22 Commits

Author SHA1 Message Date
tinkle-community
24f6421a73 feat: simplify Claw402 autopilot trading flow 2026-06-27 00:37:59 +08:00
tinkle-community
f3c33b55d7 feat(agent): make the agentic loop the primary brain path
thinkAndAct/thinkAndActStream now try the native function-calling loop
first for fresh conversations; in-flight legacy flows (skill sessions,
workflows, execution states, pending proposals) stay on the legacy stack
until they finish. NOFX_AGENT_V2=off restores the old routing entirely.
2026-06-11 01:03:08 +08:00
shinchan-zhai
ab5873e2de refactor(agent): improve legacy loop comment and extract domain variable
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>
2026-05-12 00:16:20 +08:00
shinchan-zhai
e2ccc6b911 fix(agent): eliminate cross-turn topic pollution in legacy loop
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>
2026-05-11 23:51:18 +08:00
shinchan-zhai
bf289e8eb3 fix(agent): reduce verbose responses — focus answers on user's question only
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>
2026-05-11 21:12:48 +08:00
shinchan-zhai
9f25bf49bf fix(agent): use provider registry for claw402, echo reasoning_content for thinking models, add Beta badge
- 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>
2026-05-11 20:22:32 +08:00
shinchan-zhai
ca8bed4a58 fix(agent): add TargetRef nil guards and ensureHistory for robustness
- 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>
2026-05-11 16:43:36 +08:00
shinchan-zhai
94844b7139 fix(agent): guard async maintenance goroutine and add timeout to diagnosis ctx
- 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>
2026-05-11 16:37:30 +08:00
lky-spec
e67a927a4f Refine strategy creation flow and diagnostics 2026-05-09 14:48:24 +08:00
lky-spec
2d45e7ab15 Refine agent strategy routing and config handling 2026-04-28 19:37:44 +08:00
lky-spec
5ff7212cb3 Revert "Revert "Trim agent planning tools and validate strategy patches""
This reverts commit 3619f82796.
2026-04-28 15:54:36 +08:00
lky-spec
3619f82796 Revert "Trim agent planning tools and validate strategy patches"
This reverts commit fe0dbce367.
2026-04-28 15:53:53 +08:00
lky-spec
fe0dbce367 Trim agent planning tools and validate strategy patches 2026-04-28 15:45:47 +08:00
lky-spec
30a703a827 Unify agent routing and tighten exchange config 2026-04-28 11:58:58 +08:00
lky-spec
e8eafce1e0 Require explicit agent mutation targets 2026-04-26 22:38:16 +08:00
lky-spec
ce3a8582af Simplify agent skill routing and config updates 2026-04-26 22:22:12 +08:00
lky-spec
cfd91069d3 Centralize active skill field extraction 2026-04-26 20:44:09 +08:00
lky-spec
903eb591eb Improve active skill schema handling 2026-04-26 11:58:29 +08:00
lky-spec
9ee931ee30 v2 2026-04-25 20:24:46 +08:00
lky-spec
c244e4cdf1 change v1 2026-04-25 16:18:45 +08:00
lky-spec
737f9bca95 Enhance NOFXi agent workflow and diagnostics 2026-04-19 16:06:28 +08:00
lky-spec
5c4e7502d7 feat: integrate NOFXi agent into dev 2026-04-18 16:06:42 +08:00