Preserve provider error classification on streamed failures

[M3gA-Mind]

On the streaming path, StreamAccumulator::finish mapped ModelStreamItem::ProviderFailed to TinyAgentsError::Model, stringifying away the structured ProviderError. Since is_retryable treats Model(_) as retryable, a permanent streamed failure (401 auth, insufficient_quota, model_not_found, 400) was retried and fallback-churned as transient.

Keep the ProviderError struct in a new failed_provider slot and return TinyAgentsError::Provider from finish() so the retry layer sees status/code/retryable — matching the unary path. Unstructured Failed(String) still maps to Model. Adds tests for the streamed 401 (non-retryable) and unstructured-failure paths.

Closes tinyhumansai/openhuman#4637

[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: 21 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: 694661d3-1a2f-428a-915d-e0fa3d9825e0

📥 Commits

Reviewing files that changed from the base of the PR and between b1f0d82 and 73f16c3.

📒 Files selected for processing (5)

• src/harness/model/mod.rs
• src/harness/model/test.rs
• src/harness/providers/openai/test.rs
• src/harness/stream/mod.rs
• tests/e2e_harness_provider_contracts.rs

---

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

[M3gA-Mind]

CI guardian: the Rust SDK check was red on a pre-existing main clippy failure under stable rust 1.96 (a collapsible_if in StreamAccumulator::push_tool_chunk and a duplicated #[cfg(test)] on the stream test module), inherited by this branch. Pushed a behavior-neutral lint fix so CI can go green; no change to this PR's own logic.

[M3gA-Mind]

CI guardian follow-up: with the clippy blocker cleared, CI surfaced a real test failure that was masked behind it — tests/e2e_harness_provider_contracts.rs:284 still asserted the old flattened error wording (mock provider error (internal): nope). This PR intentionally switched StreamAccumulator::finish to return the structured TinyAgentsError::Provider, whose Display renders mock returned HTTP 500 (internal): nope — and the sibling unit tests in model/test.rs/openai/test.rs were already updated, so this e2e assertion was just a missed leftover. I updated it to the new wording (no behavior change). Full cargo test and cargo test --all-features pass locally under rust 1.96. Please sanity-check the assertion matches your intended error contract.