chore(release): 0.106.3 — Lineage DAG + runLineageLoop + E2 scenario selection

[drewstone]

Ships the multi-track improvement stack: Lineage DAG (#319, git-graph of candidates, multi-parent merges, visioned tracks incl. contrarian, agent-managed governor), runLineageLoop (#322, wires the DAG to the live improvement loop), and discriminative scenario selection (#321, E2 — pick holdout by signal, drop the saturated ties run 7 exposed). Version trio bumped. Tag → OIDC publish after merge.

[tangletools]

✅ Auto-approved drewstone PR — a226ff4d

This PR was opened by the trusted drewstone account.
The full PR reviewer audit still runs separately and will publish findings if it detects issues.

_{tangletools · auto-approval · reason: drewstone_author · 2026-07-07T18:08:18Z}

[tangletools]

✅ No Blockers — a226ff4d

Review health 100/100 · Reviewer score 95/100 · Confidence 70/100 · 0 findings (none)

	opencode-kimi	glm	deepseek	aggregate
Readiness	95	95	95	95
Confidence	70	70	70	70
Correctness	95	95	95	95
Security	95	95	95	95
Testing	95	95	95	95
Architecture	95	95	95	95

Reviewer score is advisory once the run is complete and the verdict has no blockers.

Full multi-shot audit completed 2/2 planned shots over 3 changed files. Global verifier still owns final merge decision. | Full multi-shot audit completed 2/2 planned shots over 3 changed files. Global verifier still owns final merge decision. | Full multi-shot audit completed 2/2 planned shots over 3 changed files. Global verifier still owns final merge decision.

No findings.

---

_{tangletools · 2026-07-07T18:21:51Z · trace}

[tangletools]

✅ Clean — a226ff4d

Full multi-shot audit completed 2/2 planned shots over 3 changed files. Global verifier still owns final merge decision. | Full multi-shot audit completed 2/2 planned shots over 3 changed files. Global verifier still owns final merge decision. | Full multi-shot audit completed 2/2 planned shots over 3 changed files. Global verifier still owns final merge decision.

Full immutable report for this review: trace

Summary comment for this run: full summary

---

_{tangletools · 2026-07-07T18:21:51Z · immutable trace}

[tangletools]

🟢 Value Audit — sound

Verdict	sound
Concerns	1 (1 weak-concern)
Heuristic	0.0s
Duplication	0.0s
Interrogation	942.3s (2 bridge agents)
Total	942.3s

💰 Value — sound

A clean, minimal release bump (0.106.2 → 0.106.3) across the standard version trio — ships the already-merged Lineage DAG / runLineageLoop / scenario-selection feature work.

• What it does: Bumps three version strings in lockstep: package.json, clients/python/src/agent_eval_rpc/init.py (the PackageNotFoundError fallback), and clients/python/pyproject.toml — all 0.106.2 → 0.106.3. No code or behavior change; this is the release-cut for feature PRs #319/#321/#322 which were already merged to main.
• Goals it achieves: Cut a publishable release so the Lineage DAG + runLineageLoop + discriminative scenario selection work becomes consumable via npm (@tangle-network/agent-eval) and PyPI (agent-eval-rpc) under a new semver, triggering the tag → OIDC publish flow described in the PR body.
• Assessment: Sound. It is the repo's established release ritual — git log shows 0.103.0, 0.103.1, 0.103.2, 0.106.0, 0.106.1, 0.106.2 all cut as identical single-commit version trios. The bump is consistent across all three files (verified each), purely additive in semver (patch), and contains zero sneaked code changes. No grain conflict, no scope issue.
• Better / existing approach: none — this is the right approach. Checked for an existing release automation/script (scripts/, .github/workflows/, release-please, changesets) that might already encode the version-trio bump; this repo does it by hand per its prior history, and the three files are the complete set of version-bearing files (grep of the repo for '0.106.2' returns exactly these three). Nothing to reuse or extend.
• Model: opencode/zai-coding-plan/glm-5.2
• Bridge attempts: 2
• Bridge warning: opencode/kimi-for-coding/k2p7: bridge stream ended without value-audit content

🎯 Usefulness — error

usefulness agent produced no parseable value-audit JSON.

• Model: opencode/deepseek/deepseek-v4-pro
• Bridge attempts: 3
• Bridge error: opencode/zai-coding-plan/glm-5.2: bridge stream ended without value-audit content; opencode/kimi-for-coding/k2p7: bridge stream ended without value-audit content; opencode/deepseek/deepseek-v4-pro: bridge stream ended without value-audit content

💰 Value Audit

🟡 PR body diff omits pyproject.toml [maintenance] ``

The PR body says 'Changed files (2)' and shows only package.json + init.py, but the commit also bumps clients/python/pyproject.toml (0.106.2 → 0.106.3). The version trio is internally consistent (verified via git show HEAD on all three files), so this is purely a body-vs-actual-diff cosmetic mismatch, not a correctness issue. No action required to ship.

---

What this audit checks

It judges the change on its merits — not whether it was tasked out in an issue. Unticketed, fast-moving work is fine; the question is whether the change is good and whether a better or existing approach should be used instead.

Pass	What it asks
Heuristic	Vague title? Whitespace-only or cruft-bearing diff? (content signals only)
Duplication	Do added function/class names already exist elsewhere in the repo?
Value Audit	What does it do? What goal does it achieve? Is it good? Better architecture or already-exists?
Usefulness Audit	Does it integrate and fit? Will it hold up in real use and actually get used?

Findings are concerns, not blocks — the human reviewer decides what to do with them.

_{value-audit · 20260707T183611Z}