* feat(team): add custom templates and Hermes Lite workers
* docs: reorganize multilingual product guides
* ci: generate self-hosted star history
* ci: verify published star history charts
* docs: update WeChat community QR code
* docs: document DeepSeek Harness across user guides
* feat(team): harden collaboration workflows and shared workspace access
* feat(team): support Hermes Lite workers
* fix(team): prepare Hermes worker ownership
* fix(team): honor terminal narrative projection
* feat: add research team template and optimize Lite instance batch creation
- add a six-member research team template and five research agent profiles
- limit Lite instance batches to 100 instances
- use four concurrent workers while preserving response order
- validate aggregate mode capacity and avoid repeated quota and name checks
- sort the instance list by creation time
- add concurrency and capacity tests and update documentation and progress
* feat(instance): support restarting instances with environment overrides
* feat(runtime): parallelize Lite gateway scheduling and reserve port blocks
- add a configurable gateway start in-flight limit with a default of 32
- allow capacity-100 deployments to start up to 100 gateways concurrently
- reconcile batch-created Lite instances in parallel
- atomically reserve three-port blocks before calling the runtime agent
- retry with the next available block when the runtime agent reports a port conflict
- document the gateway, Chromium CDP, and browser control port contract
- add scheduler, capacity, conflict fallback, and configuration coverage
* fix: remove rebase conflict markers
* feat: add Workbuddy Pro runtime support
* feat(ui): temporarily hide unavailable runtime options
* fix(runtime): preserve long streams and pro workspace layout
* feat(runtime): manage thinking and workspace controls
* fix(team): preserve provider and preview contracts
* fix(team): unify terminal chat presentation
* fix(team): normalize chat recovery and self-check flow
* fix(db): bootstrap model reasoning migration
* fix(team): restore explicit assignment completion flow
* fix(team): reconcile validation retries and member state
* fix(team): recover root turns without blocking flow
* feat(models): combine runtime and managed thinking controls
* fix(team): coordinate dependent assignment attempts
* fix(team): recover stalled workflows without monitor writes
---------
Co-authored-by: Li-Day-Day <943831438@qq.com>
* feat: add research team template and optimize Lite instance batch creation
- add a six-member research team template and five research agent profiles
- limit Lite instance batches to 100 instances
- use four concurrent workers while preserving response order
- validate aggregate mode capacity and avoid repeated quota and name checks
- sort the instance list by creation time
- add concurrency and capacity tests and update documentation and progress
* feat(instance): support restarting instances with environment overrides
* feat(runtime): parallelize Lite gateway scheduling and reserve port blocks
- add a configurable gateway start in-flight limit with a default of 32
- allow capacity-100 deployments to start up to 100 gateways concurrently
- reconcile batch-created Lite instances in parallel
- atomically reserve three-port blocks before calling the runtime agent
- retry with the next available block when the runtime agent reports a port conflict
- document the gateway, Chromium CDP, and browser control port contract
- add scheduler, capacity, conflict fallback, and configuration coverage
* fix: remove rebase conflict markers
* fix(runtime): use single ports for Hermes Lite
Replace the obsolete https://api.minimax.chat/v1 base URL with the
current global OpenAI-compatible endpoint (https://api.minimax.io/v1)
and add the corresponding China OpenAI-compatible endpoint plus global
and China Anthropic-compatible endpoints, so the built-in MiniMax preset
covers the current regional and protocol variants.
Co-authored-by: octo-patch <266937838+octo-patch@users.noreply.github.com>
* fix: support lite cron jobs with control-plane gateway ports
* fix(team): reuse Redis Bus connections and improve workspace filename display
- Add a shared connection pool for Team Redis Bus commands
- Add coverage for Redis connection reuse
- Show full workspace filenames on hover when names are truncated
* feat: add research team template and optimize Lite instance batch creation
- add a six-member research team template and five research agent profiles
- limit Lite instance batches to 100 instances
- use four concurrent workers while preserving response order
- validate aggregate mode capacity and avoid repeated quota and name checks
- sort the instance list by creation time
- add concurrency and capacity tests and update documentation and progress
* feat(instance): support restarting instances with environment overrides
* chore: ignore local agency and team snapshots
* feat: add team agent profile templates
* KANBAN
* template
* prototype
* Fix tenant runtime pool deployment
* Fix local team profiles runtime override
* Update local team profiles testing guide
* Adapt local team profiles test deployment
* Patch tenant NFS server to ClusterIP
* Use NFS export root for workspace mounts
* Tighten team task completion projection
* Fix team event body map comparison
* before modification
* temp_peer1
* leadermodel
* team_fix
* fix(team): harden workflow completion and workspace handling
* fix(team): harden redis workflow protocol
* discord link updated
* chore: checkpoint team workflow fixes
* fix: stabilize leader kanban ledger
* fix: coalesce leader mediated work items
* fix: confirm leader-mediated member results
* fix: harden leader mediated team state
* fix: stabilize team shared runtime state
* Fix team task reconciliation and create flow
* fix: stabilize leader mediated team orchestration
* fix: refine team workspace presentation
* checkpoint: persist team workflow ledger fixes
* fix: reconcile team workflow delivery state
* fix: preserve meaningful team chat events
* docs: add team workspace quick guides
* chore: ignore local team deployment files
* fix: preserve setgid on team shared directories
* fix(team): align workspace overlays and completion projection
* fix(team): preserve workflow identity recovery
* fix(team): protect terminal workflow projection
* fix(team): preserve collaboration flow after terminal results
* feat(skill-hub): add Skill Hub catalog, publish flow, and lite materialize pipeline
Introduce Skill Hub for browsing, importing, publishing, and installing skills, with lite instance package materialization and runtime sync support.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(skill-hub): remove token-governance hooks from Skill Hub PR
Strip validateManagedRuntimeEnvironmentOverrides, network lock policy sync,
and egress proxy audit wiring that belong to the upcoming token-usage work,
so the Skill Hub branch compiles independently.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(skill-hub): update migration number in materialize docs
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(skill-hub): make RuntimeAgentClient test stub and hub tests compile-safe
Add ResyncInstanceSkills to the runtime pool handler fake client, and harden
skill hub payload helpers/tests against nil storage/instance repos so go test passes.
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat: add Skill Hub hardening with session usage tracking and egress governance
Unify Skill Hub runtime sync improvements with session-token observability,
egress network policy, and admin/instance usage reporting for reopenable PR.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(skill-hub): repair CI tests and nested skill install
* fix(ci): restore release deployment configuration
---------
Co-authored-by: heshengran <heshengran@ieisystem.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(runtime): improve Lite gateway scheduling and proxy stability
- Expand the runtime gateway port range to match 100 instances per pod
- Scale runtime deployments based on pending backlog
- Serialize gateway creation per pod and handle starting/creating states
- Clean up missing gateway bindings from runtime agent reports
- Improve Lite gateway proxy token stripping and auth header injection
- Update deployment manifests, docs, and related tests
* fix(runtime): harden Hermes Lite gateway recovery
- Add hashed gateway token aliases for short-term token compatibility
- Fix /resume conversations failing when old sessions use mismatched gateway tokens
- Recover ports only from stale error bindings without affecting active gateways
* feat(runtime): enable bidirectional desktop clipboard and direct proxy
- Enable WebTop/Selkies/Kasm clipboard by default with per-instance overrides
- Document clipboard verification, configuration pitfalls, and IME troubleshooting
- Enable direct desktop proxy in the K8s and K3s manifests
---------
Co-authored-by: litiantian03 <litiantian03@ieisystem.com>
* chore: ignore local agency and team snapshots
* feat: add team agent profile templates
* KANBAN
* template
* prototype
* Fix tenant runtime pool deployment
* Fix local team profiles runtime override
* Update local team profiles testing guide
* Adapt local team profiles test deployment
* Patch tenant NFS server to ClusterIP
* Use NFS export root for workspace mounts
* Tighten team task completion projection
* Fix team event body map comparison
* before modification
* temp_peer1
* leadermodel
* team_fix
* fix(team): harden workflow completion and workspace handling
* fix(team): harden redis workflow protocol
* discord link updated
* chore: checkpoint team workflow fixes
* fix: stabilize leader kanban ledger
* fix: coalesce leader mediated work items
* fix: confirm leader-mediated member results
* fix: harden leader mediated team state
* fix: stabilize team shared runtime state
* Fix team task reconciliation and create flow
* fix: stabilize leader mediated team orchestration
* fix: refine team workspace presentation
* checkpoint: persist team workflow ledger fixes
* fix: reconcile team workflow delivery state
* fix: preserve meaningful team chat events
* docs: add team workspace quick guides
* chore: ignore local team deployment files
* fix: preserve setgid on team shared directories
* chore: ignore local agency and team snapshots
* feat: add team agent profile templates
* KANBAN
* template
* prototype
* Fix tenant runtime pool deployment
* Fix local team profiles runtime override
* Update local team profiles testing guide
* Adapt local team profiles test deployment
* Patch tenant NFS server to ClusterIP
* Use NFS export root for workspace mounts
* Tighten team task completion projection
* Fix team event body map comparison
* before modification
* temp_peer1
* leadermodel
* team_fix
* fix(team): harden workflow completion and workspace handling
* fix(team): harden redis workflow protocol
- Add APIs for batch creating and deleting Lite instances
- Support Lite batch create, selection, and delete flows in the instance list
- Fix Lite OpenClaw/Hermes workspace initial paths and skill directory paths
- Hide transient skill temp directories from workspace browsing
- Preserve runtime query tokens when stripping ClawManager desktop access tokens
- Add an available-skills endpoint for instances with actor-aware filtering
- Persist gateway token, agent bootstrap token, and OpenClaw config snapshots for Lite instances
- Inject agent and OpenClaw bootstrap env into gateway runtimes
- Materialize and remove Lite instance skills in the workspace filesystem
- Improve instance detail skill upload, bulk attachment, workspace refresh, and layout syncing
- Support multi-select skill attachment and show risk-policy filtering hints
- Mark instance skills as removed after successful uninstall commands
- Sync skill removal state when related workspace files are deleted
- Hide removed skills and avoid reactivating them from agent inventory reports
- Clear proxy-scoped OpenClaw control storage to prevent cross-instance state leakage
- Reuse desktop direct upstream resolution and include upstream in short external access tokens
- Default and normalize Selkies stream settings for desktop runtimes
- Remove legacy deployments with the same instance-id before ensuring the current deployment
- Preserve the unsaved desktop stream profile state in the frontend
- Add tests for stream profiles, pod envs, and deployment cleanup
- Add leader election to avoid duplicate sync and Team event consumers
- Proxy desktop traffic directly from nginx to instance Services to reduce load during concurrent viewers
- Add desktop stream profiles with low / standard / high options
- Limit hostPath PV fallback to manual storageClass only
heranran