Files
gitlore/src/cli/mod.rs
Taylor Eernisse daf5a73019 feat(cli): Add search, stats, embed, sync, health, and robot-docs commands
Extends the CLI with six new commands that complete the search pipeline:

- lore search <QUERY>: Hybrid search with mode selection (lexical,
  hybrid, semantic), rich filtering (--type, --author, --project,
  --label, --path, --after, --updated-after), result limits, and
  optional explain mode showing RRF score breakdowns. Safe FTS mode
  sanitizes user input; raw mode passes through for power users.

- lore stats: Document and index statistics with optional --check
  for integrity verification and --repair to fix inconsistencies
  (orphaned documents, missing FTS entries, stale dirty queue items).

- lore embed: Generate vector embeddings via Ollama. Supports
  --retry-failed to re-attempt previously failed embeddings.

- lore generate-docs: Drain the dirty queue to regenerate documents.
  --full seeds all entities for complete rebuild. --project scopes
  to a single project.

- lore sync: Full pipeline orchestration (ingest issues + MRs,
  generate-docs, embed) with --no-embed and --no-docs flags for
  partial runs. Reports per-stage results and total elapsed time.

- lore health: Quick pre-flight check (config exists, DB exists,
  schema current). Returns exit code 1 if unhealthy. Designed for
  agent pre-flight scripts.

- lore robot-docs: Machine-readable command manifest for agent
  self-discovery. Returns all commands, flags, examples, exit codes,
  and recommended workflows as structured JSON.

Also enhances lore init with --gitlab-url, --token-env-var, and
--projects flags for fully non-interactive robot-mode initialization.
Fixes init's force/non-interactive precedence logic and adds JSON
output for robot mode.

Updates all command files for the GiError -> LoreError rename.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-30 15:47:10 -05:00

451 lines
11 KiB
Rust

//! CLI module with clap command definitions.
pub mod commands;
use clap::{Parser, Subcommand};
use std::io::IsTerminal;
/// Gitlore - Local GitLab data management with semantic search
#[derive(Parser)]
#[command(name = "lore")]
#[command(version, about, long_about = None)]
pub struct Cli {
/// Path to config file
#[arg(short = 'c', long, global = true)]
pub config: Option<String>,
/// Machine-readable JSON output (auto-enabled when piped)
#[arg(long, global = true, env = "LORE_ROBOT")]
pub robot: bool,
/// JSON output (global shorthand)
#[arg(short = 'J', long = "json", global = true)]
pub json: bool,
#[command(subcommand)]
pub command: Commands,
}
impl Cli {
/// Check if robot mode is active (explicit flag, env var, or non-TTY stdout)
pub fn is_robot_mode(&self) -> bool {
self.robot || self.json || !std::io::stdout().is_terminal()
}
}
#[derive(Subcommand)]
#[allow(clippy::large_enum_variant)]
pub enum Commands {
/// List or show issues
Issues(IssuesArgs),
/// List or show merge requests
Mrs(MrsArgs),
/// Ingest data from GitLab
Ingest(IngestArgs),
/// Count entities in local database
Count(CountArgs),
/// Show sync state
Status,
/// Verify GitLab authentication
Auth,
/// Check environment health
Doctor,
/// Show version information
Version,
/// Initialize configuration and database
Init {
/// Skip overwrite confirmation
#[arg(short = 'f', long)]
force: bool,
/// Fail if prompts would be shown
#[arg(long)]
non_interactive: bool,
/// GitLab base URL (required in robot mode)
#[arg(long)]
gitlab_url: Option<String>,
/// Environment variable name holding GitLab token (required in robot mode)
#[arg(long)]
token_env_var: Option<String>,
/// Comma-separated project paths (required in robot mode)
#[arg(long)]
projects: Option<String>,
},
/// Create timestamped database backup
Backup,
/// Delete database and reset all state
Reset {
/// Skip confirmation prompt
#[arg(short = 'y', long)]
yes: bool,
},
/// Search indexed documents
Search(SearchArgs),
/// Show document and index statistics
Stats(StatsArgs),
/// Generate searchable documents from ingested data
#[command(name = "generate-docs")]
GenerateDocs(GenerateDocsArgs),
/// Generate vector embeddings for documents via Ollama
Embed(EmbedArgs),
/// Run full sync pipeline: ingest -> generate-docs -> embed
Sync(SyncArgs),
/// Run pending database migrations
Migrate,
/// Quick health check: config, database, schema version
Health,
/// Machine-readable command manifest for agent self-discovery
#[command(name = "robot-docs")]
RobotDocs,
// --- Hidden backward-compat aliases ---
/// List issues or MRs (deprecated: use 'lore issues' or 'lore mrs')
#[command(hide = true)]
List {
/// Entity type to list
#[arg(value_parser = ["issues", "mrs"])]
entity: String,
#[arg(long, default_value = "50")]
limit: usize,
#[arg(long)]
project: Option<String>,
#[arg(long)]
state: Option<String>,
#[arg(long)]
author: Option<String>,
#[arg(long)]
assignee: Option<String>,
#[arg(long)]
label: Option<Vec<String>>,
#[arg(long)]
milestone: Option<String>,
#[arg(long)]
since: Option<String>,
#[arg(long)]
due_before: Option<String>,
#[arg(long)]
has_due_date: bool,
#[arg(long, value_parser = ["updated", "created", "iid"], default_value = "updated")]
sort: String,
#[arg(long, value_parser = ["desc", "asc"], default_value = "desc")]
order: String,
#[arg(long)]
open: bool,
#[arg(long, conflicts_with = "no_draft")]
draft: bool,
#[arg(long, conflicts_with = "draft")]
no_draft: bool,
#[arg(long)]
reviewer: Option<String>,
#[arg(long)]
target_branch: Option<String>,
#[arg(long)]
source_branch: Option<String>,
},
/// Show detailed entity information (deprecated: use 'lore issues <IID>' or 'lore mrs <IID>')
#[command(hide = true)]
Show {
/// Entity type to show
#[arg(value_parser = ["issue", "mr"])]
entity: String,
/// Entity IID
iid: i64,
#[arg(long)]
project: Option<String>,
},
/// Verify GitLab authentication (deprecated: use 'lore auth')
#[command(hide = true, name = "auth-test")]
AuthTest,
/// Show sync state (deprecated: use 'lore status')
#[command(hide = true, name = "sync-status")]
SyncStatus,
}
/// Arguments for `lore issues [IID]`
#[derive(Parser)]
pub struct IssuesArgs {
/// Issue IID (omit to list, provide to show details)
pub iid: Option<i64>,
/// Maximum results
#[arg(short = 'n', long = "limit", default_value = "50")]
pub limit: usize,
/// Filter by state (opened, closed, all)
#[arg(short = 's', long)]
pub state: Option<String>,
/// Filter by project path
#[arg(short = 'p', long)]
pub project: Option<String>,
/// Filter by author username
#[arg(short = 'a', long)]
pub author: Option<String>,
/// Filter by assignee username
#[arg(short = 'A', long)]
pub assignee: Option<String>,
/// Filter by label (repeatable, AND logic)
#[arg(short = 'l', long)]
pub label: Option<Vec<String>>,
/// Filter by milestone title
#[arg(short = 'm', long)]
pub milestone: Option<String>,
/// Filter by time (7d, 2w, 1m, or YYYY-MM-DD)
#[arg(long)]
pub since: Option<String>,
/// Filter by due date (before this date, YYYY-MM-DD)
#[arg(long = "due-before")]
pub due_before: Option<String>,
/// Show only issues with a due date
#[arg(long = "has-due")]
pub has_due: bool,
/// Sort field (updated, created, iid)
#[arg(long, value_parser = ["updated", "created", "iid"], default_value = "updated")]
pub sort: String,
/// Sort ascending (default: descending)
#[arg(long)]
pub asc: bool,
/// Open first matching item in browser
#[arg(short = 'o', long)]
pub open: bool,
}
/// Arguments for `lore mrs [IID]`
#[derive(Parser)]
pub struct MrsArgs {
/// MR IID (omit to list, provide to show details)
pub iid: Option<i64>,
/// Maximum results
#[arg(short = 'n', long = "limit", default_value = "50")]
pub limit: usize,
/// Filter by state (opened, merged, closed, locked, all)
#[arg(short = 's', long)]
pub state: Option<String>,
/// Filter by project path
#[arg(short = 'p', long)]
pub project: Option<String>,
/// Filter by author username
#[arg(short = 'a', long)]
pub author: Option<String>,
/// Filter by assignee username
#[arg(short = 'A', long)]
pub assignee: Option<String>,
/// Filter by reviewer username
#[arg(short = 'r', long)]
pub reviewer: Option<String>,
/// Filter by label (repeatable, AND logic)
#[arg(short = 'l', long)]
pub label: Option<Vec<String>>,
/// Filter by time (7d, 2w, 1m, or YYYY-MM-DD)
#[arg(long)]
pub since: Option<String>,
/// Show only draft MRs
#[arg(short = 'd', long, conflicts_with = "no_draft")]
pub draft: bool,
/// Exclude draft MRs
#[arg(short = 'D', long = "no-draft", conflicts_with = "draft")]
pub no_draft: bool,
/// Filter by target branch
#[arg(long)]
pub target: Option<String>,
/// Filter by source branch
#[arg(long)]
pub source: Option<String>,
/// Sort field (updated, created, iid)
#[arg(long, value_parser = ["updated", "created", "iid"], default_value = "updated")]
pub sort: String,
/// Sort ascending (default: descending)
#[arg(long)]
pub asc: bool,
/// Open first matching item in browser
#[arg(short = 'o', long)]
pub open: bool,
}
/// Arguments for `lore ingest [ENTITY]`
#[derive(Parser)]
pub struct IngestArgs {
/// Entity to ingest (issues, mrs). Omit to ingest everything.
#[arg(value_parser = ["issues", "mrs"])]
pub entity: Option<String>,
/// Filter to single project
#[arg(short = 'p', long)]
pub project: Option<String>,
/// Override stale sync lock
#[arg(short = 'f', long)]
pub force: bool,
/// Full re-sync: reset cursors and fetch all data from scratch
#[arg(long)]
pub full: bool,
}
/// Arguments for `lore stats`
#[derive(Parser)]
pub struct StatsArgs {
/// Run integrity checks
#[arg(long)]
pub check: bool,
/// Repair integrity issues (requires --check)
#[arg(long, requires = "check")]
pub repair: bool,
}
/// Arguments for `lore search <QUERY>`
#[derive(Parser)]
pub struct SearchArgs {
/// Search query string
pub query: String,
/// Search mode (lexical, hybrid, semantic)
#[arg(long, default_value = "hybrid")]
pub mode: String,
/// Filter by source type (issue, mr, discussion)
#[arg(long = "type", value_name = "TYPE")]
pub source_type: Option<String>,
/// Filter by author username
#[arg(long)]
pub author: Option<String>,
/// Filter by project path
#[arg(short = 'p', long)]
pub project: Option<String>,
/// Filter by label (repeatable, AND logic)
#[arg(long, action = clap::ArgAction::Append)]
pub label: Vec<String>,
/// Filter by file path (trailing / for prefix match)
#[arg(long)]
pub path: Option<String>,
/// Filter by created after (7d, 2w, or YYYY-MM-DD)
#[arg(long)]
pub after: Option<String>,
/// Filter by updated after (7d, 2w, or YYYY-MM-DD)
#[arg(long = "updated-after")]
pub updated_after: Option<String>,
/// Maximum results (default 20, max 100)
#[arg(short = 'n', long = "limit", default_value = "20")]
pub limit: usize,
/// Show ranking explanation per result
#[arg(long)]
pub explain: bool,
/// FTS query mode: safe (default) or raw
#[arg(long = "fts-mode", default_value = "safe")]
pub fts_mode: String,
}
/// Arguments for `lore generate-docs`
#[derive(Parser)]
pub struct GenerateDocsArgs {
/// Full rebuild: seed all entities into dirty queue, then drain
#[arg(long)]
pub full: bool,
/// Filter to single project
#[arg(short = 'p', long)]
pub project: Option<String>,
}
/// Arguments for `lore sync`
#[derive(Parser)]
pub struct SyncArgs {
/// Reset cursors, fetch everything
#[arg(long)]
pub full: bool,
/// Override stale lock
#[arg(long)]
pub force: bool,
/// Skip embedding step
#[arg(long)]
pub no_embed: bool,
/// Skip document regeneration
#[arg(long)]
pub no_docs: bool,
}
/// Arguments for `lore embed`
#[derive(Parser)]
pub struct EmbedArgs {
/// Retry previously failed embeddings
#[arg(long)]
pub retry_failed: bool,
}
/// Arguments for `lore count <ENTITY>`
#[derive(Parser)]
pub struct CountArgs {
/// Entity type to count (issues, mrs, discussions, notes)
#[arg(value_parser = ["issues", "mrs", "discussions", "notes"])]
pub entity: String,
/// Parent type filter: issue or mr (for discussions/notes)
#[arg(short = 'f', long = "for", value_parser = ["issue", "mr"])]
pub for_entity: Option<String>,
}