Commit Graph

20 Commits

Author SHA1 Message Date
陈少杰 b6e57d01e3 Stabilize TradingAgents contracts so orchestration and dashboard can converge
This change set introduces a versioned result contract, shared config schema/loading, provider/data adapter seams, and a no-strategy application-service skeleton so the current research graph, orchestrator layer, and dashboard backend stop drifting further apart. It also keeps the earlier MiniMax compatibility and compact-prompt work aligned with the new contract shape and extends regression coverage so degradation, fallback, and service migration remain testable during the next phases.

Constraint: Must preserve existing FastAPI entrypoints and fallback behavior while introducing an application-service seam
Constraint: Must not turn application service into a new strategy or learning layer
Rejected: Full backend rewrite to service-only execution now | too risky before contract and fallback paths stabilize
Rejected: Leave provider/data/config logic distributed across scripts and endpoints | continues boundary drift and weakens verification
Confidence: high
Scope-risk: broad
Directive: Keep future application-service changes orchestration-only; move any scoring, signal fusion, or learning logic to orchestrator or tradingagents instead
Tested: python -m compileall orchestrator tradingagents web_dashboard/backend
Tested: python -m pytest orchestrator/tests/test_signals.py orchestrator/tests/test_llm_runner.py orchestrator/tests/test_quant_runner.py orchestrator/tests/test_contract_v1alpha1.py orchestrator/tests/test_application_service.py orchestrator/tests/test_provider_adapter.py web_dashboard/backend/tests/test_main_api.py web_dashboard/backend/tests/test_portfolio_api.py web_dashboard/backend/tests/test_api_smoke.py web_dashboard/backend/tests/test_services_migration.py -q
Not-tested: live MiniMax/provider execution against external services
Not-tested: full dashboard/manual websocket flow against a running frontend
Not-tested: omx team runtime end-to-end in the primary workspace
2026-04-13 17:25:07 +08:00
陈少杰 0cd40a9bab feat: integrate TradingOrchestrator with 5-level signal dashboard
- Merge orchestrator module (Quant+LLM dual-track signal fusion)
- Replace ANALYSIS_SCRIPT_TEMPLATE to use TradingOrchestrator.get_combined_signal()
- Extend signal levels: BUY/OVERWEIGHT/HOLD/UNDERWEIGHT/SELL (direction × confidence≥0.7)
- Backend: parse SIGNAL_DETAIL: stdout line, populate quant_signal/llm_signal/confidence fields
- Backend: update _extract_decision() regex for 5-level signals
- Backend: add OVERWEIGHT/UNDERWEIGHT colors to PDF export
- Frontend: DecisionBadge classMap for all 5 signal levels
- Frontend: index.css color tokens --overweight/--underweight
- Frontend: AnalysisMonitor shows LLM signal, Quant signal, confidence% on completion
- Add orchestrator/cache/ to .gitignore

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-10 01:59:43 +08:00
Yijia-Xiao 4f965bf46a
feat: dynamic OpenRouter model selection with search (#482, #337) 2026-04-04 07:56:44 +00:00
Yijia-Xiao e75d17bc51
chore: update model lists and defaults to GPT-5.4 family 2026-03-29 19:45:36 +00:00
Yijia Xiao c61242a28c
Merge pull request #464 from CadeYu/sync-validator-models
sync model validation with cli catalog
2026-03-29 11:07:51 -07:00
Yijia-Xiao 58e99421bd
fix: pass base_url to Google and Anthropic clients for proxy support (#427) 2026-03-29 17:59:52 +00:00
CadeYu bd6a5b75b5 fix model catalog typing and known-model helper 2026-03-25 21:46:56 +08:00
CadeYu 8793336dad sync model validation with cli catalog 2026-03-25 21:23:02 +08:00
javierdejesusda 047b38971c refactor: simplify api_key mapping and consolidate tests
Apply review suggestions: use concise `or` pattern for API key
resolution, consolidate tests into parameterized subTest, move
import to module level per PEP 8.
2026-03-24 14:52:51 +01:00
javierdejesusda f5026009f9 fix(llm_clients): standardize Google API key to unified api_key param
GoogleClient now accepts the unified `api_key` parameter used by
OpenAI and Anthropic clients, mapping it to the provider-specific
`google_api_key` that ChatGoogleGenerativeAI expects. Legacy
`google_api_key` still works for backward compatibility.

Resolves TODO.md item #2 (inconsistent parameter handling).
2026-03-24 14:35:02 +01:00
Yijia-Xiao bd9b1e5efa feat: add Anthropic effort level support for Claude models
Add effort parameter (high/medium/low) for Claude 4.5+ and 4.6 models,
consistent with OpenAI reasoning_effort and Google thinking_level.
Also add content normalization for Anthropic responses.
2026-03-22 21:57:05 +00:00
Yijia-Xiao 77755f0431 chore: consolidate install, fix CLI portability, normalize LLM responses
- Point requirements.txt to pyproject.toml as single source of truth
- Resolve welcome.txt path relative to module for CLI portability
- Include cli/static files in package build
- Extract shared normalize_content for OpenAI Responses API and
  Gemini 3 list-format responses into base_client.py
- Update README install and CLI usage instructions
2026-03-22 21:38:01 +00:00
Yijia-Xiao 3ff28f3559 fix: use OpenAI Responses API for native models
Enable use_responses_api for native OpenAI provider, which supports
reasoning_effort with function tools across all model families.
Removes the UnifiedChatOpenAI subclass workaround.

Closes #403
2026-03-22 20:34:03 +00:00
阳虎 64f07671b9 fix: add http_client support for SSL certificate customization
- Add http_client and http_async_client parameters to all LLM clients
- OpenAIClient, GoogleClient, AnthropicClient now support custom httpx clients
- Fixes SSL certificate verification errors on Windows Conda environments
- Users can now pass custom httpx.Client with verify=False or custom certs

Fixes #369
2026-03-16 07:41:20 +08:00
Yijia-Xiao 551fd7f074 chore: update model lists, bump to v0.2.1, fix package build
- OpenAI: add GPT-5.4, GPT-5.4 Pro; remove o-series and legacy GPT-4o
- Anthropic: add Claude Opus 4.6, Sonnet 4.6; remove legacy 4.1/4.0/3.x
- Google: add Gemini 3.1 Pro, 3.1 Flash Lite; remove deprecated
  gemini-3-pro-preview and Gemini 2.0 series
- xAI: clean up model list to match current API
- Simplify UnifiedChatOpenAI GPT-5 temperature handling
- Add missing tradingagents/__init__.py (fixes pip install building)
2026-03-15 23:34:50 +00:00
Yijia Xiao 6cd35179fa
chore: clean up dependencies and fix Ollama auth
- Remove unused packages: praw, feedparser, eodhd, akshare, tushare, finnhub
- Fix Ollama requiring API key
2026-02-03 23:08:12 +00:00
Yijia Xiao 54cdb146d0
feat: add footer statistics tracking with LangChain callbacks
- Add StatsCallbackHandler for tracking LLM calls, tool calls, and tokens
- Integrate callbacks into TradingAgentsGraph and all LLM clients
- Dynamic agent/report counts based on selected analysts
- Fix report completion counting (tied to agent completion)
2026-02-03 22:27:20 +00:00
Yijia Xiao a3761bdd66
feat: update Ollama and OpenRouter model options
- Ollama: Add Qwen3 (8B), GPT-OSS (20B), GLM-4.7-Flash (30B)
- OpenRouter: Add NVIDIA Nemotron 3 Nano, Z.AI GLM 4.5 Air
- Add explicit Ollama provider handling in OpenAI client for consistency
2026-02-03 22:27:20 +00:00
Yijia Xiao d4dadb82fc
feat: add multi-provider LLM support with thinking configurations
Models added:
- OpenAI: GPT-5.2, GPT-5.1, GPT-5, GPT-5 Mini, GPT-5 Nano, GPT-4.1
- Anthropic: Claude Opus 4.5/4.1, Claude Sonnet 4.5/4, Claude Haiku 4.5
- Google: Gemini 3 Pro/Flash, Gemini 2.5 Flash/Flash Lite
- xAI: Grok 4, Grok 4.1 Fast (Reasoning/Non-Reasoning)

Configs updated:
- Add unified thinking_level for Gemini (maps to thinking_level for Gemini 3,
  thinking_budget for Gemini 2.5; handles Pro's lack of "minimal" support)
- Add OpenAI reasoning_effort configuration
- Add NormalizedChatGoogleGenerativeAI for consistent response handling

Fixes:
- Fix Bull/Bear researcher display truncation
- Replace ChromaDB with BM25 for memory retrieval
2026-02-03 22:27:20 +00:00
Yijia Xiao 79051580b8
feat: add multi-provider LLM support with factory pattern
- Add tradingagents/llm_clients/ with unified factory pattern
- Support OpenAI, Anthropic, Google, xAI, OpenRouter, Ollama, vLLM
- Replace direct LLM imports in trading_graph.py with create_llm_client()
- Handle provider-specific params (reasoning_effort, thinking_config)
2026-02-03 22:27:20 +00:00