Estimate tokens for tool_use, tool_result, thinking, system, and tools
blocks instead of text only, so count_tokens no longer returns 0 for
structured content and breaks Claude Code auto-compaction (#2337).
Co-authored-by: Cursor <cursoragent@cursor.com>
Add a 9Router-side proxy so the Headroom dashboard and its data
endpoints (/stats, /health, /stats-history, /transformations/feed)
stay same-origin when opened remotely through the 9Router app, and
add an "Open Headroom Dashboard" link in the Token Saver modal.
Gate /api/headroom/proxy as LOCAL_ONLY (loopback + CLI token) to
match start/stop, and strip cookie/authorization when the Headroom
target is non-loopback to avoid leaking viewer credentials.
Co-authored-by: Cursor <cursoragent@cursor.com>
Normalize every provider to one cache-inclusive convention via
canonicalizeUsage() before persist, and price cached + cache_creation as
subsets of prompt_tokens in calculateCostFromTokens() to stop
double-counting. usageRepo now delegates cost math to a single source.
Surface Cached tokens/cost across dashboard (overview, tokens, cost,
details). Merge Claude message_start cache with message_delta output so
cache counts survive. Compatible LLM nodes now allow multiple API-key
connections (key pool).
Co-authored-by: Cursor <cursoragent@cursor.com>
Add read-only GET to inspect per-credit reset inventory (status, granted,
expiry, remaining) with a Quota Tracker modal. DRY the route via shared
connection/refresh helpers; keep existing consume POST unchanged.
Co-authored-by: Cursor <cursoragent@cursor.com>
Direct MITM server startup read rootCA.key/.crt immediately and exited
when either was missing, bypassing the manager.js CA setup path.
- generate Root CA from server.js when key/cert is missing
- make generateRootCA()/generateCert() synchronous to avoid a startup
race before readFileSync
- add unit test covering synchronous Root CA creation
Co-authored-by: Cursor <cursoragent@cursor.com>
Add Kimchi as a browser-token OAuth provider routed through its
OpenAI-compatible gateway. Discover live models for /v1/models and
provider models, normalize Claude-compatible requests, and wire up
provider connection tests.
Co-authored-by: Cursor <cursoragent@cursor.com>
CodeBuddy CN bonus packs ("Bonus Pack N") are one-shot credits whose
CycleEndTime equals DeductionEndTime — they expire for good and never
replenish. The dashboard rendered their resetAt as "Reset in Xd",
implying a monthly refill.
Tag bonus packs recurring:false (refill packs recurring:true) in the
usage handler, forward the flag through parseQuotaData, and word the
quota table / progress bar as "Expires in" / "Expires at" for
one-shot packs.
Generalize Claude 5h auto-ping into a provider-generic scheduler and add
opt-in Codex auto-ping that warms the next 5h window via a tiny gpt-5.5
request when session.resetAt slides. Default off, per-connection toggle,
failure cooldown, blocking-quota skip, drains stream before success.
Closes#2107
Co-authored-by: Cursor <cursoragent@cursor.com>
Use getModelInfo instead of parseModel in /api/translator/translate
so custom OpenAI/Anthropic-compatible provider prefixes resolve
correctly, aligning the debug path with the runtime chat path.
Fixes#1083
Co-authored-by: Cursor <cursoragent@cursor.com>
isBlockedIpv6() did not normalize ::ffff:<ipv4>, allowing the SSRF
filter to be bypassed. Extract and validate via isBlockedIpv4().
Co-authored-by: Cursor <cursoragent@cursor.com>
Use full-page navigation after login/logout so the dashboard reloads
with the fresh auth cookie, and mark login/logout responses no-store.
Fixes#2100
Co-authored-by: Cursor <cursoragent@cursor.com>
- mask API keys in usage stats/history responses (apiKeyMasked)
- validate proxy URL scheme + reject shell metachars before env write
- escape HTML in OAuth callback page to prevent XSS
- atomic O_EXCL lock file to prevent TOCTOU race in MITM startServer
- set mitmIsRestarting guard synchronously before any await
Co-authored-by: Cursor <cursoragent@cursor.com>
Merge customModels from /api/models/custom into the isCustomProvider
branch so custom compatible providers display imported models instead
of the prefix/model-id placeholder. Mirrors the passthrough pattern;
filter by providerId since providerAlias stores the raw provider ID.
Co-authored-by: Cursor <cursoragent@cursor.com>
Pass Gemini AUDIO/TTS generateContent requests through to Google's native
v1beta endpoint instead of converting to chat, with per-credential fallback
(504 timeout, 502 fetch failure). Accept client keys from Bearer,
x-goog-api-key, or ?key= while forwarding only the configured Gemini
credential upstream. Expose native v1beta model names and rewrites, and add
Gemini 3.1 Flash TTS to the catalogs.
Co-authored-by: Cursor <cursoragent@cursor.com>
Fetch the live model list from the Copilot /models endpoint and surface
it through /v1/models, replacing the hardcoded github entry so newly
shipped models appear without a code change. Catalog is cached per
credential and the Copilot token is refreshed on 401/403 before retry.
Also raise the connectivity-test budget to max_tokens:16, since Claude on
Copilot emits no choices at max_tokens:1 and produced a false negative.
Co-authored-by: Cursor <cursoragent@cursor.com>
When logged in to Kiro IDE as an organization (AWS IAM Identity Center),
token import fails because IDC tokens require clientId/clientSecret for
refresh and use a different profileArn than social/builder-id accounts.
Changes:
- auto-import: read clientId/clientSecret from SSO cache client registration
file, read profileArn from Kiro IDE profile.json, normalize ARN region
- import: accept IDC credentials, use KiroService.refreshToken with them,
persist credentials for future automatic refreshes
- KiroAuthModal: pass IDC credentials from auto-detect through to import
Co-authored-by: Cursor <cursoragent@cursor.com>
- extract token saver into its own route /dashboard/token-saver
- slim down EndpointPageClient
- add token-saver nav to Header and Sidebar
Co-authored-by: Cursor <cursoragent@cursor.com>
Treat configured Headroom proxy as running when its /health endpoint
responds, even if local headroom CLI is not installed. Dashboard
Start/Stop stays limited to local loopback proxies while external
Docker sidecars can be enabled via HEADROOM_URL.
Closes#1948
Co-authored-by: Cursor <cursoragent@cursor.com>
Two additions on top of the merged CodeBuddy CN OAuth provider:
1. API key auth — connect with a direct API key (sent as
Authorization: Bearer), not only via OAuth device-code flow.
- registry: add authModes ["oauth","apikey"] + hasOAuth; combined Bearer
auth already forwards the key, token-refresh skips key connections.
- providers POST: accept dual-auth providers (authModes includes
"apikey") that live under category "oauth" — previously rejected as
"Invalid provider". Also fixes the same latent gap for xai.
2. Quota tracker — surface CodeBuddy CN credit balance on the usage
dashboard for both OAuth and API-key connections.
- registry: add transport.usage.url (Tencent billing endpoint) +
features.usage/usageApikey so the connection is quota-eligible.
- new CN-scoped handler services/usage/codebuddy-cn.js: POST the billing
meter endpoint, unwrap data.Response.Data.Accounts[]. The payload mixes
two credit types that must not be merged:
* refill/base ("基础体验包") — recurring allowance; cycle resets well
before the resource expires (CycleEndTime << DeductionEndTime).
Reads the *Cycle* balance, resetAt = next refresh. Cadence-labelled.
* bonus ("活动赠送包") — one-shot credits that expire at CycleEndTime.
Reads the plain Capacity balance. Labelled "Bonus Pack N".
One quota row per package, soonest-expiring first.
- register handler under "codebuddy-cn" in USAGE_HANDLERS.
Frontend needs no change — USAGE_SUPPORTED_PROVIDERS/USAGE_APIKEY_PROVIDERS
and the generic parseQuotaData branch already cover this shape.
Co-authored-by: Cursor <cursoragent@cursor.com>
GET /models is not part of the Anthropic API spec and many compatible
proxies do not implement it, causing the connection test to always fail
even with a valid API key.
Switch to POST /v1/messages with max_tokens=1 — the same approach used
for the built-in anthropic provider — and treat any non-401/403 response
as valid, since 400/529 still confirms the key was accepted.
Use node.defaultModel / connection.defaultModel when set so the test
respects the configured model rather than always falling back to
claude-3-haiku-20240307.
Co-authored-by: Rehan Choirul <rehanchrl@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
readConfig/readSettings/readJson across all CLI tool settings routes used
JSON.parse() but only caught ENOENT, re-throwing SyntaxError on any
corrupted or JSONC-formatted config file. The API would return 500, which
the UI misinterpreted as "tool not installed."
This patch:
- strips trailing commas before parsing (handles JSONC from opencode, etc.)
- returns null on any parse error instead of re-throwing, so the UI shows
"installed but not configured" (accurate) instead of "not installed"
- applies the same fix to all 8 affected routes: opencode, openclaw, kilo,
droid, cowork, copilot, claude, and cline
Co-authored-by: Cursor <cursoragent@cursor.com>
Build on the optional Headroom Token Saver from Carmelo Campos
(PR: feat: add optional Headroom token saver). Add managed start/stop
of the local headroom proxy from the dashboard, install detection,
status probing, and a simplified Token Saver UI.
- detect headroom CLI + python>=3.10, probe proxy /health
- spawn/stop proxy as a detached, pid-tracked process
- /api/headroom/{status,start,stop} routes, gated local-only in dashboardGuard
- one-click Start/Stop Headroom modal, no manual config needed
- claude<->openai shape conversion for /v1/compress via 9router translators
Thanks to Carmelo Campos (@carmelogunsroses) for the original Headroom integration.
Co-authored-by: Cursor <cursoragent@cursor.com>
Perplexity deprecated /models (404); switch to /v1/models for provider
test connection and models route. (#1895, fixes#1894)
Co-authored-by: Cursor <cursoragent@cursor.com>
Reject non-AWS region values before interpolating them into upstream
URLs and stop reflecting upstream response bodies to the client.
Co-authored-by: Cursor <cursoragent@cursor.com>
## Fixes
- **Kiro**: honor thinking effort budgets
- **AG/Kiro/Xiaomi**: provider fixes
- **Combo/Fusion**: flatten tool history in panel calls to prevent 503
- **LLM selector**: show custom vision models in selector and model list
- **Image**: prevent compatible nodes from shadowing provider aliases
Panel models in the fusion strategy must answer in prose. When the request
carried tools or prior tool_calls/tool messages, agentic panel models kept
emitting tool_calls instead of prose, so extractPanelText() returned empty
and the engine fell into the 503 "All fusion panel models failed" branch.
Panel fan-out now strips tools/tool_choice and flattens tool turns into
assistant prose (instead of dropping them), so panels keep the context but
cannot loop on tools. The judge still receives the unmodified history.
Co-authored-by: warelik <warelik@WARELIK-MB.local>
Co-authored-by: Cursor <cursoragent@cursor.com>
Expose user-added imageToText custom models as vision-capable chat
models in the default LLM selector and /v1/models, map custom service
kinds to runtime capabilities, and keep typed filtering for
/v1/models/{kind}.
Co-authored-by: Cursor <cursoragent@cursor.com>
Build a reserved prefix set from registry provider ids/aliases plus local
aliases, and skip compatible-node prefix matching for reserved prefixes so
built-in routes like cf/... stay on Cloudflare.
Co-authored-by: Cursor <cursoragent@cursor.com>
## Features
- **Combo Fusion strategy** — fans the prompt out to all member models in parallel, then a configurable judge model synthesizes one final answer (quorum-grace, anonymized sources, graceful degradation)
- **Per-combo strategy selector** — pick `fallback` / `round-robin` / `fusion` / `capacity` per combo (replaces the old round-robin toggle), with a judge picker for fusion
- **Capacity auto-switch** — reorders models per request so images/PDFs route to capable models first
- **Kiro headless API-key auth** (`ksk_`) + direct `claude↔kiro` route that avoids the lossy OpenAI two-hop pivot
- **Claude auto-ping** — warms the 5h quota window right after reset so a fresh window starts immediately (per-connection toggle)
## Fixes
- **Claude 429**: stop hammering the OAuth usage endpoint — cache resetAt, throttle quota refresh to 3 min, cool down after a 429 (chat unaffected)
- **Usage logs always empty**: missing `await` on `getAdapter()` in `getRecentLogs` made `/api/usage/logs` & `/api/usage/request-logs` return nothing
- **Executors**: strip params unsupported by the provider/model (drops deprecated `temperature` for claude-opus-4 → Anthropic 400)
- **Translator**: derive deterministic tool_call ids for gemini/antigravity → OpenAI so function call/response pair correctly (fixes tool-pairing 400s)
- **Antigravity**: strip `optional` from tool schemas before sending to Gemini
- **Claude-to-OpenAI**: handle OpenAI-format responses in the non-streaming path (e.g. xiaomi-tokenplan)
- **Usage views**: show edited connection names consistently across Providers & Quota Tracker
- **Security**: hardened reverse-proxy local-access trust
- **Security**: SSRF hardening on web fetch
## Internal
- Large **open-sse / translator refactor** (~40 commits): unified provider/model registry (LiteLLM-style `models[]` + `kind` field, 100 co-located registry files), single-sourced media/OAuth/refresh/token URLs, registry-based dispatch for usage & token-refresh, DRY translator concerns (buildUsage, encodeDataUri, finishReasonMap, chunkBuilder, reasoningDelta…), ESM-safe registry init, large-file splits, dead-code removal, and golden/no-regression test gates
