feat(bench): add router-aware metered OpenCode TB agent

[drewstone]

Summary

• adds a Terminal-Bench OpenCode agent that routes arbitrary provider-qualified model ids through the Tangle router
• records real token usage from OpenCode JSON events instead of returning zero tokens
• fixes subclass install-template lookup and persists OpenCode event/stderr files into the run log directory

Verification

• python3 -m py_compile bench/tb_agents/opencode_router_agent.py
• git diff --check
• git merge-tree --write-tree origin/main HEAD
• pnpm run typecheck
• pnpm test (127 files, 1,254 passed, 2 skipped)
• pnpm run lint
• pnpm run build
• pnpm run verify:package (rerun after build; initial parallel run raced with build cleaning dist)

[tangletools]

✅ Auto-approved drewstone PR — 1644175a

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 · 2026-07-07T23:29:59Z}

[tangletools]

⚪ Value Audit — audit-incomplete

Verdict	audit-incomplete
Concerns	0 (none)
Heuristic	0.0s
Duplication	0.0s
Interrogation	12.8s (2 bridge agents)
Total	12.8s

💰 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 · 20260707T233156Z}