fix(work): build_prompt never read handoff assets, so item_id-targeted handoffs never reached dispatch

[getappz]

Closes item #84. mcp__flare__handoff(item_id=<existing item>, content=...) attaches content to the item as a versioned asset, but the item's own description/comments never change — build_prompt() (src/cli/work.rs) only ever read those two fields when constructing the dispatch prompt, so a dispatched session never saw the handoff's instructions at all.

Confirmed live

Sent a detailed handoff to item #66 with exact CI-fix instructions (specific failing lines, specific fixes). The handoff succeeded and the item got relabeled ready-for-work. When the daemon dispatched it, the resulting session reported the work already done and the tree clean — it had zero awareness of the handoff's content, because none of it was ever in its prompt.

Fix

latest_handoff_content() fetches the most recently attached handoff asset — identified by the completed/remaining metadata only handoff_impl sets, so a plain asset attach of an unrelated file (a log, a screenshot) isn't mistaken for dispatch instructions — and build_prompt() inlines it under its own "Latest handoff instructions" section. Capped at 8000 chars (tail + a pointer to the full asset for anything larger) so an oversized handoff can't reintroduce the E2BIG prompt-size bug #75 just fixed from a different angle.

Test plan

• cargo test --bin agentflare cli::work:: — 30 passed, including 3 new tests (surfaces a handoff into the prompt, ignores a non-handoff asset attach, caps an oversized handoff at the tail with an asset pointer)
• cargo fmt --check — clean
• cargo clippy --locked --workspace --all-targets --all-features -- -D warnings -A unsafe_code -A clippy::pedantic — clean (CI's exact flags)

[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: 6 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: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Run ID: 2258945d-cdde-4889-bcf1-65d0131e08b2

📥 Commits

Reviewing files that changed from the base of the PR and between e1ef5b2 and b26b422.

📒 Files selected for processing (1)

• src/cli/work.rs

---

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