From aebbe6b7951995474ec80107eda5fbc9ad3a052c Mon Sep 17 00:00:00 2001
From: Taylor Eernisse <teernisse@visiostack.com>
Date: Tue, 3 Feb 2026 09:35:22 -0500
Subject: [PATCH] feat(cli): Wire --full flag for embed, add sync stage
 spinners

- Add --full / --no-full flag pair to EmbedArgs with overrides_with
  semantics matching the existing flag pattern. When active, atomically
  DELETEs all embedding_metadata and embeddings before re-embedding.

- Thread the full flag through run_embed -> run_sync so that
  'lore sync --full' triggers a complete re-embed alongside the full
  re-ingest it already performed.

- Add indicatif spinners to sync stages with dynamic stage numbering
  that adjusts when --no-docs or --no-embed skip stages. Spinners are
  hidden in robot mode.

- Update robot-docs manifest to advertise the new --full flag on the
  embed command.

- Replace hardcoded schema version 9 in health check with the
  LATEST_SCHEMA_VERSION constant from db.rs.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---
 src/cli/commands/embed.rs | 15 +++++++--
 src/cli/commands/sync.rs  | 68 ++++++++++++++++++++++++++++++++-------
 src/cli/mod.rs            |  7 ++++
 src/main.rs               | 10 +++---
 4 files changed, 82 insertions(+), 18 deletions(-)

diff --git a/src/cli/commands/embed.rs b/src/cli/commands/embed.rs
index 7a99fe7..32ccfd5 100644
--- a/src/cli/commands/embed.rs
+++ b/src/cli/commands/embed.rs
@@ -21,6 +21,7 @@ pub struct EmbedCommandResult {
 /// Run the embed command.
 pub async fn run_embed(
     config: &Config,
+    full: bool,
     retry_failed: bool,
 ) -> Result<EmbedCommandResult> {
     let db_path = get_db_path(config.storage.db_path.as_deref());
@@ -37,8 +38,18 @@ pub async fn run_embed(
     // Health check — fail fast if Ollama is down or model missing
     client.health_check().await?;
 
-    // If retry_failed, clear errors so they become pending again
-    if retry_failed {
+    if full {
+        // Clear ALL embeddings and metadata atomically for a complete re-embed.
+        // Wrapped in a transaction so a crash between the two DELETEs can't
+        // leave orphaned data.
+        conn.execute_batch(
+            "BEGIN;
+             DELETE FROM embedding_metadata;
+             DELETE FROM embeddings;
+             COMMIT;",
+        )?;
+    } else if retry_failed {
+        // Clear errors so they become pending again
         conn.execute(
             "UPDATE embedding_metadata SET last_error = NULL, attempt_count = 0
              WHERE last_error IS NOT NULL",
diff --git a/src/cli/commands/sync.rs b/src/cli/commands/sync.rs
index ae8b737..bd0007c 100644
--- a/src/cli/commands/sync.rs
+++ b/src/cli/commands/sync.rs
@@ -1,6 +1,7 @@
 //! Sync command: unified orchestrator for ingest -> generate-docs -> embed.
 
 use console::style;
+use indicatif::{ProgressBar, ProgressStyle};
 use serde::Serialize;
 use tracing::{info, warn};
 
@@ -31,6 +32,22 @@ pub struct SyncResult {
     pub documents_embedded: usize,
 }
 
+/// Create a styled spinner for a sync stage.
+fn stage_spinner(stage: u8, total: u8, msg: &str, robot_mode: bool) -> ProgressBar {
+    if robot_mode {
+        return ProgressBar::hidden();
+    }
+    let pb = ProgressBar::new_spinner();
+    pb.set_style(
+        ProgressStyle::default_spinner()
+            .template("{spinner:.blue} {msg}")
+            .expect("valid template"),
+    );
+    pb.enable_steady_tick(std::time::Duration::from_millis(80));
+    pb.set_message(format!("[{stage}/{total}] {msg}"));
+    pb
+}
+
 /// Run the full sync pipeline: ingest -> generate-docs -> embed.
 pub async fn run_sync(config: &Config, options: SyncOptions) -> Result<SyncResult> {
     let mut result = SyncResult::default();
@@ -41,41 +58,70 @@ pub async fn run_sync(config: &Config, options: SyncOptions) -> Result<SyncResul
         IngestDisplay::progress_only()
     };
 
+    let total_stages: u8 = if options.no_docs && options.no_embed {
+        2
+    } else if options.no_docs || options.no_embed {
+        3
+    } else {
+        4
+    };
+    let mut current_stage: u8 = 0;
+
     // Stage 1: Ingest issues
-    info!("Sync stage 1/4: ingesting issues");
+    current_stage += 1;
+    let spinner = stage_spinner(current_stage, total_stages, "Fetching issues from GitLab...", options.robot_mode);
+    info!("Sync stage {current_stage}/{total_stages}: ingesting issues");
     let issues_result = run_ingest(config, "issues", None, options.force, options.full, ingest_display).await?;
     result.issues_updated = issues_result.issues_upserted;
     result.discussions_fetched += issues_result.discussions_fetched;
+    spinner.finish_and_clear();
 
     // Stage 2: Ingest MRs
-    info!("Sync stage 2/4: ingesting merge requests");
+    current_stage += 1;
+    let spinner = stage_spinner(current_stage, total_stages, "Fetching merge requests from GitLab...", options.robot_mode);
+    info!("Sync stage {current_stage}/{total_stages}: ingesting merge requests");
     let mrs_result = run_ingest(config, "mrs", None, options.force, options.full, ingest_display).await?;
     result.mrs_updated = mrs_result.mrs_upserted;
     result.discussions_fetched += mrs_result.discussions_fetched;
+    spinner.finish_and_clear();
 
     // Stage 3: Generate documents (unless --no-docs)
-    if options.no_docs {
-        info!("Sync stage 3/4: skipping document generation (--no-docs)");
-    } else {
-        info!("Sync stage 3/4: generating documents");
+    if !options.no_docs {
+        current_stage += 1;
+        let spinner = stage_spinner(current_stage, total_stages, "Processing documents...", options.robot_mode);
+        info!("Sync stage {current_stage}/{total_stages}: generating documents");
         let docs_result = run_generate_docs(config, false, None)?;
         result.documents_regenerated = docs_result.regenerated;
+        spinner.finish_and_clear();
+    } else {
+        info!("Sync: skipping document generation (--no-docs)");
     }
 
     // Stage 4: Embed documents (unless --no-embed)
-    if options.no_embed {
-        info!("Sync stage 4/4: skipping embedding (--no-embed)");
-    } else {
-        info!("Sync stage 4/4: embedding documents");
-        match run_embed(config, false).await {
+    if !options.no_embed {
+        current_stage += 1;
+        let spinner = stage_spinner(current_stage, total_stages, "Generating embeddings...", options.robot_mode);
+        info!("Sync stage {current_stage}/{total_stages}: embedding documents");
+        match run_embed(config, options.full, false).await {
             Ok(embed_result) => {
                 result.documents_embedded = embed_result.embedded;
+                spinner.finish_and_clear();
             }
             Err(e) => {
                 // Graceful degradation: Ollama down is a warning, not an error
+                spinner.finish_and_clear();
+                if !options.robot_mode {
+                    eprintln!(
+                        "  {} Embedding skipped ({})",
+                        style("warn").yellow(),
+                        e
+                    );
+                }
                 warn!(error = %e, "Embedding stage failed (Ollama may be unavailable), continuing");
             }
         }
+    } else {
+        info!("Sync: skipping embedding (--no-embed)");
     }
 
     info!(
diff --git a/src/cli/mod.rs b/src/cli/mod.rs
index 25f4190..0b162af 100644
--- a/src/cli/mod.rs
+++ b/src/cli/mod.rs
@@ -483,6 +483,13 @@ pub struct SyncArgs {
 /// Arguments for `lore embed`
 #[derive(Parser)]
 pub struct EmbedArgs {
+    /// Re-embed all documents (clears existing embeddings first)
+    #[arg(long, overrides_with = "no_full")]
+    pub full: bool,
+
+    #[arg(long = "no-full", hide = true, overrides_with = "full")]
+    pub no_full: bool,
+
     /// Retry previously failed embeddings
     #[arg(long, overrides_with = "no_retry_failed")]
     pub retry_failed: bool,
diff --git a/src/main.rs b/src/main.rs
index 0a1b34a..c6f090e 100644
--- a/src/main.rs
+++ b/src/main.rs
@@ -26,7 +26,7 @@ use lore::cli::{
     Cli, Commands, CountArgs, EmbedArgs, GenerateDocsArgs, IngestArgs, IssuesArgs, MrsArgs,
     SearchArgs, StatsArgs, SyncArgs,
 };
-use lore::core::db::{create_connection, get_schema_version, run_migrations};
+use lore::core::db::{create_connection, get_schema_version, run_migrations, LATEST_SCHEMA_VERSION};
 use lore::core::error::{LoreError, RobotErrorOutput};
 use lore::core::paths::get_config_path;
 use lore::core::paths::get_db_path;
@@ -1112,8 +1112,9 @@ async fn handle_embed(
     robot_mode: bool,
 ) -> Result<(), Box<dyn std::error::Error>> {
     let config = Config::load(config_override)?;
+    let full = args.full && !args.no_full;
     let retry_failed = args.retry_failed && !args.no_retry_failed;
-    let result = run_embed(&config, retry_failed).await?;
+    let result = run_embed(&config, full, retry_failed).await?;
     if robot_mode {
         print_embed_json(&result);
     } else {
@@ -1183,8 +1184,7 @@ async fn handle_health(
                     match create_connection(&db_path) {
                         Ok(conn) => {
                             let version = get_schema_version(&conn);
-                            let latest = 9; // Number of embedded migrations
-                            (true, version, version >= latest)
+                            (true, version, version >= LATEST_SCHEMA_VERSION)
                         }
                         Err(_) => (true, 0, false),
                     }
@@ -1340,7 +1340,7 @@ fn handle_robot_docs(robot_mode: bool) -> Result<(), Box<dyn std::error::Error>>
         },
         "embed": {
             "description": "Generate vector embeddings for documents via Ollama",
-            "flags": ["--retry-failed"],
+            "flags": ["--full", "--retry-failed"],
             "example": "lore --robot embed"
         },
         "migrate": {