adapt for ModelHub agent platform

README.md

@@ -0,0 +1,42 @@
+# ModelHub Adaptation Agent
+
+This repository is packaged for the ModelHub XC agent platform.
+
+## Platform Contract
+
+- Root-level `Dockerfile`
+- Listens on port `8080`
+- Exposes `GET /health`
+- Handles `SIGTERM`
+- Reads platform-provided `STRATEGY_ID` and attaches it to task submissions as `strategyId`
+
+The root `main.py` starts a lightweight health server and runs the existing
+submission poller in a child process.
+
+## Runtime Environment
+
+Set credentials with environment variables. Do not commit local key files.
+
+- `MODELHUB_XC_TOKEN` or `XC_TOKEN`
+- `HF_TOKEN` optional, but recommended for Hugging Face API limits
+- `STRATEGY_ID` is expected to be injected by the ModelHub agent platform
+
+Optional tuning:
+
+- `MODELHUB_AGENT_POLL_INTERVAL_SECONDS` default `300`
+- `MODELHUB_AGENT_IDLE_INTERVAL_SECONDS` default `600`
+- `MODELHUB_AGENT_POST_CYCLE_COOLDOWN_SECONDS` default `30`
+- `MODELHUB_AGENT_MAX_SUBMITS_PER_RUN` default `5`
+- `MODELHUB_AGENT_DAILY_TARGET`
+- `MODELHUB_AGENT_MIN_DOWNLOADS`
+- `MODELHUB_AGENT_GPUS`
+- `MODELHUB_AGENT_EXTRA_ARGS`
+
+## Deploy
+
+Create a tag and submit the repository URL plus tag in "我的适配智能体".
+
+```bash
+git tag agent-v1
+git push origin agent-v1
+```