Responses-API clients (codex, droid) close the socket on
response.completed because the protocol has no [DONE] sentinel, so
every successful request printed "⚡ DISCONNECT: ResponseAborted"
after its own "📊 done" line. Keep the dbg("CTRL", …) trace and drop
the console line; ABORTED and ERROR still print.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The Responses API has no [DONE] sentinel, so codex closes the socket
as soon as response.completed arrives. That cancels the reader before
flush() runs — and flush() held every usage side effect, so a fully
successful request logged nothing: no 📊 done line, no token stats,
no request detail.
Extract that tail into a once-guarded finalizeStream() and also call
it right after the terminal event is forwarded, in both passthrough
and translate mode. flush() still calls it; the guard makes the
second call a no-op. Streams that end normally are unaffected, and a
terminal event carrying no usage falls through to the existing
estimate/null path rather than blocking.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
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
Capability tables are hand-maintained, so a model gains vision or a wider
context only when someone notices and edits the file. This adds a daily
sync that fills the gap for models already in the registry.
How it decides:
- Modalities (vision/pdf/audio/video) belong to the MODEL — every gateway
serving glm-5.3-flash serves the same weights — so they are keyed by
model id and shared. A majority of sources must declare one, which keeps
out lone mis-declarations: minimax-m2.5 (1 of 45), glm-4.7 (1 of 44) and
gpt-oss-120b (2 of 76) are text-only despite a reseller claiming vision.
- Context/output limits belong to the GATEWAY — each truncates differently
(glm-5 ships as 202752/16384 on one host and 204800/131072 on another) —
so they are keyed by provider + model and only the matching provider's
own numbers are trusted.
Both layers are strictly additive and sit BELOW the hand-written tables,
which short-circuit first. A capability already true stays true.
Mechanics: worker thread (the 4MB parse would block the loop ~20ms),
ETag so an unchanged catalog costs one empty request, 60s startup delay,
30min backoff on failure, MODEL_CATALOG_SYNC=off to disable. Only the
~57KB delta is kept; lookups cost ~0.1us via an mtime-guarded cache.
capabilities.js is bundled into the browser through useModelCaps, so it
cannot import node:fs — the server injects the reader via
setCatalogSource() from instrumentation.
visionPatterns.js is the last resort: a model nobody has catalogued yet
still accepts images when its id says so (qwen3-vl-plus, glm-4.6v, llava),
with image-generation and embedding ids excluded.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
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>
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.
The openai-responses branch of compressWithHeadroom returned null without
recording a reason, leaving the diagnostics panel blank and making Codex
translation failures indistinguishable from a successful compression.
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
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
Zhipu released GLM-5.3 on both api.z.ai and open.bigmodel.cn coding
endpoints. Verified live against both, returning model:"glm-5.3" with
native reasoning_content.
No other changes needed: the '*glm-5*' family pattern in capabilities.js
and 'glm-5*' in pricing.js already cover it.
Passthrough kept the client's own cache_control markers, which point at
pre-normalization offsets. Once normalize/dedupe reshaped system and tools,
the breakpoints landed mid-array and the tail was re-cached every request.
- Pin the last system block and last tool at ttl 1h (was the client's 5m)
- Anchor the last assistant turn at 5m, falling back to the final message
so a first turn still gets a breakpoint
- Fold mid-conversation system messages into the neighbouring user turn
instead of hoisting them into body.system, where the volatile token
counters invalidated the prefix on every request
- Run the anchoring after every token saver, at the final body
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
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).
Mirror the official opencode CLI fingerprint (User-Agent, x-opencode-session, x-opencode-request, x-opencode-project) on free-tier requests so the Console no longer classifies traffic as an unidentified client and rate-limits it with FreeUsageLimitError / HTTP 429.
Session id resolves conversation-stable via resolveSessionId (client session to assistant-text hash to connection) to preserve prompt caching, normalized into opencode ses_ format with a generated fallback. When the downstream client is already opencode, its headers are forwarded as-is.
Zed IDE injects a Claude-agent system prompt that Antigravity flags as
competitive, blocking the request with a 429 Quota Exhausted response.
Scan systemInstruction.parts and remove the prompt before dispatch.
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
Multiple tabs/accounts/auto-refresh funneled straight to Anthropic and tripped 429. Add a 120s TTL cache keyed by access token with in-flight promise dedup, serve the last good read on soft failure, and thread a force flag through getUsageForProvider for manual refresh. Also lower the dashboard poll cadence (180s to 600s) and stable group-by-provider so connection order stops jumping.
Co-Authored-By: Claude <noreply@anthropic.com>
Google fingerprints User-Agent/Client-Metadata on loadCodeAssist and
onboardUser, silently refusing to provision a cloudaicompanionProject
when they don't match the real IDE. Split antigravity's headers out of
the shared gemini-cli constants instead of overwriting them, so the fix
doesn't touch gemini-cli or any other provider.
Inspired by #3000 (thanks @stoXmod for flagging the resource-exhausted
issue), rewritten to keep gemini-cli untouched.
Adds exact per-model rates for 110 TokenRouter models (pulled from
TokenRouter's own pricing API) plus a dedicated thinkingFormat case
(reasoning_effort enum low/medium/high/xhigh/max) and the provider
logo. Provider registration itself already landed in a prior commit;
this fills in what PR #3043 added on top.
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.
- detectRequiredCapabilities: infer audioInput/videoInput from block
type and embedded mime, not just vision/pdf
- handleChat / handleSingleModelChat: augment combo and single-model
routing with capacity-adapter models when the target lacks a
required capability, wrapped with history stripping for the
adapter model's context window
- Enable vision + audioInput capacity-adapter pools by default for new
and existing users (mergeWithDefaults backward-compat)
- Fall back to oc/mimo-v2.5-free when an enabled pool has no models
configured, both in the backend resolver and the combos UI (auto
refill on removing the last model from a pool)
- Hide PDF/Video from the Vision Adapter UI (PDF never implemented,
Video lacks translator support) while keeping the settings shape
- Exclude combos from the model picker when opened from the Vision
Adapter section
- mimo-v2.5 registry entry now declares audioInput/videoInput
- Simplify combo strategy and Vision Adapter descriptions
detectClientTool only matched the legacy "codex-cli" User-Agent, so the
current codex-tui CLI and Codex Desktop (UA "Codex Desktop", originator
"codex_work_desktop") fell through to null and lost native passthrough —
their requests got re-translated, stripping/overwriting fields like
reasoning.summary instead of forwarding the client body as-is.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Add Self-hosted STT/TTS/Embedding providers that read baseUrl per connection
instead of a fixed registry endpoint, so 9Router can point at whisper.cpp,
faster-whisper, Kokoro-FastAPI, llama-server, vLLM, Infinity, and similar
OpenAI-compatible local servers.
Self-hosted Embedding refuses to run without a baseUrl rather than falling
back to api.openai.com like openaiCompatNode does, since that fallback would
silently send input text and the API key to OpenAI under a provider named
"Self-hosted". Also fixes embeddingsCore to catch adapter build errors as a
400 instead of letting them escape uncaught, and bounds the upstream fetch
with FETCH_CONNECT_TIMEOUT_MS to avoid hanging forever on a dead endpoint.
Self-hosted TTS treats a bare model value as the model rather than the voice,
since the generic OpenAI TTS convention (bare = voice) is backwards for a
provider where the model is the variable part.
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
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.
PAT-to-job-token exchange was duplicated between the executor and the model service, each with its own cache. Consolidate into qoderModels.js and have the executor import it.
Also add a qoder case to the API-key validate route - the generic OpenAI-compat probe cannot validate a PAT (needs job-token exchange + COSY signing first), so bulk-add always reported unknown for qoder keys.
Adds pt-... token auth as an alternative to OAuth device flow. A PAT can't
sign COSY requests directly, so it's exchanged for a short-lived job token
(jt-...) plus userId via openapi.qoder.sh, then used for signing.
Also fixes job-token traffic (jt-...) being rejected by api3.qoder.sh with
403 "Login expired" — the official qodercli serves jt- traffic from
api2.qoder.sh instead, so buildUrl/model-list routing now branches on it.
Quota usage and the dashboard add-key modal are updated to resolve PAT
credentials and label the field correctly, and bulk-add now validates
each key so it gets a real testStatus instead of a hardcoded "unknown".
Neutralize CLI-agent system prompts that trigger CodeBuddy CN's content filter, add usage/quota tracking for codebuddy-intl sharing CN's logic, and normalize codebuddy-intl request messages to the shape it expects.
handleForcedSSEToJson dropped cached prompt tokens in two ways: the
Responses branch summed only input_tokens, which excludes cache_read
and cache_creation on cache-capable upstreams (measured 2012 reported
vs ~5344 actual, 5332 from cache); and the Chat Completions branch
computed usage correctly but it didn't always reach the client (an
Anthropic response with cache_read_input_tokens: 11022 arrived with no
usage field at all). Now folds cache counters into prompt_tokens,
surfaces them via prompt_tokens_details, and re-attaches usage before
serialisation.
Tool schemas carrying uniqueItems, contains, multipleOf,
unevaluatedProperties, unevaluatedItems, or contentSchema get rejected
by the Gemini API with "Unknown name ...: Cannot find field", failing
the whole request. Add them to UNSUPPORTED_SCHEMA_CONSTRAINTS alongside
the existing stripped keywords (minItems, maxItems, format, ...).
ollama's registry entry lacked authModes, so dualAuthTypes on the providers page defaulted to oauth and its apikey connections showed as No connections on the freeTier card.
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.
