Commit Graph
16 Commits
Author SHA1 Message Date
Yijia-Xiao 7c8fe2fe9f fix(data): normalize symbols on the identity and reflection paths
resolve_instrument_identity and the reflection return lookup queried Yahoo with
the raw ticker, so broker/forex/commodity symbols (XAUUSD, BTCUSD, EURUSD)
failed identity or could mismatch the priced instrument even though the price
path already normalized them. Route both through normalize_symbol (#983, #984).
2026-06-13 20:39:52 +00:00
Yijia-Xiao 47cbb321fe feat(market): verified market-data snapshot to ground numeric claims
The market analyst could confabulate exact figures — citing a Bollinger
band or a "historically validated bounce" the data doesn't support (#830).
Add a deterministic get_verified_market_snapshot tool (latest OHLCV row,
common indicators, recent closes) the analyst must consult and treat as
the source of truth for any exact price/indicator claim, and instruct it
not to assert historical validation or support bounces without tool-backed
dates and prices.

#830
2026-05-31 01:58:32 +00:00
Yijia-Xiao d7b40a2a5c fix(graph): resolve instrument identity to stop wrong-company hallucination
Agents had no ground-truth ticker→company mapping, so the market analyst
could pattern-match a price chart to the wrong company (e.g. TOTDY read as
"TotalEnergies"), and every downstream agent inherited the bad framing.

Resolve identity once at run start via a cached, fail-open yfinance lookup
and inject company/sector/exchange into the shared instrument context that
all twelve agents consume, with an explicit do-not-substitute instruction.
Resolution runs on both the propagate() and CLI entry points.

Also replaces the bare "Continue" message-clear placeholder, which some
OpenAI-compatible providers interpreted as the user task, with a
context-anchored placeholder carrying the resolved identity and date.

#814 #888
2026-05-30 23:56:32 +00:00
CadeYu a2f343bb54 Merge remote-tracking branch 'upstream/main' into crypto-analysis-mvp
# Conflicts:
#	cli/utils.py
#	tradingagents/agents/analysts/social_media_analyst.py
#	tradingagents/agents/researchers/bear_researcher.py
2026-05-11 16:41:09 +08:00
Yijia-Xiao 6b384f74f9 feat(i18n): localize researchers, risk debators, research mgr, trader
output_language config now propagates to every user-facing agent.
Previously only the four analysts and portfolio manager respected
the setting, producing partial-localization reports with English
debate text interleaved with non-English analyst sections. Verified
live: 7 agents produce Chinese output when config is set to Chinese.

#575
2026-05-11 05:41:42 +00:00
CadeYu 99ec63f966 merge upstream main into crypto-analysis-mvp 2026-04-18 21:07:54 +08:00
Yijia-Xiao 6cddd26d6e feat: multi-language output support for analyst reports and final decision (#472) 2026-03-29 19:19:01 +00:00
Yijia-Xiao 318adda0c6 refactor: five-tier rating scale and streamlined agent prompts 2026-03-22 23:07:20 +00:00
CadeYu 08bfe70a69 fix: preserve exchange-qualified tickers across agent prompts 2026-03-21 21:10:13 +08:00
Yijia Xiao b06936f420 fix: improve data vendor implementations and tool signatures
- Add get_global_news for Alpha Vantage
- Fix get_insider_transactions signature (remove unused curr_date param)
- Remove unnecessary default params from API calls (sort, limit, tab)
2026-02-03 22:27:20 +00:00
Yijia Xiao d4dadb82fc feat: add multi-provider LLM support with thinking configurations
Models added:
- OpenAI: GPT-5.2, GPT-5.1, GPT-5, GPT-5 Mini, GPT-5 Nano, GPT-4.1
- Anthropic: Claude Opus 4.5/4.1, Claude Sonnet 4.5/4, Claude Haiku 4.5
- Google: Gemini 3 Pro/Flash, Gemini 2.5 Flash/Flash Lite
- xAI: Grok 4, Grok 4.1 Fast (Reasoning/Non-Reasoning)

Configs updated:
- Add unified thinking_level for Gemini (maps to thinking_level for Gemini 3,
  thinking_budget for Gemini 2.5; handles Pro's lack of "minimal" support)
- Add OpenAI reasoning_effort configuration
- Add NormalizedChatGoogleGenerativeAI for consistent response handling

Fixes:
- Fix Bull/Bear researcher display truncation
- Replace ChromaDB with BM25 for memory retrieval
2026-02-03 22:27:20 +00:00
luohy15 a6734d71bc WIP 2025-09-26 16:17:50 +08:00
Max Wong 43aa9c5d09 Local Ollama (#53)
- Fix typo 'Start' 'End'
- Add llama3.1 selection
- Use 'quick_think_llm' model instead of hard-coding GPT
2025-06-26 00:27:01 -04:00
Edward Sun 7eaf4d995f update clear msg bc anthropic needs at least 1 msg in chat call 2025-06-15 23:14:47 -07:00
Edward Sun da84ef43aa main works, cli bugs 2025-06-15 22:20:59 -07:00
Yijia-Xiao cc97cb6d5d chore(release): v0.1.0 – initial public release of TradingAgents 2025-06-05 04:27:57 -07:00