norrisaftcc / norrisaftcc/algorithm-liza
M1: JSONL run transcripts
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 0
- Forks
- 0
- Avg merge
- 1m
- Merged PRs (30d)
- 1
Description
Every run writes .liza/runs/<run-id>.jsonl containing every request, response, tool call and tool result, with timestamps and token counts where the server reports them.
This is load-bearing for three later things and should not be treated as logging: it is the debugging surface, the input to the growth metrics in ADR-0003, and the fixture source for deterministic tests. Design the record schema deliberately and version it with a schema field.
Done when a run produces a transcript that a replay harness can read back and reconstruct the conversation from, byte-identically.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No implementation files, tests, or entry points are named. Locate the run-writing path and the replay harness first, then define the versioned JSONL record schema around requests, responses, tool calls, tool results, timestamps, and reported token counts; done means replay reconstructs the conversation byte-identically.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- backend
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100