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>
Match captured official Antigravity IDE traffic: cloudcode-pa host,
antigravity/ide/2.1.1 User-Agent, IDE-shaped agent requestId, and drop
router-only stream/usage headers plus the legacy double system prompt.
Co-authored-by: Cursor <cursoragent@cursor.com>
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>
Ark rejects max_tokens above 128000 for GLM-5.2. Add a config-driven STRIP_RULES entry that clamps max_tokens, max_completion_tokens and max_output_tokens down to the model maxOutput before the upstream call.
Co-authored-by: Cursor <cursoragent@cursor.com>
Add four shared Caveman prompt fragments (no invented abbreviations,
preserve user language, no self-reference, no decoration) across all six
levels, and remove ULTRA contradictions around abbreviations/arrow
shorthand. Adds regression tests for the prompt rules.
Co-authored-by: Cursor <cursoragent@cursor.com>
Map role="developer" messages to top-level instructions alongside
role="system" in openaiToOpenAIResponsesRequest. Previously developer
messages matched no branch and were silently dropped from the Responses
request, losing GPT-5/Codex system-level prompts.
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>
Top-level guide for Claude Code / AI coding agents working in this repo,
complementing docs/ARCHITECTURE.md and open-sse/AGENTS.md.
Docs-only: PR's incidental code changes were dropped as they reverted #2366.
Co-Authored-By: Mohammed Faheem <mohammed.faheem@adbsafegate.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
On the translated OpenAI->Claude path, adjustMaxTokens capped max_tokens
before applyThinking set thinking.budget_tokens, so max-effort budget
(128000) could exceed a 64k-clamped max_tokens -> Anthropic 400.
prepareClaudeRequest now reconciles after the budget is known: prefer
raising max_tokens, only shrink budget when it meets/exceeds the ceiling.
Also lift the global 64000 cap: the ceiling is now the model's real
maxOutput, so high-output models (fable/mythos, opus-4.8/sonnet-4.6) get
their full budget. adjustMaxTokens gains an optional ceiling arg (default
unchanged, callers untouched); openai-to-claude passes the model maxOutput.
Native Claude Code passthrough is unaffected.
Co-Authored-By: Claude <noreply@anthropic.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
- Pass system prompt via native systemInstruction field (+ <instructions> fallback)
so Claude models stop treating it as info-only <system-reminder>
- Add Opus 4.5/4.7/4.8 (base/thinking/agentic/thinking+agentic) to Kiro registry
- normalizeModelId(): dash->dot version separator, scoped to Kiro provider only
- Replace <system-reminder> with <instructions> in claude-to-openai/openai-to-kiro
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>
handleStreamingResponse and buildOnStreamComplete each generated their
own streamDetailId for what should be one logical record — the
placeholder row (0 tokens) and the final row (real usage) never shared
an id, so the DB's ON CONFLICT(id) upsert never merged them, leaving a
permanent 0-token stub for every streaming request.
Share the id from buildOnStreamComplete with handleStreamingResponse
so both writes hit the same row.
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>
Combo mixes models, so non-Claude thinking signatures leak into
conversation history. Native passthrough forwarded them verbatim and
Anthropic rejected the request. Validate signatures and drop invalid
thinking blocks, re-inserting a placeholder when tool_use requires one.
Co-authored-by: Cursor <cursoragent@cursor.com>
- Updated capabilities for NVIDIA models to enforce OpenAI-compatible reasoning formats.
- Added new models: MiniMax M3, GLM 5.2, DeepSeek V4 Pro, DeepSeek V4 Flash, Kimi K2.6, and Nemotron 3 Ultra to the NVIDIA registry.
This enhances the provider's functionality and aligns with OpenAI standards.
IAM Identity Center (authMethod=idc) tokens failed every request with 403
"bearer token invalid". Treat idc like api_key/external_idp:
- executors/kiro.js: route idc to *.amazonaws.com CodeWhisperer surface,
region-aware from credentials.region instead of hardcoded us-east-1.
- openai-to-kiro.js / claude-to-kiro.js: send resolved profileArn or empty
for idc/external_idp, never the shared builder-id placeholder ARN.
Co-authored-by: Cursor <cursoragent@cursor.com>
Filter empty text blocks from thoughtSignature-only parts, preserve
tool_calls when functionResponse and functionCall coexist in the same
content, and skip empty regular text parts before they reach Claude.
Co-authored-by: Cursor <cursoragent@cursor.com>
Clients echo full message history each turn including reasoning_content,
which the Kimchi OpenAI gateway counts as input tokens. Multi-turn convos
balloon to 100k+ tokens and the model returns empty content.
KimchiExecutor.transformRequest now strips reasoning_content from assistant
messages when it exceeds an 8-char threshold, preserving the 1-char
placeholder injectReasoningContent sets and keeping content intact.
Co-authored-by: Cursor <cursoragent@cursor.com>
CodeBuddy CN includes "tool_calls": [] in every SSE streaming delta.
@ai-sdk/openai-compatible checks delta.tool_calls != null — an empty
array passes ([] != null is true in JS), triggering premature
reasoning-end on every reasoning chunk (0/1ms durations in OpenCode).
Strip empty tool_calls arrays in passthrough before hasValuableContent.
Zero side-effect: real tool_calls always have at least one element.
Closes#2176
Co-authored-by: Cursor <cursoragent@cursor.com>
Gemini response translation wrote OpenAI-shaped bookkeeping into the
shared state.toolCalls map, which the downstream openai-to-claude
translator uses for Claude block metadata. That pre-population skipped
blockIndex creation, so Anthropic input_json_delta events lost index.
Track Gemini function calls via state.geminiToolCallCount instead,
leaving state.toolCalls clean for the Claude translator.
Closes#2218
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>
Treat response.done as a terminal OpenAI Responses stream event so
passthrough streams ending with response.done are not flagged incomplete
and no synthetic response.failed is emitted. Restore the data: [DONE]
sentinel for same-format Responses passthrough streams.
Co-authored-by: Cursor <cursoragent@cursor.com>
Guard openai-responses compression: skip Headroom when body.input
contains non-message items (function_call, function_call_output,
reasoning) to preserve the Responses contract instead of collapsing
them into chat messages.
Co-authored-by: Cursor <cursoragent@cursor.com>
Claude Code chèn role:system cuối messages[], trước đây bị map thành assistant
khiến hội thoại không kết thúc bằng user → provider OpenAI-compat (LiteLLM)
dịch ngược Anthropic trả 400 "assistant message prefill". Map system -> user
và wrap <system-reminder> để giữ ngữ nghĩa instruction.
Co-authored-by: Cursor <cursoragent@cursor.com>
Add qwen omni (audio/video input), qwen3.5/3.6/3.7 (native vision/video),
and mark qwen coder & max as text-only reasoning models.
Co-authored-by: Cursor <cursoragent@cursor.com>
Merge adjacent same-role blocks and strip empty parts before sending to
Gemini, avoiding 400 INVALID_ARGUMENT on consecutive same-role messages.
Co-authored-by: Cursor <cursoragent@cursor.com>
Opt-in quirk preserveCacheControl keeps cache_control on content blocks
for alicode/alicode-intl, enabling DashScope prompt caching. signature
is always stripped; all other providers unchanged.
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>
Backfill DEFAULT_THINKING_AG_SIGNATURE onto functionCall parts missing it
(client history replay) and on Claude tool_use blocks, fixing 400
INVALID_ARGUMENT from Gemini-family APIs. Suppress the OpenAI-style
data: [DONE] sentinel for antigravity/gemini/vertex to avoid parser crashes.
Fixes#2193.
Co-authored-by: Cursor <cursoragent@cursor.com>
Gemini rejects the non-standard 'deprecated' keyword in nested tool
schemas with INVALID_ARGUMENT (400). Add it to UNSUPPORTED_SCHEMA_CONSTRAINTS
alongside 'optional' so it gets stripped during translation.
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.
CodeWhisperer leaks literal <thinking> blocks into assistantResponseEvent,
duplicating reasoning already routed via reasoningContentEvent. Track
inThinking state to strip these tags during SSE transform, handling split
chunks across tag boundaries.
Co-authored-by: Cursor <cursoragent@cursor.com>
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>
Set process DPI awareness (Per-Monitor V2 with fallbacks) and enable
WinForms visual styles before creating the tray NotifyIcon, so the
Windows context menu renders sharply on DPI-scaled displays.
Closes#2161
Co-authored-by: Cursor <cursoragent@cursor.com>
