Runtime Atlas · 2.1.2
Claude Code 2.1.2 Feature Testing (2.1.2)
| # | Feature | Status | Key Finding |
9signed entities
8evidenced claims
4runtime transcripts
0receipts failing
Release1
Primitive4
agent_type in SessionStart Hook tested Feature works as documented. The agent_type field is populated when --agent is specified with a valid agent name. Combo Test: Large Output Analysis in Fork inconclusive Can a forked Explore skill analyze a persisted large output file without polluting main context? FORCE_AUTOUPDATE_PLUGINS inconclusive Organizations/admins who: Large Tool Outputs to Disk tested Feature works as documented. Large outputs are saved to disk with a preview shown in context.
Test4
agent_type in SessionStart Hook — runtime test tested Hands-on runtime battle-test of agent_type in SessionStart Hook. Result: PASS. Combo Test: Large Output Analysis in Fork — runtime test inconclusive Hands-on runtime battle-test of Combo Test: Large Output Analysis in Fork. Result: INCONCLUSIVE. FORCE_AUTOUPDATE_PLUGINS — runtime test inconclusive Hands-on runtime battle-test of FORCE_AUTOUPDATE_PLUGINS. Result: INCONCLUSIVE. Large Tool Outputs to Disk — runtime test tested Hands-on runtime battle-test of Large Tool Outputs to Disk. Result: PASS.