feat: dynamically clean incompatible architectures

modelhub_submmit_api/README.md

@@ -16,7 +16,7 @@ It currently supports:
 - `main.py`: core discovery, scoring, dedup, and submission
 - `daily_runner.py`: daily wave orchestration
 - `poll_runner.py`: long-running queue refiller
-- `queue_cleanup.py`: fail-closed cleanup for active tasks that are certain to exceed GPU memory
+- `queue_cleanup.py`: fail-closed cleanup for certain OOM, architecture, and age policies
 - `runner_common.py`: shared token / key file loading
 - `hf_discovery.py`: ModelScope model discovery and inspection (keeps the legacy module name)
 - `modelhub_client.py`: ModelHub API client and token-pool routing
@@ -96,9 +96,13 @@ bash run_poll.sh --dry-run
   sub-20% rate over the latest 20 terminal tasks pauses it for 6 hours.
 - An explicit "framework does not support this model/architecture" failure learns
   a 30-day GPU + framework + task + architecture block. Architecture identity
-  comes from candidate `config.json` (`architectures`, with `model_type` only as
-  fallback), never from repository names. A newer success clears the block, and
+  comes from candidate `config.json` plus exact unsupported `model_type` or
+  `architectures` strings in the runtime log, never from repository names. A newer success clears the block, and
   generic unsupported backend/operator messages cannot create one.
+- Blacklist additions are persisted and detected every three poll cycles. A new
+  rule immediately launches a lightweight architecture-only queue scan. Exact
+  matching waiting tasks are stopped after two state checks; running tasks and
+  tasks without local framework/task metadata are protected.
 - A strategy generation lasts exactly 200 platform-accepted submissions. Rejected API calls and
   duplicates do not advance it. The next cycle refreshes platform history before submitting again.
 - Strategy state is stored in `.modelhub_state/gpu_strategy.json`; a generation never recalculates
@@ -227,6 +231,7 @@ Persistent local scheduler state is written under `.modelhub_state/`:
 - `account_capacity.json`: learned per-account active-task limits
 - `submission_exclusions.jsonl`: non-retryable model/GPU uniqueness rejections
 - `queue_cleanup_latest.json`: latest active-task sizing evidence and cancellation result
+- `architecture_compatibility_blacklist.json`: current dynamic compatibility blocks and evidence
 
 ## Verification