Report skill: restore tool_call_id counting and tool_args rules dropped in #2901

Open Beginner friendly
  • Is something wrong?
#2,903 0 comments 0 reactions 0 assignees View on GitHub

Maintainers usually reply within 1 day

Nobody has claimed this yet.

Assessment

Difficulty
2/5
Estimated time
1-3 hours
Newbie friendliness
68/100
Issue type
Documentation
Clarity
Mostly clear
Activity status
Active
Tech stack
javascript
Domain
documentation

Research direction

Read the removed rule quoted in the issue and inspect the installed hypaware-query skill and its sql.md to decide where it belongs. Restore the guidance on counting tool calls and results by tool_call_id, interpreting tool_args, and treating missing metadata as unknown. Done when the relevant skill documentation clearly covers these rules for the new report pages.

Written by the indexing model from the issue text.

Description

PR #2901 deletes hypaware-core/skills/hypaware-report/references/querying.md. This rule from it did not move into the report skill, the query skill or sql.md. The author chose to leave it out of #2901 and track it here.

Removed text (from querying.md at eb0f4795, "Identities and usage"):

A row is a message part. Count sessions by session_id, messages by their scoped message_id, and tool calls/results by tool_call_id, preserving chain identity (agent_id or conversation_id) when available. Calls have part_type='tool_call', results part_type='tool_result'; is_error and content_text describe the result. tool_args is input, not the error text, and need not be JSON. Missing metadata is unknown, not false or zero.

Why it matters: the new default Automation and Repeated work pages count tool calls, retries and errors. Without this rule a report can count rows instead of calls, read tool_args as the error, fail on non-JSON tool_args, or treat missing metadata as zero.

Decide whether to add this rule back to the installed hypaware-query skill (or its sql.md), and where.

🤖 Generated with Claude Code

Dominant language
JavaScript
Stars
11
Forks
0
Avg merge
2h 15m
Merged PRs (30d)
322

Getting set up

This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from hyparam/hypaware

All issues in hyparam/hypaware

Similar issues

More JavaScript issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.