feat: implement company pipeline orchestration with user commands for full, quick, and skip modes

2026-07-13 05:33:04 +07:00
parent a6eed9e574
commit 2310c2df7f
9 changed files with 269 additions and 94 deletions
@@ -77,6 +77,18 @@ Controller (key input → Action) → Event Loop → LLM stream → Tool executi
 - **Tools** — `trait Tool { fn name() -> &str, fn run() -> Result<String> }`, 28 impls, gated by `Harness`.
 - **Shell safety** — `tool/shell_filter/` blocks credential leaks and destructive git commands.

+### Company Pipeline (Division Architecture)
+
+- **5 divisions** in `src/app/subagent/division.rs`: Strategy, Engineering, Quality, Security, Documentation.
+- **Pipeline orchestrator** in `src/app/workflow/company.rs`: two modes:
+  - `run_company_pipeline()` — full 5-division pipeline
+  - `run_company_pipeline_quick()` — 3-division (Strategy → Engineering → Quality)
+- **Auto-CEO trigger** in `run_agent_turn()` (`actions/mod.rs`): detects complex requests via `is_complex_request()` heuristics, auto-delegates to pipeline.
+- **Override** via `/pipeline full|quick|skip` sets `MiscState::pipeline_override`, consumed on next turn.
+- **Live division progress** in TUI panel (`view/workflow.rs`): shows division name + current tool via `AgentStatus::progress`.
+- **Auto inline review** after each edit: `src/app/subagent/auto.rs` — `spawn_quick_review()` injects verdict back into LLM conversation.
+- **Background subagents** (test-gen, arch-review, security-review) fire asynchronously at turn end via `TurnEvent::SystemNote`.
+
 ## Code Documentation

 Every function, struct, enum, trait, module, and significant code block must have a doc comment (`///` or `//!`) that explains:
@@ -15,7 +15,7 @@ Zesdex is a Rust-powered AI assistant that operates directly in your terminal vi
 - **IPC Protocol** — Bidirectional state synchronization between daemon and client processes with diff-based updates.
 - **Provider Agnostic** — Configurable AI model providers with dynamic model selection, per-role temperature/token limits, and API key management.

-### Tool System (33 built-in tools)
+### Tool System (34 built-in tools)

 | Category | Tools |
 |----------|-------|
@@ -25,15 +25,23 @@ Zesdex is a Rust-powered AI assistant that operates directly in your terminal vi
 | **Git** | `git_operator`, `git_worktree`, `git_cred` |
 | **Memory** | `remember`, `recall`, `forget` |
 | **Planning** | `plan_enter`, `plan_ready`, `seqthink` |
-| **Workflow** | `workflow_run`, `note_finding` |
+| **Workflow** | `workflow_run`, `note_finding`, `company_pipeline` |
 | **Utility** | `cd`, `dir_list`, `dir_cache_update`, `pong`, `todowrite`, `todofinish` |
 | **LSP** | `lsp_connect`, `lsp_diagnostics`, `lsp_hover`, `lsp_completion`, `lsp_definition`, `lsp_references`, `lsp_disconnect` |

 ### Intelligence

+- **Company Pipeline** — Autonomous agent orchestration modeled as a company with specialized divisions. The CEO (main agent) automatically delegates work to 5 divisions in sequence:
+
+  ```
+  Strategy → Engineering → Quality → Security → Documentation
+  ```
+
+  Each division has a dedicated role, toolset, and system prompt. Controlled via `/pipeline full|quick|skip`.
+
 - **Workflow Engine** — Orchestrate complex multi-step tasks with parallel sub-agents, pipelines, and phased execution. Spawn independent workers that share findings in real-time.
 - **Self-Learning** — Persistent memory system that stores lessons, references, and project knowledge across sessions. Memories include provenance tracking, lifecycle management, and scope isolation.
- **Self-Review** — Adaptive quality review system that evaluates completed work against stored lessons and project conventions.
+- **Self-Review** — Review subagents trigger automatically after each code edit (inline) and at turn completion (background). Three types: code quality, architecture, and security.
 - **Self-Healing** — On build/test failures, spawns a sub-agent with the error context to autonomously fix issues before reporting them to the user.
 - **MCP Support** — [Model Context Protocol](https://modelcontextprotocol.io/) integration for connecting to external AI tool servers.
 - **Sequential Thinking** — Chain-of-thought reasoning tool for step-by-step problem decomposition.
@@ -85,7 +93,8 @@ src/
 │   ├── harness.rs             # Tool harness for agent execution
 │   ├── workflow/              # Workflow engine
 │   │   ├── script.rs          # Workflow script DSL
-│   │   └── engine.rs          # Workflow executor
+│   │   ├── engine.rs          # Workflow executor
+│   │   └── company.rs         # Company pipeline orchestrator
 │   ├── mcp/                   # MCP client manager
 │   │   └── manager.rs         # MCP server lifecycle and tool exposure
 │   ├── subagent/              # Sub-agent management
@@ -145,7 +154,7 @@ src/
 │       ├── manager.rs         # OAuth token manager
 │       ├── pkce.rs            # PKCE code challenge/verifier
 │       └── mod.rs
-├── tool/                      # 33 tool implementations
+├── tool/                      # 34 tool implementations
 │   ├── fs/                    # read, write, edit, delete
 │   │   ├── read.rs
 │   │   ├── write.rs
@@ -228,6 +237,10 @@ RUST_LOG=debug zesdex
 | `/help` | Show help |
 | `/clear` | Clear transcript |
 | `/model` | Select AI model provider |
+| `/pipeline` | Show current pipeline mode |
+| `/pipeline full` | Force full company pipeline (5 divisions) on next request |
+| `/pipeline quick` | Force quick pipeline (3 divisions) on next request |
+| `/pipeline skip` | Skip pipeline — handle next request directly |
 | `/exit` | Exit application |
 | `/settings` | Open settings |
 | `Any text` | Sent to the AI assistant as a prompt |
@@ -81,6 +81,10 @@ pub enum Action {
    RunWorkflow {
        script: String,
    },
+    /// User-initiated pipeline via `/pipeline full|quick|skip`.
+    RunPipeline {
+        mode: String,
+    },
 }

 /// Apply an `Action` to the application state.
@@ -530,6 +534,9 @@ pub fn apply_action(state: &mut AppStateRest, action: Action) {
                }
            }
            if turn_finished {
+                // Consume pipeline override after each turn so it doesn't
+                // persist across multiple submissions.
+                state.misc.pipeline_override = None;
                maybe_trigger_review(state);
            }
            if turn_finished || state.dirty {
@@ -591,6 +598,30 @@ pub fn apply_action(state: &mut AppStateRest, action: Action) {
            state.push_toast(Toast::new(ToastKind::Info, format!("deleted lesson: {}", name)));
            state.dirty = true;
        }
+        Action::RunPipeline { mode } => {
+            match mode.as_str() {
+                "full" => {
+                    state.misc.pipeline_override = Some("full".to_string());
+                    state.push_toast(Toast::new(ToastKind::Info, "Pipeline mode: full (5 divisions) — next request will run Strategy→Engineering→Quality→Security→Documentation".to_string()));
+                }
+                "quick" => {
+                    state.misc.pipeline_override = Some("quick".to_string());
+                    state.push_toast(Toast::new(ToastKind::Info, "Pipeline mode: quick (3 divisions) — next request will run Strategy→Engineering→Quality".to_string()));
+                }
+                "skip" => {
+                    state.misc.pipeline_override = Some("skip".to_string());
+                    state.push_toast(Toast::new(ToastKind::Info, "Pipeline mode: skip — next request will NOT run the company pipeline".to_string()));
+                }
+                "status" => {
+                    let current = state.misc.pipeline_override.as_deref().unwrap_or("auto");
+                    state.push_toast(Toast::new(ToastKind::Info, format!("Pipeline mode: {} (use /pipeline full|quick|skip to change)", current)));
+                }
+                _ => {
+                    state.push_toast(Toast::new(ToastKind::Error, format!("Unknown pipeline mode: {} (use: full, quick, skip)", mode)));
+                }
+            }
+            state.dirty = true;
+        }
        Action::RunWorkflow { script } => {
            // Open the Workflow overlay so the user can see progress.
            state.misc.overlay = Overlay::Workflow;
@@ -748,6 +779,7 @@ fn spawn_turn(state: &AppStateRest) {
    }) = true;

    let events_q = turn_events.clone();
+    let pipeline_mode = state.misc.pipeline_override.clone();

    std::thread::spawn(move || {
        let db = crate::model::msglog::open_or_create(&edit_session_dir)
@@ -767,6 +799,7 @@ fn spawn_turn(state: &AppStateRest) {
            temperature,
            max_tokens,
            abort_flag,
+            pipeline_mode,
        };
        let result = run_agent_turn(tc, &messages, &events_q);
        if let Err(e) = result {
@@ -795,6 +828,9 @@ struct TurnCtx {
    temperature: f32,
    max_tokens: Option<u32>,
    abort_flag: std::sync::Arc<std::sync::atomic::AtomicBool>,
+    /// Pipeline override: None=auto, Some("full"), Some("quick"), Some("skip").
+    /// Set by the `/pipeline` slash command. Consumed once per turn.
+    pipeline_mode: Option<String>,
 }

 /// Build an ASCII tree of the workspace directory structure for the
@@ -993,17 +1029,16 @@ fn run_agent_turn(
    }

    // ── AUTO CEO PIPELINE ──
-    // Before the main agent starts working, check if the request is complex
-    // enough to warrant the full company pipeline. If so, delegate to the
-    // divisions (Strategy → Engineering → Quality → Security → Documentation)
-    // and inject the results before the main agent even starts.
+    // Before the main agent starts working, check if the pipeline should run.
+    // The pipeline mode is determined by:
+    //   1. User override: `/pipeline full|quick|skip` (consumed once)
+    //   2. Auto-detect: `is_complex_request()` heuristics
    //
-    // This only triggers on the first turn of a session (few user messages)
-    // to avoid re-planning mid-conversation.
+    // This only triggers on the first turn of a session to avoid re-planning.
    let user_msg_count = msgs.iter()
        .filter(|m| matches!(m.role, crate::dto::chat::message::Role::User))
        .count();
-    if user_msg_count <= 2 {
+    let should_pipeline = if user_msg_count <= 2 {
        let user_request = msgs.iter()
            .rev()
            .filter(|m| matches!(m.role, crate::dto::chat::message::Role::User))
@@ -1011,61 +1046,96 @@ fn run_agent_turn(
            .and_then(|m| m.content.as_deref())
            .unwrap_or("");

-        if !user_request.is_empty()
-            && crate::app::workflow::company::is_complex_request(user_request)
-        {
-            tracing::info!(
-                "[ceo] complex request detected — delegating to company pipeline"
-            );
-
-            // Notify TUI that pipeline is starting
-            if let Ok(mut q) = events_q.lock() {
-                q.push_back(TurnEvent::SystemNote {
-                    kind: "pipeline".to_string(),
-                    message: "Company pipeline started: Strategy → Engineering → Quality → Security → Documentation".to_string(),
-                });
+        if !user_request.is_empty() {
+            match tc.pipeline_mode.as_deref() {
+                Some("skip") => {
+                    tracing::debug!("[ceo] pipeline skipped via /pipeline skip");
+                    false
+                }
+                Some("full") => true,
+                Some("quick") => true,
+                _ => crate::app::workflow::company::is_complex_request(user_request),
            }
+        } else {
+            false
+        }
+    } else {
+        false
+    };

-            // Run the full company pipeline (blocks this thread — OK since
-            // run_agent_turn already runs on a dedicated thread).
-            match crate::app::workflow::company::run_company_pipeline(
+    if should_pipeline {
+        let user_request = msgs.iter()
+            .rev()
+            .filter(|m| matches!(m.role, crate::dto::chat::message::Role::User))
+            .next()
+            .and_then(|m| m.content.as_deref())
+            .unwrap_or("");
+
+        let use_full = tc.pipeline_mode.as_deref() != Some("quick");
+        let mode_label = if use_full { "full" } else { "quick" };
+        tracing::info!(
+            "[ceo] pipeline triggered (mode={}) — delegating to company pipeline",
+            mode_label
+        );
+
+        if let Ok(mut q) = events_q.lock() {
+            q.push_back(TurnEvent::SystemNote {
+                kind: "pipeline".to_string(),
+                message: format!(
+                    "Company pipeline started ({}): {} → Engineering → Quality{}",
+                    mode_label,
+                    "Strategy",
+                    if use_full { " → Security → Documentation" } else { "" },
+                ),
+            });
+        }
+
+        let pipeline_result = if use_full {
+            crate::app::workflow::company::run_company_pipeline(
                user_request,
                &tc.edit_log_session_dir,
                &tc.workspace_roots,
                Some(events_q),
-            ) {
-                Ok(summary) => {
-                    tracing::info!("[ceo] company pipeline completed successfully");
-                    let pipeline_msg = ChatMessage::system(format!(
-                        "=== Company Pipeline — Executive Summary ===\n\
-                         The divisions have completed their work.\n\
-                         Review the results below as CEO, then deliver to the user.\n\n\
-                         {}",
-                        summary,
-                    ));
-                    archive_message(&tc.db, &tc.session_id, &pipeline_msg);
-                    msgs.push(pipeline_msg);
+            )
+        } else {
+            crate::app::workflow::company::run_company_pipeline_quick(
+                user_request,
+                &tc.edit_log_session_dir,
+                &tc.workspace_roots,
+                Some(events_q),
+            )
+        };

-                    if let Ok(mut q) = events_q.lock() {
-                        q.push_back(TurnEvent::SystemNote {
-                            kind: "pipeline".to_string(),
-                            message: "Company pipeline complete. CEO reviewing results...".to_string(),
-                        });
-                    }
-                }
-                Err(e) => {
-                    tracing::warn!("[ceo] company pipeline failed: {}", e);
-                    let fail_msg = ChatMessage::system(format!(
-                        "[Pipeline Note] The company pipeline encountered issues: {}.\n\
-                         Proceeding with direct execution as fallback.",
-                        e,
-                    ));
-                    msgs.push(fail_msg);
+        match pipeline_result {
+            Ok(summary) => {
+                tracing::info!("[ceo] company pipeline completed successfully");
+                let pipeline_msg = ChatMessage::system(format!(
+                    "[Company Pipeline: {}]\n{}",
+                    mode_label,
+                    summary,
+                ));
+                archive_message(&tc.db, &tc.session_id, &pipeline_msg);
+                msgs.push(pipeline_msg);
+
+                if let Ok(mut q) = events_q.lock() {
+                    q.push_back(TurnEvent::SystemNote {
+                        kind: "pipeline".to_string(),
+                        message: format!("Company pipeline ({}) complete. CEO reviewing results...", mode_label),
+                    });
                }
            }
-        } else {
-            tracing::debug!("[ceo] request not complex — handling directly");
+            Err(e) => {
+                tracing::warn!("[ceo] company pipeline failed: {}", e);
+                let fail_msg = ChatMessage::system(format!(
+                    "[Pipeline Note] The company pipeline encountered issues: {}.\n\
+                     Proceeding with direct execution as fallback.",
+                    e,
+                ));
+                msgs.push(fail_msg);
+            }
        }
+    } else {
+        tracing::debug!("[ceo] pipeline not triggered — handling directly");
    }

    let mut turn_step = 0usize;
@@ -69,6 +69,9 @@ pub fn apply_command(command: Command) -> Vec<Action> {
        Command::WorkflowRun { script } => {
            vec![Action::RunWorkflow { script }]
        }
+        Command::Pipeline { mode } => {
+            vec![Action::RunPipeline { mode }]
+        }
        Command::Unknown(cmd) => {
            vec![Action::SystemNote {
                kind: "error".to_string(),
@@ -90,6 +90,10 @@ const COMMANDS: &[&str] = &[
    "/model add",
    "/workflow",
    "/workflow run",
+    "/pipeline",
+    "/pipeline full",
+    "/pipeline quick",
+    "/pipeline skip",
    "/compact",
 ];

@@ -289,6 +293,13 @@ pub struct MiscState {
    pub api_context_length: Option<u32>,
    pub tick_count: u64,
    pub todo_content: String,
+    /// Pipeline mode override set by `/pipeline` command.
+    /// - `None`: auto-detect (default)
+    /// - `Some("full")`: force full pipeline
+    /// - `Some("quick")`: force quick pipeline
+    /// - `Some("skip")`: skip pipeline, handle directly
+    /// Consumed on the next agent turn.
+    pub pipeline_override: Option<String>,
 }

 impl MiscState {
@@ -307,6 +318,7 @@ impl MiscState {
            api_context_length: None,
            tick_count: 0,
            todo_content: String::new(),
+            pipeline_override: None,
        }
    }

@@ -185,7 +185,11 @@ pub fn run_company_pipeline_quick(
    Ok(build_executive_summary(user_request, &results, &all_findings, quick_divisions))
 }

-/// Build a consolidated executive summary from pipeline results.
+/// Build a compressed executive summary from pipeline results.
+///
+/// Keeps output brief to save context window space — just division verdicts
+/// and key findings, not full outputs. Full results are accessible to the
+/// CEO via the notes/findings that were archived during execution.
 fn build_executive_summary(
    request: &str,
    results: &[String],
@@ -193,41 +197,23 @@ fn build_executive_summary(
    divisions: &[division::Division],
 ) -> String {
    let mut summary = String::new();
-    summary.push_str(&format!("# Company Pipeline — Executive Summary\n\n"));
-    summary.push_str(&format!("**Request**: {}\n\n", request));
-    summary.push_str("## Division Results\n\n");
+    summary.push_str(&format!("Pipeline for: {}\n", request));

    for (i, div) in divisions.iter().enumerate() {
-        let result_summary = results.get(i)
+        let verdict = results.get(i)
            .map(|r| {
-                let first_line = r.lines().next().unwrap_or(r);
-                if first_line.len() > 120 {
-                    format!("{}...", &first_line[..117])
-                } else {
-                    first_line.to_string()
-                }
+                r.lines().next().unwrap_or(r)
+                    .chars().take(100).collect::<String>()
            })
-            .unwrap_or_else(|| "No output".to_string());
+            .unwrap_or_else(|| "—".to_string());

-        summary.push_str(&format!("### {} Division\n", div.name));
-        summary.push_str(&format!("- Role: {}\n", div.description));
-        summary.push_str(&format!("- Result: {}\n\n", result_summary));
+        summary.push_str(&format!("  {}: {}\n", div.name, verdict));
    }

    if !findings.is_empty() {
-        summary.push_str("## Cross-Division Findings\n\n");
-        for (i, f) in findings.iter().enumerate() {
-            summary.push_str(&format!("{}. {}\n", i + 1, f));
-        }
-        summary.push_str("\n");
+        summary.push_str(&format!("  Notes: {} cross-division finding(s)\n", findings.len()));
    }

-    summary.push_str("---\n");
-    summary.push_str(&format!(
-        "Pipeline completed: {} division(s) executed.\n",
-        divisions.len(),
-    ));
-
    summary
 }

@@ -239,14 +225,43 @@ fn build_executive_summary(
 ///
 /// Used by the auto-CEO pipeline trigger in run_agent_turn to decide
 /// whether to delegate to the full company pipeline or handle directly.
+///
+/// Heuristics:
+/// - Very short requests (< 10 chars) are never complex.
+/// - Negative keywords (simple/trivial/typo/quick) skip the pipeline.
+/// - Positive keywords (refactor/api/implement/architecture) trigger it.
+/// - Multi-line or multi-sentence requests are more likely complex.
 pub fn is_complex_request(request: &str) -> bool {
+    let trimmed = request.trim();
+    // Very short requests are never complex
+    if trimmed.len() < 10 {
+        return false;
+    }
+    // Single-line simple update patterns
+    let lower = trimmed.to_lowercase();
+    let negative_keywords = [
+        "simple", "trivial", "typo", "just a", "only a", "minor",
+        "quick", "tiny", "small fix", "rename", "nitpick",
+        "cosmetic", "formatting", "spelling", "grammar",
+        "bump", "version bump", "update comment",
+    ];
+    if negative_keywords.iter().any(|k| lower.contains(k)) {
+        return false;
+    }
+    // Multi-line/multi-sentence → likely complex
+    let sentences = trimmed.split(|c| c == '.' || c == '!' || c == '?')
+        .filter(|s| !s.trim().is_empty())
+        .count();
+    if sentences >= 3 {
+        return true;
+    }
+    // Positive complexity keywords
    let complexity_keywords = [
        "refactor", "redesign", "architecture", "feature", "implement",
        "migrate", "restructure", "rewrite", "new module", "new component",
        "scaffold", "multi", "multiple files", "api", "endpoint",
        "integration", "system", "workflow", "pipeline", "database",
-        "authentication", "authorization",
+        "authentication", "authorization", "full stack",
    ];
-    let lower = request.to_lowercase();
    complexity_keywords.iter().any(|k| lower.contains(k))
 }
@@ -36,6 +36,9 @@ pub struct AgentStatus {
    pub started_at: Option<i64>,
    pub completed_at: Option<i64>,
    pub error: Option<String>,
+    /// Human-readable progress message (e.g. "editing src/main.rs",
+    /// "running cargo test"). Shown in the TUI panel alongside the state.
+    pub progress: Option<String>,
 }

 /// A single agent tracked within a workflow run.
@@ -124,6 +127,7 @@ fn spawn_single_agent(
                started_at: Some(started_at),
                completed_at: None,
                error: None,
+                progress: None,
            },
        );
    }
@@ -156,26 +160,52 @@ fn spawn_single_agent(
    // long-running agents. No abort mechanism is wired yet at this level;
    // future work can expose a kill-switch per agent via the live callback.

-    // Create an mpsc channel and drain events in a background thread so
-    // run_subagent's blocking_send never blocks (previously the _rx was
-    // dropped immediately, which would cause blocking_send to panic/fail
-    // on a closed channel).
+    // Create an mpsc channel and drain events in a background thread.
+    // The drain thread also pushes intra-division progress updates to the
+    // live callback (current tool being executed), so the TUI panel shows
+    // real-time "editing X" or "running build" instead of just "Running…".
    let (tx, rx) = tokio::sync::mpsc::channel(64);
+    let drain_agent_id = agent_id.to_string();
+    let drain_agent_name = agent_name.to_string();
+    let drain_live = live.cloned();
+    let drain_started_at = started_at;
    let _drain_thread = std::thread::spawn(move || {
-        // Drain all events so run_subagent's blocking_send never blocks.
-        // Individual SubagentEvent items are not surfaced to the TUI —
-        // the live state callbacks above handle coarse-grained Running /
-        // Completed / Failed status. ToolCall / ToolResult / StepCompleted
-        // events are traced at debug level for observability.
        use crate::app::subagent::event::SubagentEvent;
        let mut rx = rx;
        while let Some(event) = rx.blocking_recv() {
            match &event {
                SubagentEvent::ToolCall { _tool, _args } => {
                    tracing::debug!("[subagent] tool call: {}", _tool);
+                    // Push intra-division progress: which tool is running
+                    if let Some(ref f) = drain_live {
+                        f(
+                            drain_agent_id.clone(),
+                            drain_agent_name.clone(),
+                            AgentStatus {
+                                state: AgentState::Running,
+                                started_at: Some(drain_started_at),
+                                completed_at: None,
+                                error: None,
+                                progress: Some(format!("tool: {}", _tool)),
+                            },
+                        );
+                    }
                }
                SubagentEvent::ToolResult { _tool, .. } => {
                    tracing::debug!("[subagent] tool result: {}", _tool);
+                    if let Some(ref f) = drain_live {
+                        f(
+                            drain_agent_id.clone(),
+                            drain_agent_name.clone(),
+                            AgentStatus {
+                                state: AgentState::Running,
+                                started_at: Some(drain_started_at),
+                                completed_at: None,
+                                error: None,
+                                progress: Some(format!("done: {}", _tool)),
+                            },
+                        );
+                    }
                }
                SubagentEvent::StepCompleted { _step, .. } => {
                    tracing::trace!("[subagent] step {} completed", _step);
@@ -226,6 +256,7 @@ fn spawn_single_agent(
                    started_at: Some(started_at),
                    completed_at: Some(completed_at),
                    error: None,
+                    progress: None,
                },
            ),
            Err(e) => f(
@@ -236,6 +267,7 @@ fn spawn_single_agent(
                    started_at: Some(started_at),
                    completed_at: Some(completed_at),
                    error: Some(e.to_string()),
+                    progress: None,
                },
            ),
        }
@@ -22,6 +22,10 @@ pub enum Command {
    WorkflowRun {
        script: String,
    },
+    /// /pipeline full|quick|skip
+    Pipeline {
+        mode: String,
+    },
    Unknown(String),
 }

@@ -75,6 +79,15 @@ pub fn parse_command(text: &str) -> Command {
        "/workflow" => Command::WorkflowRun {
            script: arg1.to_string(),
        },
+        "/pipeline" if arg1.is_empty() => Command::Pipeline {
+            mode: "status".to_string(),
+        },
+        "/pipeline" if arg1 == "full" || arg1 == "quick" || arg1 == "skip" => {
+            Command::Pipeline {
+                mode: arg1.to_string(),
+            }
+        }
+        "/pipeline" => Command::Unknown(format!("/pipeline {} (use: full|quick|skip)", arg1)),
        _ => Command::Unknown(cmd.to_string()),
    }
 }
@@ -162,6 +162,11 @@ pub fn draw_workflow_panel(frame: &mut Frame, area: Rect, state: &crate::app::st
                ),
                if let Some(ref err) = agent.status.error {
                    Span::styled(format!(" — {}", err), Style::default().fg(Theme::ERROR))
+                } else if let Some(ref prog) = agent.status.progress {
+                    Span::styled(
+                        format!("  ({})", prog),
+                        Style::default().fg(Theme::DIM),
+                    )
                } else {
                    Span::raw("")
                },