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
4.5 KiB
Modes and Approvals
DeepSeek TUI has two related concepts:
- TUI mode: what kind of visible interaction you're in (Plan/Agent/YOLO).
- Approval mode: how aggressively the UI asks before executing tools.
TUI Modes
Press Tab to complete composer menus, queue a draft as a next-turn follow-up
while a turn is running, or cycle through the visible modes when the composer is
otherwise idle: Plan → Agent → YOLO → Plan.
Press Shift+Tab to cycle reasoning effort.
Run /mode to open the mode picker, or switch directly with /mode agent,
/mode plan, /mode yolo, /mode 1, /mode 2, or /mode 3.
- Plan: design-first prompting. Read-only investigation tools stay available; shell and patch execution stay off. Use this when you want to think out loud and produce a plan to hand to a human (yourself later, or a reviewer).
- Agent: multi-step tool use. Approvals for shell and paid tools (file writes are allowed without a prompt).
- YOLO: enables shell + trust mode and auto-approves all tools. Use only in trusted repos.
All three modes have access to persistent RLM sessions through rlm_open, rlm_eval, rlm_configure, and rlm_close. Inside an RLM Python REPL, sub_query_batch fans out 1-16 cheap parallel child calls pinned to deepseek-v4-flash. The model reaches for it when work is too large or repetitive for the parent transcript.
Compatibility Notes
- Older settings files with
default_mode = "normal"still load asagent; saving rewrites the normalized value.
Escape Key Behavior
Esc is a cancel stack, not a mode switch.
- Close slash menus or transient UI first.
- Cancel the active request if a turn is running.
- Discard a queued draft if the composer is empty.
- Clear the current input if text is present.
- Otherwise it is a no-op.
Approval Mode
You can override approval behavior at runtime:
/config
# edit the approval_mode row to: suggest | auto | never
Legacy note: /set approval_mode ... was retired in favor of /config.
suggest(default): uses the per-mode rules above.auto: auto-approves all tools (similar to YOLO approval behavior, but without forcing YOLO mode).never: blocks any tool that isn't considered safe/read-only.
Small-Screen Status Behavior
When terminal height is constrained, the status area compacts first so header/chat/composer/footer remain visible:
- Loading and queued status rows are budgeted by available height.
- Queued previews collapse to compact summaries when full previews do not fit.
/queueworkflows remain available; compact status only affects rendering density.
Workspace Boundary and Trust Mode
By default, file tools are restricted to the --workspace directory. Enable trust mode to allow file access outside the workspace:
/trust
YOLO mode enables trust mode automatically.
MCP Behavior
MCP tools are exposed as mcp_<server>_<tool> and use the same approval flow as built-in tools. Read-only MCP helpers may auto-run in suggestive approval modes; MCP tools with possible side effects require approval.
See MCP.md.
Related CLI Flags
Run deepseek --help for the canonical list. Common flags:
-p, --prompt <TEXT>: one-shot prompt mode (prints and exits)--model <MODEL>: when using thedeepseekfacade, forward a DeepSeek model override to the TUI--workspace <DIR>: workspace root for file tools--yolo: start in YOLO mode-r, --resume <ID|PREFIX|latest>: resume a saved session-c, --continue: resume the most recent session in this workspace--max-subagents <N>: clamp to1..=20--mouse-capture/--no-mouse-capture: opt in or out of internal mouse scrolling, transcript selection, right-click context actions, and transcript scrollbar dragging. Mouse capture is enabled by default on non-Windows terminals so drag selection copies only transcript text and stays scoped to the transcript pane; hold Shift while dragging or use--no-mouse-capturefor raw terminal selection. It defaults off on Windows (CMD/terminal mouse-escape spam in the prompt) and inside JetBrains JediTerm — PyCharm/IDEA/CLion/etc. — where the terminal advertises mouse support but forwards SGR mouse events as raw text (#878, #898). Use--mouse-captureto opt in anywhere it's defaulted off. On Windows, raw terminal selection may cross the right sidebar because the terminal, not the TUI, owns the selection.--profile <NAME>: select config profile--config <PATH>: config file path-v, --verbose: verbose logging