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
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
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
54cdb146d0
feat: add footer statistics tracking with LangChain callbacks
...
- 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)
2026-02-03 22:27:20 +00:00
79051580b8
feat: add multi-provider LLM support with factory pattern
...
- Add tradingagents/llm_clients/ with unified factory pattern
- Support OpenAI, Anthropic, Google, xAI, OpenRouter, Ollama, vLLM
- Replace direct LLM imports in trading_graph.py with create_llm_client()
- Handle provider-specific params (reasoning_effort, thinking_config)
2026-02-03 22:27:20 +00:00
Jiaxu Liu
阳虎
Yijia Xiao