LambdaBankingConglomerate/TraderAI
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 8 Wiki Activity

feat: deepseek
Build Release EXE / build-windows-exe (release) Successful in 1m2s
Details

Browse Source
This commit is contained in:
Hudson Riggs
2026-06-08 23:41:46 -04:00
parent 00cf6f8747
commit 454bb57484
24 changed files with 1719 additions and 183 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+4 -3
View File
@@ -1,6 +1,6 @@
# TraderAI
Local Ollama-, OpenAI-, or Codex-powered chat for UEX marketplace workflows.
Local Ollama-, DeepSeek-, OpenAI-, or Codex-powered chat for UEX marketplace workflows.
## What It Does
@@ -25,9 +25,10 @@ Local Ollama-, OpenAI-, or Codex-powered chat for UEX marketplace workflows.
```
3. Create `.env` from `.env.example` and set `UEX_SECRET_KEY` and/or `UEX_BEARER_TOKEN` if you want authenticated actions.
If you want the cheapest hosted default, set `MODEL_PROVIDER=deepseek`, set `DEEPSEEK_API_KEY`, and keep `DEEPSEEK_MODEL=deepseek-v4-flash` unless you specifically want `deepseek-v4-pro`.
If you want to use OpenAI instead of Ollama, set `MODEL_PROVIDER=openai`, set `OPENAI_API_KEY`, and optionally change `OPENAI_MODEL` from the default `gpt-5.4-mini`.
If you want to use Codex models with ChatGPT/Codex OAuth, install the Codex CLI, set `MODEL_PROVIDER=codex`, and optionally change `CODEX_MODEL` from the default `gpt-5.4`. TraderAI uses the local `codex app-server` JSON-RPC interface for both authentication and chat turns.
`MODEL_REASONING_EFFORT` controls reasoning depth for OpenAI and Codex and defaults to `medium`.
`MODEL_REASONING_EFFORT` controls reasoning depth for DeepSeek, OpenAI, and Codex and defaults to `medium`.
`SCMDB_BASE_URL` defaults to `https://scmdb.net`.
`CORNERSTONE_BASE_URL` defaults to `https://finder.cstone.space`.
4. Install and run:
@@ -41,7 +42,7 @@ Local Ollama-, OpenAI-, or Codex-powered chat for UEX marketplace workflows.
## Notes
Ollama runs locally at `http://localhost:11434` by default. This app can talk to Ollama's native chat API, OpenAI's Chat Completions API, or the local Codex App Server authenticated through ChatGPT/Codex OAuth, then executes approved UEX calls in the FastAPI backend. `OLLAMA_NUM_CTX` controls the per-request Ollama context window; `64512` is the default because Ollama recommends at least 64k tokens for agent-style workflows when hardware allows it.
Ollama runs locally at `http://localhost:11434` by default. This app can talk to Ollama's native chat API, DeepSeek's OpenAI-compatible Chat Completions API, OpenAI's Chat Completions API, or the local Codex App Server authenticated through ChatGPT/Codex OAuth, then executes approved UEX calls in the FastAPI backend. `OLLAMA_NUM_CTX` controls the per-request Ollama context window; `64512` is the default because Ollama recommends at least 64k tokens for agent-style workflows when hardware allows it. DeepSeek context caching is provider-side and automatic when repeated prompt prefixes line up.
## Releases And Updates