fix: prevent repeated model GPU submissions

README.md

@@ -38,6 +38,7 @@ Optional tuning:
 - `MODELHUB_AGENT_RESERVATION_TTL_SECONDS` default `120`
 - `MODELHUB_AGENT_INSTANCE_ID` optional stable worker identity used to spread concurrent agents across accounts and candidates
 - `MODELHUB_AGENT_CLAIMS_PATH` default `.modelhub_state/submission_claims.jsonl`
+- `MODELHUB_SUBMISSION_EXCLUSIONS_PATH` default `.modelhub_state/submission_exclusions.jsonl`
 - `MODELHUB_AGENT_DAILY_TARGET`
 - `MODELHUB_AGENT_MIN_DOWNLOADS`
 - `MODELHUB_AGENT_GPUS`
@@ -77,6 +78,12 @@ locally failed model/GPU pair cools down for 24 hours instead of being excluded
 forever. The `[scan]` lines show every expansion stage, while `[daily] wave_done`
 includes `skip_reasons` so an empty candidate pool is directly diagnosable.
 
+Community deduplication is scoped to the exact model/GPU combination. A model
+adapted on one GPU remains eligible for another GPU. Before each submission the
+worker performs an uncached community check; a lookup failure defers the task
+instead of failing open. Platform uniqueness rejections are persisted per
+model/GPU in `.modelhub_state/submission_exclusions.jsonl` and are not retried.
+
 ## Concurrent Agents
 
 The token pool keeps a local reservation for every in-flight submission, so a
@@ -95,7 +102,8 @@ is retained and the runner immediately draws replacement candidates from the
 same scan instead of retrying the duplicate every cycle. Startup logs and the
 health response expose `agent_version`; version `2026.08.02.3` or newer includes
 duplicate replacement behavior, while version `2026.08.02.4` adds adaptive
-candidate-window expansion and skip-reason reporting.
+candidate-window expansion and skip-reason reporting. Version `2026.08.02.5`
+adds fail-closed model/GPU prechecks and persistent uniqueness exclusions.
 
 ## Deploy