TraceLab

Publish TraceLab snapshots from the internal repo to the public uw-syfi/TraceLab GitHub repo as clean, mergeable, incremental pull requests from a persistent public mirror branch. Use when refreshing the public site/artifacts, drafting a public release PR, reconciling a diverged public branch, or creating GitHub releases with syfi_coding_trace.jsonl.gz and syfi_coding_trace.duckdb assets after the PR is merged.

Run, summarize, plot, validate, and export normalized coding-trace JSONL files. Use when computing aggregate session/provider/model/token counts, normalized decoding-speed proxies, exact-reasoning TPOT/TTFT estimates, prefix versus append token distributions, tool latency/count summaries, generation-time and human-wait CDFs, KV-cache active ratio, cache-hit ratios, timing-fit CSV analyses, multi-round CSV traces, self-contained PNG artifacts, validator audits under validators/, or interpreting per-experiment artifacts under artifacts/.

Collect, count, and extract Claude Code and Codex CLI local histories into normalized coding-trace JSONL files. Use when running collect_llm_traces.py, extract_claude_rounds.py, extract_codex_rounds.py, collect_all_users_sudo.sh, scanning current-user or all-user homes, choosing output paths, using --fresh-extract or --append-dedup, or troubleshooting extraction counts.

Explain and work with the normalized coding-trace JSONL row format produced by extract_claude_rounds.py, extract_codex_rounds.py, and collect_llm_traces.py. Use when interpreting normalized rows, provider differences, token semantics, Claude cache creation/read/uncached fields, prefix versus append accounting, input-event summaries, timing_events, tools metadata, trace_key identity, or converting raw Claude/Codex concepts into the common analysis schema.

Read and explain raw Claude Code and Codex CLI session logs in this coding-trace repo. Use when inspecting example_sessions, raw .claude/.codex JSONL records, provider record families, duplicate-looking runtime layers, raw tool-call pairing, exposed or omitted fields, token accounting records before normalization, or representative raw windows from find_representative_session_segments.py.

Sanitize normalized coding-trace JSONL rows for public sharing. Use when preparing trace/llm_round_trace*.jsonl outputs for release, removing local paths, pseudonymizing user identifiers, dropping tools[].input, replacing session/round/tool/project identifiers with stable pseudorandom values, choosing deterministic versus random sanitizer seeds, or checking what sensitive fields remain after sanitize_round_trace.py.