feat(report): gecko report — the Agent-Readiness Scorecard (first provider delivery) - #212
Merged
Merged
Conversation
Self-contained HTML scorecard (inline CSS + inline SVG, no server, no deps): header grade+score, dimension bars, embedded call-graph SVG, ranked fixable findings checklist, a scripted Playground (deterministic intent -> derived tool -> first-call-correct call, no live LLM/network), and a correlation teaser. Deterministic and control-plane clean (structure/scores only, never a payload or secret). Adds InspectionReport.to_dict()+surface_rev and report_diff drift. CLI: gecko report <spec> [-o] [--intent]... [--since <prior.json>]. Co-Authored-By: Claude Opus 4.8 <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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The first provider delivery from the strategy panel (
docs/provider-delivery.md):gecko report <openapi.json>→ a self-contained Agent-Readiness Scorecard (HTML) — the a-ha, the surface, and the leave-behind in one file. No server, no external deps, control-plane clean.Sections
inspectdims (first-call-correct 0.4, hygiene, agent-friendliness, security) as bars.surfaceviz.render_svgembedded inline ("your API as an agent traverses it").dimension · location · the fix.search/plan_for), showing the call shape only.Drift-watch
InspectionReport.to_dict()+surface_rev+report_diff(old, new)+gecko report --since <prior.json>→ the drift delta ("score 100 → 96, broke 9 agent call-paths"). The recurring value.Verified
Real run on pegana → grade A / 96, inline graph, Playground, findings;
--sincedrift delta works. Control-plane: a test asserts noAuthorization/Bearer/secret-shaped value in the HTML (grep on the real output empty). Deterministic (same spec → identical HTML). Gate: ruff + mypy clean · full suite 1909 passed / 1 skipped ·tests/test_report.py8 passed.Next:
--sinceGitHub-Action trigger (PR-comment bot, V1.1) and the live Playground (V2, WTP-gated).🤖 Generated with Claude Code