A-shares already resolve through the Yahoo Finance vendor (Shanghai .SS,
Shenzhen .SZ) with correct identity and indicators; add the SSE/SZSE
composite benchmarks so their alpha isn't measured against SPY, and
document the exchange-suffix tickers we support (incl. A-shares, crypto).
Adds a cross-provider temperature config (and TRADINGAGENTS_TEMPERATURE),
forwarded to every LLM client when set, so runs can be made less variable
on models that honor it. Adds a README "Reproducibility" section that
separates the sources of run-to-run variation, what users can control
(temperature, non-reasoning model, pinned date), and what is inherent to
LLM-driven analysis, and notes that the identity and verified-data fixes
already removed the "different companies / fabricated prices" variance.
#178#168
SPY was hardcoded as the alpha benchmark in both the return-fetch
path and the reflection label, which produced meaningless alpha for
.NS / .T / .HK / .L / .TO / .AX / .BO listings — FX drift between a
local-currency stock and a USD index dominates the spread.
DEFAULT_CONFIG now exposes benchmark_ticker (explicit override) and
benchmark_map (suffix → regional index, with SPY as the empty-suffix
default). TRADINGAGENTS_BENCHMARK_TICKER joins the env-overlay table.
Trading graph resolves the benchmark once per ticker and threads it
through to both _fetch_returns and reflect_on_final_decision, so the
alpha label reads "Alpha vs ^N225" for Tokyo listings, "Alpha vs ^HSI"
for Hong Kong, etc., instead of the misleading "Alpha vs SPY".
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
Per-ticker article limit, global article limit, global lookback
window, and macro query list are now read from get_config()
instead of being hardcoded. Tool wrapper get_global_news passes
None defaults so config overrides flow through the LLM-tool path
too. Macro query defaults broadened from 4 US-centric strings to
5 covering Fed, S&P 500, geopolitics, ECB/BOJ/BOE, commodities.
#606#558#562
This release bundles substantial work since v0.2.3:
- Structured-output Research Manager, Trader, and Portfolio Manager
(canonical with_structured_output pattern, single LLM call per agent,
rendered markdown preserves the existing report shape).
- LangGraph checkpoint resume for crash recovery (--checkpoint flag).
- Persistent decision log replacing the per-agent BM25 memory, with
deferred reflection driven by yfinance returns + alpha vs SPY.
- DeepSeek, Qwen, GLM, and Azure OpenAI provider support; dynamic
OpenRouter model selection.
- Docker support; cache and logs moved to ~/.tradingagents/ to fix
Docker permission issues.
- Windows UTF-8 encoding fix on every file I/O site.
- 5-tier rating consistency (Buy / Overweight / Hold / Underweight / Sell)
across Research Manager, Portfolio Manager, signal processor, memory log.
Plus the small quality items in this commit:
1. Suppress noisy Pydantic serializer warnings from OpenAI Responses-API
parse path by defaulting structured-output to method="function_calling"
(root-cause fix, not a warnings filter — same typed result, no warnings).
2. Ship scripts/smoke_structured_output.py so contributors can verify
their provider's structured-output path with one command.
3. Add opt-in memory_log_max_entries config — when set, oldest resolved
memory log entries are pruned once the cap is exceeded; pending
entries (unresolved) are never pruned.
4. backend_url default changed from the OpenAI URL to None so the
per-provider client falls back to its native endpoint instead of
leaking OpenAI's URL into Gemini / other clients.
CHANGELOG.md added with the full v0.2.4 entry. 92 tests pass without API keys.
Default config had backend_url='https://api.openai.com/v1' which was
forwarded to every provider client, including Google. ChatGoogleGenerativeAI
constructed requests against that base, producing malformed URLs like
https://api.openai.com/v1/v1beta/models/gemini-2.5-flash:generateContent
that 404 with empty body.
Discovered while running propagate() against Gemini end-to-end. The
structured-output smoke worked because that path constructed the LLM
without going through the factory and without forwarding backend_url;
propagate() goes through TradingAgentsGraph.__init__ which forwards
config['backend_url'] to every provider.
Fix: default to None. Each provider client falls back to its own
endpoint (api.openai.com for OpenAI via _PROVIDER_CONFIG, Gemini's
default for Google, and so on). The CLI flow already sets backend_url
explicitly per provider when the user picks one, so that path is
unchanged.
Verified: full propagate() now passes end-to-end on both
OpenAI gpt-5.4-mini and Gemini gemini-3-flash-preview, with all nine
structure/log/signal checks green for each.
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.
The previous per-agent BM25 memory was effectively dead code — its only
caller was a commented-out line in main.py. Replace it with a single
append-only markdown decision log driven by the propagate() lifecycle.
Lifecycle:
- store_decision() appends a pending entry at the end of every run
- _resolve_pending_entries() runs at the start of the next same-ticker
run, fetches yfinance returns + alpha vs SPY, and writes one LLM
reflection per resolved entry through an atomic temp-file rename
- Portfolio Manager consumes state["past_context"] (5 most recent
same-ticker entries plus 3 cross-ticker reflection-only excerpts)
Storage at ~/.tradingagents/memory/trading_memory.md
(override: TRADINGAGENTS_MEMORY_LOG_PATH).
Tag schema:
- Pending: [YYYY-MM-DD | TICKER | Rating | pending]
- Resolved: [YYYY-MM-DD | TICKER | Rating | +X.X% | +Y.Y% | Nd]
Removes rank-bm25 dependency and the legacy reflect_and_remember()
plumbing across reflection.py, trading_graph.py, and the agent factories.
49 new tests in tests/test_memory_log.py cover the storage, deferred
reflection, prompt injection, and legacy-removal paths. Full suite
(58 tests) passes in under 2 seconds without API keys.
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.
- Replace FinnHub with Alpha Vantage API in README documentation
- Implement comprehensive Alpha Vantage modules:
- Stock data (daily OHLCV with date filtering)
- Technical indicators (SMA, EMA, MACD, RSI, Bollinger Bands, ATR)
- Fundamental data (overview, balance sheet, cashflow, income statement)
- News and sentiment data with insider transactions
- Update news analyst tools to use ticker-based news search
- Integrate Alpha Vantage vendor methods into interface routing
- Maintain backward compatibility with existing vendor system
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Yijia-Xiao