* fix: resolve subagent persona lookup for 'default' and unify resolution logic
- Add PersonaManager.get_persona_v3_by_id() to centralize v3 persona resolution
- Handle 'default' persona_id mapping to DEFAULT_PERSONALITY in subagent orchestrator
- Fix HandoffTool.default_description using agent_name parameter correctly
- Add tests for default persona in subagent config and tool deduplication
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: simplify get_default_persona_v3 using get_persona_v3_by_id
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: whatevertogo <whatevertogo@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com>
- Rewrite TestApplySandboxToolsRefactored to test ComputerToolProvider
directly (_apply_sandbox_tools was removed; old tests permanently skipped)
- Add TestExecutorCapabilityGuard with 5 strict tests for browser
capability rejection at executor level
- Fix typo: "on hehalf you" -> "on behalf of you" in subagent result
- Remove extra blank lines (ruff E303) after _apply_sandbox_tools comment
- Remove dead _build_sync_and_scan_command (no callers after refactor)
Two changes to make the tool schema sent to the LLM deterministic:
1. ToolSet.normalize() — sort tools by name before serialization.
Called at the end of build_main_agent() after all injection passes.
Eliminates ordering drift from plugin load order, MCP reconnection,
and persona tool list differences.
2. Always inject full sandbox tool set — ComputerToolProvider now
returns get_default_sandbox_tools() unconditionally, regardless of
sandbox boot state. Browser tools are always in the schema even if
the sandbox profile lacks browser capability. The executor rejects
calls to unavailable browser tools with a descriptive error instead
of silently omitting them from the schema.
This eliminates the pre-boot/post-boot tool set jump that caused
prefix cache misses on the second request of a conversation.
- Add get_default_tools/get_tools/get_system_prompt_parts to ComputerBooter base
- Each booter subclass (ShipyardNeo, Shipyard, Boxlite) declares its own tools
- ComputerToolProvider now delegates to booter API via computer_client helpers
- Add unified query API: get_sandbox_tools, get_default_sandbox_tools, etc.
- Extract Neo prompts to dedicated computer/prompts.py module
- Add booter type constants (booters/constants.py)
- Fix subagent tool path to pass sandbox_cfg and session_id
- Fix Sourcery issues: shell injection in send_message, typo in prompts,
internal tools bypass inactivated_llm_tools check
Add explicit Neo lifecycle instructions to the main agent prompt so
skill creation and updates follow payload -> candidate -> promotion
instead of direct local folder writes.
Clarify lifecycle tool descriptions and parameter semantics, including
skill_key/source_execution_ids usage and stable release sync_to_local
behavior, to reduce ambiguity and improve consistent skill publishing.
append a Shipyard Neo-specific system prompt note for filesystem
tool calls so paths are provided relative to the workspace root.
this prevents models from prepending `/workspace` and causing tool
path resolution failures
_apply_sandbox_tools now checks the booted session's capabilities
before registering browser tools (BrowserExecTool, BrowserBatchExecTool,
RunBrowserSkillTool).
- If no session exists yet (first request), all tools are registered
conservatively to avoid breaking the initial interaction
- If a session exists without browser capability, browser tools are
omitted, preventing CapabilityNotSupportedError from Bay
- Skill lifecycle tools remain unconditionally registered
* feat: implement fallback provider support for chat models and update configuration
* feat: enhance provider selection display with count and chips for selected providers
* feat: update fallback chat providers to use provider settings and add warning for non-list fallback models
* feat: enhance persona tool management and update UI localization for subagent orchestration
* fix: remove debug logging for final ProviderRequest in build_main_agent function
* feat: add computer use runtime configuration and handling for skills execution
* fix: improve user notification for disabled Computer Use feature in skills execution
* fix: preserve MCP tools in _plugin_tool_fix filter
Tools without handler_module_path (such as MCP tools and built-in tools)
were being incorrectly skipped during plugin-based tool filtering.
This fix ensures that tools without plugin association are preserved,
as they should not be affected by plugin-level filtering logic.
* fix: retain MCP tools in _plugin_tool_fix function
---------
Co-authored-by: idiotsj <idiotsj@users.noreply.github.com>
Co-authored-by: Soulter <905617992@qq.com>
* fix: merge chatui pop-up prompt into chatui default persona and improve chatui persona handle
* fix: update webchat persona handling to avoid default assignment for None
- Updated FunctionToolExecutor to improve background task handling and integrate new system prompts for proactive agents.
- Enhanced MainAgentBuildConfig with additional configuration options for tool management and context handling.
- Introduced new system prompts for proactive agents triggered by cron jobs and background tasks to improve user interaction.
- Refactored cron job management to utilize ProviderRequest for better context management and tool integration.
- Renamed cron job tools for clarity, changing "create_cron_job" to "create_future_task" and similar adjustments for consistency.
- Improved error handling and logging for cron job execution and agent responses.
- Added support for image captioning and persona management in agent requests.
