feat: v0.7.2

[kiloloop-release]

What's New in v0.7.2

Fixed

• Fixed engine and documentation correctness gaps: documentation estimates now use the docs human multiplier, CLI file/config and GitHub adapter failures stay user-facing, REST issue ingestion is reachable in token-only environments, renderer warning/detail fields are escaped and serialized, sizing heuristics prefer explicit test/docs matches, store/audit/validation edge cases are hardened, and stale skill/session/release docs are refreshed (W6: Packaging + TestPyPI dry-run flow (#14) #30, [P1] Publish to Claude Code plugin marketplace #32, Expand modifier ranges: spec_clarity floor 0.8→0.3, warm_context floor 0.85→0.3 #34, Add --spec-clarity and --warm-context CLI flags for per-run modifier override #35, Add auto warm-context detection from dispatch history #41, Research open-source community patterns to improve agent review process #42, Support issues-mode modifier passthrough for hash/space issue input #43, Bump project version to 0.1.0 #44, Daily OSS metrics report (PyPI downloads, GitHub stars, traffic) #45).
• AGENT_ESTIMATE_AUDIT_DESTINATION=stdout now emits a deprecation warning and routes audit events to stderr so report stdout remains parseable for JSON consumers (Support issues-mode modifier passthrough for hash/space issue input #43).

Also documents the agent-estimate session command surface and refreshes README/examples to match current CLI output.