- Lead with global market coverage and exchange registration links
- Position Claw402 as automatic pay-as-you-go model access
- Update VergeX links and remove stale API docs reference
- Position NOFX around US stocks, commodities, forex, and crypto
- Update the README hero, feature summary, markets section, and architecture label
- Keep the copy affirmative and avoid defensive crypto-only comparisons
- Update landing, chart, settings, and data page copy for stock trading
- Adjust branding and translations around Hyperliquid positioning
- Extend frontend config types for the updated exchange settings
- Add stock symbol panel and agent chat page wiring
- Update onboarding and tool visibility for focused trader flows
- Tighten related tests around configuration and trader scope
- Extend strategy storage and engine analysis for Hyperliquid defaults
- Rework coin source and indicator editors for the stock strategy flow
- Update Strategy Studio translations and page wiring
- Add Hyperliquid/XYZ symbol normalization tests and backend coverage
- Extend kline and market data lookup paths for US stock symbols
- Wire frontend data API types for stock-oriented market requests
Remove the old generic risk-profile defaults from the user strategy bootstrap path and replace them with concrete Hyperliquid USDC equity presets that can be selected directly when creating an AI trader.
Add three ready-to-run strategy presets: a volume-ranked US stock trend preset, a fixed mega-cap preset covering AAPL-USDC/MSFT-USDC/GOOGL-USDC/AMZN-USDC/META-USDC, and a gainers-ranked US stock breakout preset.
Normalize the presets to use Hyperliquid-native stock discovery instead of AI500/OI crypto-style sources, with conservative defaults for max positions, leverage, margin usage, confidence, risk-reward, and multi-timeframe indicators.
Make default strategy synchronization idempotent for existing users: remove obsolete unused legacy preset rows, backfill the new US stock presets, and avoid overriding an already active custom strategy.
Update the trader creation modal preview labels so Hyperliquid stock ranking and fixed US stock sources are described clearly when users select a strategy.
Add API tests covering the new preset set, legacy preset cleanup, idempotent sync behavior, and preservation of an existing active custom strategy.
Verified with: go test ./api ./store; npm run build; docker compose up -d --build nofx nofx-frontend; backend /api/health; frontend HTTP 200; compose health checks.
Clarify the rationale for not injecting conversation history in the
legacy loop comment, and extract plannerToolDomainForText result into
a named variable for readability.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add missing .nofx-glass CSS class (used in 20+ places but undefined)
- Fix Input component referencing undefined --brand-black/--brand-light-gray
- Unify background colors to #0B0E11 (was 3 different near-blacks)
- Switch body font from IBM Plex Mono to Inter for readability
- Improve chat bubble contrast (bg 0.03→0.05, border 0.05→0.08)
- Brighten timestamp (#2c2c42→#5a5a72) and disclaimer (#1e1e32→#4a4a62)
- Unify ::selection color to gold (was orange)
- Remove global button:hover translateY that conflicted with active:scale
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove conversation history injection from thinkAndActLegacyWithStore.
Previously, the legacy loop appended all prior Q&A turns, causing the
LLM to re-answer topics from earlier conversations (e.g. strategy data
leaking into a wallet balance question). Each legacy-loop call is now
treated as a standalone request with domain-filtered tools.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Root cause: when planner fails (402 payment), legacy loop dumps all system
context to LLM which outputs everything. Also final response prompt was too
weak — LLM treated all observations as required output.
Changes:
- Strengthen system prompt: "answer ONLY what user asked", no tables/tutorials
unless requested, no self-intro repeats, no "next step" suggestions
- Add compact observation summary for final response (step summaries only,
no raw JSON blobs)
- Domain-filtered tool selection in legacy loop to prevent over-fetching
- Fix domain routing: "钱包/wallet" → account domain (not model), with
exchange configs included for wallet context
- Widen wallet fast-path: no longer requires "claw402" keyword
- Anti-repetition instructions in planner step selector
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Agent now uses mcp.NewAIClientByProvider() for claw402 provider, ensuring
x402 payment signing works correctly instead of generic HTTP client
- Added ReasoningContent field to Message/LLMResponse structs and wired
serialization/parsing so DeepSeek thinking models work in multi-turn
- Added Beta badge to Agent nav tab in HeaderBar
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add NOFXi agent backend: central brain, planner runtime, skill routing,
memory/state handling, config validation, and action execution
- Add agent chat page with SSE streaming, step/status panels, and
user preferences
- Extend trader/model/exchange/strategy APIs and store for agent-driven
configuration
- Add stopCh guard in async maintenance goroutine to prevent leak on Stop()
- Add timeout context for trader diagnosis LLM calls
- Add TargetRef nil guards in all execute*Action handlers
- Add ensureHistory() for nil-safe history access
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Use PR branch (dev-nofxi) as authority for agent/ module code
- Merge dev's newer model names (MiniMax-M2.7, deepseek-v4-flash)
with PR's blockrun provider entries
- Fix duplicate agent init in main.go, keep defer-based Stop()
- Fix var type bug in store/ai_model.go (model → models)
- Remove dev-only test files incompatible with PR's evolved agent code
(to be re-synced after merge)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add nil checks for session.TargetRef in all four execute*Action
handlers (Trader/Exchange/Model/Strategy) to prevent panic on
corrupted sessions; bulk-delete and query actions are excluded
- Add ensureHistory() helper and call it in runPlannedAgentWithContextMode
to prevent nil panic when history is not initialized
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add stopCh check in runPostResponseMaintenanceAsync to respect agent
shutdown, preventing goroutine leak on Agent.Stop()
- Replace bare context.Background() in handleTraderDiagnosisSkill with
a 30s timeout context for proper deadline propagation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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>
- Add nil checks for session.TargetRef in all four execute*Action handlers
(Trader/Exchange/Model/Strategy) to prevent panic on corrupted sessions;
actions that don't need a target (query/query_list/create) are excluded.
- Fix toast.success indentation in handleToggleTrader so success messages
only fire when the API call actually succeeds.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fix Stop() race condition using sync.Once
- Add ensureHistory() to prevent nil panic in planner/dispatcher
- Add bounds check on trader ID slicing
- Log saveExecutionState and clearSetupState errors instead of discarding
- Remove always-true modelID condition in onboard setup
- Add Chinese setup keywords and expand model name aliases
- Strip max_tokens from claw402 requests to avoid thinking-model budget exhaustion
- Hide Agent nav tab (Beta) pending merge to main
- Sync tests with code changes
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>
- 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.
Co-authored-by: Dean <afei.wuhao@gmail.com>
1. Prevent double-close panic on Stop() by using sync.Once in Scheduler,
Brain, and Sentinel; remove duplicate Stop() call in main.go
2. Add trade quantity (100k) and leverage (125x) sanity caps to prevent
LLM hallucinations or input errors from reaching the exchange
3. Mask secrets in onboarding setup state — only store "****" markers in
SystemConfig instead of plaintext API keys/secrets
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.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>
* docs(readme): add quick demo video to localized READMEs (#1486)
* docs(README): add quick demo section with video link and image
* docs(README): update demo video link
* docs(i18n): add quick demo section with video link and image for multiple languages
---------
Co-authored-by: Dean <afei.wuhao@gmail.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>
* docs(README): add quick demo section with video link and image
* docs(README): update demo video link
* docs(i18n): add quick demo section with video link and image for multiple languages
---------
Co-authored-by: Dean <afei.wuhao@gmail.com>
