Share one /api/models fetch via useModelCaps cache, mount ModelSelectModal
only when open, stop double fetchModelAliases on CLI tool cards, and resolve
provider icons through a session 404 cache with missing PNGs + loading=lazy.
Also include Claude Exa MCP toggle (claude-settings + ClaudeToolCard) that
was already in the working tree.
Co-authored-by: Cursor <cursoragent@cursor.com>
Bulk-add named auto-generated keys by paste-line index, blind to existing
connection names. The backend upserts apikey connections by exact name
(connectionsRepo), so a colliding generated name silently replaced an
existing key instead of inserting a new one.
Add a collision-aware planner (src/shared/utils/bulkAdd.js) that gap-fills
the smallest free "<base> <n>" against both existing connection names and
names assigned earlier in the same batch, so a generated name is never
reused and the backend always inserts. Applies to auto-named lines, custom
name|apiKey lines, and Cloudflare name|apiKey|accountId lines.
Wire the planner into AddApiKeyModal and pass existing connection names
from the provider detail page. Add unit tests covering gap-fill, custom
names, Cloudflare 3-part format, and robustness.
Switch baseUrl from coding-intl.dashscope.aliyuncs.com (Coding Plan keys
only) to dashscope-intl.aliyuncs.com/compatible-mode so ordinary DashScope
API keys authenticate. Path /v1/chat/completions and preserveCacheControl
quirk unchanged.
Fixes#2591
Reshape Kiro direct requests so resumed client sessions reuse Kiro's
cache-affinity fields instead of starting unrelated CodeWhisperer
conversations.
- keep conversationState.conversationId stable when the client sends an
explicit session id (x-session-id, session_id, conversation_id, Claude
Code session metadata)
- add a stable conversationState.agentContinuationId per Kiro session
- send conversationState.agentTaskType: "vibe" and agentMode: "vibe",
matching the normal Kiro CLI/KAS chat path
- move Kiro thinking instructions into Kiro-compatible systemPrompt /
additionalModelRequestFields instead of generic top-level thinking
- keep volatile timestamp context out of the top-level systemPrompt; it
remains only in user content fallback
- suppress additionalModelRequestFields for legacy 4.5-era Claude/Kiro
models that reject it, while defaulting future Claude/Kiro model ids
to supported
- preserve Kiro meteringEvent credit usage internally for accounting
without leaking provider-specific fields into OpenAI-compatible usage
- prevent unrelated headerless Kiro requests from sharing one
connection-wide continuation
- cap/evict continuation sessions so long-running processes do not grow
the continuation map unbounded
- treat generated headerless Kiro sessions as one-shot so they do not
evict real explicit-session continuations
- keep credit-only Kiro metering valid for internal persistence when
token metrics are unavailable
Add Grok Build to Dashboard → CLI Tools. Apply writes a [model.9router]
custom model to ~/.grok/config.toml and sets [models].default, routing
the xAI Grok TUI through 9Router. Reset removes the slot and restores
the previous default.
Add GPT-5.6 Sol/Terra/Luna and their synthetic thinking/agentic/
thinking-agentic variants to the Kiro static catalog with the observed
272k context window and credit multipliers (2.4/1.2/0.6), register MITM
mapping slots for the new base ids, and override runtime capabilities so
the GPT-5.6 family reports the 272k window instead of the generic GPT-5
profile.
Replace the overly-broad UPSTREAM_CONNECTION_RE regex (which matched all
provider IDs with UUID suffixes) with an x-9r-internal-models-fetch
header to detect cross-instance recursive /models fetches.
fetchCompatibleModelIds now sends the header when fetching upstream
/models; the GET handler detects it and skips dynamic fetching, breaking
the recursion loop while letting compatible providers (MLX, Ollama, vLLM)
list their models. Fixes#2626.
client_metadata is an OpenAI Responses API-specific field. When translating
openai-responses requests to openai (Chat Completions), it leaked through
to providers like NVIDIA, which rejected it with a 400 "Unsupported
parameter". Strip it in the Responses-specific cleanup block alongside
input, instructions, store, and reasoning.
GitHub Copilot's /chat/completions and /responses endpoints never surface
prompt-cache token counts for Claude models. Route Claude models (detected
by name pattern) to Copilot's Anthropic-native /v1/messages shim via a new
executeWithMessagesEndpoint(), translating OpenAI-shape requests to Claude
natively so cache_control gets injected and cached_tokens surface.
Also fixes translateRequest()'s internal _toolNameMap being sent upstream,
which made Anthropic's strict schema reject tool-call requests with a 400 —
now stripped and threaded through response state. Removes the now-dead
response_format Claude JSON-mode workaround.
Broaden strip rule from /claude-opus-4/i to /claude/i so temperature is
removed for every Claude model, not just opus-4. Fixes Anthropic 400 on
OpenAI-compatible routes. #1748
Add pxpipe as an experimental fifth Token Saver: Claude-format request
bodies above a configurable size threshold are rendered as dense PNGs
via the pxpipe-proxy library API (transformAnthropicMessages) before
dispatch, cutting estimated input tokens by ~35-60% on token-dense
contexts. Integration follows the Headroom pattern: applied to the final
body in chatCore just before dispatch, fail-open on any error/timeout.
Managed npm install into DATA_DIR/pxpipe, dynamic loader with per-version
cache-bust, JSONL event log with rotation, /api/pxpipe/* endpoints, Token
Saver card (marked experimental) + /dashboard/pxpipe page, and per-request
Activated/Skipped annotation in Request Details. Disabled by default.
Add round-robin/random proxy pool rotation for no-auth free providers
(e.g. OpenCode Free) to distribute load across all active pools and
avoid per-IP rate limits. Rotation strategy is selectable per provider
in NoAuthProxyCard and persisted to settings.providerStrategies.
- add Headroom extras status + install endpoints
- show Headroom version + code/ml extras in Token Saver UI
- fix Windows interpreter selection to read from env with headroom-ai
Bulk import now parses name|apiKey|accountId lines for Cloudflare AI and
forwards accountId via providerSpecificData, with a provider-specific
placeholder and format hint.
- Backup DB only on real SCHEMA_VERSION change, not every app version bump
- Kill idle MCP stdio bridge children to prevent orphan process leaks
- Add getDistinctProviders to avoid loading every row JSON blob (OOM fix)
- Update codex model list (gpt-5.6 sol/terra/luna, drop 5.3 codex variants)
- Reorder Claude default models (fable first)
Co-authored-by: Cursor <cursoragent@cursor.com>
- Switch dev default to Turbopack (5-14x faster compile); keep webpack as dev:webpack
- Tailwind v4 source() base so JIT scans identically under both bundlers
- Lazy-load @xyflow/react via next/dynamic to keep it out of the shared bundle
- optimizePackageImports for heavy barrel imports (xyflow, dnd-kit, material-symbols, marked)
- Replace blind setTimeout waits with TCP health-check (waitServerReady)
- Run checkForUpdate in parallel instead of blocking server spawn
- Background MITM/tunnel/cloudflared kills off the critical path
Co-authored-by: Cursor <cursoragent@cursor.com>
Only update an existing Codex OAuth row when both rows share the same
chatgptAccountId, so a second Codex login no longer overwrites the first
account's rotated token pair. Also fall back to
workspaceId || chatgptAccountId || accountId for the chatgpt-account-id header.
Write the standalone app bundle and MITM bundle to NINEROUTER_CLI_APP_DIR
when set, so staged deploys can build to a separate destination before
swapping. Default output stays at cli/app when the env var is unset.
Project conversationState history/currentMessage into OpenAI-style
messages for /v1/compress, then write compressed text back into the
original Kiro fields while preserving provider payload shape. Fail open
when the proxy returns malformed or reordered messages.
Co-authored-by: Cursor <cursoragent@cursor.com>
Gemini CLI requests with small max_tokens spend the whole output budget on
thoughts after reasoning_effort maps to thinkingConfig, returning blank
content or finish=length. Raise maxOutputTokens floors per thinking level/
budget (clamped to caps.maxOutput). Also emit toolConfig
functionCallingConfig.mode=VALIDATED for Gemini CLI tool requests to avoid
MALFORMED_FUNCTION_CALL.
Co-authored-by: Cursor <cursoragent@cursor.com>
decolua