feat(eval): grouped help for the ondemand commands - #2300

Usage: agentcore eval ondemand evaluate [options]

evaluate existing sessions client-side (synchronous; prints scores)

Session source:
  --agent <agent>                  harness ID or Runtime ID whose sessions to
                                   evaluate
  --endpoint <endpoint>            Runtime endpoint qualifier (default DEFAULT)

Session filters:
  --lookback-days <lookback-days>  evaluate sessions from the last N days
  --start-time <start-time>        window start (ISO-8601, with --end-time)
  --end-time <end-time>            window end (ISO-8601, with --start-time)
  --session-ids <session-ids...>   specific session IDs
  --trace-id <trace-id>            a single trace ID (session ID is read off the
                                   span)

Evaluation:
  --evaluators <evaluators...>     evaluator ID(s) to apply
  --ground-truth <ground-truth>    expected answers (JSON
                                   EvaluationReferenceInput[])

Other options:
  -h, --help                       display help for command

Global Options:
  --region <region>                AWS region
  --debug                          debug logging (default: false)
  --json                           JSON output (default: false)
  --endpoint-url <endpoint-url>    endpoint URL override

Parameter details:

  --ground-truth (JSON: list of objects)
      Expected answers for the sessions being evaluated, so an evaluator can score a
      response against a reference instead of judging it on its own. Each entry is an
      EvaluationReferenceInput bound to a session (and optionally a trace) by its span
      context; omit an entry for a session that has no reference answer.

      Accepts inline JSON, file://<path>, or - to read stdin.

      JSON syntax:
        [
          {
            "context": {                        // [required] what this reference applies to
              "spanContext": {
                "sessionId": "string",          // [required]
                "traceId": "string"             // set for a trace-level reference
              }
            },
            "expectedResponse": { "text": "string" },   // trace-level; needs a traceId
            "assertions": [                              // session-level
              { "text": "string" },
              ...
            ],
            "expectedTrajectory": {                      // session-level
              "toolNames": ["string", ...]    // tools the agent should have called
            }
          },
          ...
        ]

      Example:
        --ground-truth '[{"context":{"spanContext":{"sessionId":"session-123"}},"assertions":[{"text":"acknowledges the shipping delay"}]}]'

        --ground-truth file://ground-truth.json

Usage: agentcore eval ondemand simulate [options]

replay a dataset against a Runtime, then evaluate the sessions client-side

Target:
  --runtime-id <runtime-id>                Runtime ID to invoke per scenario
  --endpoint <endpoint>                    Runtime endpoint qualifier (default DEFAULT)

Invocation:
  --payload-template <payload-template>    request body per example (JSON object); {input} is replaced with the input
  --header <header...>                     an ordered application header (repeatable)
  --bearer-token <bearer-token>            CUSTOM_JWT bearer token (for JWT-auth Runtimes)
  --user-id <user-id>                      Runtime user ID

Dataset:
  --dataset <dataset>                      local JSONL path or a dataset ID
  --dataset-version <dataset-version>      dataset version (with a dataset ID)

Evaluation:
  --evaluators <evaluators...>             evaluator ID(s) to apply
  --ingestion-wait-ms <ingestion-wait-ms>  ms to wait for span ingestion before grading (default 180000; 0 to skip)

Other options:
  -h, --help                               display help for command

Global Options:
  --region <region>                        AWS region
  --debug                                  debug logging (default: false)
  --json                                   JSON output (default: false)
  --endpoint-url <endpoint-url>            endpoint URL override

Parameter details:

  --payload-template (JSON object)
      The request body sent to the Runtime for each dataset example. Every occurrence
      of {input} is replaced with that example's input, so the template describes the
      shape your agent expects and {input} marks where the prompt goes.

      Example:
        --payload-template '{"prompt":"{input}"}'

        --payload-template '{"messages":[{"role":"user","content":"{input}"}],"stream":false}'