feat(improvement): emit default proposal artifacts

[drewstone]

Problem

traces improve could emit findings and recommendations but return 0 proposals unless every repo supplied a custom improvementAdapter.
That made the public improvement path stop before reviewable artifacts.

Solution

• Generate conservative proposal-only artifacts from the top recommendations when no adapter is configured.
• Keep configured adapters authoritative; if a repo provides one, it replaces the default proposal set.
• Write proposals.json alongside findings, recommendations, evidence, claims, report, and replay metadata.
• Document the default proposal artifact contract.

Proof

• pnpm test tests/improvement.test.ts passed: 5/5 tests.
• pnpm typecheck passed.
• pnpm test passed: 17/17 files, 102/102 tests.
• pnpm build passed.
• Product-context smoke from /home/drew/code/agent-dev-container-intelligence-traces:
  • command: pnpm --dir /home/drew/code/traces dev improve --harness codex --last 1 --cwd /home/drew/code/agent-dev-container-intelligence-traces --dir /tmp/traces-default-proposals-product-context
  • result: 4 findings, 4 recommendations, 4 proposals, candidateApplied=false, replay status proposal-only.
  • baseline: 34,747 spans, 615 stuck loops, 218 reaction signals, 1 tool-error run.
• git merge-tree --write-tree origin/main HEAD passed: 3274c46a3267e94f2af95fc048ef18d80038e47b.

[tangletools]

✅ Auto-approved drewstone PR — a4b7e851

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 · 2026-07-08T01:50:52Z}

[tangletools]

⚪ Value Audit — audit-incomplete

Verdict	audit-incomplete
Concerns	0 (none)
Heuristic	0.0s
Duplication	0.0s
Interrogation	12.1s (2 bridge agents)
Total	12.1s

💰 Value — error

value agent produced no parseable value-audit JSON.

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

No PR concerns were produced because the value/usefulness agent pass did not complete. Treat this audit as incomplete, not as approval.

---

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 · 20260708T015309Z}

[tangletools]

✅ Auto-approved drewstone PR — e9a04ca3

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 · 2026-07-08T01:53:30Z}