ur-agent 1.78.8 → 1.78.10

package/CHANGELOG.md

@@ -1,5 +1,55 @@
 # Changelog
 
+## 1.78.10
+
+- Provider-reported context overflow now triggers one bounded automatic
+  compaction-and-retry in the shipped build instead of immediately showing
+  `Context limit reached`. Emergency summary input replaces image/document
+  payloads with markers so a large Computer screenshot cannot prevent the
+  recovery itself; the original transcript remains unchanged. Automatic
+  recovery still respects the user's disable setting and never recurses inside
+  compact/session-memory workers.
+- The normal screen no longer paints live answer drafts or completed
+  "I'll inspect..." tool preludes. It shows stable tool progress and the final
+  answer instead; the complete provider text remains untouched in transcript
+  history, exports, verbose diagnostics, and future model context. The
+  `◭ Mashoofing…` activity row is now independent from streamed content and
+  remains mounted throughout active work, so hiding narration never hides
+  liveness. Its primary line now includes the live task-board activity after
+  the ellipsis, width-bounded to stay on one row.
+- Ollama Cloud streams now tolerate five minutes of silence during large-model
+  prefill or tool planning instead of failing after two. The deadline still
+  measures inactivity rather than total runtime and remains configurable with
+  `UR_STREAM_IDLE_TIMEOUT_MS`; remote sessions and cloud non-streaming fallback
+  keep their two-minute bounds, and real dead streams still terminate.
+
+- A new actionable work board appears immediately, even before a model emits
+  `TaskCreate`. The first explicit model task atomically replaces that automatic
+  seed, so parallel creation does not duplicate or lose work. Corrective replies
+  and interruptions now resume the existing seed or explicit unfinished board
+  instead of echoing every user message as a new task title. A successful simple
+  turn completes its seed; an aborted turn leaves it pending for honest recovery.
+- User interruptions no longer archive pending or in-progress tasks into an
+  apparently empty list. The next prompt advances the generation while keeping
+  unfinished work visible and instructs the agent to reconcile, update relevant
+  work, skip superseded work, and continue statuses. Completed terminal lists
+  move to readable history only for genuinely new work; corrective follow-ups
+  reopen the relevant active board.
+- Crew concurrency tests now declare their branches read-only, matching the
+  runtime policy that unknown shared-checkout work serializes. The artifact
+  HTTP integration test also distinguishes a managed sandbox's blanket socket
+  denial from a real occupied-port failure without changing production server
+  behavior.
+
+- Release tags can no longer be created safely from an old commit while a
+  newer version exists only in the working tree. `bun run release:tag` checks
+  that the tree is clean, the package version and newest changelog entry are in
+  `HEAD`, that exact commit is already the remote branch tip, and the version's
+  tag is unused. `--push` then creates and pushes one annotated immutable tag;
+  GitHub Actions owns GitHub Release and npm publication from the verified
+  tarball. Failed stale tags are left as history and the next patch version is
+  used instead of moving a tag.
+
 ## 1.78.8
 
 - Long model self-deliberation emitted through the ordinary answer channel is

package/README.md

@@ -785,6 +785,8 @@ bun run release:check
 bun run package:check
 npm pack --dry-run
 npm publish --dry-run
+bun run release:tag                 # read-only committed/pushed preflight
+bun run release:tag -- --push       # immutable tag; CI publishes the artifact
 ```
 
 `dist/cli.js` is intentionally tracked because GitHub installs use the bundled

package/RELEASE.md

@@ -86,14 +86,34 @@ Do not publish if the package version already exists on npm.
 
 ## Publish
 
-Only after every check passes and the working tree is clean:
+GitHub Actions publishes the exact tarball that passes the release workflow.
+Do not run `npm publish` separately and do not create a tag before the release
+commit is on the remote branch.
+
+Only after every check passes, commit the complete release and push it:
 
 ```bash
 git add .
 git commit -m "chore: polish UR-Nexus production release"
 git push origin master
-npm publish
 ```
 
+Wait for the `Test Production` workflow on that commit to pass. Then use the
+guarded tag command; its default mode is a read-only preflight:
+
+```bash
+bun run release:tag
+bun run release:tag -- --push
+```
+
+The command refuses to tag a dirty tree, an uncommitted version, a commit that
+is not yet the remote branch tip, a mismatched changelog, or a local/remote tag
+that already exists. `--push` creates one annotated immutable tag pointing at
+the verified commit. That tag starts `.github/workflows/release.yml`, which
+rebuilds and verifies the package, publishes the GitHub Release, and publishes
+the same verified tarball to npm.
+
+If a tag was accidentally pushed from the wrong commit, keep it as failed
+release history and bump to a fresh patch version. Do not move a published tag.
 If the remote default branch is not `master`, push the checked-out release
-branch instead.
+branch instead; the tag command verifies that branch by name.