chore(release): v6.14.0 — docs + version sync#229
Merged
Conversation
- CHANGELOG + CONTRIBUTORS: verify-ai-output Hallucination Guard prototype (#227, PR #228) - version sync to 6.14.0 across package.json x3, gen-context.js, src/mcp/server.js, version.json - docs: cli.md verify-ai-output command + count 40; roadmap v6.14.0 entry + stats (914 tests); index.md release label - benchmark metrics unchanged: verify-ai-output adds a command and does not affect retrieval/token; --skip-clone run was a partial cached sample, not canonical
There was a problem hiding this comment.
Pull request overview
Release preparation for v6.14.0, syncing all version identifiers across the monorepo and updating the documentation/changelog to reflect the new verify-ai-output Hallucination Guard command.
Changes:
- Bumped versions to 6.14.0 across
package.jsonfiles,gen-context.js,src/mcp/server.js, andversion.json. - Documented
verify-ai-outputin the CLI reference and updated the roadmap + landing page release label. - Added v6.14.0 entries to
CHANGELOG.mdandCONTRIBUTORS.md.
Reviewed changes
Copilot reviewed 11 out of 11 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
| version.json | Bumps published version metadata to 6.14.0. |
| src/mcp/server.js | Updates MCP server reported version to 6.14.0. |
| packages/core/package.json | Syncs sigmap-core package version to 6.14.0. |
| packages/cli/package.json | Syncs sigmap-cli package version to 6.14.0. |
| package.json | Syncs root package version to 6.14.0. |
| gen-context.js | Syncs bundled VERSION + MCP server info version to 6.14.0. |
| docs-vp/index.md | Updates homepage release badge to v6.14.0 and highlights the new feature. |
| docs-vp/guide/roadmap.md | Adds v6.14.0 shipped entry and advances current milestone to v6.15+. |
| docs-vp/guide/cli.md | Adds verify-ai-output to the command table and documents usage/output. |
| CONTRIBUTORS.md | Adds “Recent Contributors (v6.14.0)” entry. |
| CHANGELOG.md | Adds v6.14.0 release notes for verify-ai-output. |
|
|
||
| **Tags:** `verify-ai-output` · `hallucination guard` · `fake-file` · `fake-import` · `fake-symbol` · `deterministic` · `offline` · `issue #227` · `PR #228` | ||
|
|
||
| **Impact:** new command surface for trust/verification; 65 integration test files pass (13 new). Foundation for the reliable MVP (closest-match suggestions, `fake-test-file`/`fake-npm-script`, 5-repo precision proof). |
2 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
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.
Release prep for v6.14.0 (
/update-docs). Next step after merge:/ship(tag + GitHub release).What's in v6.14.0
verify-ai-output— Hallucination Guard prototype (feat: verify-ai-output (Hallucination Guard) prototype — deterministic core #227, PR feat(verify): verify-ai-output hallucination guard prototype #228): deterministic, offline command that flags fake files, imports, and symbols in an AI answer.Changes in this PR
[6.14.0]section.Recent Contributors (v6.14.0)entry.scripts/sync-versions.mjs:package.json×3,gen-context.jsVERSION,src/mcp/server.js,version.json.verify-ai-outputtable row + full section; command count 39 → 40.Benchmark metrics — intentionally unchanged
version.jsonheadline metrics (hit@5 81.1%, token reduction 96.5%, task success 53.3%, prompt reduction 41.8%, lift 6.0×) are kept as the canonical full-run values:verify-ai-outputadds a command; it does not touch retrieval or token output, so those numbers should not move from this work.--skip-clone, which benchmarks only locally-cached repos (a partial 18-repo sample) — not a canonical full run. Refreshing headline numbers requires a full live-clone run (network, ~20 min).Refreshed benchmark report JSONs from the partial run were not committed for the same reason.
🤖 Generated with Claude Code