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

..

skills

Refine strategy creation flow and diagnostics

2026-05-09 14:48:24 +08:00

active_session.go

Simplify agent skill routing and config updates

2026-04-26 22:22:12 +08:00

agent_model_selection_test.go

v2

2026-04-25 20:24:46 +08:00

agent.go

fix(agent): reduce verbose responses — focus answers on user's question only

2026-05-11 21:12:48 +08:00

ai_service_failure_test.go

Refine strategy creation flow and diagnostics

2026-05-09 14:48:24 +08:00

atomic_skill_executor.go

change v1

2026-04-25 16:18:45 +08:00

brain.go

change v1

2026-04-25 16:18:45 +08:00

central_brain.go

Refine strategy creation flow and diagnostics

2026-05-09 14:48:24 +08:00

clear_memory_test.go

change v1

2026-04-25 16:18:45 +08:00

config_validation.go

Unify agent routing and tighten exchange config

2026-04-28 11:58:58 +08:00

config_visibility_test.go

Split strategy config by strategy type

2026-04-28 20:19:24 +08:00

entity_field_catalog.go

Improve active skill schema handling

2026-04-26 11:58:29 +08:00

execution_state.go

change v1

2026-04-25 16:18:45 +08:00

history.go

change v1

2026-04-25 16:18:45 +08:00

i18n.go

change v1

2026-04-25 16:18:45 +08:00

llm_flow_extractor_test.go

Improve active skill schema handling

2026-04-26 11:58:29 +08:00

llm_flow_extractor.go

Refine strategy creation flow and diagnostics

2026-05-09 14:48:24 +08:00

llm_skill_router.go

Refine strategy creation flow and diagnostics

2026-05-09 14:48:24 +08:00

market_snapshot_test.go

v2

2026-04-25 20:24:46 +08:00

memory.go

change v1

2026-04-25 16:18:45 +08:00

model_create_flow_test.go

Centralize active skill field extraction

2026-04-26 20:44:09 +08:00

model_provider_catalog_test.go

change v1

2026-04-25 16:18:45 +08:00

model_provider_catalog.go

change v1

2026-04-25 16:18:45 +08:00

model_wallet_fastpath.go

fix(agent): reduce verbose responses — focus answers on user's question only

2026-05-11 21:12:48 +08:00

onboard.go

change v1

2026-04-25 16:18:45 +08:00

planner_runtime.go

fix(agent): reduce verbose responses — focus answers on user's question only

2026-05-11 21:12:48 +08:00

planner_tools_test.go

Revert "Revert "Trim agent planning tools and validate strategy patches""

2026-04-28 15:54:36 +08:00

preferences.go

change v1

2026-04-25 16:18:45 +08:00

prompt_context.go

change v1

2026-04-25 16:18:45 +08:00

prompt_persona.go

change v1

2026-04-25 16:18:45 +08:00

reference_memory.go

change v1

2026-04-25 16:18:45 +08:00

scheduler.go

change v1

2026-04-25 16:18:45 +08:00

sentinel.go

change v1

2026-04-25 16:18:45 +08:00

skill_catalog.go

feat: integrate NOFXi agent into dev

2026-04-18 16:06:42 +08:00

skill_dag_runtime.go

Enhance NOFXi agent workflow and diagnostics

2026-04-19 16:06:28 +08:00

skill_dag.go

Refine strategy creation flow and diagnostics

2026-05-09 14:48:24 +08:00

skill_dispatcher.go

Refine strategy creation flow and diagnostics

2026-05-09 14:48:24 +08:00

skill_domain_context.go

Refine strategy creation flow and diagnostics

2026-05-09 14:48:24 +08:00

skill_execution_handlers.go

fix(agent): add TargetRef nil guards and ensureHistory for robustness

2026-05-11 16:43:36 +08:00

skill_management_handlers.go

Refine strategy creation flow and diagnostics

2026-05-09 14:48:24 +08:00

skill_outcome.go

Refine agent strategy routing and config handling

2026-04-28 19:37:44 +08:00

skill_registry.go

Improve NOFXi agent product handling

2026-05-02 22:55:10 +08:00

skill_runner.go

change v1

2026-04-25 16:18:45 +08:00

skill_semantic_gate.go

Refine agent strategy routing and config handling

2026-04-28 19:37:44 +08:00

stock.go

feat: integrate NOFXi agent into dev

2026-04-18 16:06:42 +08:00

strategy_draft.go

Refine strategy creation flow and diagnostics

2026-05-09 14:48:24 +08:00

strategy_field_catalog.go

Refine strategy creation flow and diagnostics

2026-05-09 14:48:24 +08:00

stream_text.go

change v1

2026-04-25 16:18:45 +08:00

tools.go

fix(agent): reduce verbose responses — focus answers on user's question only

2026-05-11 21:12:48 +08:00

trade.go

change v1

2026-04-25 16:18:45 +08:00

trader_scope_test.go

Refine strategy creation flow and diagnostics

2026-05-09 14:48:24 +08:00

unified_turn_router_test.go

Refine strategy creation flow and diagnostics

2026-05-09 14:48:24 +08:00

user_facing_prompt_test.go

v2

2026-04-25 20:24:46 +08:00

user_facing_prompt.go

v2

2026-04-25 20:24:46 +08:00

web.go

Improve NOFXi agent product handling

2026-05-02 22:55:10 +08:00

workflow.go

Simplify agent skill routing and config updates

2026-04-26 22:22:12 +08:00