Hunter Bown
99c6b22e83
- Persistent RLM sessions (rlm_open/rlm_eval/rlm_close) with bounded REPL helpers - Fork-aware sub-agent sessions (agent_open/agent_eval/agent_close) with handle_read - Shared handle_read storage with slice/range/count/JSONPath projections - Slash-command routing: /rlm, /agent, /relay (/接力) for handoff prompts - Sidebar renamed to "Work" tab, consistent across Plan/Agent/YOLO modes - Tool papercuts: file_search excludes, grep_files strings, fetch_url JSON, edit_file fuzz, exec_shell merged stdout/stderr, revert_turn no-op reject - CLI reasoning-effort honoured on non-auto exec routes (#1511 @h3c-hexin) - Edit-file replacement boundaries clarified (#1516) - Pandoc output validated before probing (#1523) - Running turns steerable/repaintable (#1533, #1537) - Tasks/Activity Detail calmer under load - npm retry timeout hint (#1538 @reidliu41) - Issue templates improved (#1525 @reidliu41) - Shell: kill process group to prevent UI freeze (#828 @CrepuscularIRIS) - TUI: ignore leaked SGR mouse reports in composer (#1421 @reidliu41) - Footer: keep chips within available width (#1417 @Wenjunyun123) - Session picker: scope Ctrl+R to current workspace (#1395 @LinQ) - Removed stale competitive-analysis doc - Prompts/docs teach only new tool names
13 lines
365 B
TOML
13 lines
365 B
TOML
[package]
|
|
name = "deepseek-execpolicy"
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
license.workspace = true
|
|
repository.workspace = true
|
|
description = "Execution policy and approval model parity for DeepSeek workspace architecture"
|
|
|
|
[dependencies]
|
|
anyhow.workspace = true
|
|
deepseek-protocol = { path = "../protocol", version = "0.8.33" }
|
|
serde.workspace = true
|