sync: upstream mnemon-dev/mnemon v0.1.6 (Nanobot + Codex integration)#6
Merged
Conversation
Sort diff matches by final Similarity before selecting the overall suggestion so keyword-order candidates cannot mask stronger Jaccard matches. Includes a regression test for the ADD-over-UPDATE masking case. Validation: go test ./...; go build -o mnemon .; make vet.
Move the deduplication and diff match-ordering fixes from Unreleased into the v0.1.5 changelog section so the patch release documents the memory replacement safeguards now on master. Validation: make unit; make vet; go build -o mnemon .
Ask contributors to describe user-facing release-note impact in PRs instead of editing CHANGELOG.md directly. Maintainers now own changelog updates during release preparation, reducing routine conflicts around the Unreleased section.
- Update Nanobot README link to https://github.com/HKUDS/nanobot - Make SKILL.md usage examples recall-only to match the guardrail; soften guardrail from "never" to "prefer delegating" so the intent is clear without being overly prescriptive
Feat/nanobot integration
Add Codex as a first-class setup target alongside Claude Code, OpenClaw, and Nanobot. The installer now writes Codex-specific skill and hook assets, registers SessionStart, UserPromptSubmit, and Stop hooks in .codex/hooks.json, and supports ejecting the installed Codex surface without depending on the experimental harness layer. Document the Codex setup path and record the release-path boundary for harness code in AGENTS.md. Validation: go test ./...; go build -o mnemon .; temporary Codex setup/eject smoke checks.
feat(setup): add Codex integration
Move pending host integration notes into the v0.1.6 changelog entry and call out the harness stability boundary for the release. Validation: go test ./...
Brings chancsc/mnemon master up to date with upstream v0.1.6: - Nanobot integration (mnemon setup --target nanobot) — our PR mnemon-dev#24, merged upstream - Codex integration (mnemon setup --target codex) — upstream PR mnemon-dev#27 - Dedup false-positive fixes (Jaccard similarity, cosine threshold, negation words) - Sort diff matches by similarity before picking overall suggestion Fork-specific files preserved: NANOBOT.md, scripts/sync-upstream.sh
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
3 participants
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
Brings
chancsc/mnemonmaster fully in sync withmnemon-dev/mnemonv0.1.6.Upstream changes included
mnemon setup --target nanobot) — our PR Feat/nanobot integration mnemon-dev/mnemon#24 merged upstreammnemon setup --target codex) — upstream PR feat(setup): add Codex integration mnemon-dev/mnemon#27Fork-specific files preserved
NANOBOT.md— manifest of all nanobot-specific changes vs upstreamscripts/sync-upstream.sh— automated upstream sync scriptGenerated by Claude Code