docs: add demo video to README hero#68
Merged
Merged
Conversation
📝 WalkthroughWalkthroughAdds a README demo link, a new auth-flow compare benchmark README with reproducer and headline Anthropic metrics, an executable verify.sh that parses ChangesDocumentation Update & Verification Script
Sequence Diagram(s)sequenceDiagram
participant User
participant verify_sh
participant jq
participant NodeJS
participant report_json
User->>verify_sh: run ./verify.sh
verify_sh->>jq: ensure jq present
verify_sh->>NodeJS: execute embedded parser
NodeJS->>report_json: load & parse report.json
NodeJS->>NodeJS: extract baseline & graphify metrics
NodeJS->>verify_sh: print reduction ratios and usage dumps
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 inconclusive)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@README.md`:
- Line 15: Change the "See it in action" heading from h3 to h2 to match the
document hierarchy: replace the leading "###" with "##" for the heading text
"See it in action" so it follows the existing h1 → h2 structure and resolves the
MD001 heading-increment warning.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
|
|
||
| graphify-ts indexes a TypeScript/Node workspace (and PR diffs) into a local knowledge graph, then compiles that graph into the **smallest verifiable context pack** the agent actually needs for the task at hand. No cloud upload, no API key for indexing, no SaaS dashboard — just a local subprocess your agent talks to over MCP. | ||
|
|
||
| ### See it in action |
There was a problem hiding this comment.
Fix heading level to match document structure.
The heading uses h3 (###) but should use h2 (##) to maintain consistent document hierarchy. All other major sections in the README use h2, and markdown best practices require headings to increment by only one level at a time (h1 → h2, not h1 → h3).
📝 Proposed fix
-### See it in action
+## See it in actionAs per static analysis guidelines, this resolves the MD001 heading-increment warning.
📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| ### See it in action | |
| ## See it in action |
🧰 Tools
🪛 markdownlint-cli2 (0.22.1)
[warning] 15-15: Heading levels should only increment by one level at a time
Expected: h2; Actual: h3
(MD001, heading-increment)
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@README.md` at line 15, Change the "See it in action" heading from h3 to h2 to
match the document hierarchy: replace the leading "###" with "##" for the
heading text "See it in action" so it follows the existing h1 → h2 structure and
resolves the MD001 heading-increment warning.
- Add a caption under the embedded video so the headline numbers (31 -> 14 turns, 170s -> 107s, 2.81M -> 532K input tokens; all Anthropic-reported) are readable without watching the clip. - Scaffold docs/benchmarks/2026-05-09-govalidate-auth-e2e/ with a README describing the run setup and a verify.sh that reads the compare report.json and prints the reductions. The actual report.json + paired prompt/answer files still need to be dropped in from graphify-out/compare/2026-05-09T23-21-35/ before the benchmark is independently reproducible. - Link the new benchmark folder from the README's Public proof section so it's discoverable alongside the existing artifacts.
Adds four assertions to why-graphify-doc.test.ts so the new caption + benchmark folder are covered by the same honesty contract as the existing 2026-04-30 numbers: - README caption must contain the captured Anthropic-reported reductions (2,811,682 / 532,021 / 5.28x / 2.21x / 1.58x). - README must link the new docs/benchmarks/2026-05-09-... folder. - The new benchmark README must mention the Anthropic-reported framing and the --baseline-mode native_agent invocation. - verify.sh must exit cleanly with a clear message when report.json has not yet been dropped in. Full suite: 1384/1384 passing.
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
tests/unit/why-graphify-doc.test.ts (1)
108-108: ⚡ Quick winAvoid pinning the full second-level timestamp literal.
Line 108 hard-codes an exact run timestamp, which will cause noisy test churn on benchmark refreshes. Prefer matching stable structure (date/prefix) with a regex.
Proposed assertion softening
- expect(verify).toContain('graphify-out/compare/2026-05-09T23-21-35') + expect(verify).toMatch(/graphify-out\/compare\/2026-05-09T\d{2}-\d{2}-\d{2}/)🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@tests/unit/why-graphify-doc.test.ts` at line 108, The test currently pins a full timestamp in the assertion by using expect(verify).toContain('graphify-out/compare/2026-05-09T23-21-35'); change this to assert the stable prefix and a pattern instead of the exact second-level timestamp: update the assertion on the verify variable (the expect call) to use a regex-based match (or toMatch) that checks for "graphify-out/compare/" followed by a YYYY-MM-DD and time at least to hour-minute (omit or make seconds optional) so the test no longer fails when the run-second changes.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@tests/unit/why-graphify-doc.test.ts`:
- Around line 104-109: The test in why-graphify-doc.test.ts currently checks the
generated verify script for several strings but doesn't assert the "exits
cleanly" behavior; update the failing test case that inspects the verify
variable (inside the it(...) block that mentions "exits cleanly") to include an
assertion that the missing-file branch contains an explicit clean exit by adding
expect(verify).toContain('exit 0') so the test will fail if the script no longer
exits cleanly.
---
Nitpick comments:
In `@tests/unit/why-graphify-doc.test.ts`:
- Line 108: The test currently pins a full timestamp in the assertion by using
expect(verify).toContain('graphify-out/compare/2026-05-09T23-21-35'); change
this to assert the stable prefix and a pattern instead of the exact second-level
timestamp: update the assertion on the verify variable (the expect call) to use
a regex-based match (or toMatch) that checks for "graphify-out/compare/"
followed by a YYYY-MM-DD and time at least to hour-minute (omit or make seconds
optional) so the test no longer fails when the run-second changes.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro Plus
Run ID: bc317a4d-9229-44a8-8a59-dff7fa9fc061
📒 Files selected for processing (1)
tests/unit/why-graphify-doc.test.ts
Comment on lines
+104
to
+109
| it('ships a verify.sh reproducer that reads report.json and exits cleanly when missing', () => { | ||
| expect(verify).toContain('#!/usr/bin/env bash') | ||
| expect(verify).toContain('report.json') | ||
| expect(verify).toContain('not found') | ||
| expect(verify).toContain('graphify-out/compare/2026-05-09T23-21-35') | ||
| }) |
There was a problem hiding this comment.
The “exits cleanly” claim is not actually asserted.
On Line 104, the test says missing report.json exits cleanly, but Lines 105-109 only validate string presence. Add an assertion that the missing-file branch includes an explicit clean exit (exit 0) so this test fails on behavior regressions.
Proposed test tightening
it('ships a verify.sh reproducer that reads report.json and exits cleanly when missing', () => {
expect(verify).toContain('#!/usr/bin/env bash')
expect(verify).toContain('report.json')
- expect(verify).toContain('not found')
+ expect(verify).toMatch(/report\.json[\s\S]*not found[\s\S]*exit\s+0/i)
expect(verify).toContain('graphify-out/compare/2026-05-09T23-21-35')
})📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| it('ships a verify.sh reproducer that reads report.json and exits cleanly when missing', () => { | |
| expect(verify).toContain('#!/usr/bin/env bash') | |
| expect(verify).toContain('report.json') | |
| expect(verify).toContain('not found') | |
| expect(verify).toContain('graphify-out/compare/2026-05-09T23-21-35') | |
| }) | |
| it('ships a verify.sh reproducer that reads report.json and exits cleanly when missing', () => { | |
| expect(verify).toContain('#!/usr/bin/env bash') | |
| expect(verify).toContain('report.json') | |
| expect(verify).toMatch(/report\.json[\s\S]*not found[\s\S]*exit\s+0/i) | |
| expect(verify).toContain('graphify-out/compare/2026-05-09T23-21-35') | |
| }) |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@tests/unit/why-graphify-doc.test.ts` around lines 104 - 109, The test in
why-graphify-doc.test.ts currently checks the generated verify script for
several strings but doesn't assert the "exits cleanly" behavior; update the
failing test case that inspects the verify variable (inside the it(...) block
that mentions "exits cleanly") to include an assertion that the missing-file
branch contains an explicit clean exit by adding expect(verify).toContain('exit
0') so the test will fail if the script no longer exits cleanly.
3 tasks
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
Adds a short demo video right under the lead paragraph (above the Why graphify-ts? section) so anyone landing on the README sees the tool in action before scrolling.
The video is hosted on GitHub user-attachments (~75 MB), so nothing gets committed to the repo and the npm tarball stays unchanged. Embedded as a bare URL on its own line — that's the canonical pattern that GitHub renders as an inline player.
Test plan
npx vitest run tests/unit/why-graphify-doc.test.ts tests/unit/package-metadata.test.ts— 31/31 pass (doc-honesty assertions still satisfied)---) reads naturallySummary by CodeRabbit
Documentation
Tests