f289a156e6
Merge afdd7abaff into 4641c03340
2026-03-31 13:23:43 +01:00
afdd7abaff
Merge branch 'main' into copilot_oauth
2026-03-31 13:23:37 +01:00
4641c03340
TradingAgents v0.2.3
2026-03-29 19:50:46 +00:00
e75d17bc51
chore: update model lists and defaults to GPT-5.4 family
2026-03-29 19:45:36 +00:00
6cddd26d6e
feat: multi-language output support for analyst reports and final decision ( #472 )
2026-03-29 19:19:01 +00:00
c61242a28c
Merge pull request #464 from CadeYu/sync-validator-models
...
sync model validation with cli catalog
2026-03-29 11:07:51 -07:00
58e99421bd
fix: pass base_url to Google and Anthropic clients for proxy support ( #427 )
2026-03-29 17:59:52 +00:00
46e1b600b8
Merge pull request #453 from javierdejesusda/fix/standardize-google-api-key
...
fix(llm_clients): standardize Google API key to unified api_key param
2026-03-29 10:54:28 -07:00
ae8c8aebe8
fix: gracefully handle invalid indicator names in tool calls ( #429 )
2026-03-29 17:50:30 +00:00
f3f58bdbdc
fix: add yf_retry to yfinance news fetchers ( #445 )
2026-03-29 17:42:24 +00:00
e1113880a1
fix: prevent look-ahead bias in backtesting data fetchers ( #475 )
2026-03-29 17:34:35 +00:00
bd6a5b75b5
fix model catalog typing and known-model helper
2026-03-25 21:46:56 +08:00
8793336dad
sync model validation with cli catalog
2026-03-25 21:23:02 +08:00
047b38971c
refactor: simplify api_key mapping and consolidate tests
...
Apply review suggestions: use concise `or` pattern for API key
resolution, consolidate tests into parameterized subTest, move
import to module level per PEP 8.
2026-03-24 14:52:51 +01:00
f5026009f9
fix(llm_clients): standardize Google API key to unified api_key param
...
GoogleClient now accepts the unified `api_key` parameter used by
OpenAI and Anthropic clients, mapping it to the provider-specific
`google_api_key` that ChatGoogleGenerativeAI expects. Legacy
`google_api_key` still works for backward compatibility.
Resolves TODO.md item #2 (inconsistent parameter handling).
2026-03-24 14:35:02 +01:00
57a2ae5438
patched the Copilot client to sanitize malformed usage metadata before langchain_openai processes it
2026-03-23 15:46:04 +00:00
1cb6d4e882
Update tradingagents/llm_clients/copilot_client.py
...
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-03-23 15:38:28 +00:00
6d3b19d705
Update cli/utils.py
...
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-03-23 15:38:10 +00:00
b0754b3e39
Update tradingagents/llm_clients/copilot_client.py
...
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-03-23 15:37:36 +00:00
7064884b4f
removed the duplicate _resolve_model_options definition from utils.py (line 137), leaving the original helper in place and keeping all callers unchanged
2026-03-23 15:20:15 +00:00
d38d5e2ecb
Update tradingagents/llm_clients/copilot_client.py
...
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-03-23 15:19:04 +00:00
ab1b2883ad
update
2026-03-23 14:58:53 +00:00
e76a6742be
Update tradingagents/llm_clients/copilot_client.py
...
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-03-23 14:52:49 +00:00
ee1c3a69ee
Update tradingagents/llm_clients/copilot_client.py
...
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-03-23 14:52:40 +00:00
e0b7fed7f4
Update cli/utils.py
...
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-03-23 14:52:33 +00:00
706e6bf3a9
Update cli/utils.py
...
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-03-23 14:52:09 +00:00
902ad8b932
refactor: extract _resolve_model_options() to remove duplicated logic
...
Both select_shallow_thinking_agent and select_deep_thinking_agent had
identical Copilot/static model resolution blocks. Extract into a single
helper to improve maintainability.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-23 14:47:20 +00:00
d6ef3c5d4d
fix: raise explicit error when gh token is missing in CopilotClient
...
Replace the 'copilot' fallback string with a RuntimeError so users get
a clear message instead of a cryptic auth failure from the API.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-23 14:46:25 +00:00
6d53f33df0
fix: verify Copilot subscription access after gh auth login
...
After a successful gh auth login, call check_copilot_auth() to confirm
the new token actually has Copilot access — not just that a token exists.
Prevents proceeding with an account that has no Copilot subscription.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-23 14:45:33 +00:00
fcca3236e9
update
2026-03-23 14:12:01 +00:00
a84c69e42f
update
2026-03-23 14:03:27 +00:00
894b7bcba0
update
2026-03-23 14:01:30 +00:00
888fdfbfb9
refactor: move Copilot logic into standalone copilot_client.py
...
- Add tradingagents/llm_clients/copilot_client.py with all Copilot auth
(gh CLI token, GraphQL URL resolution, required headers) and CopilotClient
class inline — no separate auth module needed
- Simplify openai_client.py: remove Copilot code, inline codex OAuth token
logic directly (was tradingagents/auth/codex_token.py)
- Remove tradingagents/auth/ folder entirely
- Update factory.py to route 'copilot' -> CopilotClient
- Simplify cli/utils.py to delegate to copilot_client helpers
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-23 13:59:09 +00:00
24e97fb703
fix: use Responses API for Copilot models that don't support chat/completions
...
gpt-5.4, gpt-5.4-mini, and codex variants only support /responses,
not /chat/completions on the Copilot endpoint. Auto-detect and set
use_responses_api=True for these models.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-23 13:50:55 +00:00
d8ac212253
feat: add GitHub Copilot provider with OAuth auth via gh CLI
...
Replace GitHub Models (models.github.ai) with GitHub Copilot inference API
(api.individual.githubcopilot.com). Auth uses gh CLI token with required
Copilot headers (Copilot-Integration-Id, X-GitHub-Api-Version).
- Add tradingagents/auth/ module: gh token retrieval, Copilot URL resolution
via GraphQL, Codex OAuth token with auto-refresh
- Add "copilot" provider to OpenAIClient with dynamic base URL and headers
- Add live model listing from Copilot /models endpoint (27 models)
- Add perform_copilot_oauth() with Copilot access verification
- Remove all GitHub Models (models.github.ai) references
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-23 13:18:55 +00:00
589b351f2a
TradingAgents v0.2.2
2026-03-22 23:47:56 +00:00
6c9c9ce1fd
fix: set process-level UTF-8 default for cross-platform consistency
2026-03-22 23:42:37 +00:00
b8b2825783
refactor: standardize portfolio manager, five-tier rating scale, fix analyst status tracking
2026-03-22 23:30:29 +00:00
318adda0c6
refactor: five-tier rating scale and streamlined agent prompts
2026-03-22 23:07:20 +00:00
c3ba3bf428
Merge pull request #413 from CadeYu/codex/exchange-qualified-tickers
...
fix: preserve exchange-qualified tickers across agent prompts
2026-03-22 15:36:14 -07:00
7cca9c924e
fix: add exponential backoff retry for yfinance rate limits ( #426 )
2026-03-22 22:11:08 +00:00
bd9b1e5efa
feat: add Anthropic effort level support for Claude models
...
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.
2026-03-22 21:57:05 +00:00
77755f0431
chore: consolidate install, fix CLI portability, normalize LLM 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
2026-03-22 21:38:01 +00:00
0b13145dc0
fix: handle list content when writing report sections
...
Closes #400
2026-03-22 20:40:18 +00:00
3ff28f3559
fix: use OpenAI Responses API for native models
...
Enable use_responses_api for native OpenAI provider, which supports
reasoning_effort with function tools across all model families.
Removes the UnifiedChatOpenAI subclass workaround.
Closes #403
2026-03-22 20:34:03 +00:00
7d200d834a
style: inline single-use instrument context vars
2026-03-21 21:31:38 +08:00
08bfe70a69
fix: preserve exchange-qualified tickers across agent prompts
2026-03-21 21:10:13 +08:00
f362a160c3
Merge pull request #379 from yang1002378395-cmyk/fix-ssl-http-client-support
...
fix: add http_client support for SSL certificate customization
2026-03-15 16:53:04 -07:00
64f07671b9
fix: add http_client support for SSL certificate customization
...
- Add http_client and http_async_client parameters to all LLM clients
- OpenAIClient, GoogleClient, AnthropicClient now support custom httpx clients
- Fixes SSL certificate verification errors on Windows Conda environments
- Users can now pass custom httpx.Client with verify=False or custom certs
Fixes #369
2026-03-16 07:41:20 +08:00
b19c5c18fb
docs: add v0.2.1 release note to README
2026-03-15 23:39:05 +00:00
Michael Liu
Yijia-Xiao
Yijia Xiao
CadeYu
javierdejesusda
Jiaxu Liu
阳虎