fix: refill from expanded candidate history

README.md

@@ -29,7 +29,8 @@ Optional tuning:
 - `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)
+- The hosted entrypoint always uses `--max-submits-per-run 0` so stale deployment
+  settings cannot restrict a refill cycle to five submissions.
 - `MODELHUB_AGENT_ACTIVE_TASK_CAP` default `100` per account
 - `MODELHUB_CAPACITY_PROBE_INTERVAL_CYCLES` default `3`
 - `MODELHUB_CAPACITY_STATE_PATH` default `.modelhub_state/account_capacity.json`
@@ -44,6 +45,7 @@ Optional tuning:
 - `MODELHUB_GPU_STRATEGY_STATE_PATH` default `.modelhub_state/gpu_strategy.json`
 - `MODELSCOPE_PAGE_INTERVAL_SECONDS` default `0.25`
 - `MODELSCOPE_PAGE_CACHE_TTL_SECONDS` default `900`
+- `MODELHUB_AGENT_VERIFY_CACHE_TTL_SECONDS` default `900`
 
 ## Adaptive GPU Strategy
 
@@ -63,6 +65,18 @@ ModelScope HTTP 429 responses use exponential backoff and `Retry-After`. Success
 pages remain cached, so a later cycle retries the failed page instead of restarting
 the whole pagination scan.
 
+## Adaptive Candidate Discovery
+
+The configured recent window remains the fast path. If it contains no usable
+model/GPU combinations, the same run progressively expands discovery to the last
+7 days, the last 30 days, and finally older history (up to 3,000 models). Scanning
+stops as soon as enough replacement candidates have been found.
+
+Model verification results are reused for 15 minutes across poll cycles, and a
+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.
+
 ## Concurrent Agents
 
 The token pool keeps a local reservation for every in-flight submission, so a
@@ -80,7 +94,8 @@ If the platform reports that a model/GPU is already being validated, the claim
 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
-this behavior.
+duplicate replacement behavior, while version `2026.08.02.4` adds adaptive
+candidate-window expansion and skip-reason reporting.
 
 ## Deploy