Skip to content

Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors

Rust

Merge remote-tracking branch 'refs/remotes/audit-open/1539'

AkitaOnRailsb73b25317cd7
diff --cc CHANGELOG.md
index 8df19dd5,89f7324f..ba0d3fbe
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@@ -285,55 -223,13 +285,62 @@@ version in [`docs/changelog/`](docs/cha
relay and wiki sync companions take the same `rustls-webpki` bump.
### Fixed
+- An empty structured answer from a Responses-API model is now reported as
+ empty content rather than a JSON parse error. The `opencode`, `openai-oauth`
+ and `codex` paths defaulted a missing `output_text` to an empty string and
+ handed it to the parser, so the operator saw `serde: EOF while parsing a
+ value at line 1 column 0`, naming neither the model nor the cause.
+ ([#1529](https://github.com/akitaonrails/ai-memory/pull/1529))
+- Detected `core.hooksPath` when a git config set it on the same physical
+ line as the `[core]` section header, so `ai-memory-wikisync install-hook`
+ no longer writes a `.git/hooks/post-merge` that git would never run.
+ ([#1530](https://github.com/akitaonrails/ai-memory/pull/1530))
+- Counted a file's final line in `ai-memory-wikisync` diff summaries when it
+ does not end in a newline, so the `bytes/lines` figures no longer contradict
+ the `first difference at line N` printed beside them.
+ ([#1531](https://github.com/akitaonrails/ai-memory/pull/1531))
+- `ai-memory run` now refuses an `--env`/`--env-file` entry whose key carries
+ whitespace. `--env-file` lines are trimmed as a whole, not per half, so the
+ common dotenv spelling `KEY = value` produced a key with a trailing space —
+ an entry no shell or harness can read, so the override silently did nothing.
+ ([#1532](https://github.com/akitaonrails/ai-memory/pull/1532))
+- Discovered a repository page whose `--include` family names a bare top-level
+ page (`README.md`), which `ai-memory-wikisync sync` previously left out of the
+ repository side entirely, so a newly created one was never imported.
+ ([#1533](https://github.com/akitaonrails/ai-memory/pull/1533))
+- A Copilot `/responses` answer stopped by `max_output_tokens` is now reported
+ as a truncated response naming the model and its output-token count, instead
+ of an unexpected response shape reading "no error detail" — `error` is null
+ on an incomplete answer, so nothing explained the stop and the class implied
+ an unparseable reply rather than a `max_tokens` to raise.
+ ([#1534](https://github.com/akitaonrails/ai-memory/pull/1534))
+- Omitted TTL-expired pages from the page count in `memory_briefing` and
+ `memory_explore`. Every page list in a briefing already hid them, and the
+ project cards have since 3.1.x, so a project with an expired page reported
+ more latest pages than any list in the same response could show. The
+ all-versions total is unchanged, as is `ai-memory status`.
+ ([#1535](https://github.com/akitaonrails/ai-memory/pull/1535))
+
+
+- `memory_read_page` now reads a blank `path` or `query` as omitted, as its
+ sibling arguments already do. An empty or whitespace-only `query` searched
+ for an empty FTS expression and reported the inevitable miss as an internal
+ error (-32603), which a looping client reads as "retry"; an empty `path`
+ failed as "invalid path: empty path" and never tried the `query` passed
+ beside it. Both now reach the instructive "exactly one of `path` or `query`"
+ refusal, and a blank `path` beside a real `query` runs the search.
+ ([#1536](https://github.com/akitaonrails/ai-memory/pull/1536))
+- Reported a wiki page renamed away with an external tool, which arrives as a
+ rename event rather than a removal, so the next auto-commit drops it from the
+ tree instead of leaving a checkpoint naming a page that no longer exists.
+ ([#1537](https://github.com/akitaonrails/ai-memory/pull/1537))
+ - Omitted TTL-expired pages from the 7- and 30-day activity counters in
+ `memory_briefing`. A page written with a short TTL made a project look
+ active while the brief's own recent-page list was empty, which is the
+ signal an agent uses to decide how much context to pull. Session and
+ observation counters have no TTL and are unchanged.
+ ([#1539](https://github.com/akitaonrails/ai-memory/pull/1539))
+
- Memory health no longer counts a link from a superseded or TTL-expired page
version as a reference. A page whose only inbound link was removed by a later
edit was reported as linked, because the old version's `links` row survives
diff --cc crates/ai-memory-store/tests/suite/multi_session.rs
index f0bf8bc1,6da980ba..a52fe1e8
--- a/crates/ai-memory-store/tests/suite/multi_session.rs
+++ b/crates/ai-memory-store/tests/suite/multi_session.rs
@@@ -4537,66 -4537,75 +4537,139 @@@ async fn memory_health_ignores_expired_
assert_eq!(p_detail.orphans.len(), 2);
}
+/// The briefing's `pages_latest` must agree with the page lists in the same
+/// snapshot: an expired page is hidden from every one of them, so counting it
+/// in the headline makes the brief advertise a page the agent cannot reach.
+#[tokio::test]
+async fn briefing_pages_latest_ignores_expired_pages() {
+ let tmp = tempfile::tempdir().unwrap();
+ let store = Store::open(tmp.path()).unwrap();
+ let (ws, proj) = scope(&store).await;
+
+ store
+ .writer
+ .upsert_page(page(ws, proj, "notes/live.md", "Live", "content"))
+ .await
+ .unwrap();
+ let mut expired = page(ws, proj, "notes/expired.md", "Expired", "content");
+ expired.expires_at = Some(jiff::Timestamp::from_second(1).unwrap());
+ store.writer.upsert_page(expired).await.unwrap();
+
+ let live_pages = store
+ .reader
+ .list_unexpired_pages("acme", "shared-app")
+ .await
+ .unwrap();
+ assert_eq!(live_pages.len(), 1, "one of the two pages is expired");
+
+ let project = store
+ .reader
+ .briefing_for_project(ws, proj, 5, ai_memory_core::OwnerFilter::Any, false)
+ .await
+ .unwrap();
+ assert_eq!(
+ project.counts.pages_latest,
+ live_pages.len() as u64,
+ "project pages_latest counts only the unexpired latest page"
+ );
+ assert_eq!(
+ project.recent_pages.len(),
+ 1,
+ "control: the list the count is supposed to agree with holds one page"
+ );
+ // Control: the all-versions total is deliberately TTL-blind, so a fix that
+ // merely broke both counts the same way cannot satisfy this test.
+ assert_eq!(
+ project.counts.pages_all, 2,
+ "control: pages_all stays the raw all-versions total"
+ );
+
+ let workspace = store
+ .reader
+ .briefing_for_workspace(ws, 5, ai_memory_core::OwnerFilter::Any, None)
+ .await
+ .unwrap();
+ assert_eq!(workspace.counts.pages_latest, 1);
+ assert_eq!(workspace.counts.pages_all, 2);
+
+ let global = store
+ .reader
+ .briefing(5, ai_memory_core::OwnerFilter::Any)
+ .await
+ .unwrap();
+ assert_eq!(global.counts.pages_latest, 1);
+ assert_eq!(global.counts.pages_all, 2);
+}
++
+ /// The briefing's activity windows are what an agent calibrates verbosity
+ /// against, and `recent_pages` in the same snapshot already hides TTL-expired
+ /// pages. A page written today with an expiry an hour ago must not make the
+ /// project look active.
+ #[tokio::test]
+ async fn briefing_activity_windows_ignore_expired_pages() {
+ let tmp = tempfile::tempdir().unwrap();
+ let store = Store::open(tmp.path()).unwrap();
+ let (ws, proj) = scope(&store).await;
+
+ let mut expired = page(ws, proj, "notes/expired.md", "Expired", "content");
+ expired.expires_at = Some(jiff::Timestamp::from_second(1).unwrap());
+ store.writer.upsert_page(expired).await.unwrap();
+
+ let project = store
+ .reader
+ .briefing_for_project(ws, proj, 5, ai_memory_core::OwnerFilter::Any, false)
+ .await
+ .unwrap();
+ assert!(
+ project.recent_pages.is_empty(),
+ "control: the only page in the window is already hidden from the list"
+ );
+ assert_eq!(
+ project.activity_7d.pages_updated, 0,
+ "the expired page does not count as 7-day project activity"
+ );
+ assert_eq!(project.activity_30d.pages_updated, 0);
+
+ let workspace = store
+ .reader
+ .briefing_for_workspace(ws, 5, ai_memory_core::OwnerFilter::Any, None)
+ .await
+ .unwrap();
+ assert_eq!(workspace.activity_7d.pages_updated, 0);
+ assert_eq!(workspace.activity_30d.pages_updated, 0);
+
+ let global = store
+ .reader
+ .briefing(5, ai_memory_core::OwnerFilter::Any)
+ .await
+ .unwrap();
+ assert_eq!(global.activity_7d.pages_updated, 0);
+ assert_eq!(global.activity_30d.pages_updated, 0);
+
+ // Control: a live page written in the same window still counts, so the
+ // guard cannot pass by zeroing the counter outright.
+ store
+ .writer
+ .upsert_page(page(ws, proj, "notes/live.md", "Live", "content"))
+ .await
+ .unwrap();
+ let project = store
+ .reader
+ .briefing_for_project(ws, proj, 5, ai_memory_core::OwnerFilter::Any, false)
+ .await
+ .unwrap();
+ assert_eq!(project.activity_7d.pages_updated, 1);
+ assert_eq!(project.activity_30d.pages_updated, 1);
+ let workspace = store
+ .reader
+ .briefing_for_workspace(ws, 5, ai_memory_core::OwnerFilter::Any, None)
+ .await
+ .unwrap();
+ assert_eq!(workspace.activity_7d.pages_updated, 1);
+ let global = store
+ .reader
+ .briefing(5, ai_memory_core::OwnerFilter::Any)
+ .await
+ .unwrap();
+ assert_eq!(global.activity_7d.pages_updated, 1);
+ }