All conflicts were in frontend files where main had beginner-mode features
(BeginnerGuideCards, Claw402 balance alerts, mode switcher, actionable error
helpers) that dev intentionally simplified. Kept dev's version in every case.
Removed unused navigate import in SettingsPage after conflict resolution.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(payment): add new DeepSeek V4 models to claw402 endpoints and pricing
- Introduced "deepseek-v4-flash" and "deepseek-v4-pro" endpoints in claw402ModelEndpoints.
- Updated modelPrices to include pricing for the new DeepSeek V4 models.
- Added model constants for the new DeepSeek V4 models in the trader component.
* refactor(claw402): update default model to deepseek-v4-flash across components
- Changed the default model for Claw402 from "glm-5" to "deepseek-v4-flash" in multiple files, including the AI model handler and onboarding logic.
- Updated model constants and configurations in the trader component to reflect the new default model.
- Enhanced the model configuration modal to accommodate the new default model setting.
---------
Co-authored-by: Dean <afei.wuhao@gmail.com>
* feat(store): prevent deletion of active strategies and update translations (#1461)
Co-authored-by: Dean <afei.wuhao@gmail.com>
* fix: allow model switching without re-entering wallet key
Users with existing wallets could not switch AI models because the
"Start Trading" button required a valid private key even when one was
already configured. Now the button is enabled when hasExistingWallet
is true, and handleSubmit passes an empty key so the backend preserves
the existing key.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* refactor: replace window.location with useNavigate for routing in auth components (#1470)
Co-authored-by: Dean <afei.wuhao@gmail.com>
* feat(trader): implement margin mode handling for order and leverage settings
* refactor(trader): update SetMarginMode to avoid legacy endpoint and improve logging
* feat(api): enhance strategy handling by integrating claw402 wallet key validation
Added validation for the claw402 model's wallet key during strategy test runs. If the selected AI model is claw402, the server now checks for a valid wallet key and returns appropriate error messages if it's missing or if the model fails to load. This ensures better error handling and user feedback when working with AI models.
* refactor(api): streamline claw402 wallet key retrieval and error handling
Refactored the strategy handling logic to encapsulate claw402 wallet key retrieval in a new method, `resolveStrategyDataWalletKey`. This improves code readability and maintains consistent error handling for missing or invalid wallet keys during strategy test runs. The changes enhance the overall robustness of the AI model integration.
* feat(trader): add claw402 wallet key resolution for trader configuration
Implemented a new method, `resolveTraderDataWalletKey`, to retrieve the claw402 wallet key based on the selected AI model and user ID. This enhancement allows for better integration of the claw402 model within the trader configuration, ensuring that the correct wallet key is used for trading operations. The `AutoTraderConfig` struct has been updated to include the new `Claw402WalletKey` field, improving the overall handling of wallet keys in the trading process.
* feat(claw402): preflight USDC balance before AI calls (#1479)
* chore: ignore nofx-server build artifact
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(claw402): preflight USDC balance before AI calls
Short-circuit claw402 Call/CallWithRequestFull when the wallet balance
can't cover the estimated cost of the call, surfacing ErrInsufficientFunds
instead of letting x402 fail mid-flight after the sign step.
- wallet: cached balance lookup (30s TTL, per-address mutex) to avoid
hammering the Base RPC; separate error-returning and display-only APIs
so callers can distinguish zero balance from an unreachable RPC.
- claw402: 1.5× safety multiplier on the flat per-call estimate, 4.0×
for reasoner models whose chain-of-thought cost can blow past the
flat rate. Fail-open on RPC errors — x402 still gates actually-empty
wallets, and we prefer availability over extra strictness.
- shortAddr redacts the wallet in error strings to avoid leaking the
full address into telemetry bundles.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix(telemetry): report token usage for SSE streaming paths (#1475)
* fix(telemetry): report token usage for SSE streaming paths
ParseSSEStream already parsed the usage block from SSE chunks but only
printed it, so claw402 streaming calls (and native streaming) never
fired TokenUsageCallback. GA4 therefore undercounted AI usage on the
streaming path.
Return the parsed usage from ParseSSEStream and have both callers fire
the callback with their own Provider/Model.
* chore: drop leftover debug Printf in ParseSSEStream
Telemetry is now wired via TokenUsageCallback, so the Printf is
redundant noise in the stream path.
* fix(gemini): update default model to gemini-3.1-pro
Google discontinued gemini-3-pro-preview on 2026-03-26 and directs all
callers to gemini-3.1-pro / gemini-3.1-pro-preview. Users on their own
API key were getting errors from the native Gemini endpoint because the
provider default pointed at the retired ID. Claw402 was unaffected
because its route map already used gemini-3.1-pro.
Align both the native provider default and the handler's preset list
with gemini-3.1-pro so every code path sends a live model ID.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: extract ResolveClaw402WalletKey to store layer and expand OKX margin mode tests
- Move duplicated claw402 wallet resolution logic into store.AIModelStore.ResolveClaw402WalletKey
- api/strategy.go and manager/trader_manager.go now delegate to the shared method
- Add detailed doc comment on OKX SetMarginMode explaining the local-state-only approach
and why the legacy /api/v5/account/set-isolated-mode endpoint is not called
- Add 3 new test cases: cross mode leverage, OpenShort tdMode, SetTakeProfit tdMode
* fix(auth): prevent SetupPage remount from wiping freshly-set auth token (#1481)
After #1470 moved routing into react-router, SetupPage is rendered at two
different tree positions (top-level guard + /setup Route). When register
success flushSync-sets `user`, the top-level guard stops matching and the
Route-level SetupPage mounts as a new instance, re-running its cleanup
useEffect and removing the auth_token that handlePostAuthSuccess just wrote.
Subsequent requests 401 and bounce the user back to /login.
Redirect /setup to /welcome when user is already set so SetupPage is never
re-mounted during the auth transition.
* fix(wallet): handle JSON-RPC null error field in balance query
Some RPC implementations return explicit "error": null on success.
json.RawMessage deserializes this as the 4-byte literal "null", so
len() > 0 was true, causing every balance query to fail with
"rpc error: null". Skip the null literal to avoid false positives.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: deanokk <wuhao@vergex.trade>
Co-authored-by: Dean <afei.wuhao@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: root <root@localhost.localdomain>
- Move duplicated claw402 wallet resolution logic into store.AIModelStore.ResolveClaw402WalletKey
- api/strategy.go and manager/trader_manager.go now delegate to the shared method
- Add detailed doc comment on OKX SetMarginMode explaining the local-state-only approach
and why the legacy /api/v5/account/set-isolated-mode endpoint is not called
- Add 3 new test cases: cross mode leverage, OpenShort tdMode, SetTakeProfit tdMode
Google discontinued gemini-3-pro-preview on 2026-03-26 and directs all
callers to gemini-3.1-pro / gemini-3.1-pro-preview. Users on their own
API key were getting errors from the native Gemini endpoint because the
provider default pointed at the retired ID. Claw402 was unaffected
because its route map already used gemini-3.1-pro.
Align both the native provider default and the handler's preset list
with gemini-3.1-pro so every code path sends a live model ID.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Refactored the strategy handling logic to encapsulate claw402 wallet key retrieval in a new method, `resolveStrategyDataWalletKey`. This improves code readability and maintains consistent error handling for missing or invalid wallet keys during strategy test runs. The changes enhance the overall robustness of the AI model integration.
Added validation for the claw402 model's wallet key during strategy test runs. If the selected AI model is claw402, the server now checks for a valid wallet key and returns appropriate error messages if it's missing or if the model fails to load. This ensures better error handling and user feedback when working with AI models.
Add account reset functionality for users who forgot their login credentials.
The reset clears authentication data while preserving wallet private keys and
exchange configs, which are automatically adopted by the new account on
re-registration to prevent fund loss.
- Add POST /api/reset-account endpoint
- Add "Forgot account?" button on login page (zh/en/id)
- Orphan ai_models and exchanges are re-assigned to new user on register
- Onboarding reuses existing claw402 wallet instead of generating new one
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: implement exchange account state management and UI updates
- Added functionality to invalidate exchange account state cache on exchange config updates, creation, and deletion.
- Introduced new API endpoint to fetch exchange account states.
- Updated frontend components to display exchange account states, including status and balance information.
- Enhanced user experience by refreshing exchange account states after relevant actions.
* feat: enhance trader creation readiness in AITradersPage and BeginnerGuideCards
---------
Co-authored-by: Dean <afei.wuhao@gmail.com>
- Pass `lang` from register request body to createDefaultStrategies
- Support zh/en/id locales for strategy names and descriptions
- Wrap strategy creation in a transaction to prevent partial writes
- Frontend sends current UI language in register request body
- Strategy list UI: 2-line clamp, unselected border, larger spacing, smaller font for non-zh
* feat: enforce strategy limits to prevent token overflow
* fix: tune token limits after real-world testing
- Relax kline max 20→30, timeframes 3→4 (tested ~41K tokens, safe under 131K)
- Restore ranking limits to original [5,10,15,20] options (only ~1.5K token impact)
- Add static coins limit (max 3) with toast notification
- Add timeframe limit toast when exceeding 4
- Log SSE token usage (prompt/completion/total) from API response
- Fix nil logger crash in claw402 data client (engine.go)
* feat: add token estimation functionality for strategy configurations
* feat: add discard changes button in Strategy Studio for unsaved modifications
* feat: retain selected strategy after saving in Strategy Studio
* feat: enhance strategy display in Strategy Studio with improved layout and sorting of token limits
* refactor: improve layout and styling of stats display in CompetitionPage
* refactor: replace select elements with NofxSelect component for improved consistency in strategy configuration forms
* style: update NofxSelect component to use smaller text size for improved readability
* feat: implement token overflow handling in strategy updates and UI
---------
Co-authored-by: Dean <afei.wuhao@gmail.com>
Remove the entire AI Debate Arena module (~5,300 lines) to simplify
the codebase. This removes the multi-AI debate trading decision system
including backend engine, API handlers, database store, frontend page,
navigation, translations, and documentation references.
* feat(telegram): add AI agent bot with streaming and account context
- Add Telegram bot with long-polling and AI agent loop (api_call tool)
- SSE streaming with real-time message editing and ⏳ placeholder
- Account state injection at conversation start (models, exchanges,
strategies, traders, per-trader PnL and statistics)
- Lane semaphore per chat serializes concurrent messages (60s timeout)
- Idle timeout watchdog (60s) prevents hung streaming connections
- Look-ahead buffer prevents partial <api_call> tag leaking to user
- Fix PUT /strategies/:id to merge config (read-then-merge pattern)
- Add route registry with full API schema for LLM documentation
- Add TelegramConfig store and Web UI config modal
- Add GetAnyEnabled to AIModel store for bot LLM client selection
* fix(telegram): eliminate narration, add full-setup workflow and tests
- Rewrite NO NARRATION rule: response is EITHER api_call tag alone OR
final text reply — no text before api_call under any circumstances
- Ban all narration patterns: 现在我将/好的/正在/I will/Let me etc.
- Add 'create strategy + create trader + start' full setup workflow
- Add 12 automated tests covering:
- No narration leaking to user (5 narration variants tested)
- api_call tag never leaks to user
- Full setup workflow: POST strategy → verify → POST trader → start
- Start existing trader workflow
- Max iterations safety, tag stripping, parser edge cases
* refactor(agent): replace XML api_call with native function calling
Migrate the Telegram bot agent from an XML tag hack (<api_call>) to
OpenAI-native function calling via CallWithRequestFull.
Key changes:
- mcp/interface.go: add parseMCPResponseFull to clientHooks interface
- mcp/client.go: route callWithRequestFull through hooks for overridability
- mcp/claude_client.go: override parseMCPResponseFull for Claude response
format (tool_use blocks instead of choices[].message.tool_calls)
- telegram/agent/agent.go: rewrite Run() to use CallWithRequestFull;
define api_request tool with JSON Schema; implement tool-call loop
with role="tool" result messages; remove XML parsing entirely
- telegram/agent/apicall.go: remove parseAPICall (dead code)
- telegram/agent/prompt.go: simplify — remove XML format instructions,
replace with concise api_request tool usage instructions
- telegram/agent/agent_test.go: rebuild all tests using LLMResponse
objects; add TestNarrationStructurallyImpossible, TestOnChunkCalledWithFinalReply,
TestToolCallIDPropagated; remove XML-specific tests
Architecture advantage: with native function calling, the LLM returns
EITHER ToolCalls OR Content — never both. Narration is now structurally
impossible at the protocol level, not just enforced by prompt rules.
All 11 agent tests pass. mcp package tests pass.
* refactor(mcp): route buildRequestBodyFromRequest through hooks + full Anthropic format
Problem: callWithRequest/Full/Stream all called client.buildRequestBodyFromRequest
directly (not via hooks), so ClaudeClient could never override it. This meant
tool calling sent OpenAI format to Anthropic (wrong field names, wrong roles).
Changes:
mcp/interface.go
- Add buildRequestBodyFromRequest(*Request) map[string]any to clientHooks
- Improve comments: document what each hook group does and why
mcp/client.go
- All three paths (callWithRequest, callWithRequestFull, CallWithRequestStream)
now call client.hooks.buildRequestBodyFromRequest — ClaudeClient picks up
mcp/claude_client.go
- Full rewrite with format comparison table in package doc
- buildRequestBodyFromRequest: produces correct Anthropic wire format
* system prompt → top-level "system" field
* tools: parameters → input_schema, no "type:function" wrapper
* tool_choice "auto" → {"type":"auto"} object
* assistant tool calls → content[{type:tool_use, id, name, input}]
* role=tool results → role=user content[{type:tool_result,...}]
* consecutive tool results merged into single user turn
- convertMessagesToAnthropic: handles all three message types
- parseMCPResponseFull: extracts text + tool_use blocks
- parseMCPResponse: delegates to parseMCPResponseFull
All mcp and agent tests pass.
* fix(telegram): fix claude client dispatch + strategy creation workflow
- telegram/bot.go: clientForProvider now returns NewClaudeClient() for
'claude' provider (was incorrectly falling back to DeepSeekClient which
uses OpenAI wire format, breaking Anthropic API calls)
- api/server.go: fix scan_interval_minutes schema default (3, not 60);
POST /api/strategies now clearly states config is OPTIONAL with complete
working defaults; POST /api/traders removes redundant GET workflow note
- telegram/agent/prompt.go: simplify strategy creation — just POST {name}
without config (backend applies full working defaults automatically);
only include config when user requests custom settings
* test(mcp): add ClaudeClient wire format tests
Tests cover all Anthropic-specific format conversions:
- system prompt lifted to top-level field
- tools use input_schema (not parameters)
- tool_choice is object {type:auto} not string
- assistant tool calls → content[{type:tool_use}]
- consecutive tool results merged into single user turn
- parseMCPResponseFull: text, tool_use, and error cases
- x-api-key header (not Authorization: Bearer)
- /messages endpoint URL
* fix(telegram): clientForProvider returns correct client for all 7 providers
Previously qwen/kimi/grok/gemini all fell back to DeepSeekClient.
Each provider now gets its own dedicated client with correct default
base URL and model. All 7 providers now fully supported:
openai, deepseek, claude, qwen, kimi, grok, gemini
* fix(telegram): newLLMClient uses bound user's model, not any user's model
GetAnyEnabled() searched across all users in DB — if user B has an
enabled model, bot could use their API key while acting as user A.
Now uses GetDefault(botUserID) which only looks up the bound user's
enabled model, matching the same user scope as all API calls.
* fix(auth): single-user deployment by default, no open registration
Registration logic redesigned:
- Empty DB (first-time setup): registration always open, no config needed
- After first user exists: registration closed by default
- Multi-user opt-in: set REGISTRATION_ENABLED=true + MAX_USERS=N in .env
Config defaults changed:
- RegistrationEnabled: true → false (closed after first user)
- MaxUsers: 10 → 1 (single-user deployment default)
This eliminates the confusion of multiple users appearing in a personal
deployment where Telegram is bound to a single admin account.
* feat(solo): beginner-friendly onboarding — smart setup guide + direct config commands
start.sh:
- Interactive Telegram Bot Token prompt on first run
- Token format validation (must match 12345:ABC... pattern)
- Friendly step-by-step startup instructions after launch
telegram/bot.go:
- /start now shows context-aware setup guide based on actual config state:
- No AI model → explains how to configure, lists all providers
- AI model OK but no exchange → guides to configure exchange via chat
- All configured → full capabilities welcome message
- New: direct setup commands ('配置 deepseek sk-xxx') bypass LLM entirely
so AI model can be configured even before any model exists (bootstrap fix)
- All messages now in Chinese (匹配用户语言)
telegram/agent/prompt.go:
- Added first-time setup detection section
- Agent told to never ask user to visit web UI — everything via chat
* feat(i18n): bilingual EN/ZH setup guide with language selection
store/telegram_config.go:
- Add Language field to TelegramConfig (persisted in DB)
- Add SetLanguage(lang) and GetLanguage() methods
- Default language: English (en)
telegram/bot.go:
- First /start triggers language selection (1=English, 2=中文)
- /lang command to change language at any time
- awaitingLang state machine handles language choice before any other input
- buildSetupGuide() now fully bilingual (EN/ZH), context-aware:
Step 1: configure AI model (no model yet)
Step 2: configure exchange (model OK, no exchange)
Ready: show full capabilities
- tryHandleSetupCommand() bilingual: 'configure/配置 <provider> <key>'
- helpMessage(lang) fully bilingual
- All error/status messages bilingual
Default: English. isLangDefault() detects whether user has explicitly
chosen a language vs falling back to the 'en' default.
* fix(telegram): use Markdown rendering + simplify language selection condition
- sendMarkdownMsg() helper: sends with ParseMode=Markdown, falls back to plain text
- All formatted messages (langSelectionMsg, buildSetupGuide, helpMessage) now render
bold text and code blocks correctly in Telegram
- Simplify /start language check: isLangDefault(st) alone is sufficient
(lang == 'en' && isLangDefault was redundant — GetLanguage returns 'en' when empty)
* fix(start.sh): translate all user-facing text to English
Entire script was in Chinese. Now English-first throughout:
- startup banner, prompts, success/error messages
- setup_telegram(): English instructions and validation messages
- start(): English next-steps after launch
- stop/restart/clean/update/regenerate-keys/show_help: all English
* fix(telegram): remove 'default' user fallback — resolve user dynamically
- botUserID no longer captured once at startup (was 'default' if no user yet)
- resolveBotUser() reads first registered user from DB on demand:
* called on every /start (handles: registered after bot launch)
* called before every AI message (handles mid-session registration)
- If no user registered: clear English error 'No account found. Please register on the web UI first'
- start.sh: fix set_env_var appending without newline (token was concatenated to prev line)
* refactor(telegram): clean onboarding — web UI for setup, Telegram for operations
- /start shows clean status: 'setup required → open web UI' or 'ready → examples'
- Removed tryHandleSetupCommand (no more CLI-style 'configure deepseek sk-xxx')
- Removed automatic language selection on /start (use /lang anytime instead)
- newLLMClient returns nil when no model → clear guard, not fallback
- statusMsg() replaces buildSetupGuide(): two states only (missing config / ready)
- Bot is now purely an operations interface; config lives in the web UI
* refactor: single-user web-based setup — replace env config with Settings UI
Move from multi-user env-var config to single-user web-first architecture:
- Add SetupPage for first-time initialization (replaces /register)
- Add SettingsPage for AI models, exchanges, Telegram, and password management
- Enrich all API route schemas with exact ID usage documentation
- Add PUT /user/password endpoint for in-app password changes
- Remove REGISTRATION_ENABLED, MAX_USERS, TELEGRAM_BOT_TOKEN from env config
- Simplify LoginPage design, remove admin mode and registration links
- Telegram bot now resolves user email for identity display
- start.sh no longer runs interactive Telegram setup
* feat: add blockRun (x402 USDC) support to all AI model consumers
- telegram/bot.go: add blockrun-base, blockrun-sol, minimax to
clientForProvider; fix newLLMClient to prefer TelegramConfig.ModelID
over GetDefault; log USDC payment provider usage
- debate/engine.go: add blockrun-base, blockrun-sol to InitializeClients
- api/strategy.go: add blockrun-base, blockrun-sol to runRealAITest
- backtest/ai_client.go: add blockrun-base, blockrun-sol to configureMCPClient
* feat: add Claw402 (claw402.ai) x402 USDC payment provider
Add Claw402Client for claw402.ai's x402 micropayment gateway (Base USDC).
Supports 15+ AI models (GPT-5.4, Claude Opus, DeepSeek, Qwen, Grok, etc.)
with per-model endpoint routing.
- mcp/claw402.go: new client with model→endpoint mapping, x402 v2 payment flow
- mcp/blockrun_base.go: extract shared signX402Payment() for reuse
- Register "claw402" provider in all 6 consumer switch statements:
api/server.go, api/strategy.go, trader/auto_trader.go,
telegram/bot.go, debate/engine.go, backtest/ai_client.go
* feat: redesign Claw402 model config UI — friendly wallet setup, USDC guide, official logo, nginx no-cache for index.html
* refactor: centralize x402 payment flow into shared mcp/x402.go
Extract duplicated doRequestWithPayment/call/CallWithRequestFull/buildRequest/
setAuthHeader (~165 lines x3) into shared helpers in mcp/x402.go. Consolidate
shared types (x402v2PaymentRequired, x402AcceptOption, x402Resource) and remove
duplicate Solana types. Fix validAfter to 0 (official SDK standard), drain 402
body before retry, log Payment-Response tx hash, check Payment-Required before
X-Payment-Required.
* fix: stop PR template bot from overwriting user-written descriptions
The pr-template-suggester workflow was triggered on opened/edited/synchronize
events and forcefully replaced the PR body with a template when body < 100 chars.
This caused user-written descriptions to be overwritten.
Replace with a lightweight labeler (OpenClaw-style) that:
- Only adds labels (backend/frontend/docs, size: XS/S/M/L/XL)
- Never modifies the PR body
- Simplified unified PR template at .github/pull_request_template.md
* chore: simplify PR template (OpenClaw-style)
Integrates BlockRun (blockrun.ai) as a new AI provider option via x402
micropayment protocol, allowing users to access top AI models with USDC
without requiring individual API keys.
- Add BlockRun Base (EVM) and Solana wallet providers to model selector
- Implement x402 v2 EIP-712 payment signing for Base (mcp/blockrun_base.go)
- Implement x402 v2 SPL TransferChecked signing for Solana (mcp/blockrun_sol.go)
- Wire blockrun-base and blockrun-sol into trader factory (auto_trader.go)
- Register both providers in supported models API (server.go)
- Add BlockRun card UI with wallet key input in Step 0/1 of model config modal
- Add BlockRun SVG icon and ModelIcons support
- Add setup guides for Base and Solana wallet configuration (docs/)
- Available flagship models: GPT-5.4, Claude Opus 4.6, Gemini 3.1 Pro,
Grok 3, DeepSeek Chat, MiniMax M2.5
Apply security.ValidateURL() to custom_api_url in PUT /api/models before
storing — blocks private IPs, cloud metadata endpoints, and localhost.
Replace plain http.Client in mcp/config.go with security.SafeHTTPClient()
for defense-in-depth (DialContext blocks private IPs, CheckRedirect
validates targets). Add SSRF warning to WithHTTPClient() docs.
Add MiniMax as a new AI model provider with OpenAI-compatible API.
Supported models:
- MiniMax-M2.5 (default) - Peak Performance, Ultimate Value
- MiniMax-M2.5-highspeed - Same performance, faster and more agile
Changes:
- Add MiniMax client (mcp/minimax_client.go) with OpenAI-compatible API
- Add comprehensive unit tests (mcp/minimax_client_test.go)
- Add WithMiniMaxConfig option (mcp/options.go)
- Register MiniMax provider in trader, debate engine, backtest, and API
- Add MiniMax to frontend provider config and model icons
- Add MiniMax SVG icon
API Base URL: https://api.minimax.io/v1
This PR adds support for Hyperliquid's Unified Account mode where Spot USDC
balance can be used as collateral for Perpetual trading.
Changes:
- Add HyperliquidUnifiedAcct field to Exchange config (default: true)
- Update HyperliquidTrader to support unified account mode
- When enabled, Spot USDC balance is added to available trading balance
- Update API request/response structs for unified account toggle
- Update trader config propagation from exchange config
This aligns with Hyperliquid's roadmap to make Unified Account the default.
Gate.io Integration:
- Add Gate trader with full Trader interface implementation
- Add order_sync.go for background trade synchronization
- Fix quantity display (convert contracts to actual tokens via quanto_multiplier)
- Fix fill price return in OpenLong/OpenShort/CloseLong/CloseShort
- Add Gate-specific CoinAnk K-line data source support
- Add Gate to supported exchanges in frontend and backend
- Add Gate/KuCoin logo SVG icons
Trader Package Refactoring:
- Move exchange-specific code into subdirectories (binance/, bybit/, okx/, bitget/, hyperliquid/, aster/, lighter/, gate/)
- Create types/ package for shared types to avoid circular dependencies
- Move TraderTestSuite to trader/testutil package to avoid import cycles
- Update market.GetWithExchange to support exchange-specific data
* feat: add AI grid trading and market regime classification
- Add GridTrader interface with PlaceLimitOrder, CancelOrder, GetOrderBook
- Implement GridTrader for all exchanges (Binance, Bybit, OKX, Bitget, Hyperliquid, Aster, Lighter)
- Add grid engine with ATR-based boundary calculation and fund distribution
- Add market regime classification documents (Chinese/English)
- Add GridConfigEditor component for frontend configuration
* fix: implement GetOpenOrders for Lighter exchange
* debug: add logging for Lighter GetActiveOrders API call
* fix: correct Lighter API response parsing for GetOpenOrders
- Changed response field from 'data' to 'orders' to match Lighter API
- Updated OrderResponse struct to match Lighter's actual field names
- Fixed field types: price/quantity as strings, is_ask for side
* feat: implement GetOpenOrders for Aster, OKX, Bitget exchanges
- Aster: uses /fapi/v3/openOrders endpoint
- OKX: uses /api/v5/trade/orders-pending and orders-algo-pending
- Bitget: uses /api/v2/mix/order/orders-pending and orders-plan-pending
* fix: address code review issues for GetOpenOrders
- Add error logging for OKX/Bitget API failures (was silently swallowed)
- Fix Lighter position side logic to handle reduce-only orders
- Change verbose debug logs from Infof to Debugf level
* fix: provide FromAccountIndex and ApiKeyIndex for Lighter nonce auto-fetch
Root cause: SDK requires these fields to fetch nonce from API, otherwise nonce gets cached/stuck
* fix: use auth query parameter instead of Authorization header for Lighter API
* test: add Lighter API authentication tests and diagnostic tools
* fix(grid): add leverage setting before order placement
CRITICAL BUG FIX:
- Call SetLeverage() in GridTraderAdapter.PlaceLimitOrder()
- Set leverage during grid initialization
- Log leverage setting results
* fix(grid): prevent CancelOrder from canceling all orders
CRITICAL BUG FIX:
- CancelOrder no longer calls CancelAllOrders
- Try exchange-specific CancelOrder if available
- Return error if individual cancellation not supported
* fix(grid): add total position value limit check
CRITICAL: Prevent excessive position accumulation
- New checkTotalPositionLimit() function
- Checks current + pending + new order value
- Rejects orders that would exceed TotalInvestment x Leverage
- Logs clear error messages when limit exceeded
* feat(grid): implement stop loss execution
CRITICAL: Add code-level stop loss protection
- New checkAndExecuteStopLoss() function
- Checks each filled level against StopLossPct
- Automatically closes positions exceeding stop loss
- Called during every grid state sync
* feat(grid): add breakout detection and auto-pause
CRITICAL: Detect price breakout from grid range
- New checkBreakout() function to detect upper/lower breakouts
- Auto-pause grid on significant breakout (>2%)
- Cancel all orders when breakout detected
- Prevent continued losses in trending market
- Minor breakouts (1-2%) logged for AI consideration
* feat(grid): enforce max drawdown limit with emergency exit
CRITICAL: Add drawdown protection
- New checkMaxDrawdown() function tracks peak equity
- emergencyExit() closes all positions and cancels orders
- Auto-pause grid when MaxDrawdownPct exceeded
- Protect capital from excessive losses
* feat(grid): enforce daily loss limit
- Add checkDailyLossLimit() function to check if daily loss exceeds limit
- Track daily PnL with auto-reset at midnight
- Pause grid when DailyLossLimitPct exceeded
- Add updateDailyPnL() helper for realized PnL tracking
- Prevent excessive single-day losses
* fix(grid): update daily PnL when stop loss is executed
The updateDailyPnL() function was added but never called, leaving
DailyPnL always at 0 and preventing daily loss limit checks from
triggering.
This fix updates DailyPnL and TotalProfit directly in checkAndExecuteStopLoss()
when a stop loss is executed. We update directly rather than calling
updateDailyPnL() because the mutex is already held in that function.
* feat(grid): add automatic grid adjustment
- New checkGridSkew() detects imbalanced grid
- autoAdjustGrid() reinitializes around current price
- Prevents grid from becoming ineffective after drift
- Triggers when one side is 3x more filled than other
* fix(grid): recalculate bounds in autoAdjustGrid before reinitializing levels
Critical fix for grid auto-adjustment:
- Recalculate grid bounds (UpperPrice, LowerPrice, GridSpacing) centered
on current price before reinitializing grid levels
- Preserve filled positions during adjustment by saving and restoring
them to the closest new level after reinitialization
- Hold mutex lock for the entire adjustment operation to ensure atomicity
- Add locked variants of calculateDefaultBounds, calculateATRBounds, and
initializeGridLevels to use during adjustment
Without this fix, autoAdjustGrid was using old boundaries when creating
new grid levels, defeating the purpose of auto-adjustment when price
moved significantly.
* fix(grid): improve order state sync logic
- Don't assume missing orders are filled
- Compare position size to determine fill vs cancel
- Properly reset cancelled orders to empty state
- More accurate grid state tracking
* fix(grid): use actual PositionSize sum instead of count in syncGridState heuristic
The position-based heuristic was using `float64(previousFilledCount) * level.OrderQuantity`
which incorrectly assumed uniform order quantities. Since the grid uses weighted distribution
(gaussian, pyramid, uniform) where orders have different quantities, this could lead to
incorrect fill detection.
Now sums the actual PositionSize from filled levels for accurate comparison.
Also adds warning log when GetPositions() fails.
* docs: add grid market regime detection design
Design for enhanced market state recognition with:
- Multi-dimensional indicators (ATR, Bollinger, EMA, MACD, RSI)
- Multi-period box indicators (72/240/500 1h candles)
- 4-level ranging classification
- Breakout detection and handling
- Frontend risk control panel
* docs: add grid market regime implementation plan
20 tasks covering:
- Donchian channel calculation
- Box data types and API
- Regime classification (4 levels)
- Breakout detection and handling
- False breakout recovery
- Frontend risk panel
- AI prompt updates
* feat(market): add Donchian channel calculation
Add calculateDonchian function to compute highest high and lowest low
over a specified period. This is the foundation for box (range) detection
in the multi-period box indicator system for grid trading.
* fix(market): handle invalid period in calculateDonchian
* feat(market): add BoxData and RegimeLevel types
* feat(market): add GetBoxData for multi-period box calculation
Adds calculateBoxData internal function and GetBoxData public API that
fetches 1h klines and computes three Donchian box levels (short/mid/long).
This will be used by the grid trading system to detect market regime.
* feat(store): add box and regime fields to grid models
* feat(trader): add regime classification and breakout detection
Implements Tasks 6-9 for grid market regime awareness:
- Task 6: classifyRegimeLevel with Bollinger/ATR thresholds
- Task 7: detectBoxBreakout for multi-period box breakouts
- Task 8: confirmBreakout with 3-candle confirmation logic
- Task 9: getBreakoutAction mapping breakout levels to actions
* feat(trader): integrate box breakout detection into grid cycle
- Task 10: Add checkBoxBreakout with 3-candle confirmation
- Task 11: Add checkFalseBreakoutRecovery for 50% position recovery
- Task 12: Add box/breakout/regime fields to GridState
* feat: add grid risk panel with API endpoint
- Task 13: Add GridRiskInfo type to frontend
- Task 14: Add /traders/:id/grid-risk API endpoint
- Task 15: Add GetGridRiskInfo method to AutoTrader
- Task 16: Create GridRiskPanel component with i18n
* feat(kernel): add box indicators to AI prompt
- Add BoxData field to GridContext
- Add box indicator table to both zh/en prompts
- Show breakout/warning alerts based on price position
* feat(web): integrate GridRiskPanel into TraderDashboardPage
* feat(lighter): improve API key validation and market caching
- Add API key validation status tracking
- Add market list caching to reduce API calls
- Improve logging (debug vs info levels)
- Add comprehensive integration tests
- Update trader manager and store for lighter support
* fix: remove hardcoded test wallet address
* fix(grid): improve GridRiskPanel layout and fix liquidation data
- Make panel collapsible with summary badges when collapsed
- Use compact 2-column grid layout for detailed info
- Fix auth token key (token -> auth_token)
- Only calculate liquidation distance when position exists
* fix(grid): add isRunning checks to prevent trades after Stop() is called
- LoginPage: call completeRegistration instead of verifyOTP when qrCodeURL exists
- This ensures otp_verified is set to true for users completing OTP setup
- Backend: reorder maxUsers check to allow existing incomplete users to continue
- Backend: return OTP info when login with incomplete OTP setup
- Fix milliseconds to seconds conversion in parseCustomTime (AdvancedChart & ChartWithOrders)
- Add GetTraderOrdersFiltered to filter orders at database level by symbol/status
- Increase order limit from 50 to 200 for more historical orders
- Group multiple orders at same candle time and show count (B3, S5, etc.)
- Buy markers shown below bar (green), sell markers above bar (red)
- Convert all time.Time fields to int64 Unix milliseconds (UTC)
- Add PostgreSQL migration to convert timestamp columns to bigint
- Reduce Binance sync window from 7 days to 24 hours
- Fix dashboard trader name visibility (add nofx-text-main color)
- Add position value column to history table
- Remove hardcoded API keys from test files
- Add NowFunc to GORM config for UTC auto-generated timestamps
- Add .UTC() to all time.UnixMilli() calls in trader files
- Add .UTC() to all time.Now() calls in store and api files
- Fix TypeScript unused imports in frontend
- RemoveTrader now stops running trader before removing from memory
- handleUpdateTrader auto-restarts trader if it was running before update
- Add debug logs to trace scan_interval_minutes through update/save/load flow
- Add unified NofxOS API key configuration in IndicatorEditor
- Add language field to StrategyConfig for consistent prompt generation
- Auto-update prompt sections when interface language changes
- Remove scattered URL inputs from CoinSourceEditor and IndicatorEditor
- Create nofxos provider package with formatted data output
- Update kernel engine to use config-based language setting
- Add public strategy market API endpoint (/api/strategies/public)
- Add is_public and config_visible fields to Strategy model
- Add LoginRequiredOverlay component for unified auth prompts
- Add WhitelistFullPage for registration capacity limit
- Add StrategyMarketPage for browsing public strategies
- Unify navigation logic across HeaderBar, LandingPage, App
- Reduce klines API calls (fetch once on mount)
- Fix various page transition issues
shinchan-zhai
deanokk
lky-spec
root
Dean
Zavier
Hansen1018
tinkle-community
1bcMax
ximi
Muhammad Syaiful Anwar
Hao Fu