feat: research inspection tools — export_jobs, get_cost_report, search_jobs#106
Merged
Conversation
…earch_jobs Three new MCP tools for agentic systems researchers: - export_jobs: JSONL/JSON trace export with day/status filtering - get_cost_report: longitudinal cost breakdown grouped by repo, day, or status - search_jobs: full-text search over task prompts with snippet context All tools use the existing jobStore (Redis/disk) — no new dependencies. 9 new tests in index.test.ts, all passing. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
export_jobs: Export job records as JSONL or JSON for statistical analysis (id, status, repo_url, task snippet, timestamps, exit_code, output_lines, score, duration_seconds). Supportsdays,format, andstatusfilters.get_cost_report: Longitudinal cost breakdown grouped byrepo,day, orstatus. Returns total_usd, job_count, avg_cost_usd, avg_score per group — sorted by spend descending.search_jobs: Full-text search over task prompts (case-insensitive). Returns matching jobs with a context snippet showing ±50 chars around the match.All three tools read from the existing
jobStore(Redis/disk) — no new dependencies, same pattern ascost_summaryandlist_jobs.Test plan
src/index.test.tscovering all three tools and edge cases (empty results, format variants, missing query)src/index.test.tspassmeta-agent.test.tsfailures are unrelated (redis.del mock issue predating this PR)🤖 Generated with Claude Code