docs: promote readme restructure to main - #376
Conversation
link karpathy's llm-wiki idea file as the destination vouch is built toward, and state the differentiator in one place: the llm drafts the wiki, but citations are machine-verified and every page passes the review gate. also tighten the demo-video paragraph around the five-step pipeline (capture, summarize, approve, compile, recall) and note the film ends on real recall output.
docs(readme): frame vouch as a review-gated llm-wiki
📝 WalkthroughWalkthroughREADME.md now adds a living-wiki introduction, expands install and Docker guidance, replaces the quick start with a step-by-step project loop, and shortens the closing rules and links sections. ChangesREADME documentation update
Estimated code review effort: 1 (Trivial) | ~3 minutes Possibly related PRs
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
the readme accumulated sections a new user doesn't need on the way to their first working loop — 30-second tour, object model, file layout, cli surface, mcp method list, jsonl envelope shape, bundles, neighbour comparison, openclaw packaging, a stale pre-1.0 status note. all of that lives in SPEC.md, docs/, or --help output already. what remains maps one-to-one onto docs/vouch-how-it-works.mp4: install, wire claude code (init + install-mcp), set compile.llm_cmd, work a session, approve at the gate (review / review-ui), compile the wiki, recall in the next session, commit .vouch/. plus the three invariants underneath and a going-further link list. every command and claim in the new walkthrough was verified against the released 1.2.1 artifacts earlier today; all relative links checked against the tree.
docs(readme): restructure around reproducing the demo video
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`:
- Around line 69-71: The README sample output uses an unlabeled fenced block,
which triggers markdownlint MD040. Update the fenced example in the README to
use a text language label so the sample output stays lint-clean, keeping the
existing message content unchanged.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
| ``` | ||
|
|
||
| The full surface — lifecycle ops, sessions, sources, maintenance, | ||
| migration — is listed by `vouch --help` and machine-readably by | ||
| `vouch capabilities`. | ||
|
|
||
| ## MCP tools / JSONL methods (same surface, two transports) | ||
|
|
||
| Read (unrestricted): `kb.capabilities`, `kb.status`, `kb.search`, `kb.context`, `kb.read_{page,claim,entity,relation}`, `kb.list_{pages,claims,entities,relations,sources,pending}` | ||
|
|
||
| Source intake (not gated — evidence is harmless and de-duplicates): `kb.register_source`, `kb.register_source_from_path`, `kb.source_verify` | ||
|
|
||
| Write (gated → produce proposals): `kb.propose_{claim,page,entity,relation}` (with `dry_run:true` for preview-only) | ||
|
|
||
| Decisions: `kb.approve`, `kb.reject` (host trust required) | ||
|
|
||
| Lifecycle (metadata about reviewed knowledge — direct mutation, audited): `kb.supersede`, `kb.contradict`, `kb.archive`, `kb.confirm`, `kb.cite` | ||
|
|
||
| Sessions: `kb.session_start`, `kb.session_end`, `kb.crystallize` | ||
|
|
||
| Maintenance: `kb.index_rebuild`, `kb.lint`, `kb.doctor`, `kb.audit`, `kb.export`, `kb.export_check`, `kb.import_check`, `kb.import_apply` | ||
|
|
||
| ## Wiring into Claude Code | ||
|
|
||
| In your project's `.mcp.json`: | ||
|
|
||
| ```json | ||
| { | ||
| "mcpServers": { | ||
| "vouch": { | ||
| "command": "vouch", | ||
| "args": ["serve"], | ||
| "env": { "VOUCH_AGENT": "claude-code" } | ||
| } | ||
| } | ||
| } | ||
| 🔔 1 auto-captured session summary(ies) awaiting review — run `vouch review`. | ||
| ``` |
There was a problem hiding this comment.
📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick win
Label the sample output fence.
The bare fenced block triggers markdownlint (MD040). Use text so the README stays lint-clean.
♻️ Proposed fix
-```
+```text
🔔 1 auto-captured session summary(ies) awaiting review — run `vouch review`.</details>
<!-- suggestion_start -->
<details>
<summary>📝 Committable suggestion</summary>
> ‼️ **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.
```suggestion
🧰 Tools
🪛 markdownlint-cli2 (0.22.1)
[warning] 69-69: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
🤖 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` around lines 69 - 71, The README sample output uses an unlabeled
fenced block, which triggers markdownlint MD040. Update the fenced example in
the README to use a text language label so the sample output stays lint-clean,
keeping the existing message content unchanged.
Source: Linters/SAST tools
… review) markdownlint md040 wants a language on the fence; matches how the compile flow diagram was labelled after the vouchdev#362 review.
promotes the readme restructure (#375) to main so the repo front page shows the video-first walkthrough. docs-only — no code between test and main besides #375.
Summary by CodeRabbit