[Feature] console print metrics add env

[CSWYF3634076]

Motivation

• 为控制台打印增加环境变量开关
• 控制decode打印的频率
• cuda_graph字段更精确

Modifications

增加两个环境变量，控制是否打印和打印频率
参考PR #6196 进行cuda_graph字段的确定

Usage or Command

no

Accuracy Tests

no

Checklist

• Add at least a tag in the PR title.
  • Tag list: [[FDConfig],[APIServer],[Engine], [Scheduler], [PD Disaggregation], [Executor], [Graph Optimization], [Speculative Decoding], [RL], [Models], [Quantization], [Loader], [OP], [KVCache], [DataProcessor], [BugFix], [Docs], [CI], [Optimization], [Feature], [Benchmark], [Others], [XPU], [HPU], [GCU], [DCU], [Iluvatar], [Metax]]
  • You can add new tags based on the PR content, but the semantics must be clear.
• Format your code, run pre-commit before commit.
• Add unit tests. Please write the reason in this PR if no unit tests.
• Provide accuracy results.
• If the current PR is submitting to the release branch, make sure the PR has been submitted to the develop branch, then cherry-pick it to the release branch with the [Cherry-Pick] PR tag.

[paddle-bot]

Thanks for your contribution!

[Copilot]

Pull request overview

该 PR 为调度器（scheduler）在控制台输出的 metrics 日志增加环境变量开关与频率控制，并在 decode 日志中更准确地展示当前 step 是否实际使用了 CUDAGraph（结合 graph_opt_config 的不同模式）。

Changes:

• 新增环境变量 FD_CONSOLE_SCHEDULER_METRICS 控制是否打印 scheduler prefill/decode batch 日志
• 新增环境变量 FD_CONSOLE_DECODE_LOG_INTERVAL 控制 decode batch 日志打印间隔，并在 SchedulerMetricsLogger 内实现按间隔打印
• 在 ResourceManagerV1.schedule() 中更精确计算 decode 阶段日志里的 use_cudagraph 字段（参考 6196 的模式区分）

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 1 comment.

File	Description
tests/engine/test_scheduler_metrics_logger.py	增加 decode 打印间隔与环境变量读取的单测覆盖
fastdeploy/envs.py	注册新增的两个环境变量并支持惰性读取
fastdeploy/engine/sched/scheduler_metrics_logger.py	增加 decode 日志按间隔打印逻辑，并从 env 读取间隔
fastdeploy/engine/sched/resource_manager_v1.py	增加日志总开关判断，并细化 decode 日志里 use_cudagraph 的判定逻辑

[Copilot]

建议为新增的控制台日志开关/逻辑补充单元测试：当前修改在 schedule() 中新增了 envs.FD_CONSOLE_SCHEDULER_METRICS 的开关判断，并且后续对 use_cudagraph 的计算引入了多分支条件；但现有 ResourceManagerV1 相关测试未覆盖“开关为 0 时不应调用 logger”以及不同 graph_opt_config 组合下 use_cudagraph 取值是否符合预期。可以在 tests/v1/test_schedule_output.py 或新增用例里通过注入 mock 的 scheduler_metrics_logger 来断言 log_prefill_batch/log_decode_batch 的调用与参数。

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (develop@5bfc093). Learn more about missing BASE report.

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #6413   +/-   ##
==========================================
  Coverage           ?   67.93%           
==========================================
  Files              ?      391           
  Lines              ?    52558           
  Branches           ?     8202           
==========================================
  Hits               ?    35703           
  Misses             ?    14249           
  Partials           ?     2606           

Flag	Coverage Δ
GPU	67.93% <100.00%> (?)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.