Upload BLOG_DRAFT.md

BLOG_DRAFT.md

@@ -1,6 +1,6 @@
 # Field Notes: Putting a 20-Year-Old Chinese Trading Theory on a Fine-Tuned 1.7B
 
-*Built for the Build Small hackathon — a Gradio Space, a local llama.cpp sub-agent pool, a model I fine-tuned myself, and zero cloud APIs.*
+*Built for the Build Small hackathon — a custom-frontend Gradio app (`gradio.Server`), a local llama.cpp sub-agent pool, a model I fine-tuned myself, and zero cloud APIs.*
 
 ## The problem (a real one)
 
@@ -14,7 +14,9 @@ are dense Chinese jargon, and someone had to run it by hand every evening.
 **Chan Compass** fixes both: a Gradio Space that auto-updates after the US close
 (18:10 ET), answers exactly one question per ticker — *do I buy or sell tomorrow,
 at what buy point, in which zone, and where am I wrong?* — and uses a pool of small
-local models as the translators and analysts the rule engine can't be.
+local models as the translators and analysts the rule engine can't be. The results
+are persisted to disk, so when the family opens the app the next morning, the
+overnight run is already there waiting — no spinner, no recompute.
 
 ## Why small models are the honest fit
 
@@ -33,7 +35,7 @@ Early versions shared a single model behind one lock, so the moment two features
 ran at once you'd get "model busy." The fix was a **sub-agent pool** — four small
 models, each with its own lock, running through llama.cpp:
 
-* **Summary** (Signals → AI Summary) — my **fine-tuned Chan-Tuned Qwen3-1.7B**
+* **Interpreter** (Signals → AI Interpret) — my **fine-tuned Chan-Tuned Qwen3-1.7B**
 * **Narrator** (sector rotation) — Qwen3-1.7B
 * **Reporter** (watchlist news + research support) — Qwen3-1.7B
 * **Analyst** (Auto Research) — Qwen3-4B
@@ -43,7 +45,7 @@ summary writes, with no collision.
 
 ## The fine-tune (the part I'm proudest of)
 
-The Summary sub-agent runs a model I trained myself. The app captures every
+The Interpreter sub-agent runs a model I trained myself. The app captures every
 (raw read → English summary) pair it produces into a dataset on the `/data`
 bucket; a couple hundred focused pairs later, I exported the JSONL straight from
 the app's Model tab, LoRA-tuned **Qwen3-1.7B** on a free Colab T4 with Unsloth,
@@ -71,9 +73,9 @@ doing everything adequately.
   dataset** so anyone can see how the agent actually reasoned.
 * **Email any result** — each tab can email its output; on HF (where SMTP is
   blocked) delivery goes over the Resend HTTPS API, markdown rendered to clean HTML.
-* **Spectrum 2 UI** — Adobe's design language in Gradio.
+* **A real custom frontend** — instead of the default Gradio component render, `server.py` builds a `gradio.Server` that serves a hand-built React + Adobe Spectrum 2 UI at `/` and exposes the Python backend as `/api/*` JSON + streaming endpoints. It's still a Gradio app — just wearing its own clothes.
 
-## Four things I learned the hard way
+## Five things I learned the hard way
 
 1. **HF build containers are tiny.** `llama-cpp-python` got OOM-killed compiling at
    *build* time on a Space with 32 GB of *runtime* RAM. Fix: install the runtime at
@@ -89,11 +91,16 @@ doing everything adequately.
 4. **Platforms block SMTP; ship HTTPS email.** Outbound mail ports are closed on
    Spaces, so email failed with "network unreachable." The Resend REST API over
    443 works — and it needs a `User-Agent` header or Cloudflare 403s you.
+5. **A custom frontend on a Gradio Space wants `gradio.Server`, not `.launch()`.**
+   Mounting a React UI and calling `app.launch()` made Gradio's SSR startup check
+   hit `gradio_api/startup-events` and 404. The fix: treat `gradio.Server` as the
+   ASGI app it is and serve it with uvicorn (Docker SDK) — custom look, still a
+   Gradio app.
 
 ## What's next
 
 The agent traces are already public as a Hub dataset; next I want to grow the
-fine-tune set so the Summary model keeps sharpening on exactly the phrasing this
+fine-tune set so the Interpreter model keeps sharpening on exactly the phrasing this
 task needs, and feed real family usage back into that loop.
 
 *Not investment advice. Engine logic unchanged from the original; the app around