Skip to content

add-growth-conditions: batch sweep runner + skill batch section#202

Merged
realmarcin merged 1 commit into
mainfrom
feat/growth-conditions-sweep-runner
Jul 6, 2026
Merged

add-growth-conditions: batch sweep runner + skill batch section#202
realmarcin merged 1 commit into
mainfrom
feat/growth-conditions-sweep-runner

Conversation

@realmarcin

Copy link
Copy Markdown
Contributor

Extends the add-growth-conditions skill (per the request to add a batch sweep runner) so a whole-KB growth-conditions pass starts from ready source bundles instead of each extraction agent re-fetching.

What

  • scripts/growth_conditions_sweep.py — deterministic prep runner:
    • --list the records lacking both growth_media and cultivation_setup
    • --prep (live fetch): resolve each record's primary (most-cited) reference, fetch the Europe PMC abstract, and run the legal full-text access ladder (reuses scripts/fulltext_access.py: Europe PMC OA → Unpaywall → CORE → author-request draft).
    • Writes one staging bundle per record + an INDEX.md progress report bucketing each as OA_FULLTEXT / ABSTRACT_ONLY / NO_REFERENCE. Never edits kb/ — extraction + YAML writes stay the agent's job, so a curator reviews the prep first.
  • skill.md (v1.0.0 → v1.1.0): rewrote the whole-KB sweep section around the runner + INDEX report; flagged that the most-cited ref is sometimes a review, so the bundle lists every cited ref by frequency for the agent to pick the community's methods paper.

Current KB landscape (from a live --prep)

45 records lack any conditions block: 24 OA full text, 21 abstract-only (paywalled), 0 without a citable reference.

Lint-clean (black + ruff). The data enrichment from running the sweep lands in a separate follow-up PR.

🤖 Generated with Claude Code

Extends the add-growth-conditions skill (v1.0.0 -> v1.1.0) with a deterministic
sweep-prep runner so a whole-KB growth-conditions pass starts from ready source
bundles instead of each extraction agent re-fetching.

- scripts/growth_conditions_sweep.py: enumerate records lacking growth_media AND
  cultivation_setup; resolve each record's primary (most-cited) reference; fetch
  the Europe PMC abstract; run the legal full-text access ladder (reuses
  scripts/fulltext_access.py). Writes per-record staging bundles + an INDEX.md
  progress report bucketing OA_FULLTEXT / ABSTRACT_ONLY / NO_REFERENCE. Never
  edits kb/ — extraction + YAML writes stay the agent's job.
- skill.md: rewrote the "whole KB (sweep)" section around the runner + INDEX
  report; flagged the most-cited-ref-may-be-a-review pitfall (bundle lists every
  cited ref by frequency so agents can pick the community's methods paper).
- reports/growth_conditions_sweep/.gitignore: per-record bundles are regenerable;
  track only INDEX.md.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Copilot AI review requested due to automatic review settings July 6, 2026 13:00

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

@realmarcin realmarcin merged commit d94fcf6 into main Jul 6, 2026
2 checks passed
@realmarcin realmarcin deleted the feat/growth-conditions-sweep-runner branch July 6, 2026 13:24
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants