Add SSH-authenticated transports with independent settings, protocol-aware menus and snippets, and tmux session persistence.
Restore eligible iOS workspaces from encrypted transport checkpoints without adding a macOS recovery entry. Include schema migrations and regression coverage.
Update TailscaleKit to 1.0.2, align the state namespace with the app identifier, and verify scoped cleanup in signed macOS and iOS app hosts.
BREAKING CHANGE: Existing legacy Tailscale Keychain state is not migrated. Sign in again to create device-local Data Protection Keychain state.
Pin libssh2-spm 2.0.3-termind-4 and document the official submodule plus CI-applied patch workflow. Keep the maintenance gitlink and resolved revision aligned.
Validation: native regressions, all ten Apple package builds, remote binary consumer, 1758 macOS app tests, 43 focused SSH/security-key/architecture tests, and localization checks passed. The full shared framework run hit 60-second time limits in assistant conversation tests.
Bind independent Tailnet connections to group IDs while preserving legacy host identities through the V3 sync format. Persist profile cleanup retries, isolate test storage, and reject stale dialers after re-enrollment.
Recover quarantined sync records safely, refresh metrics compatibility, fix multiline shell history, and remove obsolete mobile history gates. Pin libtailscale-spm to 1.0.1 alongside its submodule revision.
Validation: default macOS suites (2679 tests), targeted iOS suites (26 tests), strict Swift formatting, shared AppStrings checks, and Chinese localization checks passed. Both subagent reviews approved.
Replace the local CSSH2 package reference with the remote libssh2-spm fork pinned to 2.0.3-termind-1. Refresh Package.resolved without changing other dependency versions.
Add native security key registration, reference import, and signing on macOS and iOS. Store references in Vault metadata and route authentication through connection, Assistant, MCP, and agent forwarding flows.
Preserve signing cancellation and actionable authentication errors for security keys and Secure Enclave. Pin the released libssh2 forks as nested submodules and refresh package resolution.
Integrate AgentKit 0.18.1 with native authorization on macOS and iOS, device-local OAuth credentials, V43 configuration persistence, and Assistant authorization prompts.
Add HTTPS callback metadata, keep native callbacks safe across actor boundaries, and distinguish authorization setup failures from cancellation. Extend the external MCP server to negotiate 2025-03-26.
Add host-owned chat creation, model discovery, messaging, reading, and waiting with durable delivery receipts. Keep tool presentation compact, mark agent-authored messages, and prevent edits that would remove tool activity.
Adopt the signed AgentKit 0.16.0 release in the package requirement, resolved revision, and submodule.
Review every 10 turns or 15 non-memory tool calls and save explicit corrections promptly. Invalidate outdated learning after lifecycle and history changes, and prevent older correction retries from overwriting newer corrections.
Replace capacity bars with entry and character counts, retain per-entry and model-input budgets, and migrate away from frozen snapshots. Upgrade the AgentKit package and submodule to signed release 0.15.0.
Pin the provider codec refactor and refreshed documentation release to
591375990284bf90858e7f049c516777432970f7. Preserve every other package pin.
Validation: AgentKit build and 218 tests, macOS and iOS app builds, strict
Swift formatting, Chinese localization, and project checks passed.
Full macOS tests: 1,598 passed, 3 failed, 8 skipped. Full iOS tests:
584 passed, 2 failed. Focused reruns passed the two Agent timing cases
and mobile Settings layout case. The previously documented Metrics
lifecycle and mobile knowledge-card rendering failures remain.
Allow optional API keys in desktop and mobile settings and share credential
resolution across model requests. Missing stored credentials remain errors.
Enable user-configured HTTP endpoints and pin signed AgentKit 0.13.1, which
omits empty authentication headers for probes and inference.
Validation: AgentKit's 216 tests and iOS's 461 tests passed, along with Swift
formatting, localization checks, native screenshots, and real HTTP smoke tests
on both apps. macOS passed 1419 of 1422 tests initially; existing Metrics timing,
waveform PNG comparison, and MCP upload runner failures were observed. MCP and
Metrics passed a focused rerun, while Metrics remains intermittent and waveform
comparison still fails. iOS simulator LAN-IP access timed out; desktop LAN-IP
and both platforms' localhost, loopback-IP, and local-domain requests passed.
Keep previously installed starter skills as ordinary user-owned records. Provide hidden read-only Skill Creator and Skill Installer instructions, use AgentKit 0.13.0 for reviewed complete GitHub package installation, and remove skill seeding and Reset.
Move Hermes Memory below MCP, use Enabled for its switch, and localize its Chinese title as persistent memory. Preserve existing user edits and synchronize user skill packages through the existing atomic store.
Validation: AgentKit 213 tests and iOS 452 tests passed. macOS app 1183 tests passed; shared frameworks passed 231/232 with the existing SpeechWaveformViewTests PNG byte-equality failure. Related skill, sync, localization and UI checks passed. Strict Swift formatting, Chinese localization checks, and git diff --check passed.
Add opt-in GRDB memory with frozen conversation snapshots, background learning, session search, and a user-only Destroy action on both platforms. Persist and synchronize complete skill packages with the new AgentKit management tools.
Pin signed AgentKit 0.12.3 and GRDB 7.11.1. Add the V18 package migration, regression coverage, bilingual UI snapshots, and architecture records.
Validation: AgentKit and iOS suites, focused macOS skills/memory/architecture/localization tests, Swift formatting, and Chinese localization checks passed. Full macOS runs exposed intermittent existing waveform-rendering and metrics-timing failures.
Kaede Akino