github-mirrors/tradingagents
1
0
Fork 0
mirror of https://github.com/TauricResearch/TradingAgents.git synced 2026-09-19 11:15:24 +03:00
Code Issues Packages Projects Releases Wiki Activity

feat(dataflows): serve US statements as filed, from SEC EDGAR

Browse Source 
- statements are limited to facts filed by the run's date, at the values filed then
- quarterly figures are picked by span, so a year to date total is not read as a quarter
- a fourth quarter is reported unavailable rather than derived
- opt in with sec_edgar in the fundamental_data chain; a non-filer falls through
This commit is contained in:
Yijia-Xiao
2026-09-17 02:37:15 +00:00
parent 8ac4371387
commit f881c4a111
4 changed files with 495 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

50
.env.example
View File

@@ -16,57 +16,43 @@ MOONSHOT_API_KEY=
GROQ_API_KEY=
NVIDIA_API_KEY=
# FRED (Federal Reserve macro data: rates, inflation, labor, growth). Free key: https://fred.stlouisfed.org/docs/api/api_key.html
# SEC EDGAR (US company filings, point-in-time). No key; a contact address SEC can reach you at.
#SEC_EDGAR_USER_AGENT=Your Name your@email.com
# FRED (Federal Reserve macro data). Free key: https://fred.stlouisfed.org/docs/api/api_key.html
#FRED_API_KEY=
# Optional: a custom OpenAI-compatible endpoint (vLLM, LM Studio, llama.cpp,
# relay). Select provider "openai_compatible" and set the base URL; the key is
# optional (local servers need none).
# Custom OpenAI-compatible endpoint (vLLM, LM Studio, llama.cpp). Local servers need no key.
#OPENAI_COMPATIBLE_API_KEY=
# AWS Bedrock (provider "bedrock", install with: pip install ".[bedrock]").
# Auth: either a Bedrock API key (bearer token, no AWS access keys) OR the AWS
# credential chain (env keys / ~/.aws/credentials / IAM role / AWS_PROFILE). Set
# the region either way; a bearer token takes precedence when both are present.
# AWS Bedrock (pip install ".[bedrock]"). Bearer token, or the AWS credential chain; set the region either way.
#AWS_BEARER_TOKEN_BEDROCK=
#AWS_DEFAULT_REGION=us-west-2
#AWS_PROFILE=
# Optional: point at a remote Ollama server. When unset, defaults to
# the local instance at http://localhost:11434/v1. Convention follows
# the broader Ollama ecosystem; both the CLI dropdown and programmatic
# client pick this up.
# Remote Ollama server. Unset uses http://localhost:11434/v1.
#OLLAMA_BASE_URL=http://your-ollama-host:11434/v1
# Optional: override DEFAULT_CONFIG without editing code.
# Any TRADINGAGENTS_* variable below, when set, replaces the matching key
# in tradingagents/default_config.py. Values are coerced to the type of
# the existing default (bool / int / str), so "true"/"3" work as expected.
# In the CLI, setting the LLM provider / models / backend URL / language
# also skips the matching interactive selection step (useful for
# OpenAI-compatible endpoints like opencode or LM Studio, and unattended runs).
# Override any DEFAULT_CONFIG key. In the CLI, a value set here skips its prompt.
#TRADINGAGENTS_LLM_PROVIDER=openai
#TRADINGAGENTS_DEEP_THINK_LLM=gpt-5.4
#TRADINGAGENTS_QUICK_THINK_LLM=gpt-5.4-mini
#TRADINGAGENTS_DEEP_THINK_LLM=gpt-5.6
#TRADINGAGENTS_QUICK_THINK_LLM=gpt-5.6-luna
#TRADINGAGENTS_LLM_BACKEND_URL=
#TRADINGAGENTS_OUTPUT_LANGUAGE=English
#TRADINGAGENTS_MAX_DEBATE_ROUNDS=1
#TRADINGAGENTS_MAX_RISK_ROUNDS=1
#TRADINGAGENTS_CHECKPOINT_ENABLED=false
# Sampling temperature (lower = less run-to-run variation on models that
# honor it). Unset leaves each provider at its default. See the README
# "Reproducibility" note — no setting makes LLM output fully deterministic.
# Lower temperature means less run-to-run variation on models that honor it.
#TRADINGAGENTS_TEMPERATURE=0.0
# LLM SDK retry budget forwarded to every provider. Unset leaves each SDK at its
# own default (usually 2). Raise it to ride out bursty 429 rate-limit throttling
# on rate-limited deployments (e.g. Azure OpenAI) instead of aborting the run.
# Retry budget for every LLM SDK. Raise it to ride out 429 throttling.
#TRADINGAGENTS_LLM_MAX_RETRIES=6
# Cap on output tokens forwarded to every provider (Gemini's max_output_tokens
# too). Unset leaves each provider at its default. Set it to bound a model that
# emits unbounded reasoning/output and hangs or trips a gateway idle timeout.
# Cap output tokens to bound a model that runs long and trips a timeout.
#TRADINGAGENTS_MAX_TOKENS=8192
# Provider-specific reasoning/thinking depth (optional; unset = provider
# default). Setting one also skips the matching interactive prompt.
# Reasoning depth per provider; setting one skips its prompt.
#TRADINGAGENTS_OPENAI_REASONING_EFFORT=medium
#TRADINGAGENTS_GOOGLE_THINKING_LEVEL=high
#TRADINGAGENTS_ANTHROPIC_EFFORT=high