test(agent): parity test backfill — credential scrub + failure classification (#4468)

[senamakel]

Draft — backfilling unit coverage for tinyagents-migration parity behaviors that #4495 shipped without tests (part of #4468). Using CI to compile/run since local cargo builds OOM on my box.

Tests added (openhuman)

• credentials (Credential scrubbing dropped from tool outputs on the tinyagents path #4453): bare AWS AKIA/ASIA, OpenAI sk-, and space-separated Bearer token redaction.
• tool_status::classify (Tool-failure classification: approval denial → 'try again', TTL expiry → auto-retry Timeout, failure missing from snapshot #4459): POLICY_DENIED_MARKER → Denied (non-recoverable); a TTL-expiry deny reason (contains "timed out") → ApprovalExpired, not Timeout.

More parity tests (and the vendored-tinyagents crate tests) to follow on this branch / a companion PR.

Submission Checklist

• N/A: tests only — no behavior change.
• Tests: the added unit tests ARE the change; validated in CI.
• N/A: no user-facing feature.
• No secrets/PII (fake example keys only).
• Follows repo conventions (inline #[cfg(test)] modules).

Refs #4468, #4453, #4459.

https://claude.ai/code/session_019j5TLsRLHsM3kqAYFyH4hR

[coderabbitai]

Warning

Review limit reached

You’ve reached a temporary PR review limit under our Fair Usage Limits Policy.

Your recent review volume is higher than typical usage, so adaptive limits are currently applied.

Next review available in: 55 minutes

Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available.
You're only billed for reviews past your plan's rate limits ($0.25/file).

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews.

How do review limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window.

Please refer docs for additional details.

Review details

⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

Run ID: 2f76084c-97e5-4e13-8ed6-4fa00d25d3fb

📥 Commits

Reviewing files that changed from the base of the PR and between a818f1b and b0407b2.

📒 Files selected for processing (4)

• src/openhuman/agent/harness/credentials.rs
• src/openhuman/tinyagents/middleware.rs
• src/openhuman/tinyagents/tests.rs
• src/openhuman/tool_status/ops.rs

---

_{Comment @coderabbitai help to get the list of available commands.}