fix(repo): preserve per-tool worktree labels

[drewstone]

Why

Long Codex sessions can run tools in multiple worktrees.
The trace exporter was stamping one session-level repo/cwd/git label across every span, so a tool call with an explicit workdir could still show the wrong branch and cwd downstream.

Change

• Keep session-level repo labels for spans without an explicit tool workdir.
• Add a per-span workdir pass for spans whose tool input includes workdir/cwd fields.
• Cache workdir repo resolution so large sessions do not run repeated git lookups.
• Add a regression test covering one session with tool calls in two different worktrees.

Proof

• pnpm test -> 17/17 files, 103/103 tests passed.
• pnpm typecheck passed.
• pnpm build passed.
• Real export proof: spans whose content includes /home/drew/code/agent-dev-container-intelligence-traces now serialize with resource_cwd=/home/drew/code/agent-dev-container-intelligence-traces, resource_branch=fix/intelligence-trace-completeness, resource_commit=d5284ec50, repo_source=span-workdir.

[tangletools]

✅ Auto-approved drewstone PR — 233cd2ee

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 · 2026-07-08T07:14:19Z}

[tangletools]

⚪ Value Audit — audit-incomplete

Verdict	audit-incomplete
Concerns	0 (none)
Heuristic	0.0s
Duplication	0.0s
Interrogation	6.5s (2 bridge agents)
Total	6.5s

💰 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 · 20260708T071611Z}