feat: time-bound runs, live stats display, and send-window metrics

[acere]

Closes #57

What

Adds time-bound test runs, a live stats display, send-window-based throughput metrics, and fixes a StopIteration bug in invocation loops.

Changes

llmeter/runner.py

• New run_duration parameter on _RunConfig/Runner/run(): clients send requests continuously for a fixed duration. Mutually exclusive with n_requests.
• New _invoke_for_duration / _invoke_duration / _invoke_duration_c methods — clean separation from count-bound _invoke_n / _invoke_n_c.
• _tick_time_bar async task advances a time-based progress bar every 0.5s.
• _run() dispatches to the right invocation path based on _time_bound flag.
• total_requests always derived from RunningStats._count (single source of truth).
• Both _invoke_n_no_wait and _invoke_for_duration use while/next() instead of for-in-cycle() to prevent StopIteration from silently killing the loop.
• record_send() called before each endpoint.invoke() for send-window timing.

llmeter/utils.py

• RunningStats.record_send(): tracks _first_send_time / _last_send_time.
• RPM in snapshot() uses send window instead of response-side elapsed time.
• New "output_tps" special spec: aggregate output tokens/s based on send window.
• snapshot() returns placeholder values ("—") when _count == 0.

llmeter/live_display.py (new)

• LiveStatsDisplay: HTML table in Jupyter (grouped columns), ANSI multi-line in terminals.
• _classify / _group_stats: auto-groups stats by key patterns (Throughput, TTFT, TTLT, Tokens, Errors).
• Updates in-place, shows placeholders immediately before first response.

llmeter/experiments.py

• LoadTest: new run_duration, low_memory, progress_bar_stats fields forwarded to each run.

docs/user_guide/run_experiments.md

• New sections: Time-bound runs, Live progress-bar statistics, Low-memory mode.

examples/Time-bound runs with Bedrock OpenAI API.ipynb (new)

• End-to-end notebook using bedrock-mantle endpoint with LoadTest, custom stats, low-memory mode, and comparison charts (RPM, TPS, TTFT, TTLT vs clients).

Tests (51 new, 504 total)

• test_running_stats.py: record_send, update, to_stats, snapshot (placeholders, rpm, output_tps, send window, aggregations).
• test_live_display.py: _classify, _group_stats, _in_notebook, LiveStatsDisplay (disabled, terminal, overwrite, prefix).
• test_experiments.py: LoadTest with run_duration/low_memory/progress_bar_stats.
• test_runner.py: time-bound validation, _invoke_for_duration, full runs with duration.

Usage

# Time-bound run
result = await runner.run(run_duration=60, clients=5)

# Time-bound LoadTest
load_test = LoadTest(
    endpoint=my_endpoint,
    payload=sample_payload,
    sequence_of_clients=[1, 5, 10, 20],
    run_duration=60,
    low_memory=True,
    output_path="outputs/load_test",
)
result = await load_test.run()
result.plot_results()