fix: coordinate concurrent account capacity filling

README.md

@@ -26,15 +26,33 @@ the image.
 
 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_POLL_INTERVAL_SECONDS` default `15`
+- `MODELHUB_AGENT_IDLE_INTERVAL_SECONDS` default `60`
+- `MODELHUB_AGENT_POST_CYCLE_COOLDOWN_SECONDS` default `2`
+- `MODELHUB_AGENT_MAX_SUBMITS_PER_RUN` default `0` (fill all currently available slots)
+- `MODELHUB_AGENT_ACTIVE_TASK_CAP` default `100` per account
+- `MODELHUB_AGENT_ACTIVE_COUNTS_TTL_SECONDS` default `15`
+- `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_AGENT_DAILY_TARGET`
 - `MODELHUB_AGENT_MIN_DOWNLOADS`
 - `MODELHUB_AGENT_GPUS`
 - `MODELHUB_AGENT_EXTRA_ARGS`
 
+## Concurrent Agents
+
+The token pool keeps a local reservation for every in-flight submission, so a
+lagging platform count cannot send all concurrent requests to the same account.
+If another process fills an account first, the submission is retried immediately
+against another account with capacity.
+
+Workers that share a filesystem also coordinate model/GPU claims through
+`.modelhub_state/submission_claims.jsonl`. Workers in isolated containers use
+different candidate ordering (derived from `STRATEGY_ID`, instance ID, or
+hostname), which reduces duplicate work while the platform remains the final
+authority for account capacity and model/GPU uniqueness.
+
 ## Deploy
 
 Create a tag and submit the repository URL plus tag in "我的适配智能体".