master

hypothesiserfeat: enhance external command handling in TUI and add tests

2c25d0e5创建于 10 天前历史提交

文件	最后提交记录	最后更新时间
channels	feat(feishu): add websocket transport support	1 个月前
cli	feat: implement per-command process groups with registry for reliable cleanup Co-Authored-By: GLM-5	11 天前
gateway	!203 fix(tui): fix context loss by saving state on LLM provider errors From: @xujing99 Reviewed-by: @hypothesiser See merge request: openeuler/xiaoO!203	10 天前
httpserver	fix(tui): input auto-wrap, Alt+Enter newline, and intelligent arrow key navigation By the way, apply cargo fmt for code style consistency. Co-Authored-By: GLM-5	14 天前
prompts	optimize: optimize skill prompt Co-Authored-By: GLM-5	10 天前
tui	feat: enhance external command handling in TUI and add tests - Refactored external command processing to improve clarity and functionality. - Introduced new functions for expanding commands and handling user arguments. - Added unit tests to ensure correct behavior of external command expansion. - Updated Cargo.lock to include new dependencies: libc and tracing.	10 天前
builtin_agent_roles.rs	feat: add built-in planning agent role and integrate into daemon configuration - Introduced a new PLAN_AGENT_ID for a read-only planning agent, including its description and prompt. - Updated DaemonConfig to install the built-in planning agent role, ensuring it cannot be overridden in user configurations. - Enhanced agent role configuration to include a max_turns field, allowing for better control over agent interactions. - Integrated the planning agent role into various components, including session management and runtime configurations. - Added tests to verify the correct installation and behavior of the planning agent role within the application.	1 个月前
daemon_config.rs	optimize: add proactive token estimation and config validation with URL optimization Co-Authored-By: GLM-5	17 天前
daemon_runtime.rs	fix(subagent): apply slim read-only profile only to default subagents The slim exploration profile (read-only tool allowlist, slim system prompt, no skills) was keyed on is_subagent (agent_id != main), so it also clobbered custom-role subagents — which carry their own prompt and tool list and must keep them. Thread subagent_role_id from spawn (SessionAgentRecord) through runtime_input_from_session into SessionRuntimeBuildInput, and gate the profile on is_default_subagent = is_subagent && role_id.is_none(). Custom-role subagents now fall back to the composed prompt + full toolset + skills (no repo map / delegation rules, which stay main-agent-only). build_tool_registry takes an explicit apply_readonly_profile flag instead of recomputing is_subagent. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	12 天前
lib.rs	feat: add LLM secrets management functionality - Introduced a new module llm_secrets for managing LLM secrets, including functions to save secrets and inject them into the environment. - Updated the CLI configuration to resolve and load secrets from the specified path, enhancing security and flexibility. - Refactored existing code to utilize the new LLM secrets management functions, ensuring a cohesive integration across the application. - Added tests to verify the correct functionality of saving and injecting LLM secrets.	1 个月前
llm_secrets.rs	optimize: add proactive token estimation and config validation with URL optimization Co-Authored-By: GLM-5	17 天前
lsp_support.rs	cargo fmt	1 个月前
main.rs	feat: implement per-command process groups with registry for reliable cleanup Co-Authored-By: GLM-5	11 天前
secrets.rs	refactor(vault): improve HSM and TEE key provider implementations - Updated HSM key provider to use private fields for library path, slot ID, and key label. - Refactored TeeType to use a more descriptive method name for string conversion. - Enhanced error messages for unavailable providers in both HSM and TEE implementations. - Simplified key initialization logic in SDF key provider using OnceLock for thread safety. - Cleaned up comments and formatting for better readability across the vault module.	24 天前