translateResponse() short-circuited untouched on claude->claude streaming,
so OAuth-cloaked tool names (CLAUDE_TOOL_SUFFIX) leaked to the client and
every tool call was rejected as unknown. Add decloakStreamChunk(), the
streaming counterpart of decloakToolNames(), and call it on the same-format
path using the already-plumbed state.toolNameMap.
GLM quota parsing only accepted TOKENS_LIMIT and wrote every limit to a
single "session" key, so credit-based plans showed nothing and later
intervals overwrote earlier ones. Accept CREDIT_LIMIT too and derive the
quota key from the limit unit (5h session, 7d weekly, tokens, custom).
Moves the parser into its own usage/glm.js, re-exported from misc.js.
Z.ai / GLM-5.2+ require a top-level reasoning_effort (low/high/max)
alongside thinking:{type:"enabled"} to control reasoning depth; the zai
branch previously only set thinking and dropped reasoning_effort, so every
GLM-5.x request ran at the model default (max). Gate the field behind
GLM-5.2+ (thinkingEffortSupported in capabilities.js) since older GLM
(4.x, 5.0, 5.1, 5-turbo, 5v-turbo) do not read it, and map client levels
to the exact low/high/max values z.ai accepts.
extractThinking now checks reasoning_effort/reasoning.effort before the
thinking object so a client-supplied effort is not overwritten by
thinking:{type:"enabled"} mapping to mode:auto.
Fixes#2721
Caveman/Ponytail injection now matches each target wire format instead of
assuming an OpenAI-shaped body:
- Chat arrays append a text block; Responses arrays append input_text and
create typed message items
- Claude inserts before the final cache-control block; Gemini preserves the
snake/camel systemInstruction wrapper
- Kiro updates systemPrompt and its mirrored first-user prefix atomically,
rolling back if the pair fails to converge
- Format label decides Claude/Gemini before the wire-shape sniff, since their
bodies also carry messages[]/contents[] and Anthropic rejects a "system"
role inside messages[]
- Delimiter-aware dedup makes injection exact-idempotent across retries, so
distinct prompts sharing a long prefix are no longer collapsed
- Every write is fail-open on frozen or proxied bodies
Saver order and X-9Router-Token-Saver: off behavior are unchanged.
Fixes#3202.
muse-spark-1.2-contributor-free returned HTTP 500 on /zen/v1/chat/completions.
The model is only served by /zen/v1/responses, so route it there via a per-model
targetFormat and normalize the Chat fields the Responses API rejects
(max_tokens -> max_output_tokens, reasoning_effort -> reasoning{effort,summary}),
clamping max/ultra down to the highest effort the model accepts (xhigh).
Routing stays per-model: the other free models (big-pickle, hy3-free, mimo,
nemotron, laguna) are not served by /responses and keep /chat/completions.
createSSEStream splits on "\n" and keeps the remainder, which only flush()
parses. That call omitted targetFormat, so parseSSELine required a "data: "
prefix and dropped whatever an NDJSON provider left without a closing
newline. The !parsed.done guard compounded it: the SSE sentinel and an
Ollama final chunk both carry done:true, but the latter is the real last
chunk holding done_reason and the token counts.
Pass targetFormat and scope the sentinel check to formats that emit one, so
the tail reaches the translator. Accumulate its usage into state the same way
the transform loop does, so finalizeStream logs those tokens instead of null.
Extract Spark rate limit windows from the Codex usage response and expose
them as spark_session/spark_weekly quotas, reusing the existing prefix
mechanism. Map codex quota types to readable dashboard labels.
Fixes#3431
Vendors shipped four multimodal models the registry did not carry:
- glm-5.3-flash — z.ai's first natively multimodal GLM-5, 1M context,
image + video + pdf input (glm, glm-cn, opencode-go)
- deepseek-v4-flash-vision-exp — image input at V4-Flash text parity,
1M context / 384k output (deepseek, opencode-go)
- grok-4.6, grok-4.5 — 500k context; 4.6 has no text output limit (xai)
Capabilities needed hand entries because the existing globs mis-matched:
*glm-5* and *deepseek-v4* carry no vision, and *grok-4* would have capped
grok-4.6 at 256k instead of 500k. The grok-4.6 pattern sits above the
generic *grok-4* so it wins the first-match lookup.
Also corrects glm-4.6v / glm-4.5v, which were missing video input and
declared no maxOutput, and backfills glm-4.6v on glm-cn — zhipuai serves
it and the sibling provider already listed it.
tests/unit/opencode-go-models.test.js pins the opencode-go model list, so
its expected array moves with the registry.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
On a 409/429 from Antigravity, fetch live quota to learn the exact
per-model resetAt instead of guessing a backoff, then skip only the
exhausted account/model pair until that time.
- antigravityQuota.js: in-memory quota cache, coalesced concurrent
refreshes, 30s throttle per connection (applied to failures too),
keeps known cache when upstream returns 401/403 error payloads
- auth.js: pre-filter exhausted account/model pairs; report the
earliest quota reset when every account is blocked; skip the
30-minute cooldown cap so the upstream resetAt is not truncated
- chat.js: antigravity 409/429 falls back on the RAM cache only, no
persistent modelLock_* for this path
- Logs identify accounts by id prefix, never email or name
Closes#3561
Xquik needs a GET request with x-api-key auth and a tweets envelope
normalizer, neither of which the generic search fallback provides. Adds a
dedicated request builder and normalizer, cursor pagination passthrough,
result-based credit usage reporting, and a validateUrl probe so key
validation hits the no-charge credits endpoint.
opencode-go hard-coded targetFormat: claude per model, so every client
format was force-routed to /messages (Codex/OpenAI clients paid a lossy
Responses->OpenAI->Claude double translation). Declare the existing
upstream multi-endpoint transports [openai, claude, openai-responses]
and guard per model via registry supportedFormats: kimi/glm/mimo only
support /chat/completions, minimax/qwen add /messages, deepseek adds
/responses. Undeclared models keep the upstream default.
Drop the bespoke OpenCodeGoExecutor (its shared _lastModel cache could
cross auth headers between concurrent requests); DefaultExecutor already
consumes runtimeTransport and injects reasoning content.
Antigravity and gemini-cli wrap their payload in { response: {...} }.
extractUsageFromResponse only tested top-level usageMetadata, so every
non-streaming antigravity request logged zero usage (IN 0 | OUT 0) and
zeroed rows in the usage dashboard. Read the envelope the same way
usageTracking.js and nonStreamingHandler.js already do; top-level
metadata keeps priority and the OpenAI/Claude branches are untouched.
Fixes#3260
x-9r-real-ip and the Host fallback were trusted from client-controlled
headers whenever custom-server.js was not in the request path (npm run
start, start:bun), letting a remote caller pose as local to skip API key
auth and reach LOCAL_ONLY_PATHS (/api/mcp/*, /api/tunnel/enable,
/api/auth/reset-password).
custom-server.js now generates a per-process secret at boot and stamps it
as x-9r-peer-token on every request it sanitizes. hasTrustedPeerHeaders()
(src/lib/auth/trustedPeer.js) gates trust in x-9r-real-ip on that secret;
otherwise the guard falls back to Host only in development, and fails
closed in production. Same gate on loginLimiter.getClientIp() so a spoofed
header cannot rotate the login lockout bucket.
Also: fix isLoopbackHostname for IPv6 (::1, ::ffff:127.0.0.1) which the
old split(":")[0] reduced to empty string; route npm run start /
start:bun through custom-server.js (postbuild copies it into
.next/standalone, build-cli.js fails without it) so documented deployments
keep passwordless local access.
Fourth Alibaba key type — Coding Plan (alicode/alicode-intl) and Model Studio
(alims-intl) both reject Token Plan keys. Registry entry only; PROVIDER_MODELS
builds from providers/registry so no executor or translator work is needed.
Singapore-only (eu-central-1 answers IllegalEndpoint) and OpenAI-compatible
transport only (the Anthropic surface is not authorized for this plan).
Closes#2754Closes#2806
Add gemini-3.7-flash and its tiered high/medium/low variants to the
Antigravity and Gemini registries, with matching capabilities, pricing
and Antigravity quota tracking.
extractModel now recognises gemini-3.7-flash-tiered alongside 3.6 and
derives the version from the request, so thinkingLevel still maps to the
right tiered alias.
Closes#3286Closes#3281
Registry entry plus one config-driven FORMAT_HANDLERS handler. The model id
travels in an HTTP `model` header rather than the JSON body, and the voice is
a reference_id (preset or cloned voice model).
Closes#2411
Inspect images[], experimental_attachments/attachments, message-level
image/image_url/audio_url, and inline data:image|audio|pdf URIs on trailing
user turns so Vision Adapter auto-switch fires for Hermes/Ollama/Vercel AI
SDK shapes. stripOpenAI now also drops msg.images and image attachments when
the active model lacks vision support.
Kimchi's transport is OpenAI-compatible (Authorization: Bearer) but the
registry declared it OAuth-only, so the dashboard, /api/providers, and
the connection test all rejected API keys. Enable dual auth
(authModes: ["oauth", "apikey"]) and add a kimchi case to
testApiKeyConnection so the Test Connection button works for both modes.
Regenerate the golden snapshot with the Kimchi entries (+ other
previously-missing providers).
Kiro IDE 1.0.228+ moved GenerateAssistantResponse from path
/generateAssistantResponse to POST / + x-amz-target header, so chat turns
bypassed MITM. The SmithyMessageDecoderStream also now requires an
initial-response frame at stream start, and agent/vibe mode sends
modelId "auto" which had no mappable slot.
- Add isChatRequest() header-based match for kiro in mitm/config.js
- Add buildInitialResponseFrame/withInitialFrame to emit the mandatory
initial-response once per stream (kiro.js)
- Add "auto" model slot and update mitmDomain to runtime.us-east-1.kiro.dev
Peek the first SSE frame in wrapQoderSSE; if statusCodeValue != 200 and the
body carries a billing signature (code 112/10605 or pricingUrl), return a
synthetic 403 so chatCore marks the connection unavailable and triggers
combo/account fallback instead of leaking the error text into chat.
wrapQoderSSE becomes async; consumed peek bytes are re-processed in the
stream start() seed loop so nothing is dropped.
Some providers (e.g. codebuddy/cbcn) attach an empty tool_calls array to every streaming chunk. An empty array is truthy in JS, so the guard 'if (delta.tool_calls)' closed the message on the first content token and emitted response.output_text.done early, dropping the remaining deltas. Guard on a non-empty array; finish_reason still closes the message and real tool calls still close it before emitting function_call items.
fixes#3234
Sync alias-baseline.json and providers-baseline.json with the current
registry (poolside, tokenrouter, selfhosted-* providers already added;
stale claudeOverlay hook and Kiro X-Amz-Target header already removed).
Qwen OAuth flow (portal.qwen.ai) stopped working reliably; drop the
executor, registry entry, OAuth provider/service, token refresh
profile, usage handler, and related test coverage and baselines.
Codex Responses Lite clients routed to a chat-native OpenAI-compatible
provider lost tool use in three places: non-streaming Chat responses
leaked the raw chat.completion envelope instead of Responses output
items, internal reasoning continuity fields leaked into the outbound
Chat body causing some upstreams to reject the request, and the
Responses to Chat request translator ignored additional_tools,
custom_tool_call, and custom_tool_call_output items entirely.
Also fixes apiType (chat vs responses) for openai-compatible nodes
being resolved from the immutable provider ID instead of the stored
node config, so editing a node's API Type had no runtime effect.
getAntigravityUsage filtered the fetchAvailableModels response through a
hardcoded importantModels list that only contained 3.5 Flash, silently
dropping the 3.6 Flash quota buckets so no usage bar rendered.
hasValidContent() only treated text/tool_use/tool_result blocks as valid
content, so a user message containing only an image block was filtered
out as empty. When it was the only non-system message, this left an
empty messages array and Anthropic rejected the request.
Cloudflare AI registry entry was missing authType/authModes, causing
the dashboard to report "No connections" despite an active API-key
connection. Closes#2969
Fix port 201281 -> 20128/v1 typo in README.zh-CN.md diagram, add
RTK Token Saver mention to README.vi.md/README.zh-CN.md, update
Tier 3 free providers to 2026 lineup, and drop hardcoded /tmp
node_modules path from tests/package.json and tests/README.md.
Merge the complete generated .next-cli-build/server tree into the
packaged CLI after the standalone copy, since Next's standalone output
is trace-pruned and can omit route modules (e.g. /api/v1/messages) or
chunks loaded dynamically. Add a post-copy integrity check for the
required API route artifacts so an incomplete package fails during
pack:cli instead of at runtime.
Fixes#2945
Adds mimo-v2.5-tts as a Media Provider TTS through the existing
OpenAI-compatible chat-completions endpoint. Voice is selected via the
top-level audio.voice field, and an optional style/language hint is
threaded through tts.js -> ttsCore.js -> the new adapter.
Map the Grok OAuth access-token tier claim to the public plan label
and prefer it over internal /user entitlement names. Fails open to
existing plan detection for opaque or malformed tokens; upstream
remains authoritative for access and quota enforcement.
Add "ultra" reasoning level for Codex GPT-5.6 Sol and Terra, and expose
Max for Luna (Luna falls back Ultra to Max since it is not supported
upstream). Scoped to cx/ routes only; Kiro and generic OpenAI routing
unchanged.
Break out tool schema and tool-history bytes in the size snapshot and
add an effective byte-savings percentage so token-saved logs reflect
the actual outbound payload reduction, not just processed content.
The global claudeHeaderCache singleton overlaid the last-seen Claude Code
client's identity headers onto every subsequent request, leaking one
client's headers (anthropic-beta, user-agent, x-stainless-*, etc.) onto
another client/account sharing the same server. Removed the singleton and
the claudeOverlay hook entirely, falling back to static per-provider
headers. anthropic-beta is now computed per-request from the requested
model, gating heavy-agent flags (advanced-tool-use, effort) to
opus/sonnet only.
Lock GitHub Copilot connections account-wide until 00:00 UTC on the
first of next month when the upstream 402 response indicates the
monthly additional-usage-limit was hit, instead of only cooling down
the requested model for 120s. Other GitHub 402 responses keep the
existing model-scoped cooldown.
`open` derives its own directory from import.meta.url at module scope.
Webpack replaces that with the build machine's absolute path as a
string literal, so a release built on macOS ships a file:///Users/...
URL that fileURLToPath rejects on Windows (no drive letter), throwing
on import. refreshXaiToken dynamic-imports the xAI OAuth service, which
imports open eagerly, so every Grok token refresh silently failed and
was swallowed by a catch that only logs a warning.
Add open to serverExternalPackages so it keeps its real import.meta.url
at runtime, and bundle it into the CLI package via ensureModuleInBundle
(same guard already used for sql.js) since externalizing it means
webpack no longer traces/copies it automatically.
With output: "standalone", next build writes server.js under
.next/standalone but leaves generated static/public assets in the
project root, so starting the standalone server directly (e.g. via PM2)
404s on JS/CSS/font/favicon requests and /login stays stuck loading.
Add a postbuild step that copies .next/static and public into the
standalone directory, skipping the workspace-traced CLI build which
already copies its own assets.
JetBrains Runtime (JBR 25+) sends an h2c upgrade on OpenAI-compatible requests, which the HTTP/1.1 server would otherwise close. Intercept the upgrade, replay the buffered request through the existing handler, and respond over HTTP/1.1.
/api/auth/status did not expose whether the auth cookie corresponds to a
valid dashboard session, so /login could only detect "auth disabled"
(requireLogin === false) and not "already logged in". Add authenticated
to the status response and redirect from /login when it's true.
Ollama: replace informational stub with real quota tracker hitting ollama.com/api/usage (session 5h + weekly 7d, 0..1 ratio) and /api/me plan label; bind handler to apiKey + add features.usageApikey so apikey connections work.
Token refresh: add backgroundTokenRefresh scheduler that refreshes OAuth connections within max(provider lead, 30min) of expiry, independent of inbound traffic (10s after boot, then every 5min, unref'd timers, DISABLE_BACKGROUND_TOKEN_REFRESH kill-switch, fail-open per tick/connection). Registered from custom-server.js (listening) and initializeApp.js. checkAndRefreshToken gains opt-in {force} for the scheduler; request path unchanged.
Remove "Ported from OmniRoute" and cockpit-tools attribution comments.
User-Agent strings and README/landing credits are left intact.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
