- Release date: 2026-03-12
- Scope: first-class Docker deployment support, stale working-agent recovery, official direct-API preset onboarding, Kimi Code provider support, and development-default API assignment across hydrated office packs.
- Added a production-oriented
Dockerfile,.dockerignore, anddocker-compose.yml. - Container runtime now uses a non-root user and standardized writable data locations.
- Runtime path resolution was updated so database/log paths behave correctly inside Docker deployments.
- README deployment guidance was added across English, Korean, Japanese, and Chinese.
- Startup and lifecycle sweeps now detect agents that are still marked
workingeven though their current task is missing or no longerin_progress. - Those agents are reset back to
idlewithcurrent_task_id = NULL. - Result: server restarts and interrupted runs no longer leave misleading “still working” agents behind in the UI.
- Settings > API now includes official presets for:
OpenCode Go (OpenAI)OpenCode Go (Anthropic)Bailian Coding Plan (OpenAI)Bailian Coding Plan (Anthropic)
- Presets now:
- lock and manage the expected Base URL
- seed fallback model lists immediately
- keep refresh/retry explicit instead of silently retry-looping after failures
- show preset identity directly on provider cards
- Existing provider-card model search remains available, so large cached model lists are still easy to filter before assignment.
- Kimi Code is now supported through the CLI execution path alongside the existing local coding providers.
- The integration was completed across:
- provider selection and display labels
- task execution/provider validation
- prompt-skill rendering
- skill learn/unlearn provider routing
- video-preprod remotion bootstrap
- provider checks in existing database schema/runtime migration paths
- Result: Kimi is no longer just a partial label-level addition; it is wired through the execution and skills flow end to end.
- The assign flow now always loads the
developmentoffice as the default baseline. - If a user has already completed initial setup for other office packs and those packs have been hydrated into runtime state, their agents and departments also appear in the assignment modal.
- Pack sections are now grouped safely, so packs that reuse the same department IDs no longer collapse into each other inside the modal.
- Result: default development assignment remains predictable, while already-initialized office packs can also receive direct API model mappings from the same settings flow.
pnpm run test:e2enow resets the isolated.tmp/e2e-runtimedatabase both before and after the Playwright run.- Playwright no longer reuses an already-running local
8810server by default. Reuse is now opt-in viaPW_REUSE_EXISTING_SERVER=1. - CRUD-heavy E2E scenarios were hardened so local validation does not keep leaving stale departments, agents, and similar CI residue behind during normal development verification.
- Result: local E2E runs are more predictable, are less likely to touch the wrong runtime, and clean up their temporary state more aggressively.
- Includes
PR #56: Docker deployment support (Dockerfile, compose, runtime path handling, multilingual docs) - Includes
PR #60: stale/orphan working-agent recovery during lifecycle startup and interval sweeps - Includes intent-preserving integration of current open PR work:
PR #62: development-pack-scoped API assignment departmentsPR #63: Kimi Code provider support and migration/runtime completionPR #64: official API presets, preset refresh hardening, and provider-card UX updates- post-integration follow-up: API assign modal now includes hydrated office packs while keeping
developmentas the default baseline
.dockerignoreDockerfiledocker-compose.ymlREADME.mdREADME_ko.mdREADME_jp.mdREADME_zh.mddocs/releases/README.mddocs/releases/v2.0.4.mdserver/config/runtime.tsserver/db/runtime.tsserver/modules/bootstrap/schema/api-providers-schema.test.tsserver/modules/bootstrap/schema/base-schema.tsserver/modules/bootstrap/schema/oauth-runtime.test.tsserver/modules/bootstrap/schema/oauth-runtime.tsserver/modules/bootstrap/schema/task-schema-migrations.tsserver/modules/lifecycle.tsserver/modules/routes/ops/api-providers.test.tsserver/modules/routes/ops/api-providers.tsserver/modules/routes/ops/skills/learn-constants.tsserver/modules/routes/ops/skills/learn-core.tsserver/modules/routes/ops/skills/types.tsserver/modules/workflow/agents/providers/usage-cli-tools.tsserver/modules/workflow/core/cli-tools.tsserver/modules/workflow/core/prompt-skills.test.tsserver/modules/workflow/core/prompt-skills.tsserver/modules/workflow/core/video-skill-bootstrap.test.tsserver/modules/workflow/core/video-skill-bootstrap.tsserver/modules/workflow/packs/video-artifact.tssrc/api-provider-presets.test.tssrc/api/providers-reports-github.tssrc/api/workflow-skills-subtasks.tssrc/components/AgentDetail.tsxsrc/components/AgentStatusPanel.tsxsrc/components/agent-detail/constants.tssrc/components/agent-manager/constants.tssrc/components/settings/ApiSettingsTab.test.tsxsrc/components/settings/ApiSettingsTab.tsxsrc/components/settings/Logos.tsxsrc/components/settings/constants.tsxsrc/components/settings/types.tssrc/components/settings/useApiProvidersState.test.tsxsrc/components/settings/useApiProvidersState.tssrc/components/skill-history/utils.tssrc/components/skills-library/model.tsxsrc/types/index.ts
pnpm run test:cipnpm run buildpnpm run test:e2e
- A schema/runtime migration is included for existing provider checks so legacy databases can accept
kimiin the relevant provider columns. - Docker deployment is additive and optional; existing local non-Docker workflows remain supported.
- Official API presets are backward compatible with manual API provider configuration.