nexusmem 0.5.4 → 0.7.0

package/CHANGELOG.md

@@ -9,6 +9,59 @@ built from, matched by publish timestamp: `v0.1.0` → `67a4776`, `v0.1.1` → `
 
 ## [Unreleased]
 
+No unreleased changes yet.
+
+## [0.7.0] — 2026-08-21
+
+### Added
+
+- `nexusmem stale --check-contradictions`: for each stale candidate, finds the most similar newer
+  node (local embedding search) and asks a local SLM (Ollama, `qwen2.5:3b` by default) whether it
+  actually contradicts the older one, instead of only surfacing by age. Suggest-only — nothing is
+  written, same as plain `stale`. Live-dogfooded against this repo's own real database and Ollama
+  instance; found and fixed a real gap along the way (below) before the feature surfaced anything
+  useful.
+- Import graph: bare Python imports with no leading dot (`import foo`, `from foo import bar`)
+  now resolve to a same-directory sibling file too, alongside the existing relative-dot support.
+  Found dogfooding two real local projects: neither used a single PEP 328 relative import, both
+  relied entirely on this flat-script style. Guarded by a static list of stdlib module names so a
+  bare `import os`/`import queue`/etc. is never mistaken for a same-named local file.
+
+### Fixed
+
+- Import graph: a Java wildcard import (`import a.b.*;`) no longer merges files from two
+  unrelated packages that happen to share a directory-name suffix (e.g. two Gradle/Maven modules
+  each with their own `.../foo`) — it now refuses to guess, same as the single-class-import case.
+- `stale --check-contradictions`'s neighbor search now looks past same-timestamp sibling nodes
+  (e.g. the many chunks one long conversation gets split into) to reach genuinely newer content.
+  Found live-dogfooding against this repo's own database: the first real candidate's closest 15
+  neighbors were all same-conversation siblings sharing its exact timestamp, so the original
+  5-neighbor default silently found zero suggestions for every candidate, regardless of what the
+  SLM would have said.
+
+## [0.6.0] — 2026-08-20
+
+### Added
+
+- Ranker: `inferred` nodes (summaries, doc snapshots) now decay twice as fast as `observed` ones
+  (git commits, diffs, shell commands) for retrieval purposes. A judgment call, not a measured
+  optimum — see `INFERRED_HALF_LIFE_RATIO` in `src/retrieval/rank.ts`.
+- `nexusmem stale`: lists aging `inferred` nodes nothing has superseded yet, as candidates for
+  `mark-stale`. A heuristic on age and provenance, not real contradiction detection — writes nothing.
+- `nexusmem status` now surfaces an `aging` line with the stale-candidate count when any exist.
+- Import graph: Python relative imports (`from .foo import bar`, `from . import x`) now produce
+  file edges too, alongside the existing JS/TS support. Absolute Python imports are still skipped —
+  same "missed edge over wrong edge" reasoning as JS/TS's bare-specifier skip.
+- Import graph: Go internal imports (resolved against `go.mod`'s module path, one edge per
+  non-test file in the imported package) and Rust `mod foo;` declarations (2018+ edition module
+  layout) now produce file edges too. External Go imports and Rust `use` paths are out of scope for
+  the same reason.
+- Import graph: Java imports (`import a.b.C;` / `import a.b.*;`, resolved by unambiguous suffix
+  match against the tracked source tree) and `__DIR__`-anchored PHP `require`/`include` now produce
+  file edges too — all six of `nexusmem scan-structure`'s tracked languages. `import static`, PHP's
+  autoloaded `use Namespace\Class;`, and any unanchored PHP include are out of scope for the same
+  "missed edge over wrong edge" reason as everywhere else in the import graph.
+
 ## [0.5.4] — 2026-08-20
 
 ### Added
@@ -428,7 +481,12 @@ First public release.
   there is no local-model summarization pass, and the conversation collector has never been audited
   for the stale-node bug that was found and fixed in the docs collector.
 
-[Unreleased]: https://github.com/yaminbkk/NexusMem/compare/v0.5.1...HEAD
+[Unreleased]: https://github.com/yaminbkk/NexusMem/compare/v0.7.0...HEAD
+[0.7.0]: https://github.com/yaminbkk/NexusMem/compare/v0.6.0...v0.7.0
+[0.6.0]: https://github.com/yaminbkk/NexusMem/compare/v0.5.4...v0.6.0
+[0.5.4]: https://github.com/yaminbkk/NexusMem/compare/v0.5.3...v0.5.4
+[0.5.3]: https://github.com/yaminbkk/NexusMem/compare/v0.5.2...v0.5.3
+[0.5.2]: https://github.com/yaminbkk/NexusMem/compare/v0.5.1...v0.5.2
 [0.5.1]: https://github.com/yaminbkk/NexusMem/compare/v0.5.0...v0.5.1
 [0.5.0]: https://github.com/yaminbkk/NexusMem/compare/v0.4.0...v0.5.0
 [0.4.0]: https://github.com/yaminbkk/NexusMem/compare/v0.3.3...v0.4.0

package/README.md

@@ -263,16 +263,25 @@ Latency on a ~530-node corpus, warm, p50 over 10 runs:
 All the SQLite work totals about 5 ms. The embedding call is the only thing on this path worth
 optimizing, and it is somebody else's process.
 
-## Manual staleness & provenance
+## Staleness & provenance
 
 Two things a memory layer needs and this one only partly has: a way to tell an observed fact from a
-guess, and a way to retire a conclusion once something contradicts it. Neither is automatic here —
-this section is what exists and what doesn't.
+guess, and a way to retire a conclusion once something contradicts it. This section is what exists
+and what doesn't.
 
 Every node carries a `provenance`: `observed` (a commit that landed, a shell command's real exit
 code) or `inferred` (a conversation turn, a session summary, a doc section — all readable as claims
-that could be wrong or go stale). Set once per collector at ingest time, and shown as a `[observed]`
-/ `[inferred]` tag on every query result.
+that could be wrong or go stale). Set once per collector at ingest time, shown as a `[observed]` /
+`[inferred]` tag on every query result, and now used to decay retrieval weight too — `inferred` nodes
+fade from ranking twice as fast as `observed` ones as they age.
+
+```bash
+nexusmem stale
+```
+
+Lists `inferred` nodes old enough (45+ days by default) that nothing has confirmed they still hold —
+a heuristic on age and provenance, not on content. It writes nothing; you decide which candidates are
+actually wrong.
 
 ```bash
 nexusmem mark-stale <oldNodeId> --supersedes <newNodeId>
@@ -281,10 +290,22 @@ nexusmem mark-stale <oldNodeId> --supersedes <newNodeId>
 Links `newNodeId` as the replacement for `oldNodeId`. The ranker down-weights the old node from then
 on (it stays queryable, just usually loses to its replacement) — nothing is deleted, unlike `forget`.
 
-**What this doesn't do:** nothing here detects staleness on its own. If a later commit contradicts an
-earlier doc section, NexusMem has no way to notice that and flag it — a human or an agent has to spot
-the contradiction and run `mark-stale` themselves. Automatic staleness detection is still an open
-problem.
+```bash
+nexusmem stale --check-contradictions
+```
+
+For each candidate, finds the most similar newer node (local embedding search) and asks a local SLM
+(Ollama, `qwen2.5:3b` by default) whether it actually contradicts the older one — real content
+comparison, not just age. A match is printed as `likely superseded by <id> <title> -- <reason>`
+under the candidate; nothing is written, same as plain `stale`. Needs Ollama running; costs one
+embedding call and, when a plausible newer node exists, one chat completion per candidate (capped at
+10 by default — pass `-n` to raise it).
+
+**What this doesn't do:** it is one small model's yes/no judgment on one older/newer pair, not a
+verified fact — treat a match as a lead to check, not a conclusion. It also only ever compares a
+candidate against nodes *found by embedding similarity*; a contradiction from an unrelated-sounding
+node would never surface. Real contradiction detection (comprehensively, not just for the pair the
+vector search happens to surface) is still an open problem.
 
 ## Where it breaks
 
@@ -352,8 +373,9 @@ problem.
 ## Commands
 
 `init`, `sync`, `query <text>`, `status` (add `--share` for a plain-text summary worth pasting
-somewhere), `projects`, `mcp`, `forget <value>`, `mark-stale <nodeId> --supersedes <newNodeId>`,
-and `hook install|remove|status`.
+somewhere), `projects`, `mcp`, `forget <value>`, `stale` (add `--check-contradictions` for a local-SLM
+content check, see above), `mark-stale <nodeId> --supersedes <newNodeId>`, and
+`hook install|remove|status`.
 
 There are also five dry-run previews (`scan-git`, `scan-diff`, `scan-shell`, `scan-docs`,
 `scan-conversation`)