fix(work): parse Claude Code stream-json reply before threading it downstream

[getappz]

Summary

• real_agent_send_hook (work_item_pipeline.rs) fed every dispatched role's raw --output-format stream-json transcript (one JSON object per line) straight into role_reply, instead of the reply text — regressed when feat(work): durable subagent-driven-development pipeline on flare-workflow #498 deleted the old coder step's transcript parsing without giving sdd_loop's shared hook an equivalent.
• For the judge role specifically, parse_judge_decision parsed the transcript's first line — a valid-but-action-less {"type":"system","subtype":"init",...} event — instead of the judge's actual decision on the last line, hard-failing every judge turn with missing field \action`` (items fix: restore ready-for-work label when a dispatched job fails after exhausting retries #478, feat(flare-workflow): step execution context + durable loop iteration resume #502, fix(claim): use an IMMEDIATE transaction in item::claim to avoid stale-snapshot database-is-locked errors #503, closes item feat(dashboard): group job rows by item, tag self-repair jobs with why they fired #489).
• Restores parse_claude_reply (agent_launch.rs) and applies it to every Claude Code role's reply via a new clean_agent_reply helper, not just the judge's, since role_reply also gets embedded verbatim into build_judge_prompt for every downstream judge call.

Test plan

• cargo test -p agentflare --bin agentflare agent_launch:: — 19 passed
• cargo test -p agentflare --bin agentflare work_item_pipeline:: — 39 passed, including a reproduction test (uncleaned_claude_stream_json_transcript_breaks_judge_parsing) confirming the exact missing field \action` failure signature, and a fix-verification test (clean_agent_reply_fixes_claude_stream_json_so_judge_parsing_succeeds`)
• cargo clippy -p agentflare --bin agentflare -- -A unsafe_code -A clippy::pedantic — clean
• cargo fmt --check -p agentflare — clean

[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: 13 minutes

Limit details: You’ve used all 1 included review currently available under your plan. You completed 60 included PR reviews in the past 7 days; at that activity level, included reviews refill at 1 review per hour.

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: 8378fd00-f31b-49fb-aaa1-a6b702dbdfae

📥 Commits

Reviewing files that changed from the base of the PR and between d11023e and 031e65c.

📒 Files selected for processing (2)

• src/agent_launch.rs
• src/work_item_pipeline.rs

---

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