feat: add queue-aware adaptive scheduling

README.md

@@ -44,18 +44,50 @@ Optional tuning:
 - `MODELHUB_AGENT_GPUS`
 - `MODELHUB_AGENT_EXTRA_ARGS`
 - `MODELHUB_GPU_STRATEGY_STATE_PATH` default `.modelhub_state/gpu_strategy.json`
+- `MODELHUB_MARKET_INTELLIGENCE_PATH` default `.modelhub_state/market_intelligence.json`
+- `MODELHUB_MARKET_QUEUE_REFRESH_SECONDS` default `600`
+- `MODELHUB_MARKET_FRAMEWORK_REFRESH_SECONDS` default `21600`
+- `MODELHUB_MARKET_THROUGHPUT_WINDOW_HOURS` default `6`
+- `MODELHUB_MARKET_FRAMEWORK_MIN_SAMPLES` default `100`
 - `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
 
-When no explicit GPU override is supplied, the worker uses a local 50/30/20
+When no explicit GPU override is supplied, the worker uses a queue-aware 50/30/20
 strategy generation:
 
 - 50%: the three long-term GPUs with the best Wilson lower confidence score and at least 100 terminal samples
-- 30%: round-robin exploration across every currently supported GPU
-- 20%: the best GPU among the latest 1,000 terminal tasks
+- 30%: exploration across every currently supported GPU
+- 20%: the top recent GPUs among the latest 1,000 terminal tasks
+
+The 50/30/20 category ratio remains exact across accepted tasks. Inside each
+category, weighted fair scheduling combines the category's historical rank with
+live public market data:
+
+- estimated backlog hours (`waiting / recent completions per hour`) instead of raw queue length
+- recent public success quality, scored with a Wilson lower confidence bound
+- machine availability, running workers, and advertised concurrency
+- a circuit breaker for unavailable or apparently stalled GPU pools
+
+This optimizes expected successful completions rather than blindly selecting the
+smallest queue. Queue/throughput data is refreshed every 10 minutes and persisted
+in `.modelhub_state/market_intelligence.json`. A failed refresh keeps the last good
+snapshot, uses a retry backoff, and never blocks normal submissions.
+
+For each compatible model/GPU pair, the worker also ranks the GPU's supported
+frameworks using ModelHub's public aggregate `modelCount` and `successCount` data,
+then blends in the worker's own GPU+framework outcomes with a capped weight.
+Only frameworks with at least 100 samples receive statistical priority; the
+legacy safe framework order remains the fallback. Framework statistics refresh
+every 6 hours, so they do not add per-model API traffic. Newly published
+frameworks are discovered automatically, but receive no novelty bonus: they can
+win only when their confidence-adjusted success score is better. A new framework
+is eligible only after the authenticated official build-config endpoint returns
+a complete config that passes local structure, placeholder, framework-name, and
+GPU-parallelism validation. Valid official configs are cached and refreshed with
+the framework snapshot; local templates remain the fail-safe fallback.
 
 Only platform-accepted tasks count. After exactly 200 accepted tasks, the next
 poll cycle reloads all account history, generates a new immutable strategy snapshot,
@@ -104,12 +136,15 @@ 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. Version `2026.08.02.5`
 adds fail-closed model/GPU prechecks and persistent uniqueness exclusions.
+Version `2026.08.04.1` adds queue/throughput intelligence, GPU health circuit
+breaking, weighted-fair scheduling, live framework/config discovery, and
+confidence-ranked public-plus-local framework selection.
 
 ## Deploy
 
 Create a tag and submit the repository URL plus tag in "我的适配智能体".
 
 ```bash
-git tag agent-v6
-git push origin agent-v6
+git tag agent-v12
+git push origin agent-v12
 ```