Commit Graph
4 Commits
Author SHA1 Message Date
Claude 632e861f7f agent: launcher probes harnessd liveness with a real request
A stale socket file survived a container idle window while the daemon
died; the [ -S ] check skipped the restart and the nested agent's MCP
server crashed at connect. The agent refused cleanly (no ledger row, no
fabrication). Liveness now means answering read_playbook, not existing.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
2026-07-10 12:11:42 +00:00
Claude abaed3c49d agent: phase2-tokei-001 — first auto-accepted win from the unattended loop
Ledger row: class 5 (algorithmic) on tokei, first-byte gate table for
the per-byte token matchers in perform_multi_line_analysis.
Speedup median 1.107, 95% CI [1.084, 1.131] vs the banked-wins baseline,
workload: 221 MB / 4360 files, single rayon thread, pinned core.

Manual audit gates (pipeline covers tests+golden+bench only):
- Differential fuzz, 10k mutated inputs across 200 batched runs:
  0 divergences after canonicalizing tokei's benign parallel-walker
  output ordering (present in pristine baseline; counts identical).
  Fuzzer added as scripts/diff-fuzz-tokei.py.
- ASan run recorded in the case study (next commit).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
2026-07-10 05:08:16 +00:00
Claude 5b198b7091 agent: per-attempt audit script for the Phase 2 grind
Mechanically re-checks a ledger row against the accept rule (CI lower
bound vs threshold, gate greenness, patch path allowlist) and prints
the full evidence for the human part of the 100% Phase 2 audit.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
2026-07-10 04:52:43 +00:00
Claude e0c5018008 agent: OS-level isolation for the agent tool boundary (SPEC §10)
harnessd gains --socket mode (Unix socket, trusted uid, mutating ops
serialized); the harness client speaks socket when
HOTPATH_HARNESS_SOCKET is set. scripts/agent-isolated.sh launches an
attempt with the agent tree confined — mountns mode (repo bind-mounted
read-only, CAP_SYS_ADMIN/CAP_SYS_PTRACE dropped; no credential copying)
or user mode (unprivileged hpagent, bench-metal shape).
scripts/isolation-check.sh + just isolation-check verify the boundary
from the agent's side: 19 checks, both modes, all passing — repo
writes, forged ledger INSERTs, trust-binary replacement, rw remounts,
and userns re-entry all refused; the harnessd socket door works.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
2026-07-10 04:43:08 +00:00