- README and .env.example cover the chatgpt provider, `tradingagents login chatgpt` (also in Docker) and logout
- README and .env.example name TRADINGAGENTS_NO_UPDATE_CHECK
- a saved report also includes complete_report.html: the report as one self-contained page with its sections listed beside the text, readable in a browser, on a phone and in print
- answering the save question at the prompt also asks about the page and offers to open it in a local browser window; --no-html and save_reports(..., html=False) skip it
- the Tauric Research logo leads the header at the top left, and a line at the foot credits TradingAgents and Tauric Research
- the page loads nothing and runs nothing (inline styles, a content-security policy); report text is rendered without raw HTML or images
- markdown-it-py is declared as a dependency
- quick_think_provider / deep_think_provider and their backend URLs (with TRADINGAGENTS_* variables) choose a tier's provider; unset, a tier uses llm_provider and backend_url
- a tier on another provider gets that provider's own settings and endpoint, and the run settings and report header name each tier's provider
- the CLI checks each tier provider's model variable and key before the run
- a Memory Log step runs beside the analysts, settles every ticker's due decisions and loads the lessons known by the trade date for the Portfolio Manager; the run no longer settles before it starts
- a settlement failure is logged and noted in the report's header instead of ending the run
- the checkpoint signature records the new layout
- TradingAgentsGraph.settle_all_pending() settles each ticker with a due decision; settle_pending and it return the decisions settled and those that failed
- post screening reads TypeSafe's own TYPESAFE_BASE_URL and appends /v1/systemone, as the TypeSafe SDKs do, so Jev can be reached through OpenRouter; the key still turns screening on
- requires-python 3.11 and pandas 3.0.6; the CI matrix runs Python 3.11 to 3.14 and ruff targets 3.11
- datetime.UTC in place of timezone.utc, and the rating, action, band, analyst and asset enums are StrEnum, which formats a member as its value
- Yahoo and Alpha Vantage date a trade by when it happened, not by its Form 4 filing, so a run dated in the past is told they are withheld instead of served trades that may not yet have been public
- Yahoo and Alpha Vantage statements, dated by the period they cover, are withheld from a run dated in the past, with a notice saying why
- statements come from SEC EDGAR by default (fundamental_data "sec_edgar,yfinance"), so a past run reads US filers as filed
- each analyst is a graph of its own (model and tools on a private message history) that returns only its report; all start together and the research debate waits for every report
- the message-clearing nodes are gone; a checkpoint saved by the sequential layout starts fresh
- TradingAgentsGraph.stream_run streams the analysts' messages for debug mode and the CLI, whose status and timing now track the analysts side by side
- --ticker, --date and --analysts answer their steps, checked as the prompts check them; --save/--no-save and --show/--no-show answer the questions after the run
- with no terminal, the run stops before it starts and names every flag or TRADINGAGENTS_* variable still needed; a missing API key and an announcement no longer wait for input
- README shows an unattended run
- docstrings, comments, messages and the README section use "memory log", matching TradingMemoryLog and memory_log_path
- the write, read and settle paths are named for what they do, not by design phase
- gpt-6-sol and gpt-6-luna are the new default deep and quick models
- claude-opus-5-5 replaces claude-opus-5 in the picker; opus-5 and gpt-5.4-mini stay known as legacy IDs
- point-in-time integrity across every dated path, and a vendor failure reported as a vendor failure
- SEC EDGAR fundamentals served as filed
- backtesting over a ticker and date grid, and the caller's portfolio as run input
- current model lineups across every provider
- the custom model option does not exist for every provider; name any model ID instead
- alpha is measured against the regional benchmark, not always SPY
- the environment overrides a fixed set of config keys
- list the providers the picker offers, and the macro data key
- drop the example call to a method that was removed
- CI gate, unified verified data-access contract, provider and data-vendor registry
- env-over-CLI config precedence, current-generation model catalog
- programmatic report output, plus sweep fixes for data and structured output
The README reproducibility example named gpt-4.1 and the structured-output smoke
script listed gemini-2.5-flash / deepseek-chat / qwen-plus / grok-4 — all retired
from the catalog. Generalize the note and refresh the smoke defaults.
Verified each provider's hard-coded list against current official docs:
- MiniMax: add MiniMax-M3 (1M ctx, multimodal) as the default; keep M2.7 line.
- Qwen: use the live qwen{3.7,3.6}-{plus,max} IDs.
- GLM: add glm-5.2 as the latest flagship.
- xAI: drop deprecated grok-4-fast-* / grok-4-0709 builds.
- DeepSeek: migrate to deepseek-v4-pro / deepseek-v4-flash (the chat/reasoner
aliases are deprecated 2026-07-24 and now map to V4 Flash).
OpenAI, Anthropic, and Gemini were already current and are unchanged.
Bedrock uses the Converse API (langchain-aws) and the AWS credential chain, so
it has its own client like Anthropic/Google rather than the OpenAI-compatible
registry. langchain-aws is an optional dependency (pip install ".[bedrock]"),
lazy-imported with a clear install hint; importing the package never requires
it. The model name is a Bedrock model ID / inference profile ID.
Each is a one-row entry in the OpenAI-compatible provider registry (base_url,
key env, CLI option); the model is user-specified since they serve many models.
The OpenAI-compatible family (openai, xAI, DeepSeek, Qwen, GLM, MiniMax,
OpenRouter, Ollama) all speak the same Chat Completions API and differ only by
base_url, key, and two narrow wire-format quirks already isolated in subclasses.
Replace the scattered base-URL dict, key handling, and client-class branches with
one ProviderSpec registry that get_llm and the factory drive off; provider quirks
stay in their subclasses. Add a generic "openai_compatible" provider for any
OpenAI-compatible server (vLLM, LM Studio, llama.cpp, relays) via backend_url +
optional key — adding a provider is now one registry row. Native Anthropic/Google
keep their own clients (genuinely different APIs). Also fixes the env backend URL
being ignored when the provider was chosen interactively (#978).
GitHub Actions: pytest across Python 3.10-3.13, a clean-install import smoke
that catches undeclared runtime deps, and a strict Ruff gate (standard rule set)
scoped to the files each PR changes. Declares python-dotenv (imported by the CLI
but previously undeclared) and adds a [dev] extra. Recommends Python 3.12 for
setup, verified from a clean isolated install.
Yijia-Xiao
