feat(enterprise): add semantic issue provider boundary

[seonghobae]

Summary

Advances #404 with the provider-neutral semantic issue extraction trust boundary after the deterministic explicit-value parser and governed criterion-observation adapter.

• adds runtime-checkable EnterpriseAtomicIssueExtractor and extract_enterprise_atomic_issues while returning the existing canonical AtomicIssueRecord contract;
• replays bounded exact source packets, valid UTF-8, Python code-point offsets, and SHA-256 source/span fingerprints;
• reconstructs fresh canonical issue, evidence-span, and counterevidence records and rejects provider-owned subclasses, mutation, duplicate identities, and overlapping evidence;
• redacts every caller-supplied provider exception and retains no raw source text;
• adds StaticEnterpriseIssueExtractor as an offline fixture/integration adapter, not an NLP model or production default;
• preserves all five assertion kinds without scoring, ranking, utility, causal, sentiment, or queue-routing arithmetic;
• documents conservative interpretation limits and synchronizes the authoritative changelog fragment.

This supersedes the automatically closed plan-only PR #534 after rebasing the branch onto the merged criterion-observation slice.

Refs #404

Merge only after the exact current head passes CI, Security Scan, SAST, package/release acceptance, statement/branch coverage, and final review.

[coderabbitai]

Warning

Review limit reached

@seonghobae, you've reached your PR review limit, so we couldn't start this review.

Next review available in: 12 minutes

Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available.
You're only billed for reviews past your plan's rate limits ($0.25/file).

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews.

How do review limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window.

Please refer docs for additional details.

Review details

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro Plus

Run ID: 89f54803-a48c-4746-aa4a-cac953ebce04

📥 Commits

Reviewing files that changed from the base of the PR and between b4ff4fb and 4528248.

📒 Files selected for processing (7)

• CHANGELOG.md
• docs/changelog.d/enterprise-semantic-issue-boundary.md
• docs/enterprise_issue_evidence_contracts.md
• docs/superpowers/plans/2026-08-05-enterprise-semantic-issue-boundary.md
• python/fast_mlsirm/scoring/enterprise_issue/__init__.py
• python/fast_mlsirm/scoring/enterprise_issue/semantic.py
• tests/test_scoring_enterprise_issue_semantic.py

---

_{Comment @coderabbitai help to get the list of available commands.}