AgentPostmortem/Agentrace

stats --json also prints the human table, so the output is not machine readable 3 days ago

bug enhancement help wanted

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

A mistyped path produces a traceback, or a message naming the wrong directory 3 days ago

bug help wanted

AgentPostmortem/Agentrace

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

New check risky_verdict: flag delete/deploy verdicts citing no artifact 3 days ago

help wanted good first issue claimed

AgentPostmortem/Agentrace

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

Make the slow_run threshold configurable with --slow-seconds 3 days ago

enhancement help wanted claimed

AgentPostmortem/Agentrace

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

Agent-controlled text printed as Rich markup unescaped 4 days ago

help wanted good first issue claimed

AgentPostmortem/Agentrace

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

New check self_contradiction: flag verdicts contradicting their own evidence 4 days ago

help wanted good first issue claimed

AgentPostmortem/Agentrace

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

New check destructive_command: flag runnable destructive shell without warnings 8 days ago

help wanted good first issue claimed

AgentPostmortem/Agentrace

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

Docs: parse_session does one pass over the transcript, not two 8 days ago

documentation good first issue claimed

AgentPostmortem/Agentrace

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

New check unquantified: flag vague answers to counting prompts 8 days ago

help wanted good first issue

AgentPostmortem/Agentrace

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

show "" matches every run and displays the first 12 days ago

help wanted good first issue claimed

AgentPostmortem/Agentrace

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

No --version flag 12 days ago

help wanted good first issue

AgentPostmortem/Agentrace

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

--dir pointed at a file reports no runs with no --file hint 12 days ago

help wanted good first issue

AgentPostmortem/Agentrace

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

Mixed tz-aware/tz-naive transcript timestamps crash the session sort 12 days ago

help wanted good first issue

AgentPostmortem/Agentrace

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

Median run is the upper middle for even counts, not the median 14 days ago

help wanted good first issue

AgentPostmortem/Agentrace

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

Negative durations from clock-skewed transcripts flow into stats 14 days ago

help wanted good first issue

AgentPostmortem/Agentrace

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

show --max accepts negative values that corrupt output slicing 14 days ago

help wanted good first issue

AgentPostmortem/Agentrace

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

Non-string timestamp crashes parsing with AttributeError 14 days ago

help wanted good first issue

AgentPostmortem/Agentrace

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

tool_use block without id crashes parse_session with KeyError 14 days ago

help wanted good first issue

AgentPostmortem/Agentrace

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

--file and --dir are not mutually exclusive, so --dir is silently ignored 27 days ago

good first issue

AgentPostmortem/Agentrace

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

hedged_claim reports the number of hedge patterns, not the number of hedged claims about 1 month ago

bug good first issue

AgentPostmortem/Agentrace

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

ruff is installed and configured but never runs in CI about 1 month ago

enhancement good first issue

AgentPostmortem/Agentrace

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

Every command loads every run of every transcript into memory about 1 month ago

enhancement help wanted

AgentPostmortem/Agentrace

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

The CLI has no tests: three open bugs all live in cli.py about 1 month ago

enhancement help wanted

AgentPostmortem/Agentrace

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

check runs every check twice per run, and --strict ignores --severity about 1 month ago

enhancement good first issue

AgentPostmortem/Agentrace

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

Bug: parse_session crashes on a transcript where only some Agent runs have timestamps about 1 month ago

bug help wanted

AgentPostmortem/Agentrace

0

Observability for Claude Code subagents. Reads session transcripts, flags the results you should not trust. Checks derived from real agent failures.

Python

#ai-agents#claude-code#cli#llm#observability#python

Open Issues Need Help