Adds a canonical PROVIDER_API_KEY_ENV mapping (14 providers including
the three dual-region pairs) and an ensure_api_key() helper. When the
selected provider's key is absent from the environment, the CLI prompts
via questionary.password, writes the value to .env via python-dotenv's
set_key (preserves existing lines), and exports it into os.environ so
the run continues without restart. Wired into cli/main.py right after
the region prompts so qwen-cn, glm-cn, and minimax-cn each check their
own region-specific key. openai_client refactored to consult the same
mapping, eliminating its private duplicate of provider→env-var data.
Adds a single _ENV_OVERRIDES table in default_config.py with type-aware
coercion (str/int/bool), so users can switch llm_provider, deep/quick
models, backend URL, output language, debate rounds, and the checkpoint
flag purely via .env. Centralizes load_dotenv in the package __init__
so the overlay applies for every entry point (CLI, main.py, programmatic).
Drops the hardcoded model assignments and duplicate dotenv loads in
main.py and cli/main.py. Verified live with OpenAI and Gemini.
#602
Zhipu serves GLM under two brands with separate accounts (Z.AI
international vs BigModel China); the CLI URL pointed at one while
the openai_client default pointed at the other. Split into glm +
glm-cn with secondary region prompt (same UX as Qwen + MiniMax).
Catalog adds glm-5-turbo and glm-4.5-air per docs.z.ai.
Qwen and MiniMax each had two main-dropdown entries (intl + CN);
consolidate to one entry per provider and prompt for region as a
secondary step. Internal provider keys (qwen-cn, minimax-cn) and
endpoint routing unchanged. Add qwen3.6-flash to the Qwen catalog
and drop the version-less aliases (qwen-flash, qwen-plus) that
auto-shift their backing model per Alibaba's docs.
#758
Opus 4.7 is the current frontier per platform.claude.com (frontier
category, listed first). Demote Opus 4.6 to second deep-tier slot.
Polish quick-tier labels to match official wording; effort docstring
includes 4.7.
Two regional endpoints (global api.minimax.io, China api.minimaxi.com)
with separate API keys. Models M2.7 / M2.5 plus -highspeed variants,
204K context. Follows the existing provider-preset pattern.
#789#609#577#546#395#378
The typer.prompt-based input could lose .SH/.SZ/.SS/.HK suffixes on
some shells, so exchange-qualified tickers like 000404.SH arrived
truncated to 000404 and failed downstream lookups. Switch to
questionary.text which reads the raw line; keep SPY-on-empty
behavior and validate the allowed character set (alnum, ._-^) up
to 32 chars.
#770
graph.stream() yields per-node deltas, not the full state. Taking
trace[-1] only captured the last node's contribution, so reports
saved to disk were missing every section except the final decision.
Merge all chunks in both the CLI path and trading_graph._run_graph's
debug branch.
#719#736
load_dotenv() with no arguments walks up from site-packages instead
of the user's CWD, so the installed tradingagents console script
silently misses the project's .env. Pass find_dotenv(usecwd=True)
so the search starts from CWD; same treatment for .env.enterprise.
#726#755#612#747#743#753#729#728#751
Long analyses can take many minutes; a crash or interruption forced users
to re-run from scratch and re-pay every LLM call. This adds an opt-in
checkpoint layer backed by per-ticker SQLite databases so the graph
resumes from the last successful node.
How to use:
- CLI: tradingagents analyze --checkpoint
- CLI: tradingagents analyze --clear-checkpoints
- Python: config["checkpoint_enabled"] = True
Lifecycle:
- propagate() recompiles the graph with a SqliteSaver when enabled and
injects a deterministic thread_id derived from ticker+date so the
same ticker+date resumes while a different date starts fresh.
- On successful completion the per-thread checkpoint rows are cleared.
- The context manager is closed in a try/finally so a crash never
leaks the SQLite connection or leaves the graph in checkpoint mode.
Storage: ~/.tradingagents/cache/checkpoints/<TICKER>.db
(override via TRADINGAGENTS_CACHE_DIR).
The checkpointer module is new (tradingagents/graph/checkpointer.py)
and the GraphSetup now returns the uncompiled workflow so it can be
recompiled with a saver when needed.
Adds langgraph-checkpoint-sqlite>=2.0.0 dependency. 3 new tests verify
the crash/resume cycle and that a different date starts fresh.
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
- 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)
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 save prompt after analysis with organized subfolder structure
- Fix report truncation by using sequential panels instead of Columns
- Add optional full report display prompt
- Add update_analyst_statuses() for unified status logic (pending/in_progress/completed)
- Normalize analyst selection to predefined ANALYST_ORDER for consistent execution
- Add message deduplication to prevent duplicates from stream_mode=values
- Restructure streaming loop so state handlers run on every chunk
- 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)
- Added support for running CLI and Ollama server via Docker
- Introduced tests for local embeddings model and standalone Docker setup
- Enabled conditional Ollama server launch via LLM_PROVIDER
