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>
Expose max in the Codex thinking dropdown for gpt-5.6-sol only (maps to
xhigh on wire; live probe rejected ultra). Include custom/kilo models
when computing provider thinking options so manually added gpt-5.6-sol
contributes its max level.
Co-authored-by: Cursor <cursoragent@cursor.com>
Translator only unwrapped tool.function when both tool.type==="function"
and tool.function were truthy. Loose/legacy OpenAI clients emit the bare
{ function: { name, parameters } } shape (no parent type), which fell
through and forwarded name: undefined upstream, rejected by strict
Anthropic-compatible gateways (MiniMax M3) as (2013) invalid tool type.
Unwrap tool.function whenever present. Built-in tools stay pass-through.
Adds regression coverage for the 4 tool shapes. See #2435.
Co-authored-by: Cursor <cursoragent@cursor.com>
Claude Code sends reasoning_effort "max" (its top level); OpenAI enum caps
at "xhigh" and rejects "max" with HTTP 400 "max effort not support".
applyFormat case "openai" now clamps "max"->"xhigh" before assigning
body.reasoning_effort; other levels pass through unchanged.
Add regression test covering client output_config.effort, direct
reasoning_effort, passthrough of xhigh/high, and budget_tokens capping.
Co-authored-by: Cursor <cursoragent@cursor.com>
isPathLike rejected any line with a colon, so Windows absolute paths
(C:\Users\me\a.js) were never recognized and find dumps went uncompacted.
find.js also split only on "/", mis-grouping backslash paths.
- autodetect: treat drive-letter prefix (X:\ or X:/) as path-like before
the general colon rejection.
- find.js: split on the last "/" or "\" separator and normalize emitted
directory labels to forward slashes.
Co-authored-by: Cursor <cursoragent@cursor.com>
- map service_tier=fast to upstream priority; drop unsupported tiers
- normalize reasoning effort max to xhigh (codex-only)
- convert 200-SSE model-capacity errors into 503 so account fallback rotates
- keep normal SSE output intact after peeking
Co-authored-by: Cursor <cursoragent@cursor.com>
VolcEngine Ark caps the Kimi family at max_tokens <= 32768, but the
model's advertised ceiling is far higher (Kimi-K2.7-Code resolves to
maxOutput 262144), so clampToModelMaxOutput alone leaves it uncapped and
the request 400s. Add a Kimi-scoped rule with an explicit maxOutputCap of
32768, combined with the model ceiling via min(). Covers max_tokens,
max_completion_tokens, max_output_tokens.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
