Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
Rust
docs: record managed continuity fixes
AkitaOnRails6bc73e00c855
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 3ca999c9..676e0415 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -31,6 +31,28 @@ version in [`docs/changelog/`](docs/changelog/):### Fixed+- Kept purge-session tombstones out of automatic hollow-project cleanup, so+ an old otherwise-empty project cannot lose replay protection immediately+ after its session is purged (GHSA-pphw-hm98-3wh4).+- Made Crush transcript cursors revision-aware within their one-second native+ timestamp bucket. Same-second inserts and edits are now imported exactly+ once, while captured recovery endpoints still exclude later revisions+ (#1813).+- Made TypeScript SDK capability initialization client-owned with independently+ cancellable waits, so one caller cannot abort another caller's shared probe+ and a later caller observes its own cancellation promptly (#1815).+- Initialized MCP sessions in the document and agentmemory importer routes,+ retaining validated session IDs and sending `notifications/initialized`, so+ conditional imports work with both stateless and `--http-stateful` servers+ (#1836).+- Explicit `ai-memory run --fresh claude` launches now expose the previously+ linked Claude session through `AI_MEMORY_PREVIOUS_SESSION_HISTORY`, including+ when the two sessions live under different Claude config homes (#1789).+- Replaced the misleading hook-refresh-only warning after a linked Codex run+ fails to acknowledge context with a `/new`-specific ownership warning. The+ wrapper does not adopt the unlinked thread because Codex supplies no trusted+ parent relationship (#1788).+- Sorted recent page lists by timestamp rather than RFC3339 text, so updateswith different fractional-second precision appear in chronological orderin the legacy recent API, project activity, folder previews and namespacediff --git a/docs/managed-workstreams.md b/docs/managed-workstreams.mdindex 80a6f13a..c3a5d27d 100644--- a/docs/managed-workstreams.md+++ b/docs/managed-workstreams.md@@ -464,7 +464,17 @@ it. The compressed copy counts as the linked session, so the launch resumes itand the transcript import reads it like the plain file. Use`ai-memory run --fresh <harness>` to deliberately skip the linkedsession and the adoption chooser. `--fresh` cannot be combined with a native-resume, continue, session, or fork selector.+resume, continue, session, or fork selector. A fresh interactive launch still+exports the linked session as `AI_MEMORY_PREVIOUS_SESSION_HISTORY` when it is+available locally. This matters when Claude's new session uses a different+configuration home: the harness can read the bounded, checkout-validated old+session without ai-memory copying it into the server.++Codex's in-session `/new` command does not expose a trustworthy parent-thread+relationship. ai-memory therefore never guesses that the new thread owns the+managed workstream. If the linked thread exits without acknowledging its+context after `/new`, the wrapper explains that the intended thread must be+selected explicitly on the next managed run.## What happens on each run@@ -574,6 +584,12 @@ OpenCode 2 compaction messages import their `summary` as a compaction event(and, when a failed compaction has no summary, `error.message`). The V1 adapteralready imported compaction parts the same way.+Crush cursors fingerprint every message revision in the newest one-second+timestamp bucket. This preserves inserts whose UUID sorts below the prior+cursor and edits whose native timestamp did not advance. Exact recovery ranges+also retain the captured endpoint fingerprints, so a revision written later in+that second is not pulled backward into an earlier interval.+Search and tail also return optional `source_record_id` and `metadata` fields.The text CLI prints the source record and correlation metadata as escaped JSON;`--json` preserves these fields for consumers. Older server responses without