Claude 54c63307dc agent: report pipeline death to the polling agent ...

comrak-010's patch added an unresolvable dependency version; the
candidate build failed before the verdict binary ran, no ledger row was
ever written, and the agent polled read_verdict into its turn cap. The
detached pipeline now traps any failure into a log marker, and
read_verdict reports status=failed with the log tail instead of
'running' forever. Attempt relaunched.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2

2026-07-11 12:08:31 +00:00

..

bench-runner

bench: GitHub Actions CI — trust-layer checks, no-net gates, runner calibration

2026-07-07 00:13:21 +00:00

diff-test

bench: GitHub Actions CI — trust-layer checks, no-net gates, runner calibration

2026-07-07 00:13:21 +00:00

harnessd

agent: report pipeline death to the polling agent

2026-07-11 12:08:31 +00:00

ledger

bench: cache+branch-sim profiles, hypothesis-granular ledger memory, long-poll read_verdict

2026-07-10 04:49:19 +00:00

report

Bootstrap hotpath from engineering spec v0.1

2026-07-06 18:34:51 +00:00

verdict

bench: GitHub Actions CI — trust-layer checks, no-net gates, runner calibration

2026-07-07 00:13:21 +00:00