Add operational-value grader for daily-ambient-context-optimizer

[Copilot]

daily-ambient-context-optimizer only publishes a recommendation issue about oversized ambient context in other workflows — it never edits files itself — so there was no deterministic way to measure whether its recommendations actually reduce ambient-context bloat over time.

Design

• Recovered adoption-time intent from commit 89383a71a (PR Add Daily Ambient Context Optimizer workflow #36642): the workflow samples recent agentic runs, inspects first-DLLM-request size, and recommends workflow-md/skill/agent trims via a single issue.
• Confirmed via changelog evidence (PR chore: apply 2026-06-04 ambient context optimizations #36992, ambient-context: reduce copilot-agent-analysis first-request size by ~28% #43619, ambient-context: remove noop-reminder imports, trim workflow prompts (~3,600 chars/run saved) #43910, chore: trim ambient context to reduce per-run token usage (~9,600 chars saved) #40874) that downstream PRs implement these recommendations, and that raw workflow-markdown character count tracks the same figure the team already reports (927a689cee: 16546→11876 chars, 28.2% cut, matching the changelog's "~28%" claim).
• Mirrors the already-accepted daily-file-diet contract (a sibling "recommend, don't fix" workflow): assignment is deterministic and independent of the issue's free-text recommendations, avoiding brittle parsing of prose.

Grader (.github/graders/daily-ambient-context-optimizer-operational-value.sh)

• Assigns each run to the largest top-level .github/workflows/*.md file (excluding itself and shared/ fragments) at the run commit.
• Primary metric: distance-to-target shrink from a 20000-char "oversized" threshold toward a 10000-char healthy target, scored via git blob evidence only (no live telemetry).
• 3-day maturation window, grounded in the ~2-hour turnaround observed for PR chore: apply 2026-06-04 ambient context optimizations #36992's implementation.
• largest-workflow-health and compliant-char-mass-share reported as separate diagnostics, kept out of the primary attainment value.

Study record

• .github/graders/daily-ambient-context-optimizer-operational-value-study.json records the design decisions, alternatives considered, and evidence citations, with designOutcome: "accepted".

Workflow wiring

• .github/workflows/daily-ambient-context-optimizer.md now declares graders.operational-value, and the compiled .lock.yml is regenerated accordingly.

Original prompt

[operational-value-study:paper-v1] daily-ambient-context-optimizer

Use the repository's .github/skills/operational-value-designer/SKILL.md to design
and verify one deterministic operational-value grader for github/gh-aw
workflow daily-ambient-context-optimizer. This is a fresh research run; do not copy another
workflow's metric or contract.

Requirements:

• Recover adoption-time intent and pre-adoption evidence independently.
• Use exactly one direct primary attainment metric in [0,1]. Keep diagnostics separate.
• Treat unavailable evidence as null, never zero. Make maturation explicit and stable.
• Support historical assignment reconstruction when case and event are null.
• If no direct operational metric is defensible, create only the study record below with designOutcome "blocked" and explain why. Never substitute activity, output volume, traces, or agent judgment.
• Change only .github/workflows/daily-ambient-context-optimizer.md, its generated lock file,
  .github/graders/daily-ambient-context-optimizer-operational-value.sh, and .github/graders/daily-ambient-context-optimizer-operational-value-study.json.
• Do not add generated historical reports to the pull request.

Write .github/graders/daily-ambient-context-optimizer-operational-value-study.json as JSON with this exact top-level shape:
{
"schemaVersion": 1,
"repository": "github/gh-aw",
"workflowId": "daily-ambient-context-optimizer",
"recordedAt": "ISO-8601 timestamp",
"recorder": "copilot-coding-agent",
"designOutcome": "accepted|rejected|blocked",
"rejectionReason": null,
"classification": {
"domain": "short research domain",
"subdomain": null,
"taskArchetype": "short label",
"interventionType": "short label",
"outcomeType": "short label",
"evidenceDirectness": "direct|proxy|activity",
"evidenceLocality": "same-repository|cross-repository|external",
"measurementLevel": "nominal|ordinal|interval|ratio",
"metricForm": "binary|proportion|rate|distance-to-target|index",
"assignmentDeterminism": "deterministic|bounded-ambiguity|ambiguous",
"intentExplicitness": "explicit|implicit|mixed",
"markdownSpecificity": "exact|bounded|open-ended",
"outcomeObservability": "immediate|delayed",
"causalClaim": "observational|comparative-not-causal"
},
"decisions": [{
"type": "intent|opportunity|assignment|evidence|maturation|metric|baseline|diagnostic",
"selected": "observable selected design",
"alternatives": ["observable rejected alternative"],
"rationale": "concise evidence-backed rationale, not hidden reasoning",
"evidenceReferences": ["commit, issue, PR, or file reference"],
"changedDuringReview": false
}],
"uncertainties": [{
"type": "measurement|assignment|evidence-availability|temporal|baseline|domain-fit|causal-attribution",
"level": "low|medium|high|unknown",
"description": "specific limitation",
"mitigation": null,
"evidenceReferences": []
}]
}

For blocked/rejected designs, rejectionReason must be a non-empty string. Record
observable contract choices and alternatives only; do not record chain-of-thought.

Validation for accepted designs:

1. .github/skills/operational-value-designer/scripts/verify-operational-value-evaluator.sh .github/graders/daily-ambient-context-optimizer-operational-value.sh
2. gh aw compile .github/workflows/daily-ambient-context-optimizer.md

Keep the pull request limited to this workflow. The local study runner will replay
history and archive reports after this task completes.