Read-only streak detector was a dumb counter that killed agents exploring
unique files (12 reads = kill regardless of uniqueness). Team tasks were
then falsely auto-completed with the kill message as "result."
Changes:
- Add uniqueness ratio to read-only streak: exploration mode (>60% unique)
uses relaxed thresholds (warn=24, kill=36) vs stuck mode (warn=8, kill=12)
- Classify team_tasks by action: list/get/search=read-only, progress=neutral,
create/complete/cancel/comment/etc.=mutating
- Add LoopKilled flag to RunResult, propagated through all 3 kill paths
- Consumer routes LoopKilled to FailTask (not CompleteTask) with clear signal
- 40 tests covering uniqueness detection, team_tasks classification,
exact #506 trace replay, boundary values, and edge cases
DRY: deduplicate tool result processing between single-tool and parallel-tool
paths. New processToolResult() and checkReadOnlyStreak() methods on *Loop
handle loop detection, event emission, media collection, deliverables, and
spawn tracking. Reduces loop.go from 1324 to 1123 LOC (-201). No behavior change.
viettranx