Observability stops at the deploy.
CodeAutopsy doesn't.
git blame tells you which commit broke prod. CodeAutopsy tells you which reasoning step of which AI agent broke it — crossing the dev-time → runtime boundary with a single OpenTelemetry span link, then handing the agent its own autopsy so it fixes itself.
This page is the overview. The app is where it actually runs — sign up, trigger a real crash, watch the autopsy resolve live.
└─ parse_discount()
└─ codeautopsy.autopsy
└─ agent.tool.Edit
"assuming input is valid"
The one trick
Four hops, each one ordinary. Chained together, they cross a boundary no other observability tool instruments.
A runtime stack frame from the crash — the only thing a normal APM gives you.
At the deployed commit, blame resolves that line to the commit that introduced it — even if it's shifted since.
(commit, file, line-range) → the AI decision span that wrote it, including its own recorded reasoning.
Stitches the runtime error trace to that dev-time decision trace — one click in SigNoz, crash to cause.
The pipeline
Six small components. None of them are clever alone — the join is the whole product.
A Claude Code PostToolUse hook that mints a dev-time decision span for every edit, carrying the agent's own reasoning and risk flags.
SQLite store plus the git-blame join engine — the resolve() API that answers "which decision wrote this line."
Runs inside the instrumented sample app. On exception, mints the linked codeautopsy.autopsy span and logs the incident.
codeautopsy autopsy <commit> <file> <line> — the chain of custody, printed for a human.
Feeds the agent its own genealogy — the reasoning that wrote the bug and the incident that proves it broke. Applies the patch, proves it with a real regression test derived from the exact failing input, and only commits + opens a PR if that test actually passes.
The pre-mortem. Runs on every pull request, resolves each added line back to its authoring decision the same way, and prices its risk flags against every crash that flag has caused so far — then comments the priced report straight on the PR, before it merges.
Day-0 validated on real infrastructure.
The span-link click navigates across traces and services in SigNoz Cloud. 100+ tests, ruff and mypy clean, containerized with Docker, gated by CI.