[P1.13] Stuck-loop detection must not mark the task COMPLETED (currently returns `AgentStatus.COMPLETED`)

[frankbria]

Severity: medium | Category: correctness | Phase: P1.13

Problem

When the same tool signature repeats 3×, _react_loop returns COMPLETED; final verification passes against the already-green repo, so a stuck agent that implemented nothing → task DONE → (with auto-close) the linked GitHub issue is closed. A stuck loop is a failure, not completion.

Evidence

codeframe/core/react_agent.py:634

Acceptance criteria

• Loop detection returns FAILED (or creates a blocker); the run result distinguishes "completed" from "terminated early due to loop".

Dependencies

None

---

_{Filed from the SaaS launch-readiness audit. Atomic: one developer, one session. Work order: strictly P0.1 → P3.12 (no forward dependencies).}

[coderabbitai]

🔗 Related PRs

#365 - feat: integrate fix_tracker escalation and blocker detection into ReactAgent [merged]
#384 - feat: adaptive iteration budget, autofix, and loop detection for ReactAgent [merged]
#425 - feat(core): wire StallAction dispatch into ReactAgent and runtime (#401) [merged]

---

📝 Issue Planner

_{Check the box below or use the @coderabbitai plan command to generate an implementation plan and prompts that you can use with your favorite coding assistant.}

• Create Plan

---

🧪 Issue enrichment is currently in open beta.

To disable automatic issue enrichment, add the following to your .coderabbit.yaml:

issue_enrichment:
  auto_enrich:
    enabled: false

💬 Have feedback or questions? Drop into our discord!