更新功能

backend/README.md

@@ -9,3 +9,40 @@ The backend owns the application API and CAD generation workflow:
 - `tests/`: Engine, API, and end-to-end generation tests.
 
 Expected development entrypoint: `app.main:app`, served by Uvicorn.
+
+## Incremental Generation Configuration
+
+Incremental generation is enabled by default. It requires a separately
+configured vision-capable review model and the Python OpenCascade/Pillow
+technical renderer; a run
+fails instead of skipping visual review when either is unavailable.
+
+```dotenv
+# Authoring provider/model must already be configured as usual.
+CDSL_INCREMENTAL_GENERATION=1
+
+# Must name one configured provider and one model listed in that provider's
+# CDSL_<PROVIDER>_VISION_MODELS setting. It is intentionally not inferred
+# from the authoring model.
+CDSL_REVIEW_PROVIDER=openai
+CDSL_REVIEW_MODEL=gpt-4.1-mini
+CDSL_OPENAI_VISION_MODELS=gpt-4.1-mini
+
+# Install Python rendering dependencies. The renderer reads the revision STEP
+# file and creates canonical images without a browser or GPU driver.
+pip install -r requirements.txt
+
+# Optional per-node retry budgets.
+CDSL_NODE_AUTHORING_ATTEMPTS=2
+CDSL_NODE_REPAIR_ATTEMPTS=2
+CDSL_NODE_REPLAN_ATTEMPTS=1
+```
+
+Every checkpoint is rebuilt from its fully materialized CDSL through the
+`cdsl_only` runtime. Checkpoint GLB files are preview-only; STEP, CDSL, and
+reports are available only after the task reaches `COMPLETED`.
+
+The generation plan contains semantic node IDs only. The backend derives the
+unique CDSL feature and sketch IDs from each node, then writes them during
+fragment materialization. This keeps naming and topology ownership stable
+without requiring the authoring model to reproduce internal identifiers.