Apply review suggestions: use concise `or` pattern for API key
resolution, consolidate tests into parameterized subTest, move
import to module level per PEP 8.
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).
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.
- 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
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
- openai_client.py: don't use self.base_url for llamacpp (it would
inherit openai default); read BACKEND_URL then LLAMACPP_BASE_URL directly
- default_config.py: remove redundant LLAMACPP_BASE_URL fallback from
backend_url, keep only generic BACKEND_URL env var
Add 'llamacpp' as a new provider for running TradingAgents fully
offline with a local llama-server (llama.cpp).
Changes:
- factory.py: register 'llamacpp' provider alongside openai/ollama
- validators.py: accept any model name for llamacpp (like ollama)
- openai_client.py: llamacpp branch sets base_url from env/config,
uses placeholder api_key so no auth error is raised
- default_config.py: load .env via python-dotenv (optional dep);
LLM_PROVIDER, BACKEND_URL, DEEP_THINK_LLM, QUICK_THINK_LLM are
all overridable via environment variables
- .env.example: document llamacpp setup alongside cloud providers
- .gitignore: ensure .env is ignored, .env.example is tracked
Fully backward-compatible: OpenAI remains the default when no
.env is present. Also works for LM Studio, vLLM, or any other
OpenAI-compatible local server via BACKEND_URL + LLM_PROVIDER=openai.
Tested with: llama.cpp llama-server + Qwen3.5-35B-A3B-Q3_K_M
- 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
- 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)
Add _clean_dataframe() to normalize stock DataFrames before stockstats:
coerce invalid dates/prices, drop rows missing Close, fill price gaps.
Also add on_bad_lines="skip" to all cached CSV reads.
LLMs (especially smaller models) sometimes pass multiple indicator
names as a single comma-separated string instead of making separate
tool calls. Split and process each individually at the tool boundary.
InvestDebateState was missing bull_history, bear_history, judge_decision.
RiskDebateState was missing aggressive_history, conservative_history,
neutral_history, latest_speaker, judge_decision. This caused KeyError
in _log_state() and reflection, especially with edge-case config values.
Prevents UnicodeEncodeError on Windows where the default encoding
(cp1252/gbk) cannot handle Unicode characters in LLM output.
Closes#77, closes#114, closes#126, closes#215, closes#332
- 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)
TPTBusiness
Yijia-Xiao
Yijia Xiao
CadeYu
javierdejesusda
OpenClaw Assistant
阳虎
makk9
Ljx-007
Edward Sun
luohy15