────────┐ │
│ │ Health │ │ ← Detect expired/banned sessions
│ │ Monitor │ │
│ └──────────┘ │
└─────────────────┘
```
**Key features:**
- Round-robin or least-used rotation across sessions
- Health checks (periodic validation that sessions are still active)
- Auto-replace expired sessions
- Rate limit tracking per session
- Failover to next session on 401/403
---
### 5. Trial / Credit Exploitation
**How it works:** Exploit free trials, signup credits, and promotional offers from API providers.
| Provider | Free Credit | Expiry | Signup Method | Feasibility | Risk |
|----------|------------|--------|---------------|-------------|------|
| OpenAI | $5-18 credit | 3 months | Email + phone | 4 | Medium |
| Anthropic | $5 credit | 3 months | Email | 3 | Medium |
| Google Cloud | $300 credit | 90 days | Google account + credit card | 3 | Medium |
| AWS Bedrock | Free tier (limited) | 12 months | AWS account | 3 | Low |
| Azure OpenAI | $200 credit | 30 days | Microsoft account + phone | 3 | Medium |
| Together AI | $5 credit | — | Email | 5 | Low |
| Fireworks AI | $1 credit | — | Email | 5 | Low |
| Cerebras | Free tier | — | Email | 5 | Low |
| Groq | Free tier | — | Email | 5 | Low |
**Auto-registration potential:** Medium — most require email verification, some require phone or credit card.
---
### 6. Leaked / Shared Credential Rotation
**How it works:** Use API keys or session tokens from public sources (GitHub leaks, shared accounts, public dashboards).
**Risk level:** CRITICAL — unauthorized access, potential legal consequences.
| Source | Credential Type | Volume | Feasibility | Risk | Notes |
|--------|----------------|--------|-------------|------|-------|
| GitHub leaks | API keys | High | 4 | Critical | Search for leaked keys in public repos |
| Public dashboards | Session tokens | Low | 3 | High | Some projects expose tokens in configs |
| Shared accounts | Login credentials | Medium | 3 | High | Account sharing communities |
**NOT RECOMMENDED** — included for completeness only. This method involves unauthorized access and potential legal liability.
---
### 7. Reverse Engineering Official APIs
**How it works:** Intercept and reverse-engineer the internal APIs used by provider web interfaces, CLI tools, and mobile apps.
| Target | Protocol | Auth Method | Complexity | Feasibility | Status |
|--------|----------|-------------|------------|-------------|--------|
| ChatGPT Web | REST + SSE | Session token + PoW | High | 5 | ✅ Done |
| Claude Web | REST + TLS | Session key + Turnstile | High | 5 | ✅ Done |
| Gemini Web | Playwright | Cookie injection | Medium | 5 | ✅ Done |
| Copilot Web | WebSocket | Hashcash PoW | Medium | 5 | ✅ Done |
| DeepSeek Web | REST + SSE | userToken + PoW | High | 5 | ✅ Done |
| Poe Web | GraphQL | p-b cookie | High | 4 | 🔲 Candidate |
| Kimi Web | REST | Session cookie | Medium | 4 | 🔲 Candidate |
| Doubao Web | REST | Session cookie | Medium | 4 | 🔲 Candidate |
**Key techniques:**
- Browser DevTools network tab for API discovery
- mitmproxy / Charles for HTTPS interception
- Playwright for automating browser interactions
- TLS fingerprint matching (JA3/JA4)
- PoW solver implementation
---
## Top Candidates for Implementation (Ranked)
| Rank | Provider | Method | Feasibility | Risk | Effort | Value |
|------|----------|--------|-------------|------|--------|-------|
| 1 | HuggingChat | Free/no-auth | 5 | None | Low | High (popular, many models) |
| 2 | Phind | Free tier | 5 | None | Low | Medium (dev-focused) |
| 3 | Poe Web | Web-cookie | 4 | Medium | High | High (many models) |
| 4 | Venice Web | Web-cookie | 4 | Low | Low | Medium (privacy) |
| 5 | v0 Vercel Web | Web-cookie | 3 | Low | Medium | Medium (code gen) |
| 6 | Kimi Web | Web-cookie | 4 | Medium | Medium | Medium (Chinese market) |
| 7 | Doubao Web | Web-cookie | 4 | Medium | Medium | Medium (Chinese market) |
| 8 | DuckDuckGo AI | Free/no-auth | 5 | None | Low | Medium (PR #2862) |
| 9 | Together AI | Trial credits | 5 | Low | Low | Low ($5 credit) |
| 10 | Fireworks AI | Trial credits | 5 | Low | Low | Low ($1 credit) |
---
## Auto-Registration Research Summary
### Disposable Email Flow
```
1. Generate temp email (Guerrilla Mail API)
2. Submit signup form (HTTP client)
3. Extract verification link from email (IMAP/API)
4. Click verification link
5. Extract session token from response
6. Store in session pool
7. Repeat when session expires
```
### OAuth Automation Flow
```
1. Create throwaway Google/GitHub account (Playwright)
2. Solve CAPTCHA (2captcha/anticaptcha API)
3. Complete phone verification (SMS-Activate)
4. Use OAuth to sign up for LLM provider
5. Extract session token
6. Store in session pool
```
### Key Challenges
- **CAPTCHAs:** Most providers use reCAPTCHA or hCaptcha. Solving services cost $1-3 per 1000 solves.
- **Phone verification:** Virtual numbers cost $0.10-0.50 per SMS. Numbers may be recycled/blacklisted.
- **IP rate limiting:** Providers track signup IP. Need proxy rotation.
- **Detection:** Providers increasingly use behavioral analysis (mouse movements, typing patterns).
- **Sustainability:** Accounts get banned. Need continuous re-registration.
---
## Session Lifecycle Management
### Full Automation Pipeline
```
Register → Verify → Extract Session → Store in Pool → Use → Detect Expiry → Re-register
```
### Health Check Strategy
- Periodic validation: send lightweight request, check response
- Expiry detection: track TTL from session creation
- Ban detection: monitor for 401/403 responses
- Auto-replace: remove unhealthy sessions, trigger re-registration
### Pool Configuration
```typescript
interface SessionPool {
providerId: string;
sessions: Session[];
rotationStrategy: 'round-robin' | 'least-used' | 'random';
maxSessions: number;
healthCheckInterval: number; // ms
autoReplace: boolean;
}
```
---
## Risk Assessment Matrix
| Method | ToS Violation | Legal Risk | Account Ban | IP Ban | Cost |
|--------|--------------|------------|-------------|--------|------|
| Web-cookie (own account) | Low | Low | Low | Low | Free |
| Free-tier providers | None | None | None | None | Free |
| Auto-registration | High | Medium | High | Medium | $0.10-0.50/account |
| Token harvesting | Low | Low | Low | Low | Free |
| Trial exploitation | Medium | Low | Medium | Low | Free |
| Leaked credentials | Critical | High | High | High | Free |
---
## References
- OmniRoute provider definitions: `src/shared/constants/providers.ts`
- Cookie auth helpers: `src/lib/providers/webCookieAuth.ts`
- Existing executors: `open-sse/executors/`
- TLS clients: `open-sse/executors/chatgptTlsClient.ts`, `perplexityTlsClient.ts`, `claudeTlsClient.ts`
- PoW solvers: `open-sse/executors/deepseek-pow.ts`, `claudeTurnstileSolver.ts`