- 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>
* 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.
* 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>
When CLAW402_WALLET_KEY env var is set, all nofxos.ai data API calls
(AI500, OI rankings, NetFlow, price rankings) are automatically routed
through claw402.ai with x402 USDC micropayment.
- provider/nofxos/claw402.go: x402 GET request client for data APIs
- provider/nofxos/client.go: claw402 mode support in doRequest()
- kernel/engine.go: auto-detect CLAW402_WALLET_KEY and enable routing
- mcp/payment/x402.go: MakeClaw402SignFunc helper
Without CLAW402_WALLET_KEY, falls back to direct nofxos.ai (backward compat).
- Extract ParseSSEStream as shared function from CallWithRequestStream
- Add DoX402RequestStream and X402CallStream for streaming x402 payments
- Switch Claw402Client.Call to use streaming (X402CallStream)
- TeeReader fallback: SSE parsing with JSON fallback for non-SSE responses
- Idle timeout watchdog (90s) protects against stalled streams
The outer retry loop in client.go re-initiates the entire x402 payment
flow on each attempt, causing duplicate USDC charges. The inner x402
retry loop (5 attempts with re-signing) already handles all retryable
scenarios. Set MaxRetries=1 for Claw402, BlockRunBase, and BlockRunSol
to ensure only one payment per AI decision.
AI inference (especially DeepSeek) often exceeds the default 120s HTTP
timeout, causing the client to disconnect while the server completes
successfully — resulting in repeated payments on each retry.
Changes:
- Set X402Timeout = 5min for all x402 providers (Claw402, BlockRunBase, BlockRunSol)
- Handle 402 during payment retry by re-extracting Payment-Required
header and re-signing instead of failing immediately
- Increase payment retry attempts from 3 to 5 for unstable gateways
shinchan-zhai
deanokk
tinkle-community